Energy Management Simulation with Multi-Agent Reinforcement Learning: An Approach to Achieve Reliability and Resilience
The share of energy produced by small-scale renewable energy sources, including photovoltaic panels and wind turbines, will significantly increase in the near future. These systems will be integrated in microgrids to strengthen the independence of energy consumers. This work deals with energy manage...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/19/7381 |
| _version_ | 1797479372245958656 |
|---|---|
| author | Kapil Deshpande Philipp Möhl Alexander Hämmerle Georg Weichhart Helmut Zörrer Andreas Pichler |
| author_facet | Kapil Deshpande Philipp Möhl Alexander Hämmerle Georg Weichhart Helmut Zörrer Andreas Pichler |
| author_sort | Kapil Deshpande |
| collection | DOAJ |
| description | The share of energy produced by small-scale renewable energy sources, including photovoltaic panels and wind turbines, will significantly increase in the near future. These systems will be integrated in microgrids to strengthen the independence of energy consumers. This work deals with energy management in microgrids, taking into account the volatile nature of renewable energy sources. In the developed approach, <i>Multi-Agent Reinforcement Learning</i> is applied, where agents represent microgrid components. The individual agents are trained to make good decisions with respect to adapting to the energy load in the grid. Training of agents leverages the historic energy profile data for energy consumption and renewable energy production. The implemented energy management simulation shows good performance and balances the energy flows. The quantitative performance evaluation includes comparisons with the exact solutions from a linear program. The computational results demonstrate good generalisation capabilities of the trained agents and the impact of these capabilities on the reliability and resilience of energy management in microgrids. |
| first_indexed | 2024-03-09T21:45:54Z |
| format | Article |
| id | doaj.art-4f26e19ca51c4ca5a06063411d64d661 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T21:45:54Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-4f26e19ca51c4ca5a06063411d64d6612023-11-23T20:18:03ZengMDPI AGEnergies1996-10732022-10-011519738110.3390/en15197381Energy Management Simulation with Multi-Agent Reinforcement Learning: An Approach to Achieve Reliability and ResilienceKapil Deshpande0Philipp Möhl1Alexander Hämmerle2Georg Weichhart3Helmut Zörrer4Andreas Pichler5Profactor GmbH, Robotics and Automation Systems Department, 4407 Steyr, AustriaProfactor GmbH, Robotics and Automation Systems Department, 4407 Steyr, AustriaProfactor GmbH, Robotics and Automation Systems Department, 4407 Steyr, AustriaProfactor GmbH, Robotics and Automation Systems Department, 4407 Steyr, AustriaProfactor GmbH, Robotics and Automation Systems Department, 4407 Steyr, AustriaProfactor GmbH, Robotics and Automation Systems Department, 4407 Steyr, AustriaThe share of energy produced by small-scale renewable energy sources, including photovoltaic panels and wind turbines, will significantly increase in the near future. These systems will be integrated in microgrids to strengthen the independence of energy consumers. This work deals with energy management in microgrids, taking into account the volatile nature of renewable energy sources. In the developed approach, <i>Multi-Agent Reinforcement Learning</i> is applied, where agents represent microgrid components. The individual agents are trained to make good decisions with respect to adapting to the energy load in the grid. Training of agents leverages the historic energy profile data for energy consumption and renewable energy production. The implemented energy management simulation shows good performance and balances the energy flows. The quantitative performance evaluation includes comparisons with the exact solutions from a linear program. The computational results demonstrate good generalisation capabilities of the trained agents and the impact of these capabilities on the reliability and resilience of energy management in microgrids.https://www.mdpi.com/1996-1073/15/19/7381energy managementmulti-agent reinforcement learningrenewable energy systemsmicrogrid |
| spellingShingle | Kapil Deshpande Philipp Möhl Alexander Hämmerle Georg Weichhart Helmut Zörrer Andreas Pichler Energy Management Simulation with Multi-Agent Reinforcement Learning: An Approach to Achieve Reliability and Resilience Energies energy management multi-agent reinforcement learning renewable energy systems microgrid |
| title | Energy Management Simulation with Multi-Agent Reinforcement Learning: An Approach to Achieve Reliability and Resilience |
| title_full | Energy Management Simulation with Multi-Agent Reinforcement Learning: An Approach to Achieve Reliability and Resilience |
| title_fullStr | Energy Management Simulation with Multi-Agent Reinforcement Learning: An Approach to Achieve Reliability and Resilience |
| title_full_unstemmed | Energy Management Simulation with Multi-Agent Reinforcement Learning: An Approach to Achieve Reliability and Resilience |
| title_short | Energy Management Simulation with Multi-Agent Reinforcement Learning: An Approach to Achieve Reliability and Resilience |
| title_sort | energy management simulation with multi agent reinforcement learning an approach to achieve reliability and resilience |
| topic | energy management multi-agent reinforcement learning renewable energy systems microgrid |
| url | https://www.mdpi.com/1996-1073/15/19/7381 |
| work_keys_str_mv | AT kapildeshpande energymanagementsimulationwithmultiagentreinforcementlearninganapproachtoachievereliabilityandresilience AT philippmohl energymanagementsimulationwithmultiagentreinforcementlearninganapproachtoachievereliabilityandresilience AT alexanderhammerle energymanagementsimulationwithmultiagentreinforcementlearninganapproachtoachievereliabilityandresilience AT georgweichhart energymanagementsimulationwithmultiagentreinforcementlearninganapproachtoachievereliabilityandresilience AT helmutzorrer energymanagementsimulationwithmultiagentreinforcementlearninganapproachtoachievereliabilityandresilience AT andreaspichler energymanagementsimulationwithmultiagentreinforcementlearninganapproachtoachievereliabilityandresilience |