Safe and Sustainable Electric Bus Charging Scheduling with Constrained Hierarchical DRL

2025-11-25

IEEE Transactions on Vehicular Technology

AI Summary

This paper addresses the safe and economic charging scheduling of electric buses under multi-source uncertainties—including photovoltaic generation volatility, dynamic electricity pricing, uncertain driving durations, and limited charging infrastructure. Method: We propose a constrained bilevel deep reinforcement learning framework: the upper level employs PPO-Lagrangian for charger allocation, while the lower level adopts MAPPO-Lagrangian to optimize spatiotemporal charging power. Battery state-of-charge (SoC) lower-bound hard constraints are handled via Lagrangian relaxation, and an option-based mechanism enables spatiotemporal abstraction and safety-aware exploration. The problem is formulated as a Constrained Markov Decision Process (CMDP) and solved under the centralized training with decentralized execution (CTDE) paradigm. Results: Experiments on real-world data demonstrate that our method ensures zero battery depletion while significantly reducing operational costs and improving safety compliance. Moreover, it achieves faster convergence compared to existing baseline methods.

Technology Category

Planning, Routing, and Scheduling: Planning/Scheduling and LearningSearch and Optimization: Learning to SearchConstraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

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

Abstract

The integration of Electric Buses (EBs) with renewable energy sources such as photovoltaic (PV) panels is a promising approach to promote sustainable and low-carbon public transportation. However, optimizing EB charging schedules to minimize operational costs while ensuring safe operation without battery depletion remains challenging - especially under real-world conditions, where uncertainties in PV generation, dynamic electricity prices, variable travel times, and limited charging infrastructure must be accounted for. In this paper, we propose a safe Hierarchical Deep Reinforcement Learning (HDRL) framework for solving the EB Charging Scheduling Problem (EBCSP) under multi-source uncertainties. We formulate the problem as a Constrained Markov Decision Process (CMDP) with options to enable temporally abstract decision-making. We develop a novel HDRL algorithm, namely Double Actor-Critic Multi-Agent Proximal Policy Optimization Lagrangian (DAC-MAPPO-Lagrangian), which integrates Lagrangian relaxation into the Double Actor-Critic (DAC) framework. At the high level, we adopt a centralized PPO-Lagrangian algorithm to learn safe charger allocation policies. At the low level, we incorporate MAPPO-Lagrangian to learn decentralized charging power decisions under the Centralized Training and Decentralized Execution (CTDE) paradigm. Extensive experiments with real-world data demonstrate that the proposed approach outperforms existing baselines in both cost minimization and safety compliance, while maintaining fast convergence speed.

Problem

• Optimizes electric bus charging schedules under uncertainties
• Ensures safe operation without battery depletion constraints
• Minimizes operational costs using hierarchical deep reinforcement learning

Innovation

• Hierarchical DRL framework for safe EB charging
• Lagrangian relaxation integrated into Double Actor-Critic
• Centralized training with decentralized execution paradigm