Non-Invasive Behavioral Reference Group Categorization Considering Temporal Granularity and Aggregation Level of Energy Use Data

Abstract

Within residences, normative messaging interventions have been gaining interest as a cost-effective way to promote energy-saving behaviors. Behavioral reference groups are one important factor in determining the effectiveness of normative messages. More personally relevant and meaningful groups are likely to promote behavior change. Using readily available energy-use profiles in a non-invasive manner permits the creation of highly personalized reference groups. Unfortunately, how data granularity (e.g., minute and hour) and aggregation (e.g., one week and one month) affect the performance of energy profile-based reference group categorization is not well understood. This research evaluates reference group categorization performance across different levels of data granularity and aggregation. We conduct a clustering analysis using one-year of energy use data from 2248 households in Holland, Michigan USA. The clustering analysis reveals that using six-hour intervals results in more personalized energy profile-based reference groups compared to using more granular data (e.g., 15 min). This also minimizes computational burdens. Further, aggregating energy-use data over all days of twelve weeks increases the group similarity compared to less aggregated data (e.g., weekdays of twelve weeks). The proposed categorization framework enables interveners to create personalized and scalable normative feedback messages.

Time-Pattern Profiling from Smart Meter Data to Detect Outliers in Energy Consumption

“…The proposed clustering-based technique outperformed the other models and detected electricity theft based on the abnormal profiles. Song et al however, focused on non-invasive energy-use profiles to categorise households into personalised groups [2]. There are similarities with the work presented in this paper, as clustering techniques are used for the grouping.…”

“…Song, K. et al, [2] Personalised energy categorisation through k-means, hierarchical clustering and self-organising maps.…”

“…There are similarities with the work presented in this paper, as clustering techniques are used for the grouping. However, the techniques in [2] focus on k-means, hierarchical clustering and self-organising maps, rather than the density-based classification techniques adopted in this paper. An overview of the background research is presented in Table 3, which outlines the advantages/disadvantages of each approach.…”

“…However, a significant amount of research also exists (some of which is presented in this paper) on how the data collected from the smart meters can be used to detect energy usage patterns in residential homes via user profiling techniques [1]. There are close synergies between the level of fuel consumption and the behaviour of the occupants within their homes [2].…”

Energy Conservation at Home: A Critical Review on the Role of End-User Behavior

“…Home energy management systems (HEMSs) have been extensively discussed in the literature, as well as the potential of utility apps and feedback in energy bills to enable or activate users' conservation practices [66,[82][83][84][85]. However, up to date, most of the experts in the field agree that effective feedback from such devices is essential not only to activate one-shot changes but especially to engage users in the long run [31,61,[86][87][88][89][90][91][92][93][94][95][96][97][98][99]. To this end, gamification is frequently mentioned as an effective means for the use of smart meters and other energy consumption feedback supports [100][101][102][103].…”