Hourly heating load forecasting for residences based on PCA-PSO-BP neural network

In order to accurately forecast the heating load, an improved BP neural network forecasting model based on principal component analysis (PCA) and particle swarm optimization (PSO) is proposed. Firstly, the PCA is used to fuse the characteristic indexes affecting the heating load to eliminate the redundancy and correlation between the indexes. At the same time, the PSO is used to optimize the initial weights and thresholds of BP neural network, which overcomes the defect that BP neural network is easy to fall into local optimization and improves the prediction accuracy of BP neural network. Based on the actual operation data of the heating system of a residential building in Beijing, the performance of the model is verified. The simulation results show that the forecasting accuracy of the improved model is improved by 4.07%.