基于PSO-SA优化的LSSVM空调负荷预测  

The LSSVM Model of Air-conditioning Load Prediction Based on the Optimization of PSO-SA

作　　者：赵超[1] 王贵评 戴坤成[1] 

机构地区：[1]福州大学石油化工学院,福建福州350108

出　　处：《智能建筑电气技术》2015年第6期58-61,74,共5页Electrical Technology of Intelligent Buildings

摘　　要：对空调负荷进行准确预测不仅对优化空调控制的意义重大,也是实现空调经济运行与节能的关键所在。为了提高建筑空调负荷的预测精度,在分析最小二乘支持向量机建模特点的基础上提出了利用PSO-SA优化的一种空调负荷预测算法。该方法利用粒子群—模拟退火方法对最小二乘支持向量机的参数进行优化选择,提高模型的精度和泛化能力。通过空调负荷预测建模的结果表明,该方法具有学习速度快、跟踪性能好以及泛化能力强等优点,为实现空调系统的优化运行奠定了基础。Accurate prediction of air-conditioning load is not only very important for the optimal control of centre air-conditioning system, but also for the economical running and energy saving of air-conditioning system. In order to improve the accuracy of the forecas- ting of building air conditioning load, a LSSVM prediction model is established based on the optimization of PSO-SA. The particle swarm optimization simulated annealing （PSO- SA） was used to select the optimal parameters of LSSVM model and improve improving the precision and generalization ability of the model. Air-conditioning load prediction modeling result indicates that this method features high learning speed, good approximation and well generalization ability. It provides good basis for the optimization of air-conditioning load.

关 键 词：空调负荷 最小二乘支持向量机 粒子群一模拟退火 

分 类 号：TU831.2[建筑科学—供热、供燃气、通风及空调工程]