Research on Multi-Agent Resource Collaborative Optimization Strategy of Distribution Transformer Area Based on Dynamic Game Theory

View at publisher Summarise with VIRAT
Authors: Jun Wu, Yilin Li, Junlei Gu, Lu Xu, Xing Wei, Shiqi Xie, Pengfei Cheng, Fang Liu
Cited by: 0
References: 2

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

As the penetration rate of distributed energy continues to increase, the operation mode of distribution transformer areas evolves from centralized control to multi-agent collaboration. Conflicts of interest and decision-making autonomy among various agents pose challenges to system optimization. This paper proposes a multi-agent resource collaborative optimization strategy for distribution transformer areas based on dynamic game, constructs a multi-agent game model covering photovoltaic, energy storage, load and system operators, and uses the multiagent reinforcement learning (MARL) method to solve the Nash equilibrium. By introducing the MADDPG algorithm and dynamic pricing mechanism, collaborative optimization is achieved through the combination of centralized training and decentralized execution. The simulation results show that the proposed strategy can effectively reduce the total system cost, enhance the new energy consumption capacity, smooth the load curve, and ensure voltage safety, providing a new idea for the operation of distribution transformer areas under the high proportion of renewable energy access.

Fields of Study & Subjects

Smart Grid Energy Management Optimal Power Flow Distribution Microgrid Control and Optimization

Publication details

Journal / source
International Conference on Electrical Automation and Artificial Intelligence (ICEAAI)
Pages
207–213
Publication date
16 January 2026
Language
EN