Research on air conditioning load regulation and energy saving in public buildings based on reinforcement learning

Abstract

To address the limitations of existing central air conditioning energy-saving algorithms—such as their inability to achieve conventional optimization or adapt to grid peak shaving, coupled with nonlinear system dynamics, environmental uncertainties, and high-dimensional optimization challenges—we propose an integrated optimization method combining environmental forecasting and DDPG reinforcement learning. This approach employs dual constraints of demand response and thermal comfort to enable adaptive continuous control without prior knowledge models, using an actual office building air conditioning system at a research institute as the test case. Experimental results demonstrate that with adjustable loads of 135 kW (25% of total load), the optimized system achieves approximately 24% annual electricity savings, 31% peak shaving efficiency, and demand response compliance exceeding 91%. By balancing energy conservation, peak load reduction, and comfort requirements, this solution provides robust support for public buildings participating in demand response programs.