基于张量距离算法预测空调系统的室内温度及供水温度

Prediction of indoor temperature and water supply temperature in air conditioning system based on tensor distance algorithm

以维持室内温度舒适和提供运行策略、节约能源为目的,设计了张量距离模型用于挖掘不断增长的历史数据中的有效信息解决空调供暖问题。考虑到空调运维数据的时空特性及各参数的多维特性,将历史数据确定日类型、划分时间段、扩充室外温度后,构造历史温度特征张量,爬虫建筑物所在地的未来室外温度插值后按同样方法扩充数据为未来温度特征张量作为输入,衡量历史时间段与预测时间段中各输入参数的张量距离,找到最小值的索引及对应的纤维,逐小时输出预测时间段空调系统的室内温度及其供水温度。连续7日的预测数据表明:基于张量距离模型预测的室内温度与实际的温度差为0.46℃,比基于支持向量回归(SVR)模型预测的温度差(0.75℃)小,更接近实际温度;基于张量距离模型预测的供水温度与实际的温度差为2.08℃,可用作供水策略。

For the purpose of stable indoor temperature and saving energy,a model named tensor distance was established to mine effective information in the growing historical data of air conditioning to solve the problem of air conditioning heating.Considering the spatio-temporal and multi-dimensional characteristics of air conditioning maintenance data,after dividing the day type,the time interval and expanding the outdoor temperature,the tensor of historical temperature was constructed.Interpolating outdoor temperature data through Web crawler,the tensor of forecast temperature was constructed.By measuring distance of each input parameter among these tensors,the index of the smallest value and the corresponding fiber were found,and the indoor temperature and its water supply temperature during the forecast period were hourly output.The results for seven days indicate that:for the difference between the predicted value with the actual value of the indoor temperature,the tensor distance model achieves 0.46℃,whereas the support vector regression model achieves 0.75℃,the indoor temperature value predicted by the tensor distance model is closer to the actual value;and for the difference between the predicted value with the actual value of the supply temperature,the tensor distance model achieves 2.08℃,so that it provides water supply temperature strategy for reference.