← Back to the feed
Energy & materialsResearch findings

A Deep Reinforcement Learning Approach for Real-Time Energy Scheduling in Green Buildings

Original published 2025.06.08 00:01 KSTAdded to Blackdeck 2026.11.08 13:06 KST

What has changed?

A model-free deep reinforcement learning method is proposed for joint real-time scheduling of heterogeneous battery systems and electric vehicles

Key points

  1. Green buildings integrating renewable energy and building energy management systems can achieve efficient energy utilization
  2. Electric vehicles, as flexible storage resources, enhance system flexibility when combined with stationary energy storage systems
  3. The proposed DRL method reduces operating costs by 37.94% to 40.01% compared to a mixed-integer linear programming approach

Connect it to your work

Collaborative operation under varying conditions is enabled by considering battery degradation and operational differences

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivDeep reinforcement learning-based joint real-time energy scheduling for green buildings with heterogeneous battery energy storage devices