Control method, system and equipment for virtual power plant containing electric vehicle and medium

Through the multi-agent deep reinforcement learning method, the Markov decision-making model is used to use the distributed partial observable Markov decision-making model to solve the problem of user information leakage and poor control effects in virtual power plants, and more efficient electric vehicle charging and discharging control is achieved, reducing electricity consumption costs and reducing user anxiety.

CN120073816APending Publication Date: 2025-05-30STATE GRID HEBEI ELECTRIC POWER CO LTD
0 Cites 1 Cited by

Patent Information

Application Number
CN202510088004.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-01-21
Publication Date
2025-05-30

AI Technical Summary

Technical Problem

The existing virtual power plant control methods containing electric vehicles have problems such as user information leakage and poor control effects, especially in large-scale scenarios, it is difficult to effectively coordinate multiple electric vehicles.

Method used

The multi-agent deep reinforcement learning method is adopted, and the Markov decision model can be observed through the distributed partially. Each charging pile in the virtual power plant is used as an agent. Reinforcement learning is used for centralized training, the optimal control strategy is obtained, and user privacy is protected during distributed execution.

Benefits of technology

It achieves better charging and discharging control performance, reduces the electricity cost of electric vehicles, reduces user mileage anxiety, and improves control effect in large-scale scenarios.

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

Abstract

The invention discloses a virtual power plant control method, system and device containing an electric vehicle and a medium, and relates to the field of virtual power plant control, and the method comprises the steps: modeling a virtual power plant control problem as a distributed partial observable Markov decision model; the distributed partial observable Markov decision process comprises a plurality of intelligent agents, the global state of a virtual power plant, joint observation of all the intelligent agents, local observation of all the intelligent agents, joint actions of all the intelligent agents, actions of all the intelligent agents and a reward function; constructing a value network and a strategy network; one agent corresponds to one policy network; performing centralized training on the value network and the strategy networks by using a reinforcement learning method to obtain an optimal control strategy corresponding to the value network and each strategy network; according to the method, user information leakage is prevented, better charging and discharging control performance is realized, the power utilization cost of the electric vehicle is reduced, and the mileage anxiety of the user is reduced.
Need to check novelty before this filing date? Find Prior Art