Heating load prediction based on particle swarm optimization support vector machine

Abstract

Heating load is affected by many uncertain factors, which makes it show certain randomness. To further improve the heating load forecasting accuracy, reduce the prediction error, using cross validation (CV) ideology in the choice of a model of performance evaluation and the superiority, combined with the advantages of particle swarm optimization (PSO), which is easy to implement and has stronger global optimization ability, the important parameters (penalty factor C and RBF kernel function parameter γ) are optimized, and the best parameters are automatically found in the training set, so as to obtain the best training model. Compared with other algorithms, the model precision of this method is improved a lot, and the prediction result is more accurate.