CSR: EAGER: Design and Implementation of a Fine-Grained Appliance Energy Profiling System for Green Building

CSR：EAGER：绿色建筑细粒度电器能源分析系统的设计和实施

• 批准号: 1255965
• 负责人: Nirmalya Roy
• 金额: $ 26.53万
• 依托单位: Washington State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-01-01 至 2013-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1255965&HistoricalAwards=false
• 关键词: CSR; EAGER; Design; Implementation; Fine

Green building applications need efficient and fine-grained determination of power consumption pattern of a wide variety of consumer-grade appliances through non-intrusive load monitoring (NILM) techniques for an effective adaptation and percolation of demand response model down to the consumer level appliances. A key inhibitor to the widespread adoption of such demand response policy at the consumer grade appliances for intelligent building energy management, is the inability of smart plug to efficiently determine, control or infer the power consumption pattern of multiple devices in tandem. In practice, deploying smart plug based NILM and acquiring the low-level power measures of a large number of devices is often difficult or impossible due to the deployment complexity and varying characteristics of devices and thus must instead be employed at the circuit-level and inferred through the incorporation of novel usage-based measurement and probabilistic level-based disaggregation algorithm. But the challenges in deploying non-intrusive load monitoring algorithm involve disaggregating individual device?s consumption from the aggregate power measurement, as well as modeling and incorporating the usage based prediction. Thus in this project we will focus on advanced machine learning and data analytics algorithms that capture the measurement based approach and circuit level NILM with the autonomous profiling and prediction logic to enable the deployment of flexible and fungible smart plug and the evolvability of future DR model in green building applications.

绿色建筑应用需要通过非侵入性负载监测(NILM)技术高效、细粒度地确定各种消费级电器的电力消耗模式，以便有效地适应和渗透需求响应模型，向下渗透到消费级电器。在消费级电器中广泛采用这种需求响应策略以进行智能建筑能源管理的一个关键制约因素是，智能插头无法有效地确定、控制或推断多个设备串联的电力消耗模式。在实践中，由于部署的复杂性和设备的变化特性，部署基于智能插头的NILM和获取大量设备的低电平功率测量通常是困难或不可能的，因此必须在电路级使用，并通过结合新的基于使用的测量和基于概率级别的分解算法来推断。但部署非侵入式负载监控算法的挑战涉及将单个设备的消耗从总功率测量中分解出来，以及建模和纳入基于使用的预测。因此，在本项目中，我们将重点关注先进的机器学习和数据分析算法，这些算法利用自主配置和预测逻辑捕获基于测量的方法和电路级NILM，以支持灵活和可替换的智能插头的部署，以及未来DR模型在绿色建筑应用中的可演进性。