Data-driven Methods for Flexible and Optimal Controls Over Central Air-conditioning Systems
Building energy saving has a significant impact on achieving the goal of"dual carbon"national strategies.To further enhance the flexible energy utilization potential and automation level of buildings,there is an urgent need to develop a comprehensive and intelligent operating methodology that integrates information technologies such as the Internet of Things and big data.This paper proposed a flexible optimization control method for central air conditioning systems.A data-driven approach was used to construct system efficiency and functional models and thereby,achieving optimization control from the perspectives of energy efficiency and cost.The main steps are as follows:First,a high-precision building cooling load forecasting model was established and the time-of-use electricity pricing was integrated to optimize cooling supply distributions and save energy costs.Second,efficiency and functional models for key equipment in central air conditioning systems were built,including chillers,water pumps,and cooling towers.Such models were then integrated to simulate operating performance under different control strategies.Finally,heuristic algorithms were employed to optimize hourly control parameters,improving operational efficiency while meeting load demands.Taking a hotel building in Shenzhen as an example,the flexible optimization control method proposed in this paper can effectively harness the flexible potential of building systems,resulting in a 19.1％energy savings and a 22.8％reduction in electricity costs.The research findings are expected to provide new insights and references for the flexible operation management of building systems.
flexible energy utilizationoptimal controlpredictive modelingdata-driven modelsbuilding energy management
NETL
NSTL
万方数据
