基于Sine-SSA-BP算法的建筑物制冷量预测

Prediction of Building Cooling Capacity Based on Sine-SSA-BP Model

建筑物制冷量的准确预测,是提高建筑能源利用效率的基础。BP神经网络被广泛应用于建筑物的冷量预测,针对BP神经网络易陷入局部最优,导致预测精度低的问题,提出一种基于麻雀搜索算法(SSA)优化BP神经网络(SSA-BP)的预测模型。以预测结果均方误差最小为优化目标,使用SSA优化BP的权值和阈值。针对SSA存在种群分布不均,影响搜索性能的问题,提出一种使用Sine混沌映射初始化种群的改进方法,构建Sine-SSA-BP预测模型。实验结果表明,与PSO-BP、GA-BP、SSA-BP相比,上述模型具有更好的预测精度。

Accurate prediction of building cooling capacity is the basis for building energy to improve energy efficiency.BP neural network is widely used to predict the cooling capacity of buildings.Aiming at the problem that BP neural network is easy to fall into local optimum,which leads to low prediction accuracy,a prediction model based on sparrow search algorithm(SSA)optimized BP neural network(SSA-BP)is proposed.Taking the minimum MSE of the prediction result as the optimization goal,SSA is used to optimize the weight and threshold of BP.Furthermore,in view of the problem of uneven population distribution in SSA,which affects search performance,an improved method for initializing the population using Sine chaotic mapping is proposed,and a Sine-SSA-BP prediction model is constructed.Experimental results show that compared with PSO-BP,GA-BP,and SSA-BP,the model has better prediction effects.