Occupancy-centric predictive control of building systems

以占用为中心的建筑系统预测控制

• 批准号: 530263-2018
• 负责人: Gunay, Burak
• 金额: $ 1.82万
• 依托单位: Carleton 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=652672
• 关键词: Occupancy; centric; predictive; control; building

It is estimated that 15 to 30% of the energy used in commercial buildings is wasted due to inefficiencies in the**operation of indoor climate control systems. Given that indoor climate control in commercial buildings in**Canada accounts for 13% of the secondary energy use, 11% of the CO2 emissions, and is a major driver for**new energy infrastructure, efficient operation of buildings represents great potential to reduce our**environmental and economic impact.**The most basic requirement for energy efficient building operation is to provide building services only when**and where they are needed, in the amount that they are needed. This requirement is inherently linked to**acquiring various forms of occupancy information. For example, the information regarding the arrival and**departure times is needed to determine the operating hours for heating and cooling equipment. The information**about the number of occupants in a building is needed to determine the ventilation rates for indoor air quality.**Despite the need for accurate occupancy information in building energy management, existing occupancy**sensing technologies are either too inaccurate (e.g., motion detector-based occupancy sensors) or too invasive**causing privacy concerns (e.g., camera-based people counting sensors). To this end, this project will develop**sensor fusion-based algorithms that can leverage low-cost data streams that are commonly available in building**automation systems to detect and forecast floor level occupancy counts. The algorithms will be extensively**tested via simulation and field implementations.**The project will make significant contributions to Canada. New occupancy sensing methods will be created.**Adoption of these methods by the industry partner, a Canadian energy analytics company, will contribute to our**knowledge-based economy. Wider usage of the algorithms will reduce the environmental and economic impact**of commercial buildings. The HQP will conduct interdisciplinary research on building performance, building**automation systems, and data mining.

据估计，商业建筑中使用的能源中有15%至30%是由于室内气候控制系统运行效率低下而浪费的。鉴于 ** 加拿大商业建筑的室内气候控制占二次能源使用量的13%，占二氧化碳排放量的11%，并且是 ** 新能源基础设施的主要驱动力，建筑物的高效运行代表着减少我们 ** 环境和经济影响的巨大潜力。节能建筑运营的最基本要求是只在需要时 ** 在需要的地方提供建筑服务，并提供所需的数量。这一要求与 ** 获取各种形式的占用信息有着内在的联系。例如，需要关于到达和 ** 离开时间的信息来确定加热和冷却设备的运行时间。需要关于建筑物内居住者数量的信息 ** 来确定室内空气质量的通风率。**尽管在建筑物能量管理中需要准确的占用信息，但是现有的占用感测技术要么太不准确（例如，基于运动检测器的占用传感器）或过于侵入性 ** 导致隐私问题（例如，基于照相机的人员计数传感器）。为此，该项目将开发基于传感器融合的算法，该算法可以利用建筑自动化系统中常用的低成本数据流来检测和预测楼层占用率。这些算法将通过模拟和现场实施进行广泛的测试。该项目将为加拿大做出重大贡献。将创建新的占用感知方法。**行业伙伴，一家加拿大能源分析公司采用这些方法，将有助于我们的知识型经济。算法的广泛使用将减少商业建筑对环境和经济的影响。HQP将对建筑性能、建筑自动化系统和数据挖掘进行跨学科研究。