A Deep Reinforcement Learning Optimization Method Considering Network Node Failures
Abstract
:1. Introduction
2. System Architecture
3. Model
3.1. IEEE-33 Node System Construction
3.2. DQN Model
3.2.1. Fundamental
- Breaking sequence dependency: by disrupting the order of samples, the experience replay mechanism helps to reduce the temporal correlation of training data and avoids the gradient estimation offset caused by a strong correlation between consecutive samples, thereby improving the generalization ability of the model.
- Data reuse: the reuse of experience samples not only improves the utilization rate of data, but also enhances the adaptability of the model to environmental dynamics, especially in scenarios where data are scarce or the acquisition cost is high.
3.2.2. Process
4. Experimental Settings
4.1. Single Node Failure in Microgrid
4.2. Multi-Node Failure in Microgrid
5. Conclusions
- From the research method and entry point, the model comprehensively considers the topology of the microgrid, rather than focusing only on a single component or local problem, thereby achieving comprehensive security optimization and ensuring that the various power nodes within the microgrid work together to pursue system-level security maximization.
- In terms of the ability to cope with the complex power grid environment, this method has made a breakthrough. Using the powerful ability of deep reinforcement learning, DRL-NNF can cope with high-dimensional state spaces and has advantages in dealing with modern microgrids with complex structures and dynamic characteristics. DRL-NNF uses the powerful characterization capability of deep networks to avoid the complex problems of traditional methods in the face of complex topologies.
- In terms of the universality of the method, the scope of application of DRL-NNF is not limited to fault control. This method is also applicable to other key areas in the operation of microgrids, such as load distribution, line loss reduction, and energy efficiency improvement. Through the migration and application of models, it is possible to flexibly switch between different optimization objectives without training new models from scratch, which greatly saves time and computing resources, and also enhances the flexibility and efficiency of microgrids in multi-faceted performance optimization.
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Taouil, K.; Aloulou, R.; Bradai, S.; Gassara, A.; Kharrat, M.W.; Louati, B.; Giordani, M. P2P Energy Exchange Architecture for Swarm Electrification-Driven PV Communities. Energies 2024, 17, 3680. [Google Scholar] [CrossRef]
- Khazali, A.; Al-Wreikat, Y.; Fraser, E.J.; Sharkh, S.M.; Cruden, A.J.; Naderi, M.; Smith, M.J.; Palmer, D.; Gladwin, D.T.; Foster, M.P.; et al. Planning a Hybrid Battery Energy Storage System for Supplying Electric Vehicle Charging Station Microgrids. Energies 2024, 17, 3631. [Google Scholar] [CrossRef]
- Fresia, M.; Robbiano, T.; Caliano, M.; Delfino, F.; Bracco, S. Optimal Operation of an Industrial Microgrid within a Renewable Energy Community: A Case Study of a Greentech Company. Energies 2024, 17, 3567. [Google Scholar] [CrossRef]
- Naseri, N.; Aboudrar, I.; El Hani, S.; Ait-Ahmed, N.; Motahhir, S.; Machmoum, M. Energy Transition and Resilient Control for Enhancing Power Availability in Microgrids Based on North African Countries: A Review. Appl. Sci. 2024, 14, 6121. [Google Scholar] [CrossRef]
- Abeg, A.I.; Islam, M.R.; Hossain, M.A.; Ishraque, M.F.; Islam, M.R.; Hossain, M.J. Capacity and operation optimization of hybrid microgrid for economic zone using a novel meta-heuristic algorithm. J. Energy Storage 2024, 94, 112314. [Google Scholar] [CrossRef]
- Aiswarya, R.; Nair, D.S.; Rajeev, T.; Vinod, V. A novel SVM based adaptive scheme for accurate fault identification in microgrid. Electr. Power Syst. Res. 2023, 221, 109439. [Google Scholar]
- Jalli, R.K.; Mishra, S.P.; Dash, P.K.; Naik, J. Fault analysis of photovoltaic based DC microgrid using deep learning randomized neural network. Appl. Soft Comput. J. 2022, 126, 109314. [Google Scholar] [CrossRef]
- Sistani, A.; Hosseini, S.A.; Sadeghi, V.S.; Taheri, B. Fault Detection in a Single-Bus DC Microgrid Connected to EV/PV Systems and Hybrid Energy Storage Using the DMD-IF Method. Sustainability 2023, 15, 16269. [Google Scholar] [CrossRef]
- Biswal, C.; Sahu, B.K.; Mishra, M.; Rout, P.K. Real-Time Grid Monitoring and Protection: A Comprehensive Survey on the Advantages of Phasor Measurement Units. Energies 2023, 16, 4054. [Google Scholar] [CrossRef]
- Najafzadeh, M.; Pouladi, J.; Daghigh, A.; Beiza, J.; Abedinzade, T. Fault Detection, Classification and Localization Along the Power Grid Line Using Optimized Machine Learning Algorithms. Int. J. Comput. Intell. Syst. 2024, 17, 49. [Google Scholar] [CrossRef]
- Taifeng, C.; Chunbo, L. Soft computing based smart grid fault detection using computerised data analysis with fuzzy machine learning model. Sustain. Comput. Inform. Syst. 2024, 41, 100945. [Google Scholar]
- Wu, Y.; Xiao, F.; Liu, F.; Sun, Y.; Deng, X.; Lin, L.; Zhu, C. A Visual Fault Detection Algorithm of Substation Equipment Based on Improved YOLOv5. Appl. Sci. 2023, 13, 11785. [Google Scholar] [CrossRef]
- Fu, L.; Li, C.; Wang, B.; Ban, Y. Fault Location of Grid-connected Microgrid Lines Based on AVMD and Double-ended Traveling Wave Ranging. J. Phys. Conf. Ser. 2023, 2662, 012028. [Google Scholar] [CrossRef]
- Pan, P.; Mandal, R.K.; Rahman Redoy Akanda, M.M. Fault Classification with Convolutional Neural Networks for Microgrid Systems. Int. Trans. Electr. Energy Syst. 2022, 2022, 8431450. [Google Scholar] [CrossRef]
- Liu, Y.; Zhang, S.; Li, L.; Wang, S.; Lu, T.; Yu, H.; Liu, W. A machine learning-based fault identification method for microgrids with distributed generations. J. Phys. Conf. Ser. 2022, 2360, 012019. [Google Scholar] [CrossRef]
- Wu, H.; Ding, D.; She, Y.; Wang, L.; Ji, B.; Chen, T. Topology Optimization of Regional Power Grid Under Large-Scale Access of Distributed Photovoltaic Power Generation. J. Nanoelectron. Optoelectron. 2022, 17, 1648–1654. [Google Scholar] [CrossRef]
- Xu, X.; Chen, S.; Zhu, Z.; Meng, A.; Zhang, J.; Wen, H.; Zhang, K. Solving dynamic economic dispatch problem of power grid based on hybrid topology crisscross optimization algorithm. In Proceedings Volume 12330, Proceedings of the International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2022), Huzhou, China, 15–18 April 2022; Guangdong Univ. of Technology (China): Guangzhou, China; Meizhou Power Supply Bureau of Guangdong Power Grid Co., Ltd. (China): Meizhou, China; Zhuhai Huacheng Power Engineering Consultants Co., Ltd. (China): Zhuhai, China, 2022. [Google Scholar]
- Wu, Y.; Chen, J.; Ru, Y.; Xu, H.; Roger, M.; Ni, M. Research on Power Communication Network Planning Based on Information Transmission Reachability Against Cyber-Attacks. IEEE Syst. J. 2020, 15, 2883–2894. [Google Scholar] [CrossRef]
- Qin, S.; Zhang, X.; Wang, J.; Guo, X.; Qi, L.; Cao, J.; Liu, Y. An Improved Q-Learning Algorithm for Optimizing Sustainable Remanufacturing Systems. Sustainability 2024, 16, 4180. [Google Scholar] [CrossRef]
- Tresca, L.; Pulvirenti, L.; Rolando, L.; Millo, F. Development of a deep Q-learning energy management system for a hybrid electric vehicle. Transp. Eng. 2024, 16, 100241. [Google Scholar] [CrossRef]
- Zhang, Q.; Wu, C.; Tian, H.; Gao, Y.; Yao, W.; Wu, L. Safety reinforcement learning control via transfer learning. Automatica 2024, 166, 111714. [Google Scholar] [CrossRef]
- Emek, Y.; Lavi, R.; Niazadeh, R.; Shi, Y. Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes. Math. Oper. Res. 2024, 49, 880–900. [Google Scholar] [CrossRef]
- Li, Q.; Lin, T.; Yu, Q.; Du, H.; Li, J.; Fu, X. Review of Deep Reinforcement Learning and Its Application in Modern Renewable Power System Control. Energies 2023, 16, 4143. [Google Scholar] [CrossRef]
- Meng, T.; Li, X.; Zhang, S.; Zhao, Y. A Hybrid Secure Scheme for Wireless Sensor Networks against Timing Attacks Using Continuous-Time Markov Chain and Queueing Model. Sensors 2016, 16, 1606. [Google Scholar] [CrossRef] [PubMed]
- Habib, K.; Habib, S.; Khan, S.; Jafaripournimchahi, A.; Xing, X. A hybrid optimization approach for strategically placing electric vehicle charging stations in a radial distribution IEEE-33 bus system. Eng. Res. Express 2024, 6, 025344. [Google Scholar] [CrossRef]
- Liu, Y.; Ding, W.; Yang, M.; Zhu, H.; Liu, L.; Jin, T. Distributed Drive Autonomous Vehicle Trajectory Tracking Control Based on Multi-Agent Deep Reinforcement Learning. Mathematics 2024, 12, 1614. [Google Scholar] [CrossRef]
- Lu, C.; Xuan, D.; Liu, S.; Tan, J.; Hu, H.; Kang, Z.; Lin, L. Active equalization control method for battery pack based on Double-DQN. J. Energy Storage 2024, 88, 111361. [Google Scholar] [CrossRef]
- Yang, X.; Liu, P.; Liu, F.; Liu, Z.; Wang, D.; Zhu, J.; Wei, T. A DOD-SOH balancing control method for dynamic reconfigurable battery systems based on DQN algorithm. Front. Energy Res. 2023, 11, 1333147. [Google Scholar] [CrossRef]
- Wang, Z.; Li, X.; Sun, L.; Zhang, H.; Liu, H.; Wang, J. Learning State-Specific Action Masks for Reinforcement Learning. Algorithms 2024, 17, 60. [Google Scholar] [CrossRef]
Faulty Node ID | Faulty Node Type | Fault Duration/h | Fault Period |
---|---|---|---|
10 | PV | 2 | 1–3 |
Nodes Involved | Before Adjustment | After Adjustment |
---|---|---|
11-18 | 10-11-12-13-14-15-16-17-18 | 22-12-11 22-12-13-14-15-16-17-18 |
Faulty Node ID | Faulty Node Type | Fault Duration/h | Fault Period |
---|---|---|---|
5 | PV | 3 | 1–4 |
14 | Load | 3 | 1–4 |
28 | Load | 3 | 1–4 |
Nodes Involved | Before Adjustment | After Adjustment |
6-18 26-33 | 6-7-8-9-10-11-12-13-14-15-16-17-18 6-26-27-28-29-30-31-32-33 | 21-8-7-6-26-27 21-8-9-10-11-12-13 21-8-9-15-16-17-18-33-32-31-30-29 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 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
Ding, X.; Liao, X.; Cui, W.; Meng, X.; Liu, R.; Ye, Q.; Li, D. A Deep Reinforcement Learning Optimization Method Considering Network Node Failures. Energies 2024, 17, 4471. https://doi.org/10.3390/en17174471
Ding X, Liao X, Cui W, Meng X, Liu R, Ye Q, Li D. A Deep Reinforcement Learning Optimization Method Considering Network Node Failures. Energies. 2024; 17(17):4471. https://doi.org/10.3390/en17174471
Chicago/Turabian StyleDing, Xueying, Xiao Liao, Wei Cui, Xiangliang Meng, Ruosong Liu, Qingshan Ye, and Donghe Li. 2024. "A Deep Reinforcement Learning Optimization Method Considering Network Node Failures" Energies 17, no. 17: 4471. https://doi.org/10.3390/en17174471