A framework for allocating personalized appliance-level disaggregated electricity consumption to daily activities

Abstract

Residential and commercial buildings account for more than 74% of total annual electricity consumption in the United States. Studies have shown that occupants' awareness of their behaviors in consuming electricity encourages them to change their unsustainable behaviors and improves the sustainable ones. As behaviors impact the ways that daily activities are performed, in order to develop a personalized appliance level model of an occupant's behavior, precise activity recognition is required. In this paper, we introduce a novel framework to allocate personalized appliance-level disaggregated electricity consumption to daily activities. In our framework, using ontology based approach, the input appliance usage data is first separated into categories of non-overlapping activity events. The separated data sets are then segmented to detect activity segments, which are next mapped into activity classes using a trained classification model. To evaluate the performance of our presented framework, an experimental validation was carried out in three test bed apartment units. Results of validation showed a total F-measure value of 0.97 for segmentation and an average accuracy of 93.41% for activity recognition. Following the activity recognition, the approximate electricity consumption associated with the recognized activities was estimated and the results of each test bed unit were compared with the others.

Infrared thermography of human face for monitoring thermoregulation performance and estimating personal thermal comfort

“…The potential energy savings from optimizing the building HVAC temperature setpoints can reach up to 37% [14] depending on the climate, building size, and materials. While the more sophisticated optimization and control algorithms might help improving the energy efficiency and thermal comfort, there is a trade-off between the controller complexity and the potential energy savings [45][46][47][48], which requires further investigations. The benefits of the control policy mentioned above for HVAC operations is not limited to energy efficiency.…”

A Non-Intrusive Load Monitoring Algorithm Based on Non-Uniform Sampling of Power Data and Deep Neural Networks

“…In the last several years, an increasing interest on the energy themes focused on the reduction of emissions from fossil sources has led the researchers to develop solutions oriented to improve the users' energy awareness in everyday life actions, as well as to assist them to better schedule these actions. Among these solutions, Non-Intrusive Load Monitoring (NILM) is surely one of the most studied [1], in addition to other useful ones, such as energy management and analytic [2,3], load task scheduling [4], or behaviour-based consumption [5]. These algorithms require high computational burden, since their results could be requested in real time to provide an immediate feedback to the user.…”

Towards unsupervised learning of thermal comfort using infrared thermography

“…In addition, occupant behavior and utilization of the new technologies requires in buildings further explorations [48][49][50][51] . It is worth mentioning that the trade-off between the complexity of the sensing devices and controllers and the energy savings can play an important role for the level of user adaptability of these methods [49,[52][53][54][55][56][57], which requires further investigations.…”