Research on DLnet prediction model based on period feature extraction
The existing forecasting methods rarely analyze the periodic characteristics of energy consumption independently.A short-term office building energy consumption prediction model(DLnet)is proposed to solve the problem of low efficiency in the utilization of periodic energy consumption data.Firstly,the period component of the energy consumption data is decomposed using STL,and the optimal period of the energy consumption data is searched by grid searching algorithm.Secondly,periodic block is constructed according to optimal period.Then,time-series block data is constructed according to the data shape of the Periodic block.Next,time-series block data and the Periodic block data are trained and learned using LSTM.Finally,the prediction results of the time-series block data and the Periodic block data are fused by linear regression.The fact demonstrates that the four prediction precision indicators of the proposed model are 7%,21%,25%,and 26%higher than those of the long short-term memory(LSTM)model.
time-series blockperiodic blockoptimal periodseasonal-trend decomposition procedures based on Loesslong short-term memory
万方数据
维普
