Automatic Switching Strategy of Grid-Connected/Off-Grid Mode of Photovoltaic Storage and Charging Integrated Station Based on Intelligent Control
DOI:
https://doi.org/10.52152/4125Keywords:
Photovoltaic storage and charging integrated station, grid-connected/off-grid mode, intelligent control, DQN-LSTM model, Switching accuracyAbstract
With the widespread application of renewable energy, photovoltaic (PV) storage and charging (SC) integrated stations are important in providing a stable power supply and optimizing energy management. Traditional integrated PV SC stations mostly use the PID (Proportion Integral Differential) control algorithm for automatic switching in grid-connected/off-grid (GC/OG) mode. The switching decision accuracy is low, energy consumption is increased, and there needs to be a more intelligent prediction of future photovoltaic power generation (PVPG), load demand and grid conditions. This paper is the first to combine the advantages of the dynamic decision-making of the DQN (Deep Q-Network) algorithm and the time series prediction of the LSTM (Long Short-Term Memory) model to study the automatic switching strategy of the grid-connected/off-grid mode of the integrated photovoltaic storage and charging station. The study first built a PV SC integrated station model, including PVPG, energy storage system, power grid model and load demand model, and set the objective function and constraints. Then, the LSTM model was used to predict the future load demand and PVPG of the PV SC integrated station, and the prediction was input into the DQN model. Finally, the DQN model combined the LSTM prediction results with the current environmental status to decide whether the PV SC integrated station should be connected to or off the grid. The experiment is based on the data of the PV SC integrated station actually deployed in a particular area from January to June 2023, and the performance of the GC/OG mode automatic switching strategy of the PV SC integrated station is statistically analyzed. The experimental results show that the strategy switching accuracy of the DQN-LSTM (Deep Q-Network-Long Short-Term Memory) model reaches 95.87%, which is 15.44% higher than the traditional PID, and the energy efficiency ratio is as high as 1.75. The experimental results show that the DQN-LSTM model combined with intelligent control can automatically switch the GC/OG mode of the integrated PV SC station, which significantly improves the accuracy and efficiency of the strategy and reduces energy consumption to a certain extent.
References
E.T. Sayed, A.G. Olabi, A.H. Alami, A. Radwan, A. Mdallal, et al. Renewable energy and energy storage systems. Energies. 2023, 16(3), 1415-1440. DOI: 10.3390/en16031415
M.M. Gulzar, A. Iqbal, D. Sibtain, M. Khalid. An innovative converterless solar PV control strategy for a grid connected hybrid PV/wind/fuel-cell system coupled with battery energy storage. IEEE Access. 2023, 11, 23245-23259. DOI: 10.1109/ACCESS.2023.3252891
P. Barman, L. Dutta, S. Bordoloi, A. Kalita, P. Buragohain, et al. Renewable energy integration with electric vehicle technology, A review of the existing smart charging approaches. Renewable and Sustainable Energy Reviews. 2023, 183(1), 1-15. DOI: 10.1016/j.rser.2023.113518
A. Mohammed, O. Saif, M. Abo-Adma, A. Fahmy, R. Elazab. Strategies and sustainability in fast charging station deployment for electric vehicles. Scientific Reports. 2024, 14(1), 283-201. DOI: 10.1038/s41598-023-50825-7
S.S.G. Acharige, M.E. Haque, M.T. Arif, N. Hosseinzadeh, K.N. Hasan, et al. Review of electric vehicle charging technologies, standards, architectures, and converter configurations. IEEE Access. 2023, 11(1), 41218-41255. DOI: 10.1109/ACCESS.2023.3267164
M. Yao, D.N. Da, X.C. Lu, Y.H. Wang. A review of capacity allocation and control strategies for electric vehicle charging stations with integrated photovoltaic and energy storage systems. World Electric Vehicle Journal. 2024, 15(3), 101-128. DOI: 10.3390/wevj15030101
K.Y. Wu, T.C. Tai, B.H. Li, C.C. Kuo. Dynamic Energy Management Strategy of a Solar-and-Energy Storage-Integrated Smart Charging Station. Applied Sciences. 2024, 14(3), 1188-1204. DOI: 10.3390/app14031188
J. Hmad, A. Houari, A.E.M. Bouzid , A. Saim, H. Trabelsi. A review on mode transition strategies between grid-connected and standalone operation of voltage source inverters-based microgrids. Energies. 2023, 16(13), 5062-5102. DOI: 10.3390/en16135062
S.V. Karemore, E.V. Kumar. Design of efficient storage unit and EP-ANFIS controller for on-grid and off-grid connected PV-WT system. Periodica Polytechnica Electrical Engineering and Computer Science. 2022, 66(4), 336-349. DOI: 10.3311/PPee.20364
V. Gopu, M.S. Nagaraj. Adaptive fuzzy PID integrated renewable power management system for off grid and on grid conditions. International Journal of Power Electronics and Drive Systems (IJPEDS). 2024, 15(4), 2580-2590. DOI: 10.11591/ijpeds.v15.i4.pp2580-2590
H.Y. Qing, C.J. Zhang, J.Y. Xu, S.L. Zeng, X.Q. Guo. A Nonlinear Multimode Controller for Seamless off-Grid of Energy Storage Inverter Under Unintentional Islanding. IEEE Transactions on Industrial Electronics. 2023, 70(12), 12354-12364. DOI: 10.1109/TIE.2022.3232639
M. Kampik, M. Fice, A. Jurkiewicz. Adaptation of a cogenerator with induction generator to an on/off-grid operation using a power electronic system. Applied Sciences. 2023, 13(10), 5866-5889. DOI: 10.3390/app13105866
V. Perumal, S.K. Kannan, C.R. Balamurugan. Grid Mode Selection Scheme based on a Novel Fractional Order Proportional Resonant Controller for Hybrid Renewable Energy Resources. Electric Power Components and Systems. 2023, 51(09), 1-20. DOI: 10.1080/15325008.2023.2202674
Y. Xu, W.J. Gao, Y.X. Li. Cost-Effective Optimization of the Grid-Connected Residential Photovoltaic Battery System Based on Reinforcement Learning. Human-Centric Computing and Information Sciences. 2024, 14(2), 1-19. DOI: 10.22967/HCIS.2024.14.002
X.K. Ding, J.W. Cao. Deep and Reinforcement Learning in Virtual Synchronous Generator, A Comprehensive Review. Energies. 2024, 17(11), 2620-2639. DOI: 10.3390/en17112620
B. Zhang, W.H. Hu, X. Xu, T. Li, Z.Y. Zhang, et al. Physical-model-free intelligent energy management for a grid-connected hybrid wind-microturbine-PV-EV energy system via deep reinforcement learning approach. Renewable Energy. 2022, 200(1), 433-448. DOI: 10.1016/j.renene.2022.09.125
M. Nicola, C.I. Nicola, D. Selișteanu. Improvement of the control of a grid connected photovoltaic system based on synergetic and sliding mode controllers using a reinforcement learning deep deterministic policy gradient agent. Energies. 2022, 15(7), 2392-2423. DOI: 10.3390/en15072392
J.J. Qi, L. Lei, K. Zheng, S.X. Yang, X.M. Shen. Optimal scheduling in IoT-driven smart isolated microgrids based on deep reinforcement learning. IEEE Internet of Things Journal. 2023, 10(18), 16284-16299. DOI: 10.48550/arXiv.2305.00127
F. Mohammad, D.K. Kang, M.A. Ahmed, Y.C. Kim. Energy demand load forecasting for electric vehicle charging stations network based on convlstm and biconvlstm architectures. IEEE Access. 2023, 11(1), 67350-67369. DOI: 10.1109/ACCESS.2023.3274657
C.Y. Yang, H. Zhou, X.M. Chen, J.J. Huang. Demand Time Series Prediction of Stacked Long Short-Term Memory Electric Vehicle Charging Stations Based on Fused Attention Mechanism. Energies. 2024, 17(9), 2041-2056. DOI: 10.3390/en17092041
P. Aduama, Z.B. Zhang, A.S. Al-Sumaiti. Multi-feature data fusion-based load forecasting of electric vehicle charging stations using a deep learning model. Energies. 2023, 16(3), 1309-1322. DOI: 10.3390/en16031309
A. Avar, E. Ghanbari. Optimal integration and planning of PV and wind renewable energy sources into distribution networks using the hybrid model of analytical techniques and metaheuristic algorithms, A deep learning-based approach. Computers and Electrical Engineering. 2024, 117, 109280. DOI: 10.1016/j.compeleceng.2024.10928
A.M. Abomazid, N.A. El-Taweel, H.E.Z. Farag. Optimal energy management of hydrogen energy facility using integrated battery energy storage and solar photovoltaic systems. IEEE Transactions on Sustainable Energy. 2022, 13(3), 1457-1468. DOI: 10.1109/TSTE.2022.3161891
Y.J. Liu, L.N. Jian, Y.W. Jia. Energy management of green charging station integrated with photovoltaics and energy storage system based on electric vehicles classification. Energy Reports. 2023, 9(1), 1961-1973. DOI: 10.1016/j.egyr.2023.04.099
P. Ray, C. Bhattacharjee, K.R. Dhenuvakonda. Swarm intelligence‐based energy management of electric vehicle charging station integrated with renewable energy sources. International Journal of Energy Research. 2022, 46(15), 21598-21618. DOI: 10.1002/er.7601
G. Krishna, R. Singh, A. Gehlot, S.V. Akram, N. Priyadarshi, et al. Digital technology implementation in battery-management systems for sustainable energy storage, Review, challenges, and recommendations. Electronics. 2022, 11(17), 2695-2718. DOI: 10.3390/electronics11172695
K. Okay, S. Eray, A. Eray. Development of prototype battery management system for PV system. Renewable Energy. 2022, 181(1), 1294-1304. DOI: 10.1016/j.renene.2021.09.118
A.F. Guven, E. Yücel. Sustainable energy integration and optimization in microgrids, enhancing efficiency with electric vehicle charging solutions. Electrical Engineering. 2024, 10(1), 1-33. DOI: 10.1007/s00202-024-02619-x
H. Xiao, X.W. Pu, W. Pei, L. Ma, T.F. Ma. A novel energy management method for networked multi-energy microgrids based on improved DQN. IEEE Transactions on Smart Grid. 2023, 14(6), 4912-4926. DOI: 10.1109/TSG.2023.3261979
X. Yang, P. Liu, F. Liu, Z.C. Liu, D.Q. Wang, J. Zhu, et al. A DOD-SOH balancing control method for dynamic reconfigurable battery systems based on DQN algorithm. Frontiers in Energy Research. 2023, 11(1), 1-13. DOI: 10.3389/fenrg.2023.1333147
F. Yang, F. Gao, B.C. Liu, S. Ci. An adaptive control framework for dynamically reconfigurable battery systems based on deep reinforcement learning. IEEE Transactions on Industrial Electronics. 2022, 69(12), 12980-12987. DOI: 10.1109/TIE.2022.3142406
K. Sivamayil, E. Rajasekar, B. Aljafari, S. Nikolovski, S. Vairavasundaram, et al. A systematic study on reinforcement learning based applications. Energies. 2023, 16(3), 1512-1534. DOI: 10.3390/en16031512
S.W. Zhai, W.Y. Li, Z.Y. Qiu, X.Y. Zhang, S.X. Hou. An improved deep reinforcement learning method for dispatch optimization strategy of modern power systems. Entropy. 2023, 25(3), 546-568. DOI: 10.3390/e25030546
E.M. Al-Ali, Y. Hajji, Y. Said, M. Hleili, A.M. Alanzi, et al. Solar energy production forecasting based on a hybrid CNN-LSTM-transformer model. Mathematics. 2023, 11(3), 676-684. DOI: 10.3390/math11030676
D.K. Dhaked, S. Dadhich, D. Birla. Power output forecasting of solar photovoltaic plant using LSTM. Green Energy and Intelligent Transportation. 2023, 2(5), 1-9. DOI: 10.1016/j.geits.2023.100113
S.S. Chandel, A. Gupta, R. Chandel, S. Tajjour. Review of deep learning techniques for power generation prediction of industrial solar photovoltaic plants. Solar Compass. 2023, 8(1), 1-12. DOI: 10.1016/j.solcom.2023.100061
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Han Fu, Xiaoyu Liu, Xiaoming Chen, Yuanqi Ni, Hong Zheng (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
