Security Constrained Dispatch for Renewable Proliferated Distribution Network Based on Safe Reinforcement Learning
As the terminal of electricity consumption, the distribution network is a vital field to lower the carbon emission of the power system. With the integration of distributed energy resources, the flexibility of the distribution network has been promoted significantly where dispatch actions can be empl...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-07-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2022.933011/full |
| _version_ | 1818112004692377600 |
|---|---|
| author | Han Cui Han Cui Yujian Ye Yujian Ye Qidong Tian Yi Tang Yi Tang |
| author_facet | Han Cui Han Cui Yujian Ye Yujian Ye Qidong Tian Yi Tang Yi Tang |
| author_sort | Han Cui |
| collection | DOAJ |
| description | As the terminal of electricity consumption, the distribution network is a vital field to lower the carbon emission of the power system. With the integration of distributed energy resources, the flexibility of the distribution network has been promoted significantly where dispatch actions can be employed to lower carbon emissions without compromising the accessibility of reliable electricity. This study proposes a security constrained dispatch policy based on safe reinforcement learning for the distribution network. The researched problem is set up as a constrained Markov decision process, where continuous-discrete mixed action space and high-dimensional state space are in place. In addition, security-related rules are embedded into the problem formulation. To guarantee the generalization of the reinforcement learning agent, various scenarios are generated in the offline training stage, including randomness of renewables, scheduled maintenance, and different load profiles. A case study is performed on a modified version of the IEEE 33-bus system, and the numerical results verify the effectiveness of the proposed method in decarbonization. |
| first_indexed | 2024-12-11T03:12:03Z |
| format | Article |
| id | doaj.art-046d87999a8042c080bcfb444ef7bd93 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-12-11T03:12:03Z |
| publishDate | 2022-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-046d87999a8042c080bcfb444ef7bd932022-12-22T01:22:50ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2022-07-011010.3389/fenrg.2022.933011933011Security Constrained Dispatch for Renewable Proliferated Distribution Network Based on Safe Reinforcement LearningHan Cui0Han Cui1Yujian Ye2Yujian Ye3Qidong Tian4Yi Tang5Yi Tang6School of Cyber Science and Engineering, Southeast University, Nanjing, ChinaKey Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, ChinaKey Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, ChinaSchool of Electrical Engineering, Southeast University, Nanjing, ChinaShenzhen Power Supply Bureau, China Southern Power Grid, Shenzhen, ChinaSchool of Cyber Science and Engineering, Southeast University, Nanjing, ChinaSchool of Electrical Engineering, Southeast University, Nanjing, ChinaAs the terminal of electricity consumption, the distribution network is a vital field to lower the carbon emission of the power system. With the integration of distributed energy resources, the flexibility of the distribution network has been promoted significantly where dispatch actions can be employed to lower carbon emissions without compromising the accessibility of reliable electricity. This study proposes a security constrained dispatch policy based on safe reinforcement learning for the distribution network. The researched problem is set up as a constrained Markov decision process, where continuous-discrete mixed action space and high-dimensional state space are in place. In addition, security-related rules are embedded into the problem formulation. To guarantee the generalization of the reinforcement learning agent, various scenarios are generated in the offline training stage, including randomness of renewables, scheduled maintenance, and different load profiles. A case study is performed on a modified version of the IEEE 33-bus system, and the numerical results verify the effectiveness of the proposed method in decarbonization.https://www.frontiersin.org/articles/10.3389/fenrg.2022.933011/fulldecarbonization dispatchactive distribution networkssafe reinforcement learningrenewable generationelectricity storage |
| spellingShingle | Han Cui Han Cui Yujian Ye Yujian Ye Qidong Tian Yi Tang Yi Tang Security Constrained Dispatch for Renewable Proliferated Distribution Network Based on Safe Reinforcement Learning Frontiers in Energy Research decarbonization dispatch active distribution networks safe reinforcement learning renewable generation electricity storage |
| title | Security Constrained Dispatch for Renewable Proliferated Distribution Network Based on Safe Reinforcement Learning |
| title_full | Security Constrained Dispatch for Renewable Proliferated Distribution Network Based on Safe Reinforcement Learning |
| title_fullStr | Security Constrained Dispatch for Renewable Proliferated Distribution Network Based on Safe Reinforcement Learning |
| title_full_unstemmed | Security Constrained Dispatch for Renewable Proliferated Distribution Network Based on Safe Reinforcement Learning |
| title_short | Security Constrained Dispatch for Renewable Proliferated Distribution Network Based on Safe Reinforcement Learning |
| title_sort | security constrained dispatch for renewable proliferated distribution network based on safe reinforcement learning |
| topic | decarbonization dispatch active distribution networks safe reinforcement learning renewable generation electricity storage |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2022.933011/full |
| work_keys_str_mv | AT hancui securityconstraineddispatchforrenewableproliferateddistributionnetworkbasedonsafereinforcementlearning AT hancui securityconstraineddispatchforrenewableproliferateddistributionnetworkbasedonsafereinforcementlearning AT yujianye securityconstraineddispatchforrenewableproliferateddistributionnetworkbasedonsafereinforcementlearning AT yujianye securityconstraineddispatchforrenewableproliferateddistributionnetworkbasedonsafereinforcementlearning AT qidongtian securityconstraineddispatchforrenewableproliferateddistributionnetworkbasedonsafereinforcementlearning AT yitang securityconstraineddispatchforrenewableproliferateddistributionnetworkbasedonsafereinforcementlearning AT yitang securityconstraineddispatchforrenewableproliferateddistributionnetworkbasedonsafereinforcementlearning |