Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 22

Integrated Energy Management of Photovoltaic and Fuel

cells for Residential House

National Taipei University of Technology

STUDENT NAME: UNDER THE GUIDENCE:


N. Raghava [PhD] Dr. Leehter Yao
106319403
Contents
• Abstract.
• Introduction.
• Hybrid Energy Management Optimization in Hems.
a. Home Appliance Model.
b. Fuel Cell Model.
c. System Overall Model
• Simulation Settings.
• Simulation Results.
• Conclusion.
• References.
Abstract

• This paper presents an analytical framework to develop a hierarchical home energy management
system (HEMS).
• The smart home is dwell of a photovoltaic (PV) module, utility grid with dynamic electricity price,
energy storage system (ESS), fuel cell (FC) and the appliances used in the household along with
three different types of load characteristics (i.e., interruptible, uninterruptible and time-varying) is
investigated.
• The nonlinear objective function is hard to solve; thus a piecewise linear function is applied to
manage it.
• A home energy management system (HEMS) formulated using mixed integer linear programming
(MILP) aims to decrease the electricity cost and the hydrogen cost for satisfying the scheduled load
demands synchronously under a single optimization framework
Introduction
• Demand-side Management (DSM), is a reliable and sustainable solution to the consumer to use less
energy during peak hours or to move the time of energy use to off-peak hours DSM is also used for
addressing the challenges by allowing more active participation of the consumer from demand side
for modifying their energy consumption behavior .
• Utilization of renewable energy sources (RES) such as PV power or wind power is used to satisfy
the household load demands a smart home which includes, DSM strategy. Due to the intermittent
nature of RES, these local generations are most often not optimally utilized.
• The power transactions between utility grid, PV module, electric vehicle, energy storage system
were used to optimize by HEMS using MILP.
• The lead-acid battery has low power density resulting in a slower response speed to fluctuations in
demand.
• In this paper, optimization of energy management for residential houses with photovoltaic panels
and fuel cells is proposed to minimize the electricity cost and the hydrogen cost for satisfying the
scheduled load demands.
HYBRID ENERGY MANAGEMENT OPTIMIZATION MODEL IN HEMS

Fig. 1 In this study the power architecture of home is considered.


Contd.

• The structure of the home energy management system in this article is shown in Figure 1. The use
of controllable electrical equipment within the home is controlled, while the monitoring of the solar
power system (solar photovoltaic system) with the use of battery packs to optimize the use of home
controllable power equipment Schedules are made, and the equipment communication system
setup will install DO controllers and smart meters on the controllable power equipment in each
corner of the home to build a complete IoT communication network.
• In the software system architecture, we use multiple embedded systems to perform real-time
monitoring of the system's hardware devices.
• It is also possible to transfer the unloading status, solar power generation capacity, and battery
charge/discharge amount of each electrical equipment to the management system and store all
relevant information in the database (MYSQL).
• Finally, webpage components provide users with instant data monitoring and optimization of
energy devices.
A. Home appliance model.

• HEMS is defined with different load characteristics where Ac1 is defined as fixed power
consumption with the set of the interruptible load. Ac2 is defined as fixed power consumption with
the set of the uninterruptible load and Ac3 is defined as a set time-varying power consumption of
variable load i.e. With the uninterruptible loads.
• The home appliance with three different sets Ac1, Ac2, and Ac3 are scheduled in real-time.
B. Fuel Cell
RP algorithm

Maximum number of epochs to train 1000

Epochs between displays 25

Generate command-line output False

Show training GUI True

Performance goal 0

Maximum time to train in seconds Inf

Minimum performance gradient 1e−5

Maximum validation failures 6

Learning rate 0.01

Increment to weight change 1.2

Decrement to weight change 0.5

Initial weight change 0.07

Maximum weight change 50.0


SCG algorithm

Maximum number of epochs to train 1000

Epochs between displays 25

Generate command-line output False

Show training GUI True

Performance goal 0

Maximum time to train in seconds Inf

Minimum performance gradient 1e−5

Maximum validation failures 6

Determine change in weight for second derivative approximation 5.0e−5

Parameter for regulating the indefiniteness of the Hessian 5.0e−7


Normalization, training and testing

𝑋𝑁 = 0.8(𝑋𝑅 − 𝑋max Τ𝑋max − 𝑋min ) + 0.1

XN : normalized value;
XR : value to be normalized;
Xmax: maximum value among all the values for related variable; and
Xmin: minimum value among all the values for related variable.
Optimal number of hidden neurons in hidden layer.

• Generally the training of an ANN model starts with a random initial weight. It is essential to find
the optimal number of neurons in the hidden layer to reach the minimum possible error in ANN
model output.
• An appropriate number of neurons in hidden layer is selected based on the results obtained for
MSE and R.
• To find the optimal number of hidden neurons in hidden layer, the training of ANN model I was
done by increasing the number of neurons one by one until it converged into a minimum mean
square error.
• Among the four algorithms, the Levenberg–Marquardt (LM) algorithm produced the R value in
the range of 0.9000. When the R value is greater than 0.9000, it means that a higher number of
predicted values are consistent with the measured values.
optimal number of hidden neurons in hidden layer (cont.)

• In ANN model I, the minimum MSE and maximum R value for training and testing was found at 24
neurons and 20 neurons, respectively. Hence, ANN model I is suitable for training but not good for
testing.
• Thus, it is very difficult to finalize the optimal number of neurons from ANN model I.
• Now, the same procedure was repeated for ANN model II.
• From the performance results of ANN model II, a minimum MSE and a maximum R value were
observed at 24 neurons, at both training and testing stage.
Selection of optimal number of neurons.
Selection of optimal number of neurons.

Number of neurons in hidden layer ANN model I ANN model II

R value for training R value for testing R value for training R value for testing

1 0.8961 0.8839 0.9012 0.8978


2 0.8916 0.8894 0.9109 0.9006
3 0.8701 0.8703 0.9317 0.9043
4 0.8996 0.8856 0.9203 0.9084
5 0.8840 0.8761 0.9061 0.9114
6 0.9105 0.8994 0.9146 0.9063
7 0.9091 0.8949 0.9084 0.9190
8 0.9034 0.8976 0.9096 0.9187
9 0.9003 0.9046 0.9071 0.9014
10 0.9054 0.9057 0.9031 0.9042
11 0.8925 0.9082 0.9168 0.9077
12 0.8953 0.9096 0.9183 0.9086
13 0.9018 0.9133 0.9207 0.9095
14 0.9078 0.9165 0.9215 0.9106
15 0.9083 0.9174 0.9291 0.9127
16 0.9115 0.9181 0.9357 0.9134
17 0.9155 0.9209 0.9388 0.9145
18 0.9202 0.9213 0.9412 0.9167
19 0.9287 0.9297 0.9452 0.9174
20 0.9289 0.9383 0.9463 0.9189
21 0.9305 0.9351 0.9497 0.9197
22 0.9313 0.9275 0.9508 0.9203
23 0.9359 0.9256 0.9523 0.9247
24 0.9363 0.9223 0.9545 0.9272
25 0.9311 0.9035 0.9512 0.9236
26 0.9286 0.9031 0.9418 0.9208
27 0.9255 0.8974 0.9386 0.9165
28 0.9216 0.8917 0.9311 0.9100
29 0.9178 0.9005 0.9216 0.9094
30 0.9018 0.8976 0.9189 0.9032
Training and testing stations used for ANN models I and II .
Training and testing stations used for ANN models I and II.

Name of the Training Testing

ANN model
Number of Number of Name of the station Number of Number of Name of the station

station data used from station data used from

each station each station

ANN model I 4 120 Chennai, Kolkatta, New 1 120 Bangalore

Delhi and Mumbai

ANN model II 5 96 Chennai, Kolkatta, New 5 24 Chennai, Kolkatta, New

Delhi, Mumbai and Delhi, Mumbai and

Bangalore Bangalore

1 𝑛
𝑀𝐴𝐸 = ෍ |𝑋𝑖 − 𝑌𝑖 |
𝑁 𝑖=1
1
 X  Yi  2
n
RMSE  i 1 i
N
where

N: total number of data;


Xi : measured monthly average global solar radiation; and
Yi : ANN predicted monthly average global solar radiation.
• The mean absolute error (MAE) is defined as a quantity which is used to measure how close the
predicted values are with measured values.
• The root mean square error (RMSE) indicates the level of scatter that ANN model produces.
Lower RMSE indicates that the developed ANN model is having good prediction accuracy.
• The linear correlation coefficient (R) value is used to find the relationship between the measured
and predicted values.
• If R = 1, it means that there is an exact linear relationship between measured and predicted
values.
• However an ANN model with lower values of MAE, RMSE and higher values of R is selected as the
best model for prediction.
Performance of ANN model I (at 24 neurons).

Performance of ANN model I (at 24 neurons).

Name of the algorithm ANN model I – training ANN model I – testing

MAE RMSE R MAE RMSE R

GD 5.7325 6.8223 0.6755 8.6860 11.2127 0.5202

LM 0.8278 1.0819 0.9363 3.4979 4.5497 0.9223

RP 2.4004 3.0722 0.7662 4.1531 5.0187 0.7616

SCG 1.4672 1.8922 0.8715 4.4588 5.1477 0.7990


Performance of ANN model II (at 24 neurons).

Performance of ANN model II (at 24 neurons).

Name of the algorithm ANN model II – training ANN model II – testing

MAE RMSE R MAE RMSE R

GD 6.1556 7.7928 0.4550 9.0903 10.7656 0.4844

LM 0.7800 1.0416 0.9545 3.0281 3.6461 0.9272

RP 2.4558 3.1033 0.7113 3.9474 4.9601 0.5852

SCG 1.3038 1.7137 0.8964 3.3172 4.0794 0.8332


Selection of best ANN model (at 24 neurons).

Selection of best ANN model (at 24 neurons).

Name of the model LM algorithm

Training Testing

MAE RMSE R MAE RMSE R

ANN model I 0.8278 1.0819 0.9363 3.4979 4.5497 0.9223

ANN Model II 0.7800 1.0416 0.9545 3.0281 3.6461 0.9272


Performance of measured and ANN predicted monthly GSR.
Conclusion

• In ANN model I, four stations data were used for training. Testing was done for a new station data,
whereas, for an ANN model II, all five stations data were used both for training and testing.
• The best ANN algorithm and model was found on the basis of minimum mean absolute error and
root mean square error and maximum linear regression coefficient.
• From the analysis of results, it was found that the predicted values are in good agreement with
measured values in Levenberg–Marquardt (LM) algorithm.
• THANK YOU

You might also like