CPS: Breakthrough: Low-cost Continuous Virtual Energy Audits in Cyber-Physical Building Envelope

建筑物（包括办公室、商场和住宅公寓）的用电量占一个国家能源支出和碳足迹的很大一部分。据估计，建筑物消耗了美国总发电量的72%。然而，不幸的是，30%的能源消耗被浪费了。虚拟能源评估是一种以最少的专家干预，以低成本优化建筑能源效率，最大限度地减少浪费的方法。虚拟能源审计包括对建筑能源使用的不同来源进行彻底和近乎实时的分析，负载电器和设备的个性化能源足迹，以及主动识别能源漏洞和空气泄漏。该项目建立了一个低成本的解决方案，结合了非侵入式单点能源监测和低成本红外摄像机的使用，提供持续的能源审计。该系统将向房东或住宅用户提供连续的虚拟审计报告。该系统将部署在马里兰州巴尔的摩市的低收入社区，在那里，不良的绝缘问题被认为是财政上无法克服的，而确定这些问题的低成本解决方案对房东来说很重要。为了开发可扩展的低成本虚拟能源审计系统，本突破性研究追求智能建筑感知、计算和驱动的接口。该项目将在三个主要研究重点领域下执行。首先，它利用自主发现、分析和基于规则的预测模型来捕获分解的功率测量和设备的实际使用模式之间的关系，以查明任何异常消耗。其次，pi开发用于低成本低频热图扫描和漏气检测的零能量远红外成像传感器。第三，项目设计和评估网络物理建筑传感系统，从控制级设计的角度进行虚拟能源审计，推动实现深度节能和建筑效率。此外，与Constellation合作的pi将举办建筑能源教育项目和研讨会，让本科生，高中和代表性不足的学生群体了解如何设计和编程电表和智能插头。

Electricity usage of buildings (including offices, malls and residential apartments) represents a significant portion of a nation's energy expenditure and carbon footprint. Buildings are estimated to consume 72% of the total electricity production in the US. Unfortunately, however, 30% of this energy consumption is wasted. Virtual energy assessment is an approach that can optimize building energy efficiency and minimize waste at a low cost with minimal expert intervention. A virtual energy audit includes a thorough and near real time analysis of different sources of building energy usage, individualized energy footprints of load appliances and devices, and proactive identification of energy holes and air leakages. This project builds a low cost solution that combines the use of non-intrusive single point energy monitoring and low cost IR cameras to provide continuous energy audits. The system will provide continuous virtual audit reports to the landlords or residential users. The system will be deployed in low-income neighborhoods in Baltimore City, Maryland, where poor insulation problems are assumed to be fiscally insurmountable and low cost solutions to determining these issues is important for the landlords. To develop a scalable low cost virtual energy auditing system, this breakthrough research pursues the interfaces of smart building sensing, computing and actuation. The project will be executed under three main research thrust areas. First, it utilizes an autonomous discovery, profiling and rule-based predictive model to capture the relationship between disaggregated power measures and a device's actual usage patterns to pinpoint any abnormal consumption. Second, the PIs develop zero-energy far-infrared imaging sensors for low cost low frequency heat map scanning and air leakage detection. Third, the project engineers and evaluates cyber-physical building sensing system with a control level design perspective for virtual energy auditing that drives the realization of deep energy savings and building efficiency. Additionally, the PIs with collaboration from Constellation will host building energy education projects and workshop where undergraduate, high school, and underrepresented group of students would understand how to design and program energy meters and smart plugs.