MARL-based flexible distributed energy network multi-agent collaborative optimization method

By employing a multi-agent collaborative optimization method for flexible distributed energy networks based on MARL, combined with intelligent soft switching and network topology reconfiguration, the global collaborative optimization problem of flexible interconnected power distribution systems with a high proportion of renewable energy access is solved, achieving efficient and secure distributed decision-making and user data privacy protection.

CN121769896APending Publication Date: 2026-03-31INST OF ELECTRICAL ENG CHINESE ACAD OF SCI
0 Cites 2 Cited by

Patent Information

Application Number
CN202512012159.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-29
Publication Date
2026-03-31

AI Technical Summary

Technical Problem

Traditional centralized dispatch and trading models are difficult to adapt to flexible interconnected distribution systems with a high proportion of renewable energy. Existing MARL methods fail to deeply couple the physical network model, resulting in high computational complexity, neglect of user privacy in information transparency, and difficulty in achieving global collaborative optimization.

Method used

A multi-agent collaborative optimization method based on MARL for flexible distributed energy networks is adopted. By constructing a unified framework and combining intelligent soft switching and network topology reconfiguration technologies, a learning and decision-making process for multiple agents is established to ensure that the strategy follows the physical laws of the distribution network and achieves decentralized collaboration under local observation, thus protecting user data privacy.

Benefits of technology

It effectively reduces the total active power loss of the system, increases the proportion of local consumption of distributed energy, enhances the resilience of the community power grid, adapts to the uncertainty of source and load, and realizes efficient global strategy formation and safe and reliable distributed decision-making.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a flexible distributed energy network multi-agent collaborative optimization method based on MARL, and the method comprises the steps: building a distributed energy network multi-agent interaction framework which comprises a local energy transaction model for distinguishing an intelligent soft switching path, a network cost model based on a power transmission distribution factor, and a power distribution network operator and user income model; a physical system operation constraint model is established and covers intelligent soft switch operation characteristics, network topology radial constraint, energy storage charging and discharging dynamic states, controllable distributed power supply and photovoltaic output limitation, translational load scheduling and DistFlow power flow constraint. And finally, constructing a collaborative optimization mechanism based on a multi-agent near-end strategy optimization algorithm, modeling the system into a partially observable Markov decision process, adopting a centralized training distributed execution framework, and guaranteeing transaction security and data privacy through block chain evidence storage, RSA encryption and an intelligent contract. The system economy and the operation flexibility are improved.
Need to check novelty before this filing date? Find Prior Art