Modified Parallel Cat Swarm Optimization in SVM Modeling for Short-term Cooling Load Forecasting

In order to improve forecasting accuracy of cooling load, this paper applies support vector machine (SVM) model with modified parallel cat swarm optimization (MPCSO) to forecast next-day cooling load in district cooling system(DCS). By extracting the Eigen value of the input historical load data, principal component analysis (PCA) algorithm is used to reduce the complexity of the data sequence. Based on cats’ cooperation and competition, an MPCSO algorithm is proposed to optimize the hyper parameters for the SVM model. Finally, the SVM model with MPCSO (namely MPCSO-SVM) is established to conduct the short-term cooling load forecasting. Numerical example results show that the proposed model outperforms the existing alternative models. Thus, the proposed model is effective and applicable to cooling load forecasting.