A novel building cooling load prediction based on SVR and SAPSO

Accurate building cooling load forecasting is the precondition for the optimal control and energy saving operation of HVAC systems. Hourly cooling load forecasting is a difficult work as the load at a given point is dependent not only on the load at the previous hour but also on the load at the same hour on the previous day. So the accuracy of forecasting is influenced by many unpredicted factors. Support vector machine (SVM) is a novel type of learning machine, which has been successfully employed to solve nonlinear regression and time series problems. The key problem of SVM is the selection of SVM free parameters. In this paper, it is proposed a new optimal model, which is based on Simulated Annealing Particle Swarm Optimization Algorithm (SAPSO) that combines the advantages of PSO algorithm and SA algorithm. The strong searching ability of SA was employed to PSO algorithm to avoid the premature convergence with better stability and astringency. The SA based PSO algorithm was used to optimize the free parameters of SVM model. The study used the proposed model to forecast load of cooling load system. The numerical simulation results demonstrate that the accuracy of SA-PSO based SVM model outperforms that of the traditional SVM load forecasting model.