Technology Category
Intelligent Robots: Learning & Optimization for ROBSearch and Optimization: Sampling/Simulation-based SearchPlanning, Routing, and Scheduling: Planning with Language Models
BuildingGym: An open-source toolbox for AI-based building energy management using reinforcement learning
🤖 AI Summary
Existing reinforcement learning (RL) frameworks for building energy management lack flexibility and scalability, often restricting control to single-building, isolated scenarios without integration of external signals. Method: This paper introduces an open-source, research-oriented RL control platform built upon EnergyPlus as the simulation core. It supports both system-level and zone-level energy optimization and natively integrates external signals—such as smart grid electricity pricing and electric vehicle (EV) charge/discharge scheduling—to transcend traditional building-boundary limitations. The platform features a plug-and-play architecture enabling modular replacement of RL algorithms, environment interfaces, and simulators, alongside end-to-end training configurations and multi-scenario deployment capabilities. Contribution/Results: Evaluated on constant and dynamic cooling load management tasks, built-in RL agents achieve significant energy efficiency improvements, demonstrating the platform’s effectiveness and generalizability in complex, interactive energy systems.
Technology Category
Application Category
📝 Abstract
Reinforcement learning (RL) has proven effective for AI-based building energy management. However, there is a lack of flexible framework to implement RL across various control problems in building energy management. To address this gap, we propose BuildingGym, an open-source tool designed as a research-friendly and flexible framework for training RL control strategies for common challenges in building energy management. BuildingGym integrates EnergyPlus as its core simulator, making it suitable for both system-level and room-level control. Additionally, BuildingGym is able to accept external signals as control inputs instead of taking the building as a stand-alone entity. This feature makes BuildingGym applicable for more flexible environments, e.g. smart grid and EVs community. The tool provides several built-in RL algorithms for control strategy training, simplifying the process for building managers to obtain optimal control strategies. Users can achieve this by following a few straightforward steps to configure BuildingGym for optimization control for common problems in the building energy management field. Moreover, AI specialists can easily implement and test state-of-the-art control algorithms within the platform. BuildingGym bridges the gap between building managers and AI specialists by allowing for the easy configuration and replacement of RL algorithms, simulators, and control environments or problems. With BuildingGym, we efficiently set up training tasks for cooling load management, targeting both constant and dynamic cooling load management. The built-in algorithms demonstrated strong performance across both tasks, highlighting the effectiveness of BuildingGym in optimizing cooling strategies.
Problem
Research questions and friction points this paper is trying to address.
Lack of flexible reinforcement learning framework for building energy management
Need for integrating external signals like smart grid into control systems
Difficulty in implementing and testing AI control strategies for buildings
Innovation
Methods, ideas, or system contributions that make the work stand out.
Open-source reinforcement learning toolbox for buildings
Integrates EnergyPlus simulator for multi-level control
Accepts external signals for smart grid integration
🔎 Similar Papers
