期刊
SUSTAINABLE CITIES AND SOCIETY
卷 79, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.scs.2022.103667
关键词
Artificial neural network; Digital twi n; Machine learning; Data-driven modeling; Thermally activated build i n g system; Build i n g energy managem e n t
资金
- DAI-DAN Co., Ltd
This study proposes a new modeling method based on dual-structured optimization process to create a prediction model that accurately predicts temperature changes within 24 hours, suitable for small-scale office buildings.
Heating, ventilation, and air-conditioning (HVAC) account for a large proportion of energ y consumption. Improving the energy efficiency of HVAC and utilizing increased amounts of renewable energ y are effective strategies for achieving decarbonization. While thermal storage is one of the key technologies that solves a renewable energy issue that has the temporal and geographical gaps between supply and demand , operation planning using optimization methods, such as model predictive control, is important owing to the complexit y of the system. A prediction model with high accuracy and low computational load is required because the per-formance of model predictive control typically depends on it. Further, to facilitate its extensive use in common buildings, it is necessary to develop a simple modeling method that requires no expertise. This study proposes a framework based on a dual-structured optimization process as a modeling method to create a prediction model. This method was applied to an actual small-scale office building. It was confirmed that such a model which accurately predicts up to 24 h ahead within approximately 1 s can be created. 1
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据