空调负荷预测模型及仿真研究  

Prediction model and simulation study on air conditioning load

作　　者：徐今强[1,2,3] 肖睿[1,2] 黄冲[1,2] 冯自平[1,2] 

机构地区：[1]中国科学院广州能源研究所 [2]中国科学院可再生能源与天然气水合物重点实验室,广东广州510640 [3]广东海洋大学海洋遥感与信息技术实验室,广东湛江524088

出　　处：《华中科技大学学报（自然科学版）》2009年第S1期259-262,共4页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金委-广东省联合基金资助项目(U0634005);国家高技术研究发展计划资助项目(2007AA05Z224);广东海洋大学自然科学研究项目(0812099)

摘　　要：为改善蓄冰中央空调系统控制性能及提高能效,开发了一种基于遗传算法的广义回归神经网络模型,用于预测蓄冰中央空调逐时冷负荷.该模型以前一日已知的24 h室外温度为输入,以次日逐时冷负荷为输出,在遗传算法寻优网络平滑因子时,以均方差最小构造适应度函数.该模型克服了利用梯度下降法优化平滑因子时易陷入局部极值的缺点,通过对负荷预测值和计算值的比较分析验证了模型的有效性和精度,可用于蓄冰空调系统的动态优化控制.In order to improve the control performance and enhance the energy efficiency of ice-storage air conditioning,a new general regression neural network(GRNN) model based on genetic algorithms was developed to predict the hourly cooling load of ice-storage central air conditioning.When modeling the external temperature recorded every hour between 0:00 and 24:00 of the previous day were used as network input,the hourly cooling load of the next day as output,the fitness function aiming at the mean square error was constructed when optimizing the smooth factor of GRNN.The presented model could overcome the defect caused by gradient descent method which easy to fall into local extreme points,the validity and precision of the model had been verified with comparing the predictive load and calculative load,which could be applied to the dynamic optimal control of the ice-storage air conditioning system.

关 键 词：空调 逐时冷负荷 预测 遗传算法 广义回归神经网络 仿真 

分 类 号：TM925.12[电气工程—电力电子与电力传动]