GA−Reinforced Deep Neural Network for Net Electric Load Forecasting in Microgrids with Renewable Energy Resources for Scheduling Battery Energy Storage Systems
Abstract
:1. Introduction
1.1. Background
1.2. Current Research on Load Prediction
1.3. Contribution of the Paper
2. Operational Strategy of BESS and Prediction System
2.1. Operational Strategy of BESS
2.2. The Structure of the Prediction System
3. BP and GA–BP Neural Network Modeling
3.1. BP Neural Network Modeling
3.2. GA–BP Neural Network
4. BP and GA–BP Neural Network Realization
4.1. BP Neural Network Model Design
4.2. BP Neural Network Model Analysis
Algorithm 1: BP neural network parameters |
Procedure test1() temp ← randperm(size(X, 1)) for i ← 1 to 60 do P_train[i] ← X[temp(i)] end for for i ← 61 to end do P_test[i] ← X[temp(i)] end for M ← size(P_train, 2); for i ← 1 to 60 do T_train[i] ← Y[temp(i)] end for for i ← 61 to end do T_test[i] ← Y[temp(i)] end for N ← size(T_test, 2) net. trainParam.epochs ← 1000 net. trainParam.goal ← 1e−3 net. trainParam.lr ← 0.01 end procedure |
4.3. GA–BP Neural Network Model Analysis
Algorithm 2: GA–BP neural network parameters |
Procedure test2() net. trainParam.epochs ← 1000 net. trainParam.goal ← 1e−4 net. trainParam.lr ← 0.01 net. trainParam.showWindow ← 0 maxgen ← 100 sizepop ← 10 pcross ← 0.8 pmutation ← 0.1 end procedure |
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Chandak, S.; Rout, P.K. The implementation framework of a microgrid: A review. Int. J. Energy Res. 2021, 45, 3523–3547. [Google Scholar] [CrossRef]
- Azimi Nasab, M.; Zand, M.; Eskandari, M.; Sanjeevikumar, P.; Siano, P. Optimal planning of electrical appliance of residential units in a smart home network using cloud services. Smart Cities 2021, 4, 1173–1195. [Google Scholar] [CrossRef]
- Yu, B.; Guo, J.; Zhou, C.; Gan, Z.; Yu, J.; Lu, F. A review on microgrid technology with distributed energy. In Proceedings of the 2017 International Conference on Smart Grid and Electrical Automation (ICSGEA), IEEE, Changsha, China, 27–28 May 2017. [Google Scholar]
- Eskandari, M.; Li, L.; Moradi, M.H.; Siano, P.; Blaabjerg, F. Active power sharing and frequency restoration in an autonomous networked microgrid. IEEE Trans. Power Syst. 2019, 34, 4706–4717. [Google Scholar] [CrossRef]
- Moradi, M.H.; Eskandari, M. A hybrid method for Simultaneous optimization of DG capacity and operational strategy in microgrids considering uncertainty in electricity price forecasting. Renew. Energy 2014, 68, 697–714. [Google Scholar] [CrossRef]
- Alvarez-Diazcomas, A.; López, H.; Carrillo-Serrano, R.V.; Rodríguez-Reséndiz, J.; Vázquez, N.; Herrera-Ruiz, G. A Novel Integrated Topology to Interface Electric Vehicles and Renewable Energies with the Grid. Energies 2019, 12, 4091. [Google Scholar] [CrossRef]
- Moradi, M.H.; Eskandari, M.; Hosseinian, S.M. Operational strategy optimization in an optimal sized smart microgrid. IEEE Trans. Smart Grid 2015, 6, 1087–1095. [Google Scholar] [CrossRef]
- Karami, H.; Sanjari, M.J.; Hosseinian, S.H.; Gharehpetian, G.B. An optimal dispatch algorithm for managing residential distributed energy resources. IEEE Trans. Smart Grid 2014, 5, 2360–2367. [Google Scholar] [CrossRef]
- He, J. The development and utilization of microgrid technologies in China. Energy Sources Part A Recovery Util. Environ. Eff. 2019, 41, 1535–1556. [Google Scholar] [CrossRef]
- Moradi, M.H.; Eskandari, M.; Hosseinian, S.M. Cooperative control strategy of energy storage systems and micro sources for stabilizing microgrids in different operation modes. Int. J. Electr. Power Energy Syst. 2016, 6, 390–400. [Google Scholar] [CrossRef]
- Estévez-Bén, A.A.; López Tapia, H.J.C.; Carrillo-Serrano, R.V.; Rodríguez-Reséndiz, J.; Vázquez Nava, N. A new predictive control strategy for multilevel current-source inverter grid-connected. Electronics 2019, 8, 902. [Google Scholar] [CrossRef] [Green Version]
- Eskandari, M.; Rajabi, A.; Savkin, A.V.; Moradi, M.H.; Dong, Z.Y. Battery energy storage systems (BESSs) and the economy-dynamics of microgrids: Review, analysis, and classification for standardization of BESSs applications. J. Energy Storage 2022, 55, 105627. [Google Scholar] [CrossRef]
- Wang, Y.; Rousis, A.O.; Strbac, G. On microgrids and resilience: A comprehensive review on modeling and operational strategies. Renew. Sustain. Energy Rev. 2020, 134, 110313. [Google Scholar] [CrossRef]
- Lopes JA, P.; Moreira, C.L.; Madureira, A.G. Defining control strategies for microgrids islanded operation. IEEE Trans. Power Syst. 2006, 21, 916–924. [Google Scholar] [CrossRef]
- López, H.; Rodríguez-Reséndiz, J.; Guo, X.; Vázquez, N.; Carrillo-Serrano, R.V. Transformerless common-mode current-source inverter grid-connected for PV applications. IEEE Access 2018, 6, 62944–62953. [Google Scholar] [CrossRef]
- Pearre, N.; Swan, L. Combining wind, solar, and in-stream tidal electricity generation with energy storage using a load-perturbation control strategy. Energy 2020, 203, 117898. [Google Scholar] [CrossRef]
- Hernandez, L.; Baladrón, C.; Aguiar, J.M.; Carro, B.; Sanchez-Esguevillas, A.J.; Lloret, J. Short-term load forecasting for microgrids based on artificial neural networks. Energies 2013, 6, 1385–1408. [Google Scholar] [CrossRef]
- Park, D.C.; El-Sharkawi, M.A.; Marks, R.J.; Atlas, L.E.; Damborg, M.J. Electric load forecasting using an artificial neural network. IEEE Trans. Power Syst. 1991, 6, 442–449. [Google Scholar] [CrossRef]
- Bai, B.; Zhang, J.; Wu, X.; Zhu, W.G.; Li, X. Reliability prediction-based improved dynamic weight particle swarm optimization and back propagation neural network in engineering systems. Expert Syst. Appl. 2021, 177, 114952. [Google Scholar] [CrossRef]
- Tyagi, A.; Bhushan, B.; Singh, R.V. Big Data Analytics for Wireless Sensor Networks and Smart Grids: Applications, Design Issues, and Future Challenges. In Integration of WSNs into Internet of Things; CRC Press: Boca Raton, FL, USA, 2021; pp. 135–163. [Google Scholar]
- Lu, Y.; Wang, G. A load forecasting model based on support vector regression with whale optimization algorithm. Multimed. Tools Appl. 2022, 1–21. [Google Scholar] [CrossRef]
- Tian, W.; Bao, Y.; Liu, W. Wind Power Forecasting by the BP Neural Network with the Support of Machine Learning. Math. Probl. Eng. 2022, 2022, 7952860. [Google Scholar] [CrossRef]
- Eskandari, M.; Li, L. Microgrid operation improvement by adaptive virtual impedance. IET Renew. Power Gener. 2019, 13, 296–307. [Google Scholar] [CrossRef]
- Moradi, M.H.; Eskandari, M.; Siano, P. Safe transition from connection mode to islanding mode in Microgrids. In Proceedings of the 2016 24th Iranian Conference on Electrical Engineering (ICEE), IEEE, Shiraz, Iran, 10–12 May 2016; pp. 1902–1907. [Google Scholar]
- Cheng, Z.; Jia, D.; Li, Z.; Xu, S.; Si, J. Multi-time-scale energy management for microgrid using expected-scenario-oriented stochastic optimization. Sustain. Energy Grids Netw. 2022, 30, 100670. [Google Scholar] [CrossRef]
- Bartolini, A.; Carducci, F.; Muñoz, C.B.; Comodi, G. Energy storage and multi energy systems in local energy communities with high renewable energy penetration. Renew. Energy 2020, 159, 595–609. [Google Scholar] [CrossRef]
- Cha, J.W.; Joo, S.K. Probabilistic Short-Term Load Forecasting Incorporating Behind-the-Meter (BTM) Photovoltaic (PV) Generation and Battery Energy Storage Systems (BESSs). Energies 2021, 14, 7067. [Google Scholar] [CrossRef]
- Mansouri, M.; Eskandari, M.; Asadi, Y.; Siano, P.; Alhelou, H.H. Pre-Perturbation Operational Strategy Scheduling in Microgrids by Two-Stage Adjustable Robust Optimization. IEEE Access 2022, 10, 74655–74670. [Google Scholar] [CrossRef]
- Zhao, Z.; Xin, H.; Ren, Y.; Guo, X. Application and comparison of BP neural network algorithm in MATLAB. In Proceedings of the 2010 International Conference on Measuring Technology and Mechatronics Automation, IEEE, Changsha, China, 13–14 March 2010; Volume 1. [Google Scholar]
- Rodríguez-Abreo, O.; Rodríguez-Reséndiz, J.; Montoya-Santiyanes, L.A.; Álvarez-Alvarado, J.M. Non-linear regression models with vibration amplitude optimization algorithms in a microturbine. Sensors 2021, 22, 130. [Google Scholar] [CrossRef]
- Torres-Salinas, H.; Rodríguez-Reséndiz, J.; Cruz-Miguel, E.E.; Ángeles-Hurtado, L.A. Fuzzy Logic and Genetic-Based Algorithm for a Servo Control System. Micromachines 2022, 13, 586. [Google Scholar] [CrossRef]
- Katoch, S.; Chauhan, S.S.; Kumar, V. A review on genetic algorithm: Past, present, and future. Multimed. Tools Appl. 2021, 80, 8091–8126. [Google Scholar] [CrossRef]
- Nagapurkar, P.; Smith, J.D. Techno-economic optimization and social costs assessment of microgrid-conventional grid integration using genetic algorithm and Artificial Neural Networks: A case study for two US cities. J. Clean. Prod. 2019, 229, 552–569. [Google Scholar] [CrossRef]
Input | |||||||
---|---|---|---|---|---|---|---|
Day | Temperature | Pressure | Humidity | Wind Speed | Sine Value of Wind Angle | Cosine Value of Wind Angle | Output |
1.00 | 290.16 | 1029 | 55 | 5 | −0.5 | −0.866025 | 1359 |
2.00 | 290.66 | 1029 | 55 | 5 | −0.766044443 | −0.642788 | 1404 |
3.00 | 290.67 | 1029 | 59 | 4 | −0.766044443 | −0.642788 | 1481 |
4.00 | 287.64 | 1029 | 62 | 4 | −0.866025404 | −0.5 | 1577 |
5.00 | 285.63 | 1029 | 67 | 5 | −0.866025404 | −0.5 | 1513 |
6.00 | 283.63 | 1030 | 71 | 3 | −0.866025404 | −0.5 | 1453 |
7.00 | 283.13 | 1030 | 71 | 4 | −0.866025404 | −0.5 | 1577 |
8.00 | 283.13 | 1030 | 71 | 4 | −0.939692621 | −0.34202 | 1897 |
9.00 | 282.14 | 1030 | 81 | 2 | −0.984807753 | −0.173648 | 2133 |
10.00 | 283.14 | 1030 | 76 | 2 | −0.984807753 | −0.173648 | 2081 |
11.00 | 282.13 | 1030 | 76 | 5 | −0.866025404 | −0.5 | 2012 |
12.00 | 282.14 | 1030 | 81 | 1 | −0.939692621 | 0.3420201 | 1841 |
13.00 | 281.64 | 1030 | 81 | 1 | −0.984807753 | 0.1736482 | 1800 |
14.00 | 280.64 | 1030 | 87 | 2 | −0.984807753 | −0.173648 | 1882 |
15.00 | 280.64 | 1030 | 87 | 4 | −0.939692621 | −0.34202 | 2025 |
16.00 | 281.15 | 1030 | 87 | 3 | −0.939692621 | −0.34202 | 2157 |
17.00 | 280.14 | 1030 | 81 | 3 | −0.866025404 | −0.5 | 2112 |
18.00 | 280.64 | 1030 | 81 | 1 | 0 | 1 | 2021 |
19.00 | 280.64 | 1030 | 81 | 3 | −0.984807753 | −0.173648 | 2077 |
20.00 | 282.66 | 1031 | 81 | 2 | −0.984807753 | −0.173648 | 2131 |
21.00 | 286.16 | 1031 | 71 | 4 | −0.939692621 | −0.34202 | 2319 |
22.00 | 288.66 | 1031 | 62 | 4 | −0.866025404 | −0.5 | 2702 |
23.00 | 290.66 | 1031 | 55 | 4 | −0.866025404 | −0.5 | 2996 |
24.00 | 291.66 | 1030 | 52 | 4 | −0.64278761 | −0.766044 | 3139 |
25.00 | 292.16 | 1029 | 48 | 3 | −0.64278761 | −0.766044 | 3217 |
26.00 | 292.16 | 1029 | 52 | 3 | −0.766044443 | −0.642788 | 3183 |
27.00 | 291.66 | 1029 | 55 | 2 | −0.766044443 | −0.642788 | 3092 |
28.00 | 288.66 | 1029 | 67 | 2 | −0.866025404 | −0.5 | 3065 |
29.00 | 285.64 | 1030 | 76 | 4 | −0.866025404 | −0.5 | 2936 |
30.00 | 284.15 | 1030 | 81 | 3 | −0.939692621 | −0.34202 | 2681 |
31.00 | 282.64 | 1030 | 87 | 2 | −0.984807753 | −0.173648 | 2592 |
32.00 | 282.64 | 1030 | 87 | 4 | −0.939692621 | −0.34202 | 2543 |
33.00 | 282.15 | 1030 | 87 | 2 | −0.984807753 | −0.173648 | 2503 |
34.00 | 281.64 | 1031 | 87 | 3 | −1 | 0 | 2581 |
35.00 | 280.64 | 1031 | 93 | 2 | −0.984807753 | −0.173648 | 2608 |
36.00 | 280.15 | 1030 | 93 | 2 | −1 | 0 | 2422 |
37.00 | 280.64 | 1030 | 87 | 2 | −1 | 0 | 2217 |
38.00 | 279.64 | 1030 | 93 | 2 | −0.939692621 | 0.3420201 | 1875 |
39.00 | 279.15 | 1030 | 100 | 1 | −0.984807753 | −0.173648 | 1561 |
40.00 | 279.64 | 1030 | 93 | 2 | −1 | 0 | 1213 |
41.00 | 279.15 | 1030 | 93 | 2 | −0.984807753 | −0.173648 | 1020 |
42.00 | 278.64 | 1030 | 93 | 2 | −1 | 0 | 1103 |
43.00 | 279.14 | 1030 | 93 | 3 | −0.984807753 | −0.173648 | 1249 |
44.00 | 281.66 | 1031 | 93 | 1 | −1 | 0 | 1323 |
45.00 | 285.66 | 1031 | 71 | 2 | −0.984807753 | 0.1736482 | 1286 |
46.00 | 288.16 | 1031 | 67 | 2 | −1 | 0 | 1325 |
47.00 | 291.16 | 1030 | 59 | 1 | 0 | 1 | 1370 |
48.00 | 292.15 | 1029 | 52 | 1 | −0.342020143 | −0.939693 | 1456 |
49.00 | 292.66 | 1029 | 52 | 1 | 0 | 1 | 1605 |
50.00 | 292.66 | 1028 | 59 | 3 | 0.766044443 | −0.642788 | 1658 |
51.00 | 291.66 | 1028 | 55 | 3 | 0.766044443 | −0.642788 | 1592 |
52.00 | 288.15 | 1028 | 72 | 1 | 0.766044443 | −0.642788 | 1455 |
53.00 | 286.14 | 1029 | 76 | 1 | 0.866025404 | −0.5 | 1489 |
54.00 | 284.14 | 1029 | 81 | 1 | 0.325568154 | −0.945519 | 1471 |
55.00 | 282.64 | 1029 | 93 | 0 | 0 | 1 | 1418 |
56.00 | 281.66 | 1029 | 100 | 1 | −1 | 0 | 1286 |
57.00 | 280.64 | 1029 | 100 | 2 | −0.939692621 | 0.3420201 | 1117 |
58.00 | 280.64 | 1029 | 93 | 2 | −0.939692621 | 0.3420201 | 973 |
59.00 | 280.15 | 1029 | 100 | 2 | −0.866025404 | 0.5 | 891 |
60.00 | 280.15 | 1028 | 93 | 1 | −0.984807753 | 0.1736482 | 764 |
61.00 | 279.64 | 1028 | 93 | 2 | −0.866025404 | 0.5 | 697 |
62.00 | 279.64 | 1028 | 93 | 1 | −0.984807753 | 0.1736482 | 604 |
63.00 | 279.15 | 1028 | 93 | 2 | −1 | 0 | 584 |
64.00 | 278.64 | 1027 | 93 | 2 | −0.984807753 | 0.1736482 | 617 |
65.00 | 278.15 | 1027 | 100 | 2 | −1 | 0 | 673 |
66.00 | 278.15 | 1027 | 93 | 2 | −0.939692621 | 0.3420201 | 778 |
67.00 | 277.64 | 1027 | 93 | 2 | −0.939692621 | 0.3420201 | 924 |
68.00 | 280.15 | 1028 | 87 | 1 | −0.984807753 | 0.1736482 | 1092 |
69.00 | 284.15 | 1028 | 71 | 0 | 0 | 1 | 1198 |
70.00 | 287.16 | 1028 | 62 | 0 | 0 | 1 | 1240 |
71.00 | 289.66 | 1028 | 59 | 1 | 0 | 1 | 1326 |
72.00 | 290.15 | 1027 | 55 | 1 | 0.866025404 | 0.5 | 1398 |
73.00 | 290.15 | 1027 | 55 | 1 | 0.017452406 | 0.9998477 | 1537 |
74.00 | 290.15 | 1026 | 51 | 0 | 0 | 1 | 1792 |
75.00 | 291.15 | 1026 | 45 | 0 | 0 | 1 | 2025 |
76.00 | 291.15 | 1026 | 45 | 0 | 0 | 1 | 2340 |
77.00 | 287.15 | 1026 | 58 | 1 | 0.017452406 | 0 | 2462 |
78.00 | 284.15 | 1027 | 71 | 0 | 0 | 1 | 2672 |
79.00 | 282.15 | 1027 | 71 | 1 | 0.017452406 | 0.9998477 | 2852 |
80.00 | 281.15 | 1027 | 87 | 1 | 0.017452406 | 0.9998477 | 3037 |
81.00 | 280.15 | 1028 | 93 | 1 | 0.017452406 | 0.9998477 | 3340 |
82.00 | 279.15 | 1028 | 93 | 2 | 0.034899497 | 0.9993908 | 3444 |
83.00 | 278.15 | 1028 | 93 | 2 | 0.034899497 | 0.9993908 | 3319 |
84.00 | 278.15 | 1028 | 93 | 2 | 0.034899497 | 0.9993908 | 3168 |
85.00 | 278.15 | 1028 | 93 | 1 | 0.017452406 | 0.9998477 | 3127 |
86.00 | 278.15 | 1027 | 93 | 1 | 0.017452406 | 0.9998477 | 3379 |
87.00 | 277.15 | 1028 | 93 | 2 | 0.034899497 | 0.9993908 | 3729 |
88.00 | 277.15 | 1028 | 100 | 2 | 0.034899497 | 0.9993908 | 4059 |
89.00 | 277.15 | 1027 | 93 | 1 | 0.017452406 | 0.9998477 | 4340 |
90.00 | 276.15 | 1028 | 93 | 1 | 0.017452406 | 0.9998477 | 4785 |
91.00 | 276.15 | 1028 | 93 | 2 | 0.034899497 | 0.9993908 | 5464 |
92.00 | 276.15 | 1029 | 93 | 2 | 0.034899497 | 0.9993908 | 5848 |
93.00 | 280.15 | 1029 | 81 | 1 | 0.017452406 | 0.9998477 | 6151 |
94.00 | 283.15 | 1029 | 66 | 2 | 0.034899497 | 0.9993908 | 6461 |
95.00 | 285.15 | 1030 | 66 | 1 | 0.017452406 | 0.9998477 | 6871 |
96.00 | 286.15 | 1030 | 62 | 1 | 0.017452406 | 0.9998477 | 7062 |
MAE | MSE | RMSE | R2 | MAPE | |
---|---|---|---|---|---|
BP neural network | 2.2985 | 30.3493 | 5.509 | 0.6029 | 0.2791 |
GA–BP neural network | 1.1213 | 2.20221 | 1.422 | 0.966 | 0.0683 |
Error reduction (%) | 51.20% | 93.30% | 74.18% | 36.30% | 75.50% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zheng, C.; Eskandari, M.; Li, M.; Sun, Z. GA−Reinforced Deep Neural Network for Net Electric Load Forecasting in Microgrids with Renewable Energy Resources for Scheduling Battery Energy Storage Systems. Algorithms 2022, 15, 338. https://doi.org/10.3390/a15100338
Zheng C, Eskandari M, Li M, Sun Z. GA−Reinforced Deep Neural Network for Net Electric Load Forecasting in Microgrids with Renewable Energy Resources for Scheduling Battery Energy Storage Systems. Algorithms. 2022; 15(10):338. https://doi.org/10.3390/a15100338
Chicago/Turabian StyleZheng, Chaoran, Mohsen Eskandari, Ming Li, and Zeyue Sun. 2022. "GA−Reinforced Deep Neural Network for Net Electric Load Forecasting in Microgrids with Renewable Energy Resources for Scheduling Battery Energy Storage Systems" Algorithms 15, no. 10: 338. https://doi.org/10.3390/a15100338
APA StyleZheng, C., Eskandari, M., Li, M., & Sun, Z. (2022). GA−Reinforced Deep Neural Network for Net Electric Load Forecasting in Microgrids with Renewable Energy Resources for Scheduling Battery Energy Storage Systems. Algorithms, 15(10), 338. https://doi.org/10.3390/a15100338