Press Start to Charge: Videogaming the Online Centralized Charging Scheduling Problem

2026-01-18

AI Summary

This study addresses the online centralized electric vehicle (EV) charging scheduling problem—dynamically assigning charging times to vehicles arriving in real time under capacity constraints to achieve load balancing. The authors propose a gamified modeling approach that reformulates the scheduling process as a game of placing “charging blocks” within a spatiotemporal grid subject to capacity limits. By integrating heuristic strategies, expert demonstrations, and the DAgger algorithm to train an image-to-action policy network, this work introduces the first gamified framework for this domain, reducing model complexity and yielding a tighter generalization bound than conventional vector-based representations. Experimental results demonstrate significant performance gains over heuristic, vector-based baselines, and supervised learning methods across diverse arrival patterns. A case study in Montreal shows annual system cost savings of tens of millions of dollars and a notable deferral of grid infrastructure upgrades.

Technology Category

• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Multiagent Systems: Adversarial Agents
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

We study the online centralized charging scheduling problem (OCCSP). In this problem, a central authority must decide, in real time, when to charge dynamically arriving electric vehicles (EVs), subject to capacity limits, with the objective of balancing load across a finite planning horizon. To solve the problem, we first gamify it; that is, we model it as a game where charging blocks are placed within temporal and capacity constraints on a grid. We design heuristic policies, train learning agents with expert demonstrations, and improve them using Dataset Aggregation (DAgger). From a theoretical standpoint, we show that gamification reduces model complexity and yields tighter generalization bounds than vector-based formulations. Experiments across multiple EV arrival patterns confirm that gamified learning enhances load balancing. In particular, the image-to-movement model trained with DAgger consistently outperforms heuristic baselines, vector-based approaches, and supervised learning agents, while also demonstrating robustness in sensitivity analyses. These operational gains translate into tangible economic value. In a real-world case study for the Greater Montr\'eal Area (Qu\'ebec, Canada) using utility cost data, the proposed methods lower system costs by tens of millions of dollars per year over the prevailing practice and show clear potential to delay costly grid upgrades.

Problem

• online centralized charging scheduling
• electric vehicles
• load balancing
• real-time decision making
• capacity constraints

Innovation

• gamification
• online charging scheduling
• DAgger
• load balancing
• electric vehicles