A collaborative optimization control method for charging stations based on dual-center q-learning

Abstract

The invention discloses a dual-center Q-learning-based collaborative optimization control method for charging stations, which includes: 1. describing the control process of two randomly arriving charging service requests for electric vehicles as an event-driven decision-making process; 2. charging The control process of the charging electric vehicle at the station responding to the peak-shaving electricity price plan of the grid is described as a sequential decision-making process; 3. The peak-shaving electricity price and the online service status of the charging pile are regarded as the system state; Whether to access and provide charging service as the access control action; 4. At the moment of peak shaving electricity price distribution, select the charging and discharging actions of all AC charging electric vehicles in service as the peak shaving control action; 5 Use the Q learning algorithm to control the system's electric The vehicle access control center and the peak shaving response control center conduct online collaborative optimization. The invention can carry out effective intelligent access control and peak-shaving response control of electric vehicles to the charging station, so as to adapt to the peak-shaving demand of the power grid.

Description

technical field [0001] The invention belongs to the technical field of intelligent control and optimization, and specifically relates to a dual-center Q-learning-based collaborative optimization control method for charging stations. Background technique [0002] my country is currently the largest automobile consumer market in the world. Automobile manufacturers have shifted the focus of R&D and production from traditional energy-powered vehicles to new energy vehicles. Among them, electric vehicles will be the development of new energy vehicles for a long period of time. Mainstream, with huge consumption potential, the market share will also increase. The charging pile is an important infrastructure for providing charging services for electric vehicles, and it is also an important link in the process of industrialization and commercialization of electric vehicles. With the rapid development of the electric vehicle industry and the substantial increase in the number of elect...

AI Technical Summary

Problems solved by technology

[0003] The existing grid electricity price adopts a very simple and fixed time-of-use electricity price mechanism. It does not dynamically formulate or adjust the grid peak-shaving electricity price plan according to the actual forecast of the grid's source load, and the charging station service system does not follow the actual grid peak load regulation. The electricity price plan dynamically and adaptively performs adaptive access control on the charging request of electric vehicles, and performs adaptive peak-shaving response control on the charging and discharging actions of electric vehicles

Images