jismart2023012: Application and Development of Reinforcement Learning in Building Energy System

Abstract

As global energy demand continues to grow and environmental concerns intensify, the energy consumption of buildings, accounting for approximately one-third of global energy usage, is expected to increase in the coming decades. This raises concerns about climate change. Building Energy Systems (BES) represent a strategic approach to mitigate these impacts, balancing energy demand-supply mismatches and improving building energy efficiency. Reinforcement learning, as a machine learning method, has been employed to control various energy systems to enhance energy efficiency and reduce energy costs for users. This applies to systems such as electric vehicles, Heating, Ventilation, and Air Conditioning (HVAC) systems, smart appliances, batteries, and more. It holds significant promise in optimizing building performance and achieving energy savings. This article provides an overview of the current state of research in this field, summarizes the challenges currently faced, and outlines future research directions. Future research can delve deeper into reinforcement learning control strategies for different building types and application scenarios, aiming for broader applications and greater energy benefits.