Short-term building thermal load prediction method
The invention discloses a short-term building thermal load prediction method, and the method comprises the steps: firstly selecting meteorological data and heat supply data in a given time period, andconstructing a data set as an input variable; preprocessing the data of the input variable; performi...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a short-term building thermal load prediction method, and the method comprises the steps: firstly selecting meteorological data and heat supply data in a given time period, andconstructing a data set as an input variable; preprocessing the data of the input variable; performing feature extraction on the preprocessed input variables by using a long short-term memory LSTM network to realize high-level feature learning; an Attention mechanism is added into the LSTM network, and by allocating attention weights, key features influencing output variables in output features of the LSTM network are endowed with larger weights; and finally, operating an LSTM network to realize short-term building thermal load prediction. The method can solve the problems that a traditionalthermal load prediction method cannot deeply mine data features and information is lost when an LSTM network processes a long sequence, and therefore the precision of thermal load prediction is improved.
本发明公开了一种短时期建筑热负荷预测的方法, |
---|