Online Dynamic Pricing for Electric Vehicle Charging Stations with Reservations

2024-10-07

arXiv.org

AI Summary

This paper addresses revenue optimization for high-demand fast-charging stations by proposing an online dynamic pricing model that jointly coordinates reservation, parking, and charging services. The problem is formulated as a continuous-time revenue maximization problem under Poisson arrival processes and solved via a discretized Markov decision process (MDP). We systematically analyze, for the first time, the discretization error induced by embedding Poisson arrivals into a discrete-time MDP framework. To balance theoretical rigor and computational efficiency, we design a novel online pricing mechanism leveraging Monte Carlo Tree Search (MCTS)-based heuristics, enabling low-latency and scalable deployment. Extensive experiments demonstrate that our approach significantly improves revenue—particularly under high utilization—while maintaining robustness and practicality. The resulting solution provides a deployable, theoretically grounded dynamic pricing framework for real-world EV charging infrastructure.

Technology Category

• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Online Learning & Bandits

Application Category

• Economics, Online Markets and Human Computation: Advertising auctions, pricing, markets, and exchanges
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

This paper introduces a novel model for online dynamic pricing of electric vehicle charging services that integrates reservation, parking, and charging into a comprehensive bundle priced as a whole. Our approach focuses on the individual high-demand, fast-charging location, employing a Poisson process as a model of charging reservation arrivals, and develops an online dynamic pricing strategy optimized through a Markov Decision Process (MDP). A key contribution is the novel analysis of discretization error introduced when incorporating the continuous-time Poisson process into the discrete MDP framework. The MDP model's feasibility is demonstrated with a heuristic dynamic pricing method based on Monte-Carlo tree search, offering a viable path for real-world applications.

Problem

• Dynamic pricing for EV charging with reservations
• Modeling charging demand via Poisson process
• Optimizing pricing strategy using MDP framework

Innovation

• Integrates reservation, parking, charging into bundled pricing
• Uses Poisson process for charging reservation arrivals modeling
• Employs MDP and Monte-Carlo tree search for pricing