Technical gazette, Vol. 33 No. 6, 2026.
Original scientific paper
https://doi.org/10.17559/TV-20260619003677
Research on Multi-Agent Distributed Optimization Control under the Operating Mode of the New Power System
Siqian Huang
; School of Intelligent Engineering, Shandong Management University, 250357, Jinan Shandong, China
*
Qifan Yang
; School of Intelligent Engineering, Shandong Management University, 250357, Jinan Shandong, China
Mingxing Zhang
; State Grid Shandong Electric Power Company Ultra High Voltage Company, 250021, Jinan Shandong, China
* Corresponding author.
Abstract
Multi-agent systems provide distributed decision-making and self-organizing coordination for dynamic control of the new power system. This study develops a multi-agent collaborative regulation framework for this application. First, game theory, consensus protocols, and crowd-sensing mechanisms are reviewed as complementary coordination tools. Second, a fully distributed multi-agent reinforcement learning architecture based on Q-learning is proposed. A reward recorder is introduced by redesigning the incentive function, and distributed linear matrix feedback (DLMF) constrains the state and action spaces during training. The method is evaluated using a generalized constrained distributed optimization model and case simulations. The results show that the proposed framework improves economic performance, operational safety, and disturbance resilience, providing a technical route toward a safe, stable, green, and low-carbon power system.
Keywords
consensus algorithm; distributed optimization; deep reinforcement learning; dynamic collaborative control; game theory; multi-agent reinforcement learning
Hrčak ID:
353076
URI
Publication date:
7.11.2026.
Visits: 0 *