Implementation of novel occupant-centric control strategies in commercial buildings

在商业建筑中实施新颖的以居住者为中心的控制策略

• 批准号: 568511-2021
• 负责人: Ouf, MohamedMMMA
• 金额: $ 1.46万
• 依托单位: Concordia University
• 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
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=746366
• 关键词: Implementation; novel; occupant; centric; control

The proposed project will strengthen the partnership between researchers at Concordia and Carleton Universities with BrainBox AI, a Montreal-based leader in building automation. The project aims to continue the development of "occupant-centric control" algorithms which balance between energy efficiency and occupant comfort by using machine learning techniques to learn and predict occupant preferences. In particular, this project will also entail deploying the developed algorithms in existing commercial buildings to demonstrate and quantify their effect on reducing energy consumption and improving occupant comfort. Through these real-life applications, the proposed project will identify and address technical and non-technical barriers that may hinder the implementation of advanced control strategies in existing buildings. With access to more than 18 million building square feet of buildings across different sectors in Canada, the partner organization will leverage the outcomes of this research to complement their existing libraries of solutions and algorithms for smart building controls. Ultimately, these technologies will provide significant tangible reductions in buildings' energy use and CO2 emissions for their clients, which will strengthen their position as a global leader in integrating Artificial Intelligence (AI) in building operations. Research outcomes can also be easily deployed at minimal capital cost in many of Canada's over half a million commercial buildings, which collectively consume approximately 40% of national energy use. Furthermore, this partnership will provide Highly Qualified Personnel (HQP) with a unique opportunity to gain relevant industry experience that will allow them to fully understand building systems and controls technologies related to their research. They will be able to work with data from real buildings and interact with their systems and components, while gaining interdisciplinary research skills combining building engineering with building sciences; both of which are strongly and urgently needed in the Canadian building industry.

拟议中的项目将加强康科迪亚大学和卡尔顿大学的研究人员与总部位于蒙特利尔的建筑自动化领先者Brainbox AI之间的合作。该项目旨在通过使用机器学习技术来学习和预测乘员偏好，继续开发能够在能源效率和乘员舒适度之间取得平衡的“以乘员为中心的控制”算法。特别是，该项目还需要在现有商业建筑中部署开发的算法，以演示和量化它们在降低能源消耗和改善乘员舒适性方面的效果。通过这些实际应用，拟议的项目将确定和解决可能阻碍在现有建筑中实施先进控制战略的技术和非技术障碍。通过使用加拿大不同行业超过1800万平方英尺的建筑，合作伙伴组织将利用这项研究的成果来补充其现有的智能建筑控制解决方案和算法库。最终，这些技术将为其客户显著减少建筑物的能源消耗和二氧化碳排放，这将加强其在将人工智能(AI)整合到建筑运营中的全球领先地位。研究成果还可以以最低的资本成本轻松部署在加拿大超过50万座商业建筑中的许多建筑中，这些建筑总共消耗了全国约40%的能源。此外，这一合作关系将为高素质人员(HQP)提供一个获得相关行业经验的独特机会，使他们能够充分了解与其研究相关的建筑系统和控制技术。他们将能够处理真实建筑的数据，并与其系统和组件进行交互，同时获得结合建筑工程和建筑科学的跨学科研究技能；加拿大建筑业强烈而迫切地需要这两种技能。