Energy efficiency in cooling systems: integrating machine learning and meta-heuristic algorithms for precise cooling load prediction

Abstract

Abstract Since cooling load estimation directly impacts air conditioning control and chiller optimization, it is essential for increasing the energy efficiency of cooling systems. Machine learning outshines traditional regression analysis by efficiently managing vast datasets and discerning complex patterns influenced by various factors like occupancy, building materials, and meteorology. These capabilities greatly enhance building management and energy optimization. The primary objective of this study is to introduce a framework based on ML algorithms to accurately predict cooling loads in buildings. The Decision Tree model was chosen as the core algorithm for this purpose. Furthermore, as an innovative approach, four metaheuristic algorithms – namely, the Improved Arithmetic Optimization Algorithm, Prairie Dog Optimization, Covariance Matrix Adaptation Evolution Strategy, and Coyote Optimization Algorithm – were employed to enhance the predictive capabilities of the Decision Tree model. The dataset which utilized in this study derived from previous studies, the data comprised of eight input parameters, including Relative Compactness, Surface Area, Wall Area, Roof Area, Overall Height, Orientation, Glazing Area, and Glazing Area Distribution. With an astonishing R 2 value of 0.995 and a lowest Root Mean Square Error value of 0.660, the DTPD (DT + PDO) model performs exceptionally well. These astounding findings demonstrate the DTPD model’s unmatched precision in forecasting the results of cooling loads and point to its potential for useful implementation in actual building management situations. Properly predicting and managing cooling loads ensures that indoor environments remain comfortable and healthy for occupants. Maintaining optimal temperature and humidity levels not only enhances comfort but also supports good indoor air quality.