Download as pdf or txt
Download as pdf or txt
You are on page 1of 47

(12) INTERNATIONAL APPLICATION PUBLISHED UNDER THE PATENT COOPERATION TREATY (PCT)

(19) World Intellectual Property


Organization
International Bureau (10) International Publication Number
(43) International Publication Date WO 2018/004464 Al
04 January 2018 (04.01.2018) W ! P O PCT

(51) International Patent Classification: DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN,
G05B 13/04 (2006.01) F24F 11/00 (2006.01) HR, HU, ID, IL, IN, IR, IS, JO, JP, KE, KG, KH, KN, KP,
KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME,
(21) International Application Number:
MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ,
PCT/SG20 17/050324
OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA,
(22) International Filing Date: SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN,
29 June 2017 (29.06.2017) TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW.
(25) Filing Language: English (84) Designated States (unless otherwise indicated, for every
kind of regional protection available): ARIPO (BW, GH,
(26) Publication Langi English
GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ,
(30) Priority Data: UG, ZM, ZW), Eurasian (AM, AZ, BY, KG, KZ, RU, TJ,
10201605346S 29 June 2016 (29.06.2016) SG TM), European (AL, AT, BE, BG, CH, CY, CZ, DE, DK,
EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV,
(71) Applicant: KIRKHAM GROUP PTE LTD [SG/SG]; MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM,
1 Fusionopolis Walk, #02-1 1 North Tower, Singapore TR), OAPI (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW,
138628 (SG). KM, ML, MR, NE, SN, TD, TG).
(72) Inventors: CHAI, Kok Soon; 385, Goodview Gardens,
Bukit Batok West Avenue 5, # 1 1-334, Singapore 650385 Declarations under Rule 4.17:
(SG). LAI, Choon Hoo; 25, Hazel Park Terrace, #18-02, — of inventorship (Rule 4.1 7(iv))
Singapore 678948 (SG).
Published:
(74) Agent: AMICA LAW LLC; 30 Raffles Place, #14-01 — with international search report (Art. 21(3))
Chevron House, Singapore 048622 (SG).
(81) Designated States (unless otherwise indicated, for every
kind of national protection available): AE, AG, AL, AM,
AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ,
CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO,

(54) Title: LARGE SCALE MACHINE LEARNING-BASED CHILLER PLANTS MODELING, OPTIMIZATION AND DIAG-
NOSIS
(57) Abstract: The invention relates to a data driven, or a hybrid rule-based
and data driven Energy/Building Management System, such as for chiller plants,
which has ability to learn from the data and evaluate performance. According
to the invention, a computer-implemented method trains prediction models for
each equipment model and chiller plant model using baseline data, predicts a
parameter for each equipment model and chiller plant model using baseline da
ta, computes differential parameter of each equipment based on the predicted
and actual parameters of each equipment, computes differential parameter of the
chiller plant based on the predicted and actual parameters of the chiller plant,
compute a differential parameter resulting from chiller plant optimization, by
subtracting the differential parameters of the various equipment from the differ
ential parameter of the chiller plant,ascertaining a presence of abnormality in the
differential parameter resulting from chiller plant optimization and generating a
notification if the differential parameter resulting from chiller plant optimization
is ascertained abnormal.

o
© 417
00
o
Large Scale Machine Learning-based Chiller Plants Modeling, Optimization and
Diagnosis

Field of Invention

Embodiments of the invention relate to energy or management system (EMS/BMS)


for buildings and chiller plants, particularly to a data driven, or a hybrid rule-based and data
driven EMS/BMS, and method and system for modeling, optimizing and evaluating chiller
plant and chiller plant equipment.

Background

Description of Related Art

Chiller plant optimization is one of the most crucial tasks to smart building systems,
as the energy consumption of a chiller plant comprises over 40% of the total energy
consumption of a modern building. Poor efficiency is commonly observed in existing chiller
plant systems, due to the excessive overhead and technical challenges faced in manual
tuning. In practice, a large number of chiller plants and buildings are optimized during the
first few months in operation, when experienced engineers spend huge efforts on fine-tuning
the chiller plants to achieve near-optimal performance. However, the efficiency of these
chiller plants deteriorates quickly when the engineers with expertise leave the projects, such
that the configuration of the chiller plant does not adapt well to the varying environmental
and equipment conditions. A fully optimized chiller plant may run at excellent efficiency
during office hours, but performs poorly at nights/weekends/public holidays. Moreover, even
veterans in the industry may not always make correct decisions on chiller plant optimization.
The extremely high complexity of chiller plants often leads to ineffectiveness of conventional
tuning tricks used by the engineers. The best engineers may only tune the chiller plant
system in a trial-and-error fashion, trying to understand the chiller plants with their
experience and sometimes simple heuristics.

A chiller plant consumes 30-40% of power consumption in a building. Chiller plant


power is calculated by the summation of the total power consumption of chiller, chilled and
condenser water pumps and cooling towers. Sophisticated tradeoff of comfort and
equipment operating conditions etc. are required to minimize the total power consumption of
the chiller plant over a long period of time. The existing method relies on a data driven model
that accurately models and optimizes a type of chiller plant for a short period of time. This
method requires time consuming effort to develop new models for different types of chiller

l
plant. The model is also a best fit for the data for a relatively short period of time, but it loses
predicting accuracy over new data set after a period of chiller plant operation.

Reference is made to [1] and [2]. In [1], Nguyen developed Table 1 to describe the
existing HVAC optimization process that is divided into Preprocessing, Running Optimization
and Post-processing. In [2], neural network was applied to air conditioning and chiller plants
systems.

Table 1 - General HVAC optimization process

[1], [2] and other existing systems focus on model development and system
optimization for one specific chiller plant and for relatively short period of time. For any of the
existing systems to be suitable as an industrial solution, it will face major challenges to meet
"scalability, adaptability and continuous learning" requirements.

Summary

The invention can be implemented, but not limited to as an energy or management


system (EMS/BMS) for buildings and chiller plants. In particular, the invention is to transform
existing EMS/BMS from rule-based to a data driven, or a hybrid rule-based and data driven
EMS/BMS. Under rule-based EMS/BMS, control engineers develop a set of rules based on
domain expertise in advance during the design stage. The rule-based EMS/BMS use
predetermined rules to control HVAC equipment with set points. During operation and
maintenance stage, the field engineers and technicians update the set points to improve
energy efficiency, comfort or maintenance. However, the rule-based EMS/BMS lacks the
ability to improve by itself with experience because it lacks the ability to learn from the data.
The invention provides the EMS/BMS with ability for autonomous learning and control.

The invention is related to the application of a data driven, machine learning-based


control system (may be referred to as "Learning-based Energy Optimization system" or "LEO
system") that uses machine learning model for diagnostics and energy efficiency
optimization of chiller plants. The system reads and processes measurement and verification
(M&V) sensor data for chiller plant such as chilled water and condenser temperatures and
flow rates, equipment power, and learns to represent the equipment in the chiller plants to
predict equipment and chiller plant power.

One aspect of the invention covers the application of a method and system to use
data driven model and sub-models, e.g. neural networks with inputs layers, multiple hidden
layers, and output layers, to represent the actual equipment and predict equipment and
chiller plant power, performance and efficiency. The system learns to represent the chiller
plant and equipment high level characteristics from relative accuracy of the predicted values.
It further learns to represent detailed equipment characteristics such as but not limited to

equipment efficiency, performance etc. to provide data driven, detailed and actionable
diagnostics information for further analysis, diagnostics or energy efficiency optimization.

Another aspect of the invention covers the application of the data driven and deep
learning with model and sub-models to predict and evaluate efficiency and performance of
the system and various equipment. The model and sub-models are trained to predict system
and equipment power and performance using trained data, X train , and evaluated with a set of
accuracy matrix, Macc . The model and sub-models are evaluated with a set of cross
validation data, X cr0S s, for accuracy evaluation. By evaluating and meeting certain accuracy
requirements in Macc , the model and sub-models are used as the baseline for predicting
power, performance and efficiency from the M&V data, X test, of the equipment and of chiller
plant in the future. The model and sub-models predict the performance values of the system
and equipment to be used for comparison for the actual performance values. The system
refers to the accuracy matrix and variance in performance of system and subsystems
between the training Xtrain , cross validation X cross and testing xte st data sets to conclude
performance evaluation of the system and subsystem over time.

Another aspect of the invention covers a method and system that refers to the
performance matrix of equipment for large scale chiller plant comparisons and cross learning.
Another aspect of the invention covers a data driven "universal" model that
generalizes the system and equipment performance, power and efficiency using the
measurement and verification sensor data of the chiller plants that the model is trained on,
as well as the cross validation data and testing data that the model have not been trained on.
This includes a method and system to achieve the best trade-off for optimizing the
generalization of any chiller plants. It includes a method to model the chiller plant life cycle
for continuous and automated learning, modelling and optimization.

According to one aspect of the invention, a computer-implemented method is


provided and comprises:

training a plurality of prediction models using first baseline data, the prediction
models being for chiller plant and a plurality of equipment comprising cooling tower
(CT), condenser water pump (CWP), chiller, chilled water pump (CHWP);
computing, using the prediction models, a plurality of predicted parameters of
the plurality of equipment and the chiller plant using test data;
computing a plurality of differential parameters of the plurality of equipment
based on the predicted parameters of the plurality of equipment and a plurality of
actual parameters of the plurality of equipment;
computing a differential parameter of the chiller plant based on the predicted
parameter of the chiller plant and an actual parameter of the chiller plant;
computing a differential parameter resulting from chiller plant optimization, by
subtracting the differential parameters of the plurality of equipment from the
differential parameter of the chiller plant;

ascertaining a presence of abnormality in the differential parameter resulting


from chiller plant optimization; and

if the presence of abnormality in the differential parameter resulting from


chiller plant optimization is ascertained, generating a first notification which identifies
a request for human intervention.

The computer-implemented method may further comprise:

ascertaining a presence of abnormality in any one of the plurality of


equipment based on the differential parameters of the plurality of equipment; and

if the presence of abnormality in any one of the differential parameters of the


plurality of equipment is ascertained, performing at least one of the following steps:
generating a second notification which identifies the presence of abnormality
in the any one of the plurality of equipment, and

training one of the prediction models, which corresponds to the any one of the
plurality of equipment, using second baseline data.

In the above computer-implemented method, the parameters may be power, or a


combination of power, flow and temperature, depending on the prediction parameters of the
prediction models being used.

According to another aspect of the invention, a system is provided and comprises at


least one computing unit; and at least one memory storage for storing computer-executable
instructions that, when executed by the at least one computing unit, cause performance of
operations comprising any one of the computer-implemented methods described in the
above paragraphs.

Brief Description of Drawings

Embodiments of the invention are disclosed hereinafter with reference to the


drawings, in which:

Figure 1 shows a system architecture of the LEO system;

Figure 2A shows a machine learning life cycle that addresses the challenges of
scalability, adaptability and learning;

Figure 2B shows a basic concept of generalization of model for chiller plants, and
four phases required to build a model that achieves universal fitting of chiller plant data;

Figure 3A shows a prediction model for chiller plant;

Figure 3B shows prediction models for chiller plant equipment e.g. cooling tower,
condenser water pump, chiller model, chilled water pump, using an equipment performance
decomposition-based approach with increasing levels of abstraction;

Figure 3C shows one embodiment of prediction models for chiller plant equipment,
e.g. cooling tower, condenser water pump, chiller model, chilled water pump;

Figure 3D shows another embodiment of prediction models for chiller plant


equipment, e.g. cooling tower, condenser water pump, chiller model, chilled water pump;
Figure 3E shows one example of a prediction model for cooling tower;

Figure 3F shows one example of a prediction model for condenser water pump;

Figure 3G shows one example of a prediction model for chilled water pump;

Figure 3H shows another embodiment of prediction models for chiller plant


equipment, based on Figures 3C, 3E to 3G;

Figure 4 shows a prediction process using the equipment performance


decomposition-based approach;

Figure 5 shows that the LEO system provides visualization data with targeted areas
for human intervention and automatic optimization as compared to existing HVAC Big Data
Tools;

Figure 6 shows that LEO system performs machine and statistics machine learning
to deliver two types of results;

Figure 7 shows an implementation of block 415 to compare predicted and actual


value of condenser pump power to detect abnormality;

Figure 8 shows introduction of high variances to training data for cooling tower by the
invention;

Figure 9 shows a comparison of predicted total chiller plant power, actual total chiller
plant power and a deviation therebetween;

Figure 10 shows evaluation of chiller performance in which baseline data is provided


during baseline time period 1 to 17 April while test data is provided during test period 18
March to 23 May;

Figure 11 shows a representation of optimization options, e.g. CWP flow and CT


approach, and the corresponding power requirement; and

Figure 1 shows a schematic representation of a data driven, or a hybrid rule-based


and data driven EMS/BMS.

Detailed Description of Invention

In the following description, numerous specific details are set forth in order to provide

a thorough understanding of various illustrative embodiments of the invention. It will be


understood, however, to one skilled in the art, that embodiments of the invention may be
practiced without some or all of these specific details. In other instances, well known process
operations have not been described in detail in order not to unnecessarily obscure pertinent
aspects of embodiments being described. In the drawings, like reference numerals refer to
same or similar functionalities or features throughout the several views.

Embodiments described in the context of one of the methods or devices or systems


are analogously valid for the other methods or devices or systems. Similarly, embodiments
described in the context of a method are analogously valid for a system or device, and vice
versa.

Features that are described in the context of an embodiment may correspondingly be


applicable to the same or similar features in the other embodiments. Features that are
described in the context of an embodiment may correspondingly be applicable to the other
embodiments, even if not explicitly described in these other embodiments. Furthermore,
additions and/or combinations and/or alternatives as described for a feature in the context of
an embodiment may correspondingly be applicable to the same or similar feature in the
other embodiments.
As used herein, the articles "a", "an" and "the" as used with regard to a feature or
element include a reference to one or more of the features or elements.
As used herein, the term "and/or" includes any and all combinations of one or more
of the associated listed items.
As used herein, the term "each other" denotes a reciprocal relation between two or
more objects, depending on the number of objects involved.
As used herein, the term "coupled" and related terms are used in an operational
sense and are not necessarily limited to a direct physical connection or coupling. Thus, for
example, two devices may be coupled directly, or via one or more intermediary devices. As
another example, devices may be coupled in such a way that data or information may be
passed therebetween without sharing physical connection with each other. Based on the
present disclosure, a person of ordinary skill in the art will appreciate a variety of ways in
which coupling exists in accordance with the aforementioned definition.

As used herein, the terms "first," "second," and "third," etc. are used merely as labels,
and are not intended to impose numerical requirements on their objects.

As used herein, the term "power" includes references to "power consumption" and
may be interchangeably used; the terms "model" and "sub-model" include references to
"prediction models" and "machine learning models", and may be interchangeably used; the
terms "cooling load" includes references to "cooling tonnage" and may be interchangeably
used.

As used herein, the term "deviation", depending on context, refers to absolute


difference between values, or a difference between one of a set of values and some fixed
value, usually the mean of the set, and therefore may be interchangeably used with the term
"difference".

Figure 1 shows the system architecture of LEO system that receives real time M&V
(measurement and verification) data from chiller plant, or historical data from different
sources to trigger continuous machine learning life cycles. A machine learning life cycle
includes preprocessing, optimization and post-processing.

Figure 2A shows the novel machine learning life cycle that addresses the challenges
of scalability, adaptability and learning. The machine learning life cycle is divided into two
major phases, namely i) model training phase and ii) large scale machine learning-based
prediction and optimization phase.

Model training phase (in blocks 201 a and 201 b of Figure 2A)

The machine learning phase involves the development of a "universal model" that
generalizes by fitting accurately to the measurement and verification data of a smaller
sample of chiller plants. In particularly, the model comprises of sub-models that represent
performance, power and efficiency of equipment such as chillers, chilled water and
condenser water pumps, cooling towers. The equipment list can be extended to airside
equipment such as air handling units and fan coil units etc. The main objective in the training
phase is to achieve the best fit for a relative small sample of chiller plants with the M&V data

t-Phase,
while satisfying the best fit for large scale of chiller plants' M&V data that the model
is not trained to fit in the training phase. In summary, the "universal model", is trained using
the Xt-phase data, but it is expected to predict performance, power, performance and efficiency
of future M&V data X m i-Phase without reprogramming. Deep neural network and multi-level
regression model would likely be the best way to build the universal model. In Ref [3], Wei
describes a data driven method to model a chiller plant. Wei applies BFGS (broydene-
fletcheregoldfarbeshanno) method to a one-output-unit MLP (multi-layer perceptron) to train
a network to represent the prediction model. Monfet and Lee also applied neural network to
represent prediction models that predict single output. These models are black box
approaches that predict an output, e.g. chiller plant power or efficiency with multiple inputs.
The invention applies a novel deep learning approach that decomposes a chiller plant model
to multiple sub-models e.g. equipment models (see Figure 3B), to form a final prediction
model.

Other preprocessing tasks will also be performed in the model training phase
[4],[5],[6].

Large scale machine learning phase (in blocks 202 to 208 of Figure 2A .

The LEO system with "universal model" is ready for large scale machine learning in
this phase. All the tasks performed in the large scale machine learning phase are automated,
and LEO system will only prompt for user intervention if it detects abnormal sensor data that
is beyond uncertainty levels. The large scale learning phase is divided into 5 tasks:

a) Automatic model training and fine tuning for a specific chiller plant (in block
202) . The LEO receives sensor data from different M&V data sources, X m
Phase, where ml-phase refers to machine learning phase, and automatically
trains features and its weights to accurately fit the data, X m i-Phase- E system
shall initiate a set of performance and accuracy diagnostics for sensor data
accuracy and uncertainty. Figure 2B shows the novel framework that LEO
system applies for the development of the prediction model for the chiller
plant. It further applies the novel equipment decomposition-based model
development approach to improve the speed and accuracy of model training.
b) Optimization (in block 203) . It shall trigger an optimization program to
determine the optimum values of certain set points, SP m i- P h ase that minimize
total chiller plant power consumption. Block 203 may be performed using
existing methods.
c) Efficiency evaluation and sensitivity analysis (in block 204) . LEO system will
evaluate the actual efficiency of the chiller plant and uncertainties of the
sensor data to determine the fitness of the universal model. It decides to
trigger a bottom up, localized model retraining that will evaluate performance
and efficiency of individual equipment. Equations 5 and 6 are applied as a
novel differential equipment performance approach to evaluate the equipment,
and chiller plant efficiency.
d) Story Development from the raw data (in block 205) . LEO system will apply
the differential equipment performance approach to develop a story with time
line and descriptions on the changes of equipment and chiller plant
performance and energy efficiency. LEO recursively splits the raw data into
different time periods based on the differential equipment performance
approach.
e) Retrain the model (in block 206) . The invention applies the concept of
differential equipment performance to evaluate i) the effectiveness of energy
efficiency optimization algorithm, ii) the deviation of equipment performance
and efficiency and decide how to retrain the universal model to improve
fitness to the M&V data, and manage uncertainty.
f) Localized machine learning in 207 . The task is started once the model's
fitness to the M&V data is in question. The localized machine learning is a
localized, sub-model training approach that trains for fitness of the data to
individual equipment
g) Stop training 208 . The task is started once the uncertainty of the data
accuracy exceeds certain level, and the sensor data is not fit for input to the
model for optimization. A user is informed to fix the sensor data before
machine learning can resume optimization .

In summary, the major novelties are equipment decomposition-based model


development approach in block 202, differential equipment performance approach in block
204, and methods to evaluate the effectiveness of optimization algorithm and deviation of
equipment performance in block 205.

Method of Generalization for Chiller Plant

Figure 2B shows the basic concept of generalization of model for chiller plants. The
"universal model" is a multi-model based on a hybrid of deep neural network supported by
continuous machine learning life cycles. The novelty is in model development process as
well as the continuous machine learning life cycles. Figure 2B shows that 4 phases are
required to build a model that achieves universal fitting of chiller plant data.

Phase 1 - Actual Model Development

Chiller plant M&V data can be modeled as inputs x . . x n to be associated with one or
more outputs y (see Figure 3A). The model would learn a set of weights w . -w and
compute their outputs f(x,w) .
There are multiple requirements to be met to achieve a universal model. The first
requirement is an optimization problem to minimize total chiller plant power vs total chiller
plant cooling tonnage, i.e.

Min { Rtotal } .

The total power consumption of various chiller plant equipment is modelled by P


total

P + P + P + P + P . Figures 3A and 3B show a novel equipment performance


chwp chiller cwp ct air

decomposition-based approach to represent a prediction model that will meet the second
requirement. The third requirement is a Phase 3 requirement that would be met by modeling
special features that detect changes in the life cycle of a chiller plant.

Figure 3A and 3B show a model and sub-models for learning to represent chiller
plants with a similar architecture with different level of abstractions. The total equipment
power of a chiller plant is P = P + P + P + P + P . Formally, the sub-models
total chwp chiller cwp ct air

are trained to represent the f(x) : R → R , where D is the size of input vector X and L is the
size of the output vector f(x). In particularly, the f(x) Chw P for block 309 in Figure 3B represents
the power and efficiency for chilled water pumps with data sets of flow rates and other
features as inputs for training. The f(x) cwp block 307 in figure 3B also represents the power
and efficiency for condenser pumps using features such as flow rates as inputs.

The f(x) ct and f(x) Chiiier that represent the power and efficiency of cooling towers and
chillers are significantly more difficult to be modelled. The motivation of the algorithm is to
learn to model the power and efficiency of the cooling towers and chillers to trade off better
ratios of total power over total cooling tonnage.

For chillers, chiller power consumption f(x) Chiiier for block 308 in figure 3B can be
modelled by independent parameters stated in the chiller manufacturing datasheet such as
chilled water supply set point, condenser supply temperature, usgpm/rt (flow rate) for chilled
water and condenser water, and the cooling tonnage supplied by the chiller. These
parameters are used to train with the chiller's power consumption to obtain the f(x) Chiiier-

For cooling tower, the problem is constructed such that given some noisy
observations of a dependent variable at certain values of the independent variables {wet
bulb, dry bulb, rh, cooling load and may other variables}, what is the best estimate of the
dependent variable at a new value, f(x) ct for block 306 in figure 3B.

The chiller plant power consumption f(x)chiiierpiam modelled by independent variables


such as weather (such as wet bulb, relative humidity (RH) and dry bulb), cooling load, and
as in Figure 3A.

Phase 2 - Equipment Decomposition-based Model Development

The novel LEO modelling is based on a divide and conquer-approach that


decomposes a chiller plant power prediction problem to sub-models for better efficiency and
useful statistical inference. The following is the original mathematical problem.

P + P + P + P + P (equation 1)
chwp chiller cwp ct air

E = E + E + E + E + E (equation 2)
total chwp chiller cwp ct air

_ c w Pchiller Pcw Pet Pair


Rtotal Rtotal Rtotal total total

Find the Min {P / R } , and the Min {P } (equation 3 )


total total total

P o a
i refers to total equipment power, Pchwp refers to chilled water pump power, P chi ne refers
to chiller power, Pcwp refers to condenser water pump power, Pc, refers to cooling tower
power, Pai refers to air side equipment power.

R total refers to total cooling load.

E total refers to equipment efficiency, E chwp refers to chilled water pump efficiency, Echi iier refers
to chiller efficiency, Ecwp refers to condenser water pump efficiency, Ec, refers to cooling
tower efficiency, Eai refers to air-side equipment efficiency.

The novelty of the decomposition approach is the architecture levels of abstractions


with multiple layers for chiller plants. The first motivation for the modelling with architecture
level of abstractions is to learn to represent the chiller plants equipment powers, and
ultimately infer equipment and chiller efficiency from the representation. The second
motivation is to construct the architecture levels of abstractions that will generalize to
represent power for any chiller plant without reprogramming. Figure 3A describes the basic
representation system of a chiller plant from data. Figure 3B shows a specific representation
learning method for a chiller plant's sensor data that is based on increasing levels of
abstraction. It starts with low level abstractions such as flow rates, temperatures and powers,
and progresses to project features to power and performance of specific equipment types.
The projected features to specific equipment types are used to train to predict powers of the
equipment types.

Figure 3B describes geometrical connections between representation learning that


receives measurement and verification (M&V) data of a chiller plant and transforms the M&V
data into equipment related subset features. Many existing feature engineering methods can
be applied to transform full features to subset features but they do not describe the specific
geometrical connections for chiller plants. The advantages of the representation learning
method described in figure 3B are the faster speed of training subset features (blocks 302-
305) to equipment specific output values (blocks 306-309), and the availability of the middle
levels of abstraction for further equipment specific performance evaluation. The training
speed is particularly important for adaptive control systems, e.g. for HVAC or manufacturing,
that make real time control and decision makings.

Features engineering, representation learning from data etc. may be based on


existing methods, but the geometrical connections for the representation learning are novel.

A set of prediction models are provided for a chiller plant and a plurality of equipment
comprising cooling tower, condenser water pump, chiller and chilled water pump. These
models are configured to train or machine learn from baseline data and thereafter predict
parameters, e.g. power, flow and/or temperature, for their respective chiller plant or
equipment during test period.

Figure 3A shows a prediction model for chiller plant, e.g. chiller plant model 320,
which is configured to predict chiller plant power based on weather and cooling load (RT).
Weather and cooling load are independent variables.

Figure 3C illustrates a prediction model for various chiller plant equipment


(hereinafter may be referred to as "equipment").

In Figure 3C, a first prediction model 306 is configured to predict a condenser water

temperature into chiller (cwshdr); a second prediction model 307 configured to predict a
condenser water flow in/out chiller (cwfhdr); a third prediction model 309 is configured to
predict a chilled water flow in/out chiller (chfhdr); and a fourth prediction model 308 is
configured to predict a chiller power (chkw) based on the condenser water temperature into
chiller (cwshdr), the condenser water flow in/out chiller (cwfhdr), the chilled water flow in/out
chiller (chfhdr), a cooling load and a chiller set-point (chsp).

Reference is made to Figure 3D which shows one embodiment of the prediction


model of Figure 3C.

In Figure 3D, the first prediction model 306 includes a first and a second sub-model.

The first sub-model 306a, e.g. cooling tower model (CT), which is for cooling tower
equipment is configured to predict cooling tower power ("ctkw"), e.g. in kilowatts, based on
VSD (variable speed drive) speed of cooling tower fan ("ct_speed"). The second sub-model
306b, e.g. condenser water temperature model (CWTM), which is for condenser water pump
equipment, is configured to predict condenser water temperature into chillers ("cwshdr")
based on weather and VSD (variable speed drive) speed of cooling tower fan ("ct_speed").

In Figure 3D, the second prediction model 307 includes a third and a fourth s ub

model. The third sub-model 307a, e.g. condenser water flow model (CWFM), which is for
condenser water pump equipment, is configured to predict condenser water flow in/out of
chillers ("cwfhdr") based on VSD speed of condenser water pump ("cwp speed"). The fourth
sub-model 307b, e.g. condenser water pump model (CWP), which is for condenser water
pump equipment, is configured to predict condenser water pump power ("cwpkw") based on
VSD speed of condenser water pump ("cwp speed").

In Figure 3D, the third prediction model 309 includes a fifth and a sixth sub-model.

The fifth sub-model 309a, e.g. chilled water pump model (CHWP), which is for chilled water
pump equipment, is configured to predict chilled water pump power ("chwpkw") based on
VSD speed of chilled water pump ("chwp speed"). The sixth sub-model 309b, e.g. chilled
water flow sub- model (CHFM), which is for chilled water pump equipment, is configured to
predict chilled water flow in/out of chillers ("chfhdr") based on VSD speed of chilled water
pump ("chwp speed").

In Figure 3D, the fourth prediction model 308, e.g. chiller model 308, which is for

chiller equipment, is configured to predict chiller power ("chkw") based on condenser water
flow in/out of chillers ("cwfhdr"), condenser water temperature into chillers ("cwshdr"), chilled
water flow in/out of chillers ("chfhdr"), cooling load and chilled water set point ("chsp").
Cooling load and chilled water set point ("chsp") are independent variables.

The set of prediction models may further comprise a fifth prediction model 310, e.g
chiller plant equipment model (see Figure 3B), which is configured to predict total equipment
power based on cooling tower power ("ctkw"), condenser water pump power ("cwpkw"),
chiller power ("chkw") and chilled water pump power ("chwpkw") from prediction models 306,
307, 308, 309.

Reference is made to Figure 3E which shows another example of the first prediction
model of Figure 3C. The first prediction model 306 of Figure 3E is configured to predict
condenser water temperature into chiller (cwshdr) based on weather data, cooling load,
cooling tower power (ctkw).

Reference is made to Figure 3F which shows another example of the second


prediction model of Figure 3C. The second prediction model 307 of Figure 3E is configured
to predict condenser water flow in/out chiller (cwfhdr) based on condenser water pump
power (cwpkw).

Reference is made to Figure 3G which shows another example of the third prediction
model of Figure 3C.The third prediction model 309 of Figure 3E is configured to predict
chilled water flow in/out chiller (chfhdr) based on chilled water pump power (chwpkw).

In some embodiments, any or all of the first, second, third prediction models of Figure

3D may be replaced by the respective model of Figures 3E, 3F and 3G, and the predicted
parameters would be modified according to the replacement models as described in relation
to Figures 3E, 3F and 3G.

In some other embodiments, that all of the first, second, third prediction models of

Figures 3E, 3F and 3G may be combined with the fourth prediction model 308 to arrive at
Figure 3H which shows another embodiment of the prediction model of Figure 3C. The
predicted parameters would be modified according to the replacement models as described
in relation to Figures 3E, 3F and 3G.

Phase 3 - Time based model training using baseline, test and cross-validation data
Performance evaluation process for a chiller plant to meet phase 3's requirement in
Figure 2B is explained below.
Performance evaluation is based on the concept of comparing the actual present
power (Pow present ) versus the actual historical power (Pow historica i) at similar conditions. The
conditions are the reverse projection of the actual power consumption to the prediction
features in blocks 306-309 in figure 3B. This can be achieved using a couple of methods, e.g.
deep learning models that estimate the relationship between dependent variables (blocks
306-309), e.g. powers, and independent variables, or features (blocks 302-309), e.g. flow
rates, temperatures and powers. The chiller plant level performance comparing a period of
present time t(pres,t) = {t(pres,1) .... T(pres,n)} to a period of historical time t(his,t) =
{t(his,1)... t(his,m)}. Equipment performance decomposition-based approach in Figure 3 B
builds a prediction model that estimates the equipment and plant level dependent variables,
e.g. power consumption, using some given independent variables.

a) Equipment evaluation.
Differential power is computed by comparing Pow p eSent d Pow h iStoricai using the
following equation:

DeltaPoWdiff.totai - ∑ Pow historica i (equation 5)


A negative differential power can be used to infer a reduction in power

consumption by equipment with similar independent variables in blocks 306-309 in


figure 3B. A positive differential power can be used to infer an increase in power
consumption by equipment. Referring to power consumption of total equipment,
P = p + p + p + P + P , the DeltaPoWequip.diff, where eq i P can be
total chwp chiller cwp ct air

described by = {chiller plant, chillers, chilled water pumps, condenser water


pumps, cooling towers, air-side equipment}.
b) Performance Evaluation.
The performance evaluation can be done for different levels of abstraction as
stated by block 3 1 1 in figure 3B. By training prediction models in figure 3B, the
DeltaPow equip,diff , where e q ui
= { chillers, chilled water pumps, condenser water
pumps, cooling towers, air-side equipment}. The change in power consumption for
all equipment is computed.
c) Energy efficiency computation.
The energy efficiency of equipment and chiller plant can be computed by dividing
the summation of power over summation of cooling tonnage. There are two major
reasons contributing to the change of total chiller plant power consumption for a
chiller plant: i) change of equipment efficiency due to aging, wear and tear, change
of water distribution efficiency, etc., ii) improvement due to chiller plant
optimization [7][8].
Accordingly, a differential power or change in power consumption contributed by
chiller plant optimization, DeltaPow opt,di „ , may be computed by the following
equation :

DeltaPow opt,diff = DeltaPow chi e P ant,diff


- (DeltaPow chi ner,diff + DeltaPow chwp,diff +
DeltaPow cw P di + DeltaPow ct,d iff + Uncertainty) (equation 6)

In equation 6 , uncertainty is contributed by the errors in the modelling, and

deviations of the data. In certain embodiments, this uncertainty is not addressed


and may be considered negligible.

Figure 4 shows a prediction process which uses equipment performance


decomposition-based approach. While Figure 4 shows the process being applied to
equipment, the process may be applied to chiller plant in a similar manner.

In block 401 , an operator decides what the objective of the prediction process is.

There may be two different objectives in the prediction process - i) objective 1 - Continuous
chiller plant representation learning and automatic optimization, ii) objective 2 - Story telling
from the M&V data for diagnostics.

In block 403, for objective 1, LEO divides raw or existing M&V data from sensors into

different time periods, and classifies them as baseline data, cross-validation data and test
data. For objective 2 , LEO classifies the M&V data into a baseline, a cross validation and a
number of (or at least one) test periods. Accordingly, data from baseline time period may be
referred to as "baseline data"; data from cross-validation time period may be referred to as
"cross-validation data"; data from test time period may be referred to as "test data". It is to be
appreciated that the cross-validation time period may be a subset of the baseline time period.
It is to be appreciated that the baseline time period and the test time period may or may not

be mutually exclusive.

In block 405, prediction models for equipment 306a, 306b, 307a, 307b, 308, 309a,

309b are trained to predict equipment power using baseline data. Training may be
performed by neural network model, Gaussian process, or other suitable methods, to
produce trained prediction models, e.g. cooling tower model 306a to predict cooling tower
power, condenser water pump model 306b, 307a, 307b to predict condenser water pump
power, chilled water pump model 309a, 309b to predict chilled water pump power, chiller
model 308 to predict chiller power (see blocks 407a, 407b, 407c, 407d). Similarly, prediction
model 320 for chiller plant is trained using baseline data to produce a trained chiller plant
model 320 to predict chiller plant power.

In blocks 409a, 409b and 409c, the trained prediction models, after training in block

405, are used to predict power for each equipment and for the selected time periods of block
403. As illustrated in block 409a, using baseline data, a predicted power is computed for
each equipment. As illustrated in block 409b, using cross-validation data, a predicted power
is computed for each equipment. As illustrated in block 409c, using test data, a predicted
power is computed for each equipment. Similarly, predicted power is computed for chiller
plant separately, using baseline, cross-validation and test data.

Blocks 4 1 1a , 4 1 1b and 4 1 1c analyze the uncertainties of the various data sets to


evaluate the confidence levels of the sensor data for the prediction models.

The predicted power computed using baseline data (see block 409a) may be
compared with the predicted power computed using cross-validation data (see block 409b)
to compute a deviation. For example, for cooling tower, predicted power computed using
baseline data is compared with predicted power computed using cross-validation data to
compute a deviation therebetween. Similar comparison and/or computation of deviation is
also performed for each of the remaining equipment i.e. chilled water pump, condenser
water pump, chiller, as well as for chiller plant.

In block 4 1 3 , model accuracy or fitness e.g. in terms of resolving bias and overfitting,

is analysed for each equipment based on the above-computed deviation between predicted
power using baseline data and predicted power using cross-validation data. For example,
for cooling tower, if the computed deviation falls within a predetermined threshold or limit,
accuracy of the cooling tower model is validated. However, if the computed deviation
exceeds the predetermined threshold or limit, the cooling tower model is not accurate or is
unfit and may require re-training of the cooling tower model. If re-training of the cooling

tower model is required, the process proceeds or returns to block 403 where a different
baseline data is to be selected and training of the cooling tower model takes place based on
the selected different baseline data.

The same procedure of comparison against a respective predetermined threshold is


separately applied to each of the remaining equipment, i.e. chilled water pump, condenser
water pump, chiller, as well as for chiller plant to ascertain accuracy of their respective
prediction models. If any of the remaining equipment is ascertained inaccurate or unfit, the
process proceeds or returns to block 403 where a different baseline is to be selected and
training of the respective model takes place using the selected different baseline data.
Ref [9] describes the application of cross-validation for accuracy estimation and model
selection.

In block 4 1 5 , a presence or absence of abnormality in equipment is ascertained based

on a change in performance of each equipment. Change in equipment performance is


computed using differential approach of equations 5 and 6 and using predicted and actual
power for test period. For example, for condenser water pump, a predicted power computed
from test data is compared with actual power during test period to compute a differential
power. Similar computation is performed to compute separate differential powers for the
remaining equipment, e.g. chilled water pump, condenser water pump, chiller, as well as for
chiller plant.

To ascertain presence of abnormality in equipment, the computed differential power of


an equipment as computed in block 415 is compared against a respective predetermined
threshold. If the computed differential power exceeds the predetermined threshold, a
notification is generated and provided to an operator to notify a presence of abnormality in
the equipment and/or prompt the operator to perform manual check on the abnormal
equipment. Further, the process may proceed or return to block 403 to re-train the particular
abnormal equipment model based on a different baseline data. The foregoing comparison
and/or notification steps are similarly performed for each equipment.

For example, Figure 7 shows an implementation of block 4 1 5 to compare predicted


and actual value of condenser pump power to detect abnormality in condenser pump. To
assess the deviation of predictive values vs the actual values, formulas such as mean error
square, or many other formulas to measure the errors can be applied. A high deviation can
be inferred as an increase in condenser power consumption for similar flow rates. As shown
in Figure 7 , similar power is observed on 22 nd March and 28th March, however, flow rate on

22 nd March is higher while flow rate on 28th March is lower. An increased deviation of
around 24%, from baseline value, on 28th March infers a presence of abnormality in the
condenser water pump. By using scatter diagram, or scatter plot, the plot uses condenser
flow rates to determine power consumption of the condenser pumps.

Figure 10 shows another implementation of block 415 to compare predicted and


actual value of chiller power to detect abnormality in chiller. In Figure 10 , baseline time
period is from 1 to 17 April and baseline data is represented by line 1001 ; test period is from
18 March to 23 May and line 1002 represents a percentage deviation between predicted and
actual power during the test period. The percentage deviation may be computed by dividing
an absolute difference between actual power and predicted power by actual power, and
expressing the quotient in percentage.
Change in equipment efficiency may also be evaluated as efficiency may be derived
from change in equipment performance, e.g. computed as a quotient of power or differential
power over cooling tonnage.

To achieve objective 2 , the LEO system may perform recursive searches to identify
the change in equipment performance (block 4 1 5) to infer the root causes for the change of
chiller plant efficiency. The recursive searches may be performed by splitting the raw data
into multiple time periods, repeating the computations of block 4 1 5 , and comparing
equipment performance and/or efficiency over these multiple time periods.

Block 417 evaluates the effectiveness of chiller plant optimization. To evaluate the
effectiveness, e.g. improvement or decline, of chiller plant optimization, a differential power
or change in power consumption contributed by chiller plant optimization is computed. To
this end, the differential powers of total equipment and of chiller plant are computed.

To compute differential powers of total equipment, the differential powers computed in


block 415 for each equipment are added up or summed to compute or obtain a summation
which is referred to as "total equipment differential powers".

To compute differential power of the chiller plant, a predicted power computed from
test data, using the chiller plant model 320, is compared with actual power of chiller plant
during test period to compute a difference therebetween.

Applying Equation 6 and assuming the uncertainties component in Equation 6 as well


as air-side equipment are not addressed, a differential power resulting from chiller plant
optimization is computed by subtracting the total equipment differential powers from the
differential power of the chiller plant, and may be used to evaluate the effectiveness of chiller
plant optimization.

From block 4 1 7 , the total change of equipment performance and/or efficiency may be
used to isolate the results of optimum control strategies, and the change of sensor
accuracies.

For example, if the computed differential power resulting from chiller plant optimization
implies an improvement in chiller plant operation, e.g. the computed differential power
resulting from chiller plant optimization is a negative value or becomes an increasingly
negative value over a period of time, this shows that power consumption has decreased,
chiller plant optimization has been effective and therefore human intervention may not be
required. However, if the computed differential power resulting from chiller plant optimization
implies a decline in chiller plant operation, e.g. breaches a predetermined threshold, a
presence of abnormality is ascertained and a notification is generated and provided to an
operator to request human intervention, e.g. manual check on physical equipment and/or
optimization strategies. This predetermined threshold may be defined as: the computed
differential power resulting from chiller plant optimization is a positive value greater than a
predetermined value, or becomes an increasingly positive value over a period of time, etc. If
abnormality in the computed differential power resulting from chiller plant optimization is
ascertained present, the process may proceed to block 405 to re-train the equipment models.

When the computed differential power resulting from chiller plant optimization (block
4 1 7) is considered together with the differential powers of each or total equipment (block
4 1 5), an improvement in their differential powers implies that chiller plant optimization has
been effective and therefore human intervention may not be required; conversely, a decline
in their differential powers implies presence of abnormality in chiller plant optimization and/or

equipment performance and therefore a notification may be generated and provided to an


operator to request human intervention. If the differential powers show a conflicting trend,
e.g. an improvement in computed differential power resulting from chiller plant optimization
and a decline in differential power of any equipment, or vice versa, this may imply a
presence of abnormality in the particular equipment and/or chiller plant optimization, and
therefore a notification may be generated to identify the particular abnormality and provided
to an operator to request human intervention. In view of the foregoing description, the results
from block 415 and 417 assist the operator in identifying presence of abnormality in chiller
plant optimization and/or equipment and root cause(s) of the abnormality.

For example, a representation of optimization strategies or options, e.g. optimize CWP


flow and CT approach, and the corresponding power requirement, may be provided as
shown in Figure 11. For CT approach, operator may determine, from the representation and
based on real-time weather and cooling tonnage, the CT temperature from 1 to 5 degrees
Celsius which will be most efficient, i.e. minimize power. For CWP approach, operator may
determine, from the representation and based on real-time weather and cooling tonnage, the
CWP flow which will be most efficient, i.e. minimize power. Accordingly, the LEO system is
able to learn from the data and perform autonomous control to achieve the most optimized
set points.

Equipment performance decomposition-based approach described in Figure 4 can be


further reconfigured into many different processes for, but not limited to, performance
comparison. One or more time periods of data may be set as baselines for training prediction
models as shown in Figures 3B, 3C 3D or 3H, and one or more periods of the data is subset
for comparison. Equipment and chiller plant performance comparison can be achieved by
applying differential equations 5 and 6 , and summation for one or more baselines and other
periods of the data.

Figure 9 shows an evaluation of chiller plant performance based on a comparison of


predicted total chiller plant power 901 and actual total chiller plant power 902 to evaluate the
value of improvement. Figure 9 also shows a percentage deviation 903 of actual from
predicted total chiller plant power. This deviation 903 refers to the differential power of the
chiller plant as mentioned in blocks 4 1 5 and 4 1 7 .

The foregoing paragraphs describing the process of Figure 4 are based on the
prediction models of Figure 3D, where the power parameters are predicted and compared. It
is to be appreciated that if the process illustrated in Figure 4 is based on the prediction
models of Figure 3H, or based on the prediction models of Figure 3D being replaced, in part,
by any of the prediction models of Figure 3E, 3F and 3F, the foregoing computation,
comparison and/or analysis steps would be suitably modified. Particularly, as the first
prediction model 306 of Figure 3E predicts a temperature parameter, the second prediction
model 307 of Figure 3F predicts a flow parameter, the third prediction model 309 of Figure
3G predicts a flow parameter while the fourth prediction model 308 for chiller predicts a
power parameter, the steps described in relation to blocks 4 1 1, 4 1 3 , 4 1 5 and/or 4 1 7 will be
performed based on differential flow parameters, differential temperature and/or differential
power. Alternatively, flow and/or temperature parameters may be converted to power
parameter as known to person skilled in the art during performance of the steps of blocks
4 1 1, 413, 4 15 and/or 4 17 .

Data Enrichment of Equipment

The lack of generality in the data is an important problem of existing systems, which
does not attract attention in almost all existing studies on chiller plants. Simple data
modelling over the existing chiller plant data may result in useless model with high
generalization error. In an extreme case, a chiller plant always runs at a fixed configuration,
e.g., fixed VSD speed for pumps and fans. By training data from this chiller plant, the result
ing data model is only applicable to the current configuration, and does not generate
meaningful prediction for any other configuration. Figure 8 plots the data distribution over
cooling tower speed (CT Speed) and cooling tower power, collected in fully controlled chiller
plant with a fixed VSD configuration setting (denoted as original data 801) and random VSD
configuration (denoted as rich data 802) respectively. The cooling tower fan is mainly
operated at the speed between 20% to 40% of the maximum speed. The results show that
data model using fixed VSD configuration does not have much generalization capability
when other configurations are used by the chiller plant whereas the invention enables
training based on a wider data variation.

Comparing LEO to the existing HVAC big data tools

Existing tools such as Lucid and Green Koncepts apply big data technologies to
generate nice visualization charts and data. However, better classification of energy data is
not sufficient and it still requires intensive and real time analysis to translate data into actions.
Energy management systems must advance from providing charts and data to automatic
optimization and targeted diagnostics information. The users of energy management
systems are technicians and facility managers who do not have time and expertise to
develop advanced machine learning techniques to translate data and charts to actions that
improve energy efficiency.

Figure 5 shows that the LEO system provides visualization data with targeted areas
for human intervention and automatic optimization as compared to existing HVAC Big Data
Tools.

Figure 6 shows that LEO system performs machine and statistics machine learning
to deliver 2 types of results: i) Automatic optimization that results in improved energy
efficiency, ii) Provide some very specific actionable information for users to take specific
actions. For example, LEO system suggests that the energy efficiency of the chiller 3 is
gradually going down by x.xx% since it was serviced 3 months ago. LEO system predicts
that restoring the energy efficiency of the chiller to its original conditions would result in a
saving of $xxx per months.

Hybrid Rule-based and Data Driven Energy/Building Management System

Figure 12 shows an implementation, but not limited to, an energy or management


system (EMS/BMS) for buildings and chiller plants. In particularly, the invention transforms
the existing EMS/BMS from rule-based to a data driven, or a hybrid rule-based and data
driven EMS/BMS. The system architecture includes a real time control system 1201 for in-
premise control, and a non real time cloud-based system 1202 for data management,
machine learning and remote diagnostics.
The cloud-based system 1202 or server includes at least one cloud-based computing
unit, a memory storage for storing data, e.g. baseline data, cross-validation data and test
data, and computer-executable instructions, communication module for receiving and/or
transmitting data to and/or from the in premise real time control system 1201 , input/output
device, e.g. display unit, and other appropriate components. The cloud-based computing
unit is communicably coupled to the memory storage, communication module, and
input/output device, and configured to implement machine learning and/or diagnostics.

The in-premise control system 1201 includes sensors and/or actuators 1203 which
are communicably coupled to chiller plant equipment for sensing data parameters, e.g.
measure speed, flow, temperature and/or power, of equipment and/or for controlling
equipment.

The in-premise control system 1201 further includes energy/building management


system 1204 using direct digital controllers (DDCs) or programmable logic controllers (PLCs)
with rules for chiller plant, air handling units (AHUs), fan coil units (FCUs), etc. The
energy/building management system 1204 may include at least one computing unit which is
communicably coupled to the sensors and actuator 1203, directly or indirectly by
communication module.

The in-premise control 1201 further includes the LEO system 1204 (see also Figure 1)
which is configured to perform real-time learning, control, optimization and diagnostics. The
LEO system 1204 includes at least one memory storage, and at least one computing unit
communicably coupled thereto. The memory storage is configured to store data (e.g.
baseline data, cross-validation data, test data), prediction models, and computer-executable
instructions that, when executed by the at least one computing unit, cause performance of
operations as described in the present disclosure and in relation to blocks 401 to 417. The
computing unit of the LEO system may be communicably coupled to the sensors and/or
actuators 1203, directly or indirectly, to receive measured data transmitted by the sensors
and/or actuators 1203.

The LEO system 1204 is communicably coupled to the cloud server 1202 for data
transmission therebetween, and to at least an input/output device, e.g. display unit and data
entry unit, to provide a user interface. The user interface or display unit is configured to
display notifications and/or diagnostics from the LEO system 1205, and allow viewing of
reports generated by the LEO system 1205. The user interface 1206 or input unit is further
configured to allow an operator, e.g. building and/or database manager, provide instructions
to control equipment and/or chiller plant.
Other embodiments will be apparent to those skilled in the art from consideration of
the specification and practice of the invention. Furthermore, certain terminology has been
used for the purposes of descriptive clarity, and not to limit the disclosed embodiments of the
invention. The embodiments and features described above should be considered exemplary.

List of References

[1] Nguyen, A . T.; Reiter, S.; Rigo, P. A review on simulation-based optimization methods
applied to building performance analysis. Applied Energy 1 13 (2014) 1043-1058.

[2] Applications of artificial neural networks for refrigeration, air-conditioning and heat pump
systems— A review, RENEWABLE AND SUSTAINABLE ENERGY REVIEWS FEBRUARY
2012.

[3] Xiupeng Wei, Guanglin Xu, Andrew Kusiak, "Modeling and optimization of a chiller plant",
Energy, 2014, Elsevier.
[4] Vakiloroaya, V., Q . P. Ha, and B . Samali. "Energy-efficient HVAC systems: Simulation-
empirical modelling and gradient optimization." Automation in Construction 3 1 (2013): 176-
185.
[5] D. Monfet, R . Zmeureanu, Ongoing commissioning of water-cooled electric chillers using
benchmarking models, Applied Energy 92 (201 2) 99-108.
[6] Lee, T.-S.; Liao, K.-Y.; Lu, W.-C. Evaluation of the suitability of empirically-based
models for predicting energy performance of centrifugal water chillers with variable chilled
water flow. Appl. Energy 201 2 , 93, 583-595.

[7] Hartman, Thomas. "All-variable speed centrifugal chiller plants." ASHRAE journal 43.9
(2001): 43.

[8] Yu, F. W., and K . T . Chan. "Optimization of water-cooled chiller system with load-based
speed control." Applied Energy 85.10 (2008): 931 -950.

[9] Kohavi, Ron. "A study of cross-validation and bootstrap for accuracy estimation and
model selection." Ijcai. Vol. 14. No. 2 . 1995.
Claims

1. A computer-implemented method comprising:


training a plurality of prediction models using first baseline data, the prediction
models being for chiller plant and a plurality of equipment comprising cooling tower (CT),
condenser water pump (CWP), chiller, chilled water pump (CHWP);
computing, using the prediction models, a plurality of predicted parameters of the
plurality of equipment and the chiller plant using test data;
computing a plurality of differential parameters of the plurality of equipment based on
the predicted parameters of the plurality of equipment and a plurality of actual parameters of
the plurality of equipment;
computing a differential parameter of the chiller plant based on the predicted
parameter of the chiller plant and an actual parameter of the chiller plant;
computing a differential parameter resulting from chiller plant optimization, by
subtracting the differential parameters of the plurality of equipment from the differential
parameter of the chiller plant;

ascertaining a presence of abnormality in the differential parameter resulting from


chiller plant optimization; and

if the presence of abnormality in the differential parameter resulting from chiller plant
optimization is ascertained, generating a first notification which identifies a request for
human intervention.

2 . The method of claim 1, further comprising:

ascertaining a presence of abnormality in any one of the plurality of equipment based


on the differential parameters of the plurality of equipment; and

if the presence of abnormality in any one of the differential parameters of the plurality
of equipment is ascertained, performing at least one of the following steps:

generating a second notification which identifies the presence of abnormality


in the any one of the plurality of equipment, and

training one of the prediction models, which corresponds to the any one of the
plurality of equipment, using second baseline data.
3 . The method of any one of claims 1 to 2 , further comprising:
computing a first plurality of deviations between the predicted parameters of the
plurality of equipment using the baseline data and the predicted parameters of the plurality of
equipment using cross-validated data;
computing a second deviation between the predicted parameter of the chiller plant
using the baseline data and the predicted parameter of the chiller plant using cross-
validation data; and
ascertaining accuracy of the prediction models based on the first deviations and the
second deviation.

4 . The method of claim 3 , further comprising:


if any one of the prediction models is ascertained inaccurate, training the any one of
the prediction models using baseline data different from the first baseline data.

5 . The method of any one of claims 1 to 4 , wherein the prediction models include:
a first prediction model configured to predict a condenser water temperature into
chiller (cwshdr);
a second prediction model configured to predict a condenser water flow in/out chiller
(cwfhdr);
a third prediction model configured to predict a chilled water flow in/out chiller
(chfhdr); and
a fourth prediction model configured to predict chiller power (chkw) based on the
condenser water temperature into chiller (cwshdr), the condenser water flow in/out chiller
(cwfhdr), the chilled water flow in/out chiller (chfhdr), a cooling load and a chiller set-point
(chsp).

6 . The method of claim 5 , wherein


the first prediction model includes a first sub-model configured to predict a cooling
tower power (ctkw) based on a VSD (variable speed drive) cooling tower fan (ct_speed), and
a second sub-model configured to predict the condenser water temperature into chiller
(cwshdr) based on the VSD speed of cooling tower fan (ct_speed) and a weather data;
the second prediction model includes a third sub-model configured to predict the
condenser water flow in/out chiller (cwfhdr) based on a VSD speed of condenser water
pump (cwp speed), and a fourth sub-model configured to predict condenser water pump
power (cwpkw) based on the VSD speed of condenser water pump (cwp speed); and
the third prediction model includes a fifth sub-model configured to predict a chilled
water pump power (chpkw) based on a VSD speed of chilled water pump speed
(chwp speed); and a sixth sub-model configured to predict the chilled water flow in/out
chiller (chfhdr) based on the VSD speed of chilled water pump speed (chwp speed).

7 . The method of any of claims 1 to 6 , wherein the parameters include power.

8 . The method of claim 5 , wherein


the first prediction model is configured to predict the condenser water temperature
into chiller (cwshdr) based on a weather data, a cooling load, a cooling tower power (ctkw);
the second prediction model is configured to predict the condenser water flow in/out
chiller (cwfhdr) based on a condenser water pump power (cwpkw); and
the third prediction model is configured to predict a chilled water flow in/out chiller
(chfhdr) based on a chilled water pump power (chwpkw).

9 . The method of any one of claims 1 to 5 and 8 , wherein the parameters include power,
flow and temperature.

10. A system comprising:


at least one computing unit; and
at least one memory storage for storing computer-executable instructions that, when
executed by the at least one computing unit, cause performance of operations comprising:
training a plurality of prediction models using first baseline data, the prediction
models being for chiller plant and a plurality of equipment comprising cooling tower (CT),
condenser water pump (CWP), chiller, chilled water pump (CHWP);
computing, using the prediction models, a plurality of predicted parameters of the
plurality of equipment and the chiller plant using test data;
computing a plurality of differential parameters of the plurality of equipment based on
the predicted parameters of the plurality of equipment and a plurality of actual parameters of
the plurality of equipment;
computing a differential parameter of the chiller plant based on the predicted
parameter of the chiller plant and an actual parameter of the chiller plant;
computing a differential parameter resulting from chiller plant optimization, by
subtracting the differential parameters of the plurality of equipment from the differential
parameter of the chiller plant;

ascertaining a presence of abnormality in the differential parameter resulting from


chiller plant optimization; and
if the presence of abnormality in the differential parameter resulting from chiller plant
optimization is ascertained, generating a first notification which identifies a request for
human intervention.

11. The system of claim 10 , wherein the operations further comprising:

ascertaining a presence of abnormality in any one of the plurality of equipment based


on the differential parameters of the plurality of equipment; and

if the presence of abnormality in any one of the differential parameters of the plurality
of equipment is ascertained, performing at least one of the following steps:

generating a second notification which identifies the presence of abnormality


in the any one of the plurality of equipment, and

training one of the prediction models, which corresponds to the any one of the
plurality of equipment, using second baseline data.

12. The system of any one of claims 10 to 11, wherein the operations further comprising:
computing a first plurality of deviations between the predicted parameters of the
plurality of equipment using the baseline data and the predicted parameters of the plurality of
equipment using cross-validated data;
computing a second deviation between the predicted parameter of the chiller plant
using the baseline data and the predicted parameter of the chiller plant using cross-
validation data; and
ascertaining accuracy of the prediction models based on the first deviations and the
second deviation.

13 . The system of claim 12 , wherein the operations further comprising:


if any one of the prediction models is ascertained inaccurate, training the any one of
the prediction models using baseline data different from the first baseline data.

14. The system of any one of claims 10 to 13, wherein the prediction models include:
a first prediction model configured to predict a condenser water temperature into
chiller (cwshdr);
a second prediction model configured to predict a condenser water flow in/out chiller
(cwfhdr);
a third prediction model configured to predict a chilled water flow in/out chiller
(chfhdr); and
a fourth prediction model configured to predict chiller power (chkw) based on the
condenser water temperature into chiller (cwshdr), the condenser water flow in/out chiller
(cwfhdr), the chilled water flow in/out chiller (chfhdr), a cooling load and a chiller set-point
(chsp).

15. The system of claim 14, wherein


the first prediction model includes a first sub-model configured to predict a cooling
tower power (ctkw) based on a VSD (variable speed drive) cooling tower fan (ct_speed), and
a second sub-model configured to predict the condenser water temperature into chiller
(cwshdr) based on the VSD speed of cooling tower fan (ct_speed) and a weather data;
the second prediction model includes a third sub-model configured to predict the
condenser water flow in/out chiller (cwfhdr) based on a VSD speed of condenser water
pump (cwp speed), and a fourth sub-model configured to predict condenser water pump
power (cwpkw) based on the VSD speed of condenser water pump (cwp speed); and
the third prediction model includes a fifth sub-model configured to predict a chilled
water pump power (chpkw) based on a VSD speed of chilled water pump speed
(chwp speed); and a sixth sub-model configured to predict the chilled water flow in/out
chiller (chfhdr) based on the VSD speed of chilled water pump speed (chwp speed).

16. The system of any of claims 10 to 15, wherein the parameters include power.

17. The system of claim 14, wherein


the first prediction model is configured to predict the condenser water temperature
into chiller (cwshdr) based on a weather data, a cooling load, a cooling tower power (ctkw);
the second prediction model is configured to predict the condenser water flow in/out
chiller (cwfhdr) based on a condenser water pump power (cwpkw); and
the third prediction model is configured to predict a chilled water flow in/out chiller
(chfhdr) based on a chilled water pump power (chwpkw).

18. The system of any one of claims 10 to 14 and 17, wherein the parameters include power,
flow and temperature.

19. The system of any one of claims 10 to 18, further comprising:


a plurality of sensors located at the plurality of equipment and communicably coupled
to the at least one computing unit, the sensors being configured to measure at least the
actual power of the plurality of equipment and transmit data comprising the actual power of
the plurality of equipment to the at least one computing unit.

20. The system of any one of claims 10 to 19, further comprising:


a display unit configured to display the first and/or the second notification.
n erna ona app ca on o.

PCT/SG201 7/050324

A. CLASSIFICATION OF SUBJECT MATTER

G05B 13/04 (2006.01) F24F 11/00 (2018.01)


According to International Patent Classification (IPC)

B. FIELDS SEARCHED
Minimum documentation searched (classification system followed by classification symbols)
G05B, F24F

Documentation searched other than minimum documentation to the extent that such documents are included in the fields searched

Electronic data base consulted during the international search (name of data base and, where practicable, search terms used)
FAMPAT: model, chiller, plant, equipment, predicted, actual, differential, subtract, abnormality, optimization, condenser,
¾ , fti†, ¾ , ¾ , , and related terms.

C. DOCUMENTS CONSIDERED TO BE RELEVANT


Category * Citation of document, with indication, where appropriate, of the relevant passages Relevant to claim No.

A US 201 4/02291 4 6 A 1 (GONZALEZ I. F. ET AL. ) 14 August 201 4 1-20


whole document

A US 201 1/01 90946 A 1 (WONG C . H . Y . ET AL.) 4 August 201 1 -


whole document

A C N 103234256 A (SHANGHAI DAXI ENERGY TECHNOLOGY) 7 August 201 3


whole document of the original non-English language document (a machine
translation is enclosed only for your reference)

| Further documents are listed in the continuation of Box C . | See patent family annex.

'Special categories of cited documents:


"A" document defining the general state of the art which is not "T" later document published after the international filing date or
considered to be of particular relevance priority date and not in conflict with the application but cited to
understand the principle or theory underlying the invention
"E" earlier application or patent but published on or after the
international filing date "X" document of particular relevance; the claimed invention
cannot be considered novel or cannot be considered to
"L" document which may throw doubts on priority claim(s) or involve an inventive step when the document is taken alone
which is cited to establish the publication date of another
citation or other special reason (as specified) "Y " document of particular relevance; the claimed invention
cannot be considered to involve an inventive step when the
"0" document referring to an oral disclosure, use, exhibition or document is combined with one or more other such
other means documents, such combination being obvious to a person
"P" document published prior to the international filing date but skllled h e art
later than the priority date claimed &» document member of the same patent family

Date of the actual completion of the international search Date of mailing of the international search report
0 1/08/201 7 . ,
27/07/201 7 (day/month/year) (day/month/year)

Name and mailing address of the ISA SG Authorized officer


Intellectual Property Office of Singapore
OS # 011B0r 1sMBa nsu lifeRCo edntre Zhao Xue (Dr)

Singapore 189554
Email: pct@ipos.gov.sg IPOS Customer Service Tel. No. : (+65) 6339 861 6

Form PCT/ISA/21 0 (second sheet) (January 201 5 )


n erna ona app ca on o .
PCT/SG201 7/050324

C (Continuation). DOCUMENTS CONSIDERED TO BE RELEVANT


Category * Citation of document, with indication, where appropriate, of the relevant passages Relevant to claim No.

A US 201 2/0083927 A 1 (NAKAMURA T . ET AL.) 5 April 201 2 -


whole document

A CN 104566765 A (KARSUN INTERNATIONAL HOLDING) 29 April 201 5 -


whole document of the original non-English language document (a machine
translation is enclosed only for your reference)

A US 2009/0093892 A 1 (KANT R . ET AL.) 9 April 2009


whole document

Form PCT/ISA/21 0 (continuation of second sheet ( 1 )) (January 201 5)


n erna ona app ca on o.
Information o n patent family members
PCT/SG201 7/050324

Note: This Annex lists known patent family members relating to the patent documents cited in this International Search
Report. This Authority is in no way liable for these particulars which are merely given for the purpose of information.

Patent document Publication date Patent family Publication date


cited in search report member(s)
US 201 4/0229146 A 1 14/08/201 4 WO 201 4/1 24341 A 1 14/08/201 4

US 201 1/01 90946 A 1 04/08/201 1 CN1 0 1363653 A 11/02/2009

WO 201 0/0201 60 A 1 25/02/201 0

CN 103234256 A 07/08/201 3 NONE

US 201 2/0083927 A 1 05/04/201 2 JP 2012080679 A 19/04/201 2

JP 201221 0 15 1 A 25/10/201 2

SG 179328 A 1 27/04/201 2

CN 104566765 A 29/04/201 5 NONE

US 2009/0093892 A 1 09/04/2009 WO 2009/0461 97 A 1 09/04/2009

Form PCT/ISA/21 0 (patent family annex) (January 201 5 )

You might also like