对商业建筑中与进度和运营相关的节能机会进行自动检测，可以帮助建筑业主降低运营费用，同时减少不利的社会影响，如全球温室气体排放。我们提出了自动识别商业建筑中某些能效机会（EEO）的方法，仅使用整个建筑的耗电量和当地气候数据。我们的两步方法使用分段线性回归和基于密度的稳健回归模型残差聚类来检测与计划和运行相关的耗电故障。本文讨论了将该方法应用于两栋全电力办公楼的结果，旨在证明我们的模型在识别此类EEO方面的有效性。文中还提出了将分析结果方便、简洁地呈现给建筑管理人员和操作人员的方法。 引文:2016年冬季会议，佛罗里达州奥兰多，2016年交易，第122卷第。1.

Automated detection of schedule- and operation-relatedenergy savings opportunities in commercial buildings can helpbuilding owners lower operating expenses while also reducingadverse societal impacts such as global greenhouse gas emissions.We propose automated methods of identifying certainenergy-efficiency opportunities (EEOs) in commercial buildingsusing only whole-building electricity consumption andlocal climate data. Our two-step approach uses piecewiselinear regression and density-based robust regression modelresidual clustering to detect both schedule- and operation relatedelectricity consumption faults. This paper discussesresults obtained from applying this approach to two all-electricoffice buildings meant to demonstrate our model’s effectivenessin identifying such EEOs. Ways by which the analysisresults can be conveniently and succinctly presented to buildingmanagers and operators are also suggested.