CAREER: Intelligent Energy Retrofit Decisions for Large-scale Residential Buildings

职业：大型住宅建筑的智能能源改造决策

• 批准号: 2046374
• 负责人: Dong Zhao
• 金额: $ 50.56万
• 依托单位: Michigan State University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-01 至 2026-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2046374&HistoricalAwards=false
• 关键词: CAREER; Intelligent; Energy; Retrofit; Decisions

Large-scale retrofits of existing buildings can potentially reduce energy use by 60%-80% and carbon emissions by 30%. Large-scale retrofits are critical in America where more than 44% of existing buildings are expected to be replaced or renovated by 2050. Retrofits of residential buildings have potential to save more energy than commercial buildings. Although the technologies for residential buildings are not complicated, large-scale retrofits are held back due to a lack of understanding human-building interaction and the high complexity of community systems. This knowledge gap results in inaccurate and unnecessary retrofit decisions and causes wasted energy and investment. For example, an energy-efficient stove is not useful if occupants rarely cook. To address this gap, the investigator has created a new concept of routine occupant behavior (ROB) to indicate the stable occupant behaviors that are essential for building retrofit decisions. The research program aims to better understand human-building integration and produce intelligent, cost-effective, and transformative energy retrofit decisions for large-scale residential buildings. Built upon the ROB concept, the PI proposes a highly integrated research and education/outreach plan.The research outcomes targeted are: (1) definition of ROB via a theoretical framework and a detection tool; (2) optimization of whole-community retrofit decisions via dynamic human-building networks; and (3) enablement of across-community retrofit knowledge transfer via an intelligent lifelong learning model. Research outcomes are to be validated using data from four testbeds with up to 3,000 single-family and multifamily units across multiple climate zones and geographic landscapes. The holistic education/outreach program aims to prepare the next generation of convergent researchers and engineers with knowledge, skills, and abilities in green technology and philosophy.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

对现有建筑进行大规模改造可以减少60%-80%的能源使用和30%的碳排放。在美国，大规模的改造至关重要，预计到2050年，超过44%的现有建筑将被替换或翻新。住宅建筑的改造有可能比商业建筑节省更多的能源。虽然住宅建筑的技术并不复杂，但由于缺乏对人与建筑相互作用的理解以及社区系统的高度复杂性，大规模的改造受到阻碍。这种知识差距导致不准确和不必要的改造决策，并导致浪费能源和投资。例如，如果居住者很少做饭，节能炉灶就没有用。为了解决这一问题，研究人员提出了一个新的概念，即日常居住者行为（ROB），以表明稳定的居住者行为是必不可少的建筑改造决策。该研究计划旨在更好地了解人与建筑的融合，并为大型住宅建筑提供智能，具有成本效益和变革性的能源改造决策。基于ROB概念，PI提出了一个高度整合的研究和教育/外展计划，目标研究成果包括：（1）通过理论框架和检测工具定义ROB;（2）通过动态的人类建筑网络优化整个社区的改造决策;以及（3）通过智能终身学习模型实现跨社区改造知识转移。研究结果将使用来自四个测试平台的数据进行验证，这些测试平台包括多个气候带和地理景观中多达3，000个单户和多户单元。整体教育/推广计划旨在培养下一代具有绿色技术和哲学知识、技能和能力的聚合研究人员和工程师。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Application of occupant behavior prediction model on residential big data analysis

居住者行为预测模型在住宅大数据分析中的应用

• DOI: 10.1145/3486611.3491121
• 发表时间: 2021
• 期刊: and Transportation
• 作者: Mo, Yunjeong;Zhao, Dong
• 通讯作者: Zhao, Dong

Construction Cost Decomposition of Residential Building Energy Retrofit

• DOI: 10.3390/buildings13061363
• 发表时间: 2023-06-01
• 期刊: BUILDINGS
• 影响因子: 3.8
• 作者: Zhao，Dong;Mo，Yunjeong
• 通讯作者: Mo，Yunjeong

Spatial Analysis on Routine Occupant Behavior Patterns and Associated Factors in Residential Buildings

住宅建筑中居住者日常行为模式及相关因素的空间分析

• DOI: 10.1061/9780784483961.035
• 发表时间: 2022
• 期刊: ASCE's construction research congress
• 作者: Mo, Yunjeong;Zhao, Dong
• 通讯作者: Zhao, Dong

Decision-Making Approach to Urban Energy Retrofit—A Comprehensive Review

• DOI: 10.3390/buildings13061425
• 发表时间: 2023-05
• 期刊: Buildings
• 影响因子: 3.8
• 作者: Lei Shu;Dong Zhao

Effective factors for residential building energy modeling using feature engineering

• DOI: 10.1016/j.jobe.2021.102891
• 发表时间: 2021-06
• 期刊: Journal of building engineering
• 影响因子: 6.4
• 作者: Yunjeong Mo;Dong Zhao