An improved model for building energy consumption prediction based on time-series analysis

Abstract

The development and popularisation of renewable energy is necessary. The application of renewable energy technology in buildings is an important research direction. Moreover, the prediction of renewable energy consumption in this direction is an essential research content. In view of this, a building energy consumption prediction model of renewable energy based on time-series analysis and a support vector machine (SVM) is proposed. The performance test of this model showed that its loss value was as low as 1.5% in the training set, and the loss value was 4.1% in the test set. In addition, it showed the highest accuracy rate of 95.5% in the neural network accuracy test, which is significantly higher than that of traditional algorithms. About the overall energy consumption prediction ability of the model, the experimental results showed that the lowest error of the energy consumption prediction model was 2.3%, the average relative error of the traditional SVM model in the same data set was 6.8% and that of the chaotic time-series model was 4.1%. Compared with the prediction ability of the traditional models currently used, the prediction ability of the energy consumption prediction model has been greatly improved, and it has the potential to be put into practical application.