基于PSO-RBF的建筑能耗预测模型研究

Prediction Model of Building Energy Consumption Based on PSO-RBF

通过研究分析夏热冬冷地区公共建筑能耗变化特点,建立了RBF神经网络建筑能耗预测模型。在此基础上运用微粒群算法对模型优化,建立了基于PSO-RBF的建筑能耗预测模型。利用大量数据构造样本集,运用软件分别对优化前后的预测模型进行训练,并运用到典型公共建筑能耗值的预测实例中。结果表明基于PSO-RBF的建筑能耗预测模型的学习能力和预测能力强,能较准确地实现公共建筑能耗预测。

The model of energy consumption prediction is built after analyzing characteristics on energy consumption changes of public building in hot summer and cold winter area. Particle swarm optimization algorithm is used to optimize the model, and the PSO-RBF neural network prediction model is established. Using the energy consumption data of subject research, the samples of building energy consumption is built. Then the RBF neural network and PSO-RBF neural network are trained on MA TLAB. Experiments are conducted to predict energy consumption values of typical public buildings. The results show that accuracy of the prediction model is improved obviously after being optimized, and it has strong learning and predicting ability. The model can predict energy consumption value of public buildings accurately.