A Priority Scheduling Strategy of a Microgrid Using a Deep Reinforcement Learning Method
- Resource Type
- Conference
- Authors
- Dong, Lun; Huang, Yuan; Xu, Xiao; Zhang, Zhenyuan; Liu, Junyong; Pan, Li; Hu, Weihao
- Source
- 2023 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia) Industrial and Commercial Power System Asia (I&CPS Asia), 2023 IEEE/IAS. :1490-1496 Jul, 2023
- Subject
- Power, Energy and Industry Applications
Renewable energy sources
Fluctuations
Costs
Simulation
Optimization methods
Microgrids
Reinforcement learning
Renewable energy
Microgrid
Fluctuation
Scheduling
Data-driven approach
- Language
The fluctuation of renewable energy leads to a severe power fluctuation on the tie-line between microgrid (MG) and the power grid. A novel scheduling strategy is proposed in this paper to reduce power fluctuation based on a data-driven approach. The scheduling strategy is divided into two steps based on the scheduling priority of gas turbines, battery storage systems, and power-to-hydrogen devices. The aim is to minimize the penalties caused by the tie-line power fluctuation and operation costs of MG. And the scheduling optimization models are expressed as a Markov decision process. Simulation results verify the effectiveness of the proposed strategy.