Decision Support Tool for Optimizing the Energy Efficient of Buildings

优化建筑物能源效率的决策支持工具

• 批准号: 533325-2018
• 负责人: Zhao, Lian
• 金额: $ 1.82万
• 依托单位: Ryerson University
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2018
• 资助国家: 加拿大
• 起止时间: 2018-01-01 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=669772
• 关键词: Decision; Support; Tool; Optimizing; Energy

The construction industry in Canada has been developing automated technologies for smart buildings.At the**individual building level, Building Automation Systems (BAS) is a key technology for smart buildings. These**systems monitor and control building systems, generating a huge amount of data. Whilst this data embeds**imported and critical information about the building dynamics, little has been analyzed to obtain thorough**understanding on the building systems.Current decision support systems are mostly based on prior-knowledge,**which is normally represented by a huge set of equations and empirical relationships, without sufficient**knowledge about the actual systems that can be obtained online through analyzing the operational data and a**self-learning process. This proposed research is aimed to investigate how to best understand the information**embedded in BAS operational data and how to use this understanding to optimize the operation of the building.**In the project, we will integrate a model that can thoroughly analyze BAS operational data from data capturing**systems to provide building managers with a tool for optimizing building operations. Our work will have the**following novel contributions: (1) the decision support system will be capable of correlating the different**dynamic and static variables to provide suggestion for optimization.(2) the decision support system, also will**be able to quantify the lagged or delayed cause-effect relationships among the building parameters. (3) allows**for building manager to simulate predicted performance measures as the result of interventions.In a nut**shell,This research project can increase the competitive edge of the collaborating company in the construction**industry thereby contributing to Canada's economy while protecting environment.In addition, this project will**also be a very useful platform to provide students(HQP) with hands on marketable career oriented experience.

加拿大的建筑行业一直在开发智能建筑的自动化技术。在**个体建筑层面，楼宇自动化系统（BAS）是智能建筑的关键技术。这些**系统监视和控制建筑系统，生成大量数据。虽然这些数据嵌入了关于建筑动力学的导入和关键信息，但很少进行分析来获得对建筑系统的彻底理解。当前的决策支持系统大多基于先验知识，通常由大量方程和经验关系表示，没有足够的关于实际系统的知识，这些知识可以通过分析操作数据和自学习过程在线获得。本研究旨在探讨如何最好地理解 BAS 运营数据中嵌入的信息**，以及如何利用这种理解来优化建筑物的运营。**在该项目中，我们将集成一个可以彻底分析来自数据捕获系统的 BAS 运营数据的模型，为建筑管理者提供优化建筑运营的工具。我们的工作将具有**以下新颖的贡献：（1）决策支持系统将能够关联不同的**动态和静态变量，以提供优化建议。（2）决策支持系统还将**能够量化建筑参数之间滞后或延迟的因果关系。 (3) 允许建筑经理模拟干预结果的预测绩效测量。简而言之，该研究项目可以提高合作公司在建筑**行业的竞争优势，从而在保护环境的同时为加拿大经济做出贡献。此外，该项目也将成为一个非常有用的平台，为学生（HQP）提供面向市场的职业导向经验。