Access Control Method for EV Charging Stations Based on State Aggregation and Q-Learning

This paper presents intelligent access control for a charging station and a framework for dynamically and adaptively managing charging requests from randomly arriving electric vehicles(EVs),to increase the revenue of the station.First,charging service requests from random EV arrivals are described as an event-driven sequential decision process,and the decision-making relies on an eventextended state that is composed of the real-time electricity price,real-time charging station state,and EV arrival event.Second,a state aggregation method is introduced to reduce the state space by first aggregating the charging station state in the form of the remaining charging time and then further aggregating it via sort coding.Besides,mathematical calculations of the code value are provided,and their uniqueness and continuous integer characteristics are proved.Then,a corresponding Q-learning method is proposed to derive an optimal or suboptimal access control policy.The results of a case study demonstrate that the proposed learning optimisation method based on the event-extended state aggregation performs better than flat Q-learning.The space complexity and time complexity are significantly reduced,which substantially improves the learning efficiency and optimisation performance.

Planning and Real-time Pricing of EV Charging Stations Considering Social Welfare and Profitability Balance

This paper presents a planning and real-time pricing approach for EV charging stations(CSs).The approach takes the form of a bi-level model to fully consider the interest of both the government and EV charging station operators in the planning process.From the perspective of maximizing social welfare,the government acts as the decision-maker of the upper level that optimizes the charging price matrix,and uses it as a transfer variable to indirectly influence the decisions of the lower level operators.Then each operator at the lower level determines their scale according to the goal of maximizing their own revenue,and feeds the scale matrix back to the upper level.A Logit model is applied to predict the drivers’preference when selecting a CS.Furthermore,an improved particle swarm optimization(PSO)with the utilization of a penalty function is introduced to solve the nonlinear nonconvex bi-level model.The paper applies the proposed Bi-level planning model to a singlecenter small/medium-sized city with three scenarios to evaluate its performance,including the equipment utilization rate,payback period,traffic attraction ability,etc.The result verifies that the model performs very well in typical CS distribution scenarios with a reasonable station payback period(average 6.5 years),and relatively high equipment utilization rate,44.32%.