Operation strategy for engineered natural ventilation using machine learning under sparse data conditions. Issue 1 (23rd December 2021)

• Record Type: Journal Article
• Authors: Hiyama, Kyosuke; Takeuchi, Kenichiro; Omodaka, Yuichi; Srisamranrungruang, Thanyalak
• Is Part Of: Japan architectural review. Volume 5:Issue 1(2022)
• Page Start: 119
• Page End: 126
• Publication Date: 2021-12-23
• Subjects: curse of dimensionality -- data sparsity -- green building -- machine learning -- natural ventilation; Building -- Periodicals; Building -- Japan -- Periodicals; Architectural design -- Periodicals; 690
• DOI: 10.1002/2475-8876.12255
• Languages: English
• ISSNs: 2475-8876

Abstract

Abstract: Machine learning (ML) is a useful technique for improving building operations. However, if data can only be obtained from a target building, the data shortage will limit the use of general ML models. To overcome this issue, simplified targets and limited numbers of feature variables are required. In building engineering, building physics can be used to promote ML implementations. In this paper, a case study targeting the operation of engineered natural ventilation is performed based on energy simulations. The target issue is simplified to select the preferable opening pattern, full or half open, throughout the day. Two models using two or three feature variable types are compared. The ML method can effectively predict the correct operation scheme, even in the first year of use. The correct answer rate in the case of three variable types increases from 83% to 95% in the second year, although no significant improvement is observed in the case with two variable types. The results imply the strategy of creating a simplified model first and improving the model following data acquisition works for ML model implementation in building operations. Abstract : A case study targeting the operation of engineered natural ventilation is performed based on energy simulations to verify the feasibility of machine learnings in building operations. The results imply that practical machine learning models can be built for building operation prediction, even in cases where the amount of usable data is limited.