Load predictions for district heating systems based on a wnn model 基于小波网模型的区域供热系统负荷预测
Research on load prediction model of air condition system based on elman neural network 型神经网络的空调负荷预测模型
Thermal load prediction for heating systems based on wavelet and neural network 基于双层规划模型的电梯交通系统群组优化
So , the research of hourly meteorological parameters and cooling load prediction is a must 因此,必须进行逐时室外气象参数和冷负荷的预测研究。
Experiment stated clearly that two loading prediction by means of this calculation model was quite reasonable 实验研究表明,在二级加载下该计算模型的预测结果是相当令人满意的。
Then , mre reaches 3 . 21 % for workday and 5 . 96 % for holiday . a unique next 24 hours hourly cooling load prediction ann model is established 对工作日负荷预测,其平均预测误差是3 . 21 ;对假日负荷,其平均预测误差是5 . 96 。
At present , the practical control of ice storage based on the correction of load prediction and off - line optimization is not seen in literature 迄今为止,国内外有关文献中,尚未见到关于冰蓄冷系统基于预测和离线忧化结果在线修汀来指导实际控制的文章。
The result of cooling load prediction is true , believable and satisfying . the prediction precision of ann network is almost the same with that of the others introduced in foreign documents 预测结果正确、可信,并取得了令人满意的效果,其预测准确度与国外同类方法基本持平。
6 . since the error in both the meteorological parameters and cooling load prediction is unavoidable , the online correction of prediction and offline optimization results is needed 无论是气象参数预测,还是冷负荷的预测总难免出现偏差,这就需要对短期预测和离线优化结果进行在线修正。
Mae of hourly load prediction reduced to 65 . 07kwh and eep reduced to 2 . 60 % . this kind of model has not been reported by literature . a cost - minimum model for ice storage system is established and numerical calculation is carried out 建立了空调逐时负荷的24小时提前预测多点输出动态模型,更进一步提高了负荷预测的精度,使得逐时负荷预测平均绝对误差降低到了65 . 07kwh ,期望相对误差降低到了2 . 60 。