The ReBuild Initiative - A nexus for research into data-driven retrofit solutions for energy-efficient buildings
The ReBuild Initiative - A nexus for research into data-driven retrofit solutions for energy-efficient buildings
批准号:
566285-2021
负责人:
Evins, RalphRP
金额:
$32.96万
依托单位:
依托单位国家:
加拿大
项目类别:
Alliance Grants
财政年份:
2022
资助国家:
加拿大
项目状态:
已结题
起止时间:
2022-01-01 至 2023-12-31
中文摘要
减少现有建筑的能源消耗是实现气候变化缓解目标的关键。气候变化对弱势群体的影响不成比例,翻新可以改善他们的住房条件。我们需要更好的计算机模型来了解我们的建筑是如何运行的,以提供强有力的设计解决方案和基于证据的政策。使用机器学习的数据驱动方法具有巨大的潜力,因为我们的建筑提供了大量数据,但目前用于减少排放的数据很少。这些可以与现有的基于物理的模型相结合,也可以用来加快模拟过程。重建倡议是一个行业-政府-学术界联盟,将开展16项研究活动,涵盖挑战的广度和复杂性,每项活动都与合作伙伴组织共同设计,以满足他们的需求。重要的是要在专业人员、服务提供商和政策制定者使用的方法之间找到协同作用。这些合作将有助于提炼和解决数据驱动的建筑能源改造中的关键问题,例如:哪些机器学习方法在解决每个问题方面都有效?这些方法如何与现有的基于模拟的方法集成?需要哪些数据集来支持它们,以及如何评估它们?如何利用和部署这些发展,以提供改进的工具、分析和政策措施?该倡议的目标是:(A)开发新的方法和工具,利用数据驱动的方法做出建筑能源改造决策,(B)促进学术界、工业界和政府合作伙伴之间的知识、数据和软件交流,以及(C)影响加拿大未来关于现有建筑的政策和法规。合作伙伴将测试和应用基于Web的工具,以提高盈利能力、市场渗透率和效率。它将为现有建筑法规的制定以及市政、省和联邦各级的其他政策提供信息。它还将培训一批拥有专业知识的熟练工人,将尖端方法应用于工业、政府和学术界的紧迫问题。
英文摘要
Reducing energy use in existing buildings is key to meeting climate change mitigation goals. Climate change disproportionally affects disadvantaged peoples, and retrofits can improve their housing conditions. Better computer models of how our buildings are performing are needed to give robust design solutions and evidence-based policies. Data-driven methods that use machine-learning have great potential as our buildings provide lots of data, but little is currently used for reducing emissions. These can be combined with existing models based on physics, and also used to speed up the simulation process.The ReBuild Initiative is an industry-government-academia consortium that will undertake 16 research activities that encompass the breadth and complexity of the challenge, each co-designed with a partner organization to address their needs. It is important to find synergies between the methods used by professionals, service providers and policy-makers. These collaborations will help refine and address key questions in data-driven building energy retrofits such as: Which machine learning methods are effective in tackling each problem? How can these methods integrate with existing simulation-based approaches? What datasets are needed to power them, and how can they be evaluated? How should these developments be leveraged and deployed to deliver improved tools, analyses and policy measures?The goals of the Initiative are: (a) to develop new methods and tools for building energy retrofit decisions using data-driven approaches, (b) to facilitate the exchange of knowledge, data and software between academia, industry and government partners, and (c) to influence future policy and regulation in Canada regarding existing buildings. Web-based tools will be tested and applied by partners to improve profitability, market penetration and efficiency. It will inform the development of a code for existing buildings and other policies at municipal, provincial and federal levels. It will also train a cohort of skilled workers with expertise to apply cutting-edge methods to pressing problems in industry, government and academia.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Using component surrogate models in the integrated design process for high-performance buildings
-
批准号:580451-2022
-
项目类别:Alliance Grants
-
资助金额:$1.46万
-
财政年份:2022
-
负责人:Evins, RalphRP
-
依托单位:
海外基金