Beyond Profit: A Multi-Objective Framework for Electric Vehicle Charging Station Operations

TL;DR

The paper tackles real-time pricing and port-wise continuous charging scheduling for EV charging stations, introducing reputation as a key multi-objective factor. It formulates the problem as an MDP and solves it with a Soft Actor-Critic algorithm augmented by a linear programming based safe layer to ensure feasibility under total capacity and deadline constraints, along with adaptive entropy-temperature tuning to improve convergence. The approach jointly optimizes profit and reputation, where reputation is modeled via a price fluctuation penalty, and is validated on real data, achieving average Joint Pricing and Reputation (JPR) gains of $25.45\%$ to $52.20\%$ over strong baselines. This work demonstrates the practical viability of multi-objective RL for EV charging networks with continuous action spaces and realistic physical constraints, offering a pathway to improved long-term performance and customer trust.

Abstract

This paper explores the pricing and scheduling strategies of the electric vehicle charging stations in response to the rising demand for cleaner transportation. Most of the existing methods focus on maximizing the energy efficiency or the charging station profit, however, the reputation of EVs is also a key factor for the long-term charging station operations. To address these gaps, we propose a novel framework for jointly optimizing pricing and continuous-multiple charging rates. Our approach aims to maximize both charging station profit and reputation, considering multi-objective optimization and continuous rate control within physical constraints. Introducing a pricing fluctuating penalty for reputation modeling and a linear programming-based safe layer for constraints, we confront the complexity of continuous charging rates' action space. To enhance convergence, we explore a soft action critic framework with novel entropy temperature tunning technique. The experiments conducted with real data demonstrate that the proposed method can provide extra 25.45\%-52.20\% average JPR than the representative baselines.

Figures (4)

• Figure 1: Actor Network with Safe Layer.
• Figure 2: Performance comparison versus different algorithms.
• Figure 3: Performance comparison versus number of charging ports.
• Figure 4: Performance comparison versus electricity prices.