摘要
为了节省冰蓄冷中央空调系统的运行费用,准确地预测空调冷负荷是必不可少的。采用db1小波对冰蓄冷空调冷负荷序列进行分解,分别对低频和高频序列采用BP网络进行预测,将预测结果进行叠加得到最终预测值。结合实例进行了空调逐时冷负荷预测,通过小波-BP网络与BP网络预测结果的对比,可知小波-BP网络预测的效果更好。
In order to save operating cost of ice-storage air-conditioning system, the accurately forecasting of cooling load prediction is necessary. Decomposed cooling load series to low-frequency and high-frequency by dbl wavelet, forecast with BP neural network respectively, synthesizse finally. Predicts the hourly ice-stor- age air-conditioning load with a real example, Contrast with the BP network method,fie forecasting results by wavelet-BP network is much better than BP network.
出处
《低温建筑技术》
2009年第3期93-95,共3页
Low Temperature Architecture Technology
关键词
冰蓄冷空调
小波
神经网络
负荷预测
ice-storage air-conditioning
wavelet analysis
neural network
load forecasting
