Optimal dispatch of integrated energy system based on deep reinforcement learning
Optimized scheduling of integrated energy systems is of great significance for achieving multi-energy complementarity and economic operation of the system. However, the intermittency of renewable energy sources and the uncertainty of user energy demand cause random fluctuations in the supply and dem...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484723013987 |
| _version_ | 1797374190412627968 |
|---|---|
| author | Xiang Zhou Jiye Wang Xinying Wang Sheng Chen |
| author_facet | Xiang Zhou Jiye Wang Xinying Wang Sheng Chen |
| author_sort | Xiang Zhou |
| collection | DOAJ |
| description | Optimized scheduling of integrated energy systems is of great significance for achieving multi-energy complementarity and economic operation of the system. However, the intermittency of renewable energy sources and the uncertainty of user energy demand cause random fluctuations in the supply and demand sides of the system. Traditional scheduling methods are difficult to accurately adapt to the dynamic changes of the actual environment. In view of the uncertainty associated with renewable energy and load in integrated energy systems, an optimal dispatch method based on deep reinforcement learning is proposed. This study first outlines the methodology of deep reinforcement learning and then presents an optimal dispatch model based on this approach. The model incorporates a well-designed state space, action space, and reward function. Next, the process of model solving using the Asynchronous Advantage Actor-Critic (A3C) algorithm is described. Finally, simulation results demonstrate that the proposed method can adaptively respond to the uncertainty of energy sources and loads, and achieve optimal performance comparable to that of traditional mathematical programming methods. |
| first_indexed | 2024-03-08T19:02:16Z |
| format | Article |
| id | doaj.art-dc4796c956044bb4b3a670739ac7c74a |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-03-08T19:02:16Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-dc4796c956044bb4b3a670739ac7c74a2023-12-28T05:18:11ZengElsevierEnergy Reports2352-48472023-11-019373378Optimal dispatch of integrated energy system based on deep reinforcement learningXiang Zhou0Jiye Wang1Xinying Wang2Sheng Chen3Corresponding author.; China Electric Power Research Institute, Haidian District, Beijing 100192, ChinaChina Electric Power Research Institute, Haidian District, Beijing 100192, ChinaChina Electric Power Research Institute, Haidian District, Beijing 100192, ChinaChina Electric Power Research Institute, Haidian District, Beijing 100192, ChinaOptimized scheduling of integrated energy systems is of great significance for achieving multi-energy complementarity and economic operation of the system. However, the intermittency of renewable energy sources and the uncertainty of user energy demand cause random fluctuations in the supply and demand sides of the system. Traditional scheduling methods are difficult to accurately adapt to the dynamic changes of the actual environment. In view of the uncertainty associated with renewable energy and load in integrated energy systems, an optimal dispatch method based on deep reinforcement learning is proposed. This study first outlines the methodology of deep reinforcement learning and then presents an optimal dispatch model based on this approach. The model incorporates a well-designed state space, action space, and reward function. Next, the process of model solving using the Asynchronous Advantage Actor-Critic (A3C) algorithm is described. Finally, simulation results demonstrate that the proposed method can adaptively respond to the uncertainty of energy sources and loads, and achieve optimal performance comparable to that of traditional mathematical programming methods.http://www.sciencedirect.com/science/article/pii/S2352484723013987Integrated energy systemOptimal dispatchDeep reinforcement learningUncertainty |
| spellingShingle | Xiang Zhou Jiye Wang Xinying Wang Sheng Chen Optimal dispatch of integrated energy system based on deep reinforcement learning Energy Reports Integrated energy system Optimal dispatch Deep reinforcement learning Uncertainty |
| title | Optimal dispatch of integrated energy system based on deep reinforcement learning |
| title_full | Optimal dispatch of integrated energy system based on deep reinforcement learning |
| title_fullStr | Optimal dispatch of integrated energy system based on deep reinforcement learning |
| title_full_unstemmed | Optimal dispatch of integrated energy system based on deep reinforcement learning |
| title_short | Optimal dispatch of integrated energy system based on deep reinforcement learning |
| title_sort | optimal dispatch of integrated energy system based on deep reinforcement learning |
| topic | Integrated energy system Optimal dispatch Deep reinforcement learning Uncertainty |
| url | http://www.sciencedirect.com/science/article/pii/S2352484723013987 |
| work_keys_str_mv | AT xiangzhou optimaldispatchofintegratedenergysystembasedondeepreinforcementlearning AT jiyewang optimaldispatchofintegratedenergysystembasedondeepreinforcementlearning AT xinyingwang optimaldispatchofintegratedenergysystembasedondeepreinforcementlearning AT shengchen optimaldispatchofintegratedenergysystembasedondeepreinforcementlearning |