A multi-objective optimization method based on an adaptive meta-model for classroom design with smart electrochromic windows. (15th March 2022)

• Record Type: Journal Article
• Authors: Xu, Yizhe; Yan, Chengchu; Yan, Shanhui; Liu, Huifang; Pan, Yan; Zhu, Faxing; Jiang, Yanlong
• Is Part Of: Energy. Volume 243(2022)
• Publication Date: 2022-03-15
• Subjects: Smart electrochromic window -- Envelope optimization -- Meta-model -- School classroom -- Multi-objective; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2021.122777
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Electrochromic windows are one of the most promising technologies in smart windows. They offer flexible control of indoor thermal environments, lighting environments and energy. The classroom environment has an important impact on the health of primary and secondary school students, but a comfortable indoor environment often requires high energy consumption. This paper presents a multi-objective optimization method for the application of electrochromic window technology to the envelope design of primary and secondary school classrooms. Based on an envelope design method that considers the daylighting windows and viewing windows separately, the feasibility and effect of electrochromic window technology in the classroom are discussed through sensitivity analysis. Then, an adaptive meta-model method is used to improve the model's accuracy and stability. Finally, a multi-objective optimization algorithm is coupled with the optimized meta-model to generate the optimal design scheme set. The proposed multi-objective optimization method is applied to a typical classroom case in Nanjing. The results show that compared with the traditional design scheme, the indicators (TES, TDM and UDINo ) of the optimized schemes are improved. Among them, TES decreased by 254 kWh at most, TDM decreased by 119.3 h at most, and UDINo increased by 65.4% at most. Highlights: A multi-objective optimization method based on adaptive meta-model is presented. Optimization considering daylighting, thermal comfort and energy saving. The feasibility and effect of electrochromic window in classroom are discussed. NSGA-II is applied to ANN model training and structure optimization. The control strategy of electrochromic window in classroom is optimized.