{"ID":2855422,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14112","arxiv_id":"2510.14112","title":"STEMS: Spatial-Temporal Enhanced Safe Multi-Agent Coordination for Building Energy Management","abstract":"Building energy management is essential for achieving carbon reduction goals, improving occupant comfort, and reducing energy costs. Coordinated building energy management faces critical challenges in exploiting spatial-temporal dependencies while ensuring operational safety across multi-building systems. Current multi-building energy systems face three key challenges: insufficient spatial-temporal information exploitation, lack of rigorous safety guarantees, and system complexity. This paper proposes Spatial-Temporal Enhanced Safe Multi-Agent Coordination (STEMS), a novel safety-constrained multi-agent reinforcement learning framework for coordinated building energy management. STEMS integrates two core components: (1) a spatial-temporal graph representation learning framework using a GCN-Transformer fusion architecture to capture inter-building relationships and temporal patterns, and (2) a safety-constrained multi-agent RL algorithm incorporating Control Barrier Functions to provide mathematical safety guarantees. Extensive experiments on real-world building datasets demonstrate STEMS's superior performance over existing methods, showing that STEMS achieves 21% cost reduction, 18% emission reduction, and dramatically reduces safety violations from 35.1% to 5.6% while maintaining optimal comfort with only 0.13 discomfort proportion. The framework also demonstrates strong robustness during extreme weather conditions and maintains effectiveness across different building types.","short_abstract":"Building energy management is essential for achieving carbon reduction goals, improving occupant comfort, and reducing energy costs. Coordinated building energy management faces critical challenges in exploiting spatial-temporal dependencies while ensuring operational safety across multi-building systems. Current multi...","url_abs":"https://arxiv.org/abs/2510.14112","url_pdf":"https://arxiv.org/pdf/2510.14112v2","authors":"[\"Huiliang Zhang\",\"Di Wu\",\"Arnaud Zinflou\",\"Benoit Boulet\"]","published":"2025-10-15T21:33:58Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Transformer\"]","has_code":false}