Grid-Interactive Multi-Zone Building Control Using Reinforcement Learning with Global-Local Policy Search [electronic resource] : Preprint

• Ngôn ngữ: eng
• Ký hiệu phân loại: 006.6 Computer graphics
• Thông tin xuất bản: Washington, D.C. : Oak Ridge, Tenn. : United States. Dept. of Energy. Office of Energy Efficiency and Renewable Energy ; Distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy, 2021
• Mô tả vật lý: Size: 3.93 MB : , digital, PDF file.
• Bộ sưu tập: Metadata
• ID: 256031
• Chủ đề: 1. 30 ee - building technologies office (ee-5b); 2. Building control; 3. Demand response; 4. Reinforcement learning

Tóm tắt

In this paper, we develop a grid-interactive multi-zone building controller based on a deep reinforcement learning (RL) approach. The controller is designed to facilitate building operation during normal conditions and demand response events, while ensuring occupants comfort and energy efficiency. We leverage a continuous action space RL formulation, and devise a two-stage global-local RL training framework. In the first stage, a global fast policy search is performed using a gradient-free RL algorithm. In the second stage, a local fine-tuning is conducted using a policy gradient method. In contrast to the state-of-the-art model predictive control (MPC) approach, the proposed RL controller does not require complex computation during real-time operation and can adapt to non-linear building models. We illustrate the controller performance numerically using a five-zone commercial building.