Accurate heating, ventilation and air conditioning system load prediction for residential buildings using improved ant colony optimization and wavelet neural network

Abstract Accurate prediction of the building load is crucial to ensure the energy saving and improve the operational efficiency of the heating, ventilation, and air conditioning (HVAC) system. In this study, the heating load (HL) and cooling load (CL) of buildings are analyzed using the Spearman method considering eight influencing factors: relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution. The ant colony optimization (ACO) method is used to optimize the ability of a wavelet neural network (WNN) to predict the HL and CL values of residential buildings. The linearly decreasing inertia weight and self-adaptive mutation operator are introduced to improve the optimizing capability of the ACO. An improved ACO-WNN (I-ACO-WNN) model is proposed to achieve a high-precision building load forecasting, and the formulas including the influence factors of the building load, are proposed. The regression coefficient values of the proposed forecasting model of HL and CL are 0.9714 and 0.9783, respectively. Compared to the traditional WNN model, the root mean square error values of HL and CL predictions by the I-ACO-WNN model are decreased by 66.01% and 73.28%, respectively; while the mean absolute error values are decreased by 82.44% and 84.82%, respectively; also, the mean absolute percentage error values are reduced by 81.21% and 85.31%, respectively; lastly, the mean square error values are reduced by 88.44% and 92.86%, respectively. The proposed prediction model can be used as a reliable tool for HL and CL estimation in future intelligent urban planning.