Professional Documents
Culture Documents
kusiak2010
kusiak2010
kusiak2010
Applied Energy
journal homepage: www.elsevier.com/locate/apenergy
a r t i c l e i n f o a b s t r a c t
Article history: A data-driven optimization approach for minimization of the cooling output of an air handling unit (AHU)
Received 9 December 2008 is presented. The models used in this research are built with data mining algorithms. The performance of
Received in revised form 25 May 2009 dynamic models build by four different data mining algorithms is studied. A model extracted by a neural
Accepted 8 June 2009
network is selected for identifying the functional mapping between specific outputs and controllable and
Available online 4 July 2009
non-controllable inputs of the AHU. To minimize the cooling output while maintaining the corresponding
thermal properties of the supply air within a certain range, a bi-objective optimization model is proposed.
Keywords:
The evolutionary strategy algorithm is applied to solve the optimization problem with the optimal con-
HVAC
Air handling unit
trol settings obtained at each time stamp. The minimized AHU’s cooling output reduces the chiller’s load,
Data mining which leads to energy savings.
Neural network Ó 2009 Elsevier Ltd. All rights reserved.
Multi-objective optimization
Evolutionary computation
Dynamic modeling
Cooling output
0306-2619/$ - see front matter Ó 2009 Elsevier Ltd. All rights reserved.
doi:10.1016/j.apenergy.2009.06.010
902 A. Kusiak, M. Li / Applied Energy 87 (2010) 901–909
where Qchl is the part cooling load and Qchr is the full cooling capac- humidity are treated as constraints, with their values changing in
ity, a design parameter specified for a certain type of chiller. The a certain range so that the air thermal properties are not compro-
relationship between the PLR and the power input of the chiller mised as the cooling output is minimized to reduce the energy
[2] is expressed in the following equation: consumption.
3
kW ¼ a þ bPLR þ cPLR2 þ dPLR ð2Þ
3. Industrial case study
where a, b, c, d are coefficients determined by the chiller design.
Typically, as the chiller’s load ratio increases from, for example, The approach proposed in this paper has been tested on the
60–100%, the power input increases [14]. Therefore, by optimizing data collected at the Energy Resource Station (ERS) in Ankeny,
the PLR, or more specifically Qchl, as shown in (3), energy is saved Iowa. The ERS is designed for testing and demonstrating commer-
due to the reduced power input. cial HVAC systems. The data includes more than 300 variables cap-
Q chl ¼ C pw mw ðT chwr T chws Þ ð3Þ tured at the AHU, heating and chilling plants, and different testing
zones. The sampling time interval is 1 min, and data points col-
where Qchl is the cooling load, Cpw is the specific heat capacity of lected are the last values recorded at 1-min time intervals, rather
chilled water, mw is the mass flow rate of the chilled water, and than the average data used in other applications.
Tchwr and Tchws is the chiller water supply and return temperature,
respectively [18]. 3.1. Variable selection and data dimensionality reduction
In the AHU side, the cooling output of the cooling coil accounts
for the major load of a chiller. As the chilled water flows through In this paper, a data set collected at the AHU over a two-day
the pipes to the cooling coil in the air handling unit (AHU) and re- period was used for model development, testing, and analysis.
turns to the chiller for cooling after absorbing heat, both the mea- The data set includes over 90 variables, including the data collected
sured values of the cooling coil entering water temperature at coils, dampers, fans, ducts, and pipes. A schematic diagram of
Tchwcewt and the cooling coil exiting water temperature Tchwclwt the AHU is shown in Fig. 1.
are selected as approximations of the Tchws, Tchwr. Therefore, the Variable selection is performed to eliminate variables of rela-
load Qchl is represented by cooling output Q 0chl using the approxi- tively less importance in this two-day data set, since it can im-
mations of Tchwr and Tchws shown as follows: prove the comprehensibility, scalability, and possibly, accuracy
Q 0chl ¼ C pw mw ðT chwclwt T chwcewt Þ ð4Þ of the resulting models [20]. For example, relative open damper
values are important in the AHU, and they directly determine
To minimize Q 0chl , the function y1(t) = f1() should be established be- the amount of air volume in or out. But in this scenario, these
tween the output Q 0chl and the input variables of the AHU. The input variables are removed in the variable selection process because
variables fall into three categories: the previous status of Q 0chl , con- their values remain almost the same in the two-day data set. This
trollable variables, and uncontrollable variables. The function y1(t) is also true for the heating coil because, in this case, the heating
[16] is shown as follows: water coil valve is 100% closed in the two-day data set and no
heating process is performed. Many methods, like wrappers
y1 ðtÞ ¼ f1 ½y1 ðt dÞd2Dy ; ½xðt dÞd2Dx ; ½v ðt dÞd2Dv ð5Þ
[21], can be used to reduce the dimensionality of the variable
where y1(t d) e R includes previous states of y1(t), e.g., y1(t 1) space. However, the wrapper-type approaches can be computa-
and y1(t 2); x e Rk is a vector of k controllable variables with time tionally expensive, as a specific search algorithm searches the
variables, e.g., x1 is the cooling coil valve position variable and space of all possible variables and evaluates each subset of vari-
x1(t 1) refers to its previous state at t 1 time stamp; v e Rm is ables after building a model based on this subset. In this paper,
a vector of m uncontrollable variables with time variables, e.g., v1 a boosting tree algorithm [7,22] was applied to reduce the num-
is the outside air temperature variable and v1(t 2) refers to its pre- ber of variables at a relatively low computational effort. Boosting
vious state at t 2 time stamp; Dy, Dx, and Dv are sets containing tree methods have been applied in many areas [23]. They gener-
time variables of the corresponding variables, e.g., Dx1 = {0,1}, which ate standard measures of variable importance that can be used to
means there are two values for variables x1, and they are x1(t), develop optimal feature sets. The boosting tree algorithm is ro-
x1(t 1), respectively. bust and effective in eliminating variables (input variables) that
Let y1 = f1() be an objective function to be optimized by global are not relevant.
search algorithms determining optimal controllable variables in Four significant variables have been selected as inputs to the
Sections 3.4 and 3.5. Models of y2 ¼ f2 ðÞ and y3 ¼ f3 ðÞ, where y2 model of cooling output, supply air temperature, and supply air
is the supply air temperature and y3 is the supply air humidity, humidity. Two of them are controllable variables, i.e., the cooling
should be built using the same controllable and uncontrollable in- coil chilled water valve position and the relative speed of the sup-
puts, since different values of both controllable and uncontrollable ply air fan. The other two are uncontrollable variables, the outside
variables not only influence the cooling output, but also affect the air temperature and the chilled water supply temperature. The
supply air quality. The optimization model considered in this re- outside air temperature measured at the inlet duct is an indepen-
search is presented in the following equation dent variable. The chilled water supply temperature determined by
the control settings of the chillers is relatively independent of the
min y1
controllable variables in AHU.
y1 ðtÞ ¼ f1 ð½y1 ðt dÞd2Dy ; ½xðt dÞd2Dx ; ½v ðt dÞd2Dv Þ The time delay should also be considered in modeling the AHU.
y2 ðtÞ ¼ f2 ð½y2 ðt dÞd2Dy ; ½xðt dÞd2Dx ; ½v ðt dÞd2Dv Þ For instance, past values of some variables may have more impact
on the model accuracy of the HVAC system than their current val-
y3 ðtÞ ¼ f3 ð½y3 ðt dÞd2Dy ; ½xðt dÞd2Dx ; ½v ðt dÞd2Dv Þ ð6Þ
ues. The boosting tree algorithm was used to select the most signif-
subject to : icant time delays (periods) at which the values of the variables
xi 2 Sxi i is the number of controllable vectors should be considered. Table 1 lists the variables selected to model
yj 2 Syj j ¼ 2; 3 the cooling output, supply air temperature, and supply air humid-
ity at time stamp t. Two of them, namely x1(t) and x2(t), are current
A modified evolutionary strategy algorithm is used to search for time controllable variables, which will be optimized in the next
optimal control settings. The AHU supply air temperature and section.
A. Kusiak, M. Li / Applied Energy 87 (2010) 901–909 903
Return fan
Return
air
Recirculation
Exhaust air
air
Damper
Damper
Heating Cooling
Damper Mixed coil coil
air
Outside Supply
air air
Supply fan
Valve Valve
Supply Return
water Return Supply water
water water
Fig. 1. Schematic diagram of the AHU.
Table 1
Variables selected for building model (6) at t time stamp.
3.2. Cooling output modeling and validation regression introduced by Breiman and Cutler [1]. Unlike the stan-
dard classification trees that use the best split among all variables
As shown in Eq. (4), Q 0chl can be computed from the measured at each node for splitting, the random forest algorithm uses the best
values of the water temperature entering the cooling coil, the water split among a subset of randomly selected predictors at that node.
temperature leaving the cooling coil and the flow rate of the chilled The support vector machine is a supervised learning method based
water. The value computed from Eq. (4) approximates the part load on kernel functions and is used for classification and function
of a chiller. Values of Q 0chl obtained at the previous time periods also approximation. Using specific kernel functions, original feature
affect the current value of Q 0chl . Therefore, y1(t 1), y1(t 2), space is transformed into a high-dimensional space where a sepa-
y1(t 3), and y1(t 4) have been selected as the previous values rated hyper-plane is constructed with the maximum margin.
(states) of Q 0chl together with the variables selected above to build By applying four data mining algorithms to build the cooling
the cooling output model f1() at t time stamp. output model, a comparative analysis of the generated results
has been performed. The data set of 1440 observations (one-day
y1 ðtÞ ¼ f ðy1 ðt 1Þ; y1 ðt 2Þ; y1 ðt 3Þ; y1 ðt 4Þ;
data, July 19, 2005) was divided into a training data set (70% were
x1 ðtÞ; x2 ðtÞ; x1 ðt 4Þ; v 1 ðt 4Þ; v 2 ðt 3ÞÞ ð7Þ randomly sampled data points) and a testing data set (the remain-
Four data mining algorithms, including the multi-layer perceptron ing 30% of the data). The quality of the predictive models has been
(MLP) neural network, boosting tree [8], random forest [1], and sup- compared using the following metrics: Mean Absolute Error (MAE),
port vector machine [17] have been applied to build predictive Standard Deviation (Std), and Mean Relative Error (MRE) defined in
models of the cooling output. The multi-layer perceptron is a com- the following equations:
monly used feed forward neural network consisting of a number of N
1 X ^
units organized into multiple layers. Through adaptive adjusting MAE ¼ zi zi ð8Þ
N i¼1
weights among units under supervised learning, the MLP is capable sffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
PN
of identifying and learning patterns based on input data sets and ^
i¼1 ðjzi zi j MAEÞ
the corresponding target values. The boosting tree [7,22] is a data Std ¼ ð9Þ
N1
mining algorithm involving the application of boosting methods PN j^zi zi j
i¼1 zi 100%
to regression trees used in classification as well as in regression. MRE ¼ ð10Þ
The random forest is a data mining method for classification and N
904 A. Kusiak, M. Li / Applied Energy 87 (2010) 901–909
where ^z is the predicted value, z is the observed value, and N is the Table 3
size of the test data set. The description of the two-day data set.
Table 2 summarizes the prediction performance of the cooling Data Start time End time Description
output models built by four data mining algorithms. set
The results in Table 2 demonstrate that the model built by the 1 6/19/2005 6/19/2005 Training data set; 1440
MLP neural network produces the most accurate and stable results. 0:00 23:59 observations
Therefore, the MLP neural network algorithm is selected for build- 2 6/20/2005 6/20/2005 Test data set; 1440 observations
0:00 23:59
ing a predictive model of a cooling output from a larger data set.
The first-day data from the two-day data set is used as the training
set to build the model, while the second day is used as the testing
data set to validate the model. Table 3 shows the description of the
two data sets.
For the hidden and output neurons of the MLP neural network
algorithm, five different activation functions were selected as can-
didates, namely, the logistic, identity, tanh, exponential, and sine
functions. The number of hidden units was selected between 5
and 18, and the weight decay for both the hidden and output layer
varied from 0.0001 to 0.001. In the final neural network model,
nine hidden neurons are chosen. The activation functions in the
hidden and the output layers are exponential functions. Fig. 2 illus-
trates 200 1-min data points drawn from the test data set to vali-
date the accuracy of the model.
The predicted load function in Fig. 2 follows fairly closely the
observed load curve. Table 4 summarizes the numerical values of
the performance statistics. Fig. 2. Validation of the cooling output model with 200 test points.
Cooling output
3.4. Optimization model
MAE Std MRE (%) Max Min
MLP NN 0.1841 0.1666 0.20 1.5686 0.0008 Models learned by the MLP neural network have been used for
Random forest 0.2018 0.1770 0.22 1.3473 0.0001 optimization. To minimize the cooling output, the objective func-
Boosting tree 0.2475 0.2280 0.27 1.5004 0.0004
tion is represented as y1 = f1(). Major constraints are supply air
SVM 0.1938 0.1532 0.22 0.7682 0.0002
temperature and humidity, so y2 ¼ f2 ðÞ and y3 ¼ f3 ðÞ need to be
A. Kusiak, M. Li / Applied Energy 87 (2010) 901–909 905
objective function (14) can push y2(t) and y3(t) towards their
bounds. Then, the optimization model can be modified to (15).
minðobj1 ; obj2 Þ
x1 ðtÞ;x2 ðtÞ
subject to :
y1 ðtÞ ¼ f ðy1 ðt 1Þ; y1 ðt 2Þ; y1 ðt 3Þ; y1 ðt 4Þ;
x1 ðtÞ; x2 ðtÞ; x1 ðt 4Þ; v 1 ðt 4Þ; v 2 ðt 3ÞÞ
y2 ðtÞ ¼ f ðy2 ðt 1Þ; y2 ðt 2Þ; y2 ðt 3Þ; y2 ðt 4Þ; ð15Þ
x1 ðtÞ; x2 ðtÞ; x1 ðt 4Þ; v 1 ðt 4Þ; v 2 ðt 3ÞÞ
y3 ðtÞ ¼ f ðy3 ðt 1Þ; y3 ðt 2Þ; y3 ðt 3Þ; y3 ðt 4Þ;
x1 ðtÞ; x2 ðtÞ; x1 ðt 4Þ; v 1 ðt 4Þ; v 2 ðt 3ÞÞ
Fig. 4. Validation of the supply air humidity model with 200 test points.
50 x1 ðtÞ 90
70 x2 ðtÞ 75
subject to : Fig. 5. Values of the objective function obj1 for different ratios of the parent and
offspring sizes.
y1 ðtÞ ¼ f ðy1 ðt 1Þ; y1 ðt 2Þ; y1 ðt 3Þ; y1 ðt 4Þ;
x1 ðtÞ; x2 ðtÞ; x1 ðt 4Þ; v 1 ðt 4Þ; v 2 ðt 3ÞÞ
y2 ðtÞ ¼ f ðy2 ðt 1Þ; y2 ðt 2Þ; y2 ðt 3Þ; y2 ðt 4Þ;
x1 ðtÞ; x2 ðtÞ; x1 ðt 4Þ; v 1 ðt 4Þ; v 2 ðt 3ÞÞ ð13Þ
y3 ðtÞ ¼ f ðy3 ðt 1Þ; y3 ðt 2Þ; y3 ðt 3Þ; y3 ðt 4Þ;
x1 ðtÞ; x2 ðtÞ; x1 ðt 4Þ; v 1 ðt 4Þ; v 2 ðt 3ÞÞ
12:2 y2 ðtÞ 13:3
87 y3 ðtÞ 90
50 x1 ðtÞ 90
70 x2 ðtÞ 75
The constraints y2(t) and y3(t) in (13) are neural network derived
models. Solving such a nonlinear constrained optimization problem
is a challenge. To solve model (13), its constraints are placed into
the objective function shown in the following equation:
Fig. 6. Values of the objective function obj1 for different initial population sizes.
maxf0; 12:2 y2 ðtÞg þ maxf0; y2 ðtÞ 13:3g
þ maxf0; 70 y3 ðtÞg þ maxf0; y3 ðtÞ 90g ð14Þ
Each of the four terms in (14) remains 0, and the sum equals 0 when
y2(t) and y3(t) are within their bounds. When either y2(t) or y3(t)
violates a constraint, the sum becomes a positive number. The lar-
ger this constraint is, the larger the sum. Therefore, minimizing the
Table 5
Prediction accuracy of the MLP neural network model.
where obj1 = y1, obj2 = max {0, 12.2 y2(t)} + max {0, y2(t) 13.3} + Different solutions trade off differently between the two objec-
max {0, 70 - y3(t)} + max {0, y3(t) 90}. tives. Optimal solutions change with the weights assigned to the
To solve this bi-objective optimization problem, an evolution- objectives. It is possible that one solution is better than the other
ary strategy algorithm is used. Note that this optimization model for one objective (e.g., cooling output minimization) but is worse
is solved at different time stamps in Section 3.5. Observed values for the other objective (e.g., supply air temperature). Neither can
rather than the predicted values are used at the next point optimi- dominate the other, and they are called non-dominated solutions.
zation. For example, to obtain y1 at t stamp, the observed values The Strength Pareto Evolutionary Algorithm (SPEA) [4,19] is used
y1(t 1), y1(t 2), y1(t 3), and y1(t 4) are used rather than to search the space of non-dominated solutions and update them
the predicted ones. to the elite set at each generation. To solve the model at hand, cer-
tain steps of the SPEA algorithm have been modified, which are
3.5. The evolutionary strategy algorithm presented next.
Unlike single objective optimization, the solution to a bi-objec- Step 1: Initialize a population P and create an empty external
tive optimization problem converges to the Pareto-optimal front. population P to store elite solutions.
Fig. 8. Distribution of the offspring and elite objective values (2nd generation).
Fig. 9. Distribution of the offspring and elite objective values (10th generation).
A. Kusiak, M. Li / Applied Energy 87 (2010) 901–909 907
Step 2: Find non-dominated solutions in P and copy them into P. make sure all solutions remain in the specified search space. For
Step 3: Find non-dominated solutions in P and update the elite x1(t), set r1 = 0.4 and for x2(t), set r1 = 0.1. In case no feasible solu-
population P. tion satisfying the supply air temperature and humidity con-
Step 4: Assign fitness values to each individual in P and P. straints exists, the evolutionary strategy algorithm is repeated.
Step 5: Select Nparent individuals into Pparent from P þ P by using The parameters of this algorithm are tuned to meet the solution
the binary tournament selection scheme with quality and the computational cost requirements. The values of
replacement. the parameters used in the evolutionary strategy algorithm, such
Step 6: Randomly select two individuals and choose the better as the ratio of the parent and offspring size, the initial population
individual to fill in the Poffspring. Poffspring has the same size, and the maximum number of generations (the stopping crite-
population size as P. rion), are set as follows.
Step 7: Apply recombination and mutation operators to Poffspring For three time stamps, namely 12:09 AM, 8:57 AM and 8:08 PM,
and go back to Step 2 until the stopping criterion (here Fig. 5 demonstrates the fitness function values for different ratios
the maximum number of generations) is met. of parent and offspring sizes. Note that the objective function at
the vertical axis refers to the obj1 in model (15), not the fitness val-
Usually in Step 3 and Step 4, clustering is used to reduce the size ues computed in Eqs. (16) and (17) at each generation.
of the elite population. However, for the model considered in this As shown in the Fig. 5, the parent offspring ratio of 1/3 is se-
paper, the elite set is not large and the clustering step is ignored. lected as producing the best quality results. Using this ratio, initial
In Step 4, the fitness functions assigned for individuals in P and P dif- population sizes from 40 to 200 individuals have been tested, and
fer. For individuals in the elite population P, the fitness function is: the results are shown in Fig. 6.
Fig. 6 shows that the initial population size of 120 minimizes
ni
Si ¼ ð16Þ the objective value and therefore is selected as the optimal initial
Nþ1 population size. Fig. 7 shows the average value of the objective
where Si is the fitness of ith elite individual in the external popula- function for the elite solutions at each generation. The elite popu-
tion P; ni is the number of individuals in P that solution i dominates, lation is updated at each generation, and the average value con-
N is the population size of P. verges as the number of iterations increases.
For the individuals in current population P, the fitness function As shown in the Fig. 7, when the number of iterations exceeds
is: 110, the average value of the objective function obj1 of elite solu-
X tions converges to a small value that slightly fluctuates. Therefore,
Sj ¼ 1 þ Si ð17Þ the maximum generation number is set to 110 as the stopping cri-
i2A
terion for the evolutionary computation algorithm.
where Sj is the fitness of jth individual in the current population P, Si Figs. 8–11 present distributions of the offspring and elite popu-
is the fitness of ith elite, which dominates the solution j, A is a elite lation sets at different generations, respectively. The horizontal
set including all elite solutions that dominate the solution j. axis refers to obj1 and the vertical axis to obj2. As the number of
The mutation operation in Step 7 is realized by adding noise Dxi generations increases, the distributions of offspring and elite indi-
to the xi, where xi is the ith controllable variable and Dxi is a Gauss- viduals move from the right to the left, thus following a minimiz-
ian distribution with zero mean and standard deviation r [5]. Solu- ing trend. The algorithm terminates when the generation number
tion xi is updated to x0i by x0i ¼ xi þ Nð0; rÞ. The value of r is reaches the maximum number, and the minimum obj1 with obj2
selected for each variable, and it remains fixed for all generations. equals 0 (y2(t) and y2(t) obey the constraints) and will be chosen
The mutated solutions are checked for possible constraint viola- as the final optimal value for optimized cooling output. The opti-
tions. When a constraint is violated, the value of the violating solu- mal controllable settings which are obtained correspond to the
tion is replaced with a corresponding constraint-bound value to minimum cooling output.
Fig. 10. Distribution of the offspring and elite objective values (20th generation).
908 A. Kusiak, M. Li / Applied Energy 87 (2010) 901–909
Fig. 11. Distribution of the offspring and elite objective values (30th generation).
air at the cooling coil end part. For this reason, adjusting the chilled 72
water entering the cooling coil valve position at the same time to 71.5
decrease the heat transfer from the water side to the air side can 71
70.5
70
120 69.5
110 69
68.5
100 68
90 1 11 21 31 41 51 61 71 81 91
Cooling output
70 Fig. 14. The first 100 points of the recommended supply air relative fan speed.
60
50
decrease the difference in temperature of the chilled water enter-
40 ing and leaving. A lower temperature difference refers to a smaller
1 11 21 31 41 51 61 71 81 91 cooling output for the cooling coil and the chiller. Therefore, by
adjusting two controllable variables simultaneously at each time
Optimized cooling output Original cooling output
stamp to minimize the cooling output, an energy saving potential
Fig. 12. The first 100 points of the optimized cooling output. can be achieved from the chiller side.
A. Kusiak, M. Li / Applied Energy 87 (2010) 901–909 909
13.2 References
13.0
[1] Breiman L. Random forests. Mach Learn 2001;45(1):5–32.
12.8 [2] Chang YC, Lin JK, Chuang MH. Optimal chiller loading by genetic algorithm for
Temperature (°C)
88.4 [13] Mathews EH, Botha CP, Arndt DC, Malan A. HVAC control strategies to enhance
88.2 comfort and minimize energy usage. Energy Build 2001;33(8):853–63.
88 [14] Nadeem M. Evaluation of overall chiller performance characteristics. Air
87.8 Condition Refrig J 2001:7–9.
[15] Nassif N, Moujaes S. A cost-effective operating strategy to reduce energy
87.6
consumption in a HVAC system. Int J Energy Res 2008;32(6):543–58.
87.4 [16] Song Z, Kusiak A. Optimization of temporal processes: a model predictive
87.2 control approach. IEEE Trans Evolut Computat 2009;13(1):169–79.
87 [17] Vapnik VN. The nature of statistical learning theory. New York: Springer; 2000.
86.8 [18] Yu FW, Chan KT. Part load performance of air-cooled centrifugal chillers with
1 11 21 31 41 51 61 71 81 91 variable speed condenser fan control. Build Environ 2007;42(11):3816–29.
[19] Zitzler E, Thiele L. Multi-objective evolutionary algorithms: a comparative case
Supply air humidity after optimization Original supply air humidity
Study and the strength Pareto approach. IEEE Trans Evolut Comput
1999;3(4):257–71.
Fig. 16. The first 100 points of the measured and optimized supply air humidity. [20] Wang J. Data mining: opportunities and challenges. Idea Group Inc.; 2003.
[21] Kohavi R, John GH. Wrappers for feature subset selection. Artif Intell
1997;97(1–2):273–324.
4. Conclusions [22] Hastie T, Tibshirani R, Firedman JH. The elements of statistical learning. New
York: Springer; 2001.
[23] McDonald JA, Sheehan FH. Ventriculogram segmentation using boosted
In this paper, the cooling output of an Air Handling Unit (AHU) decision trees. In: Proceedings of SPIE medical imaging, vol. 5370; 2004. p.
was minimized by using a data-driven approach. Data mining algo- 1804–14.
[24] Ari S, Khalifa HE, Dannenhoffer JF, Wilcoxen P, Isik C. Fuzzy logic and neural
rithms were applied to build dynamic models for controllable and network approximation to indoor comfort and energy optimization. In: IEEE
uncontrollable input variables and output variables, such as cool- NAFIPS conference; 2006. p. 692–5.
ing output, supply air temperature, and humidity. A modified evo- [25] Kintner-Meyer M, Emery AF. Optimal control of an HVAC system using cold
storage and building thermal capacitance. Energy Build 1995;23(1):19–31.
lutionary strategy algorithm was applied to solve the bi-objective
[26] Hou Z, Lian Z, Yao Y, Yuan X. Cooling-load prediction by the combination of
optimization model while providing values of optimal controllable rough set theory and an artificial neural-network based on data-fusion
variables. The simulation results demonstrated that the cooling technique. Appl Energy 2006;83(9):1033–46.
[27] Gebreslassie BH, Guillen-Gosalbaz G, Jimenez L, Boer D. Design of
output was reduced while the supply air temperature and humid-
environmentally conscious absorption cooling systems via multi-objective
ity in the AHU remained in an acceptable range. A reduced cooling optimization and life cycle assessment. Appl Energy 2009;86(9):1712–22.
output decreased the part load for the chiller, and therefore energy [28] Mathews EH, Arndt DC, Piani CB, van Heerdan E. Developing cost efficient
consumption was reduced. Further research involving wider control strategies to ensure optimal energy use and sufficient indoor comfort.
Appl Energy 2000;66(2):135–59.
ranges of data is needed. In this paper, one step optimization [29] Ben-Nakhi AE, Mahmoud MA. Energy conservation in buildings through
was discussed. In the future research, iterative replacement of efficient A/C control using neural networks. Appl Energy 2002;73(1):5–23.
the observed values with the predicted ones will be considered.
Acknowledgment