An energy management strategy for integrated electricity-thermal energy systems using the DQN-CE algorithm
To address the uncertainty and intermittency of renewable energy output in integrated electricity-thermal energy systems， a reinforcement learning method for energy management is proposed， aiming to minimize the operating costs of the system. First， an energy management model for the integrated elec...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
zhejiang electric power
2025-01-01
|
| Series: | Zhejiang dianli |
| Subjects: | |
| Online Access: | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=002a0f5e-a813-4b61-8f6a-d70722c1fd49 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823857101095567360 |
|---|---|
| author | ZHU Jiejie PI Zhiyong CHEN Daicai TAN Hong |
| author_facet | ZHU Jiejie PI Zhiyong CHEN Daicai TAN Hong |
| author_sort | ZHU Jiejie |
| collection | DOAJ |
| description | To address the uncertainty and intermittency of renewable energy output in integrated electricity-thermal energy systems， a reinforcement learning method for energy management is proposed， aiming to minimize the operating costs of the system. First， an energy management model for the integrated electricity-thermal energy system is established. Next， the energy management process of the system， which includes renewable energy， is transformed into a Markov decision process （MDP）. The DQN-CE （Deep Q-Network with cross-entropy） algorithm， integrating NoisyNet and a self-attention mechanism， is then used to train the agent through interactive learning. Finally， case study analysis shows that the agent trained using the proposed method can respond in real time to the uncertainties of renewable energy and manage the energy of the integrated electricity-thermal energy system with renewable sources online. |
| format | Article |
| id | doaj-art-eb3001705ac2404d9beb6fcc8ed1fdcb |
| institution | Kabale University |
| issn | 1007-1881 |
| language | zho |
| publishDate | 2025-01-01 |
| publisher | zhejiang electric power |
| record_format | Article |
| series | Zhejiang dianli |
| spelling | doaj-art-eb3001705ac2404d9beb6fcc8ed1fdcb2025-02-12T00:54:58Zzhozhejiang electric powerZhejiang dianli1007-18812025-01-01441445310.19585/j.zjdl.2025010051007-1881（2025）01-0044-10An energy management strategy for integrated electricity-thermal energy systems using the DQN-CE algorithmZHU Jiejie0PI Zhiyong1CHEN Daicai2TAN Hong3College of Electrical Engineering and New Energy， China Three Gorges University， Yichang， Hubei 443002， ChinaState Grid Jingmen Power Supply Company， Jingmen， Hubei 448000， ChinaState Grid Lichuan Power Supply Company， Lichuan， Hubei 445499， ChinaCollege of Electrical Engineering and New Energy， China Three Gorges University， Yichang， Hubei 443002， ChinaTo address the uncertainty and intermittency of renewable energy output in integrated electricity-thermal energy systems， a reinforcement learning method for energy management is proposed， aiming to minimize the operating costs of the system. First， an energy management model for the integrated electricity-thermal energy system is established. Next， the energy management process of the system， which includes renewable energy， is transformed into a Markov decision process （MDP）. The DQN-CE （Deep Q-Network with cross-entropy） algorithm， integrating NoisyNet and a self-attention mechanism， is then used to train the agent through interactive learning. Finally， case study analysis shows that the agent trained using the proposed method can respond in real time to the uncertainties of renewable energy and manage the energy of the integrated electricity-thermal energy system with renewable sources online.https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=002a0f5e-a813-4b61-8f6a-d70722c1fd49noisynetdeep q-networkself-attention mechanismcross-entropy loss function |
| spellingShingle | ZHU Jiejie PI Zhiyong CHEN Daicai TAN Hong An energy management strategy for integrated electricity-thermal energy systems using the DQN-CE algorithm Zhejiang dianli noisynet deep q-network self-attention mechanism cross-entropy loss function |
| title | An energy management strategy for integrated electricity-thermal energy systems using the DQN-CE algorithm |
| title_full | An energy management strategy for integrated electricity-thermal energy systems using the DQN-CE algorithm |
| title_fullStr | An energy management strategy for integrated electricity-thermal energy systems using the DQN-CE algorithm |
| title_full_unstemmed | An energy management strategy for integrated electricity-thermal energy systems using the DQN-CE algorithm |
| title_short | An energy management strategy for integrated electricity-thermal energy systems using the DQN-CE algorithm |
| title_sort | energy management strategy for integrated electricity thermal energy systems using the dqn ce algorithm |
| topic | noisynet deep q-network self-attention mechanism cross-entropy loss function |
| url | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=002a0f5e-a813-4b61-8f6a-d70722c1fd49 |
| work_keys_str_mv | AT zhujiejie anenergymanagementstrategyforintegratedelectricitythermalenergysystemsusingthedqncealgorithm AT pizhiyong anenergymanagementstrategyforintegratedelectricitythermalenergysystemsusingthedqncealgorithm AT chendaicai anenergymanagementstrategyforintegratedelectricitythermalenergysystemsusingthedqncealgorithm AT tanhong anenergymanagementstrategyforintegratedelectricitythermalenergysystemsusingthedqncealgorithm AT zhujiejie energymanagementstrategyforintegratedelectricitythermalenergysystemsusingthedqncealgorithm AT pizhiyong energymanagementstrategyforintegratedelectricitythermalenergysystemsusingthedqncealgorithm AT chendaicai energymanagementstrategyforintegratedelectricitythermalenergysystemsusingthedqncealgorithm AT tanhong energymanagementstrategyforintegratedelectricitythermalenergysystemsusingthedqncealgorithm |