We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基于多阶段注意力机制的建筑空调负荷预测方法.
- Authors
陈东海; 马 旭; 王 波; 朱晓杰; 白文博
- Abstract
Load forecasting of building air conditioning is of great significance for improving the accuracy of power load forecasting of buildings and regional distribution networks. In order to improve the load forecasting accuracy of building air conditioning, a load forecasting method based on multi-stage attention mechanism is proposed. First, the attention module of influencing factors is constructed to fully consider the importance difference of different influencing factors for load forecasting of building air conditioning. Second, the LSTM network model is used to extract the implicit features of influencing factors in each hour. Finally, the temporal attention module is constructed to differentiate the implicit features of the influencing factors in different hours according to the importance of building air conditioning load forecasting to obtain the results of the air conditioning load forecasting. The example results show that the construction of the influencing factor attention module and the temporal attention module are both conducive to improving the model’s ability to fit the building air-conditioning load, thus effectively improving the load prediction accuracy of building air-conditioning.
- Subjects
AIR conditioning
- Publication
Zhejiang Electric Power, 2023, Vol 42, Issue 10, p57
- ISSN
1007-1881
- Publication type
Article
- DOI
10.19585/j.zjdl.202310007