A Data-Driven Analytic Approach for Demand Response of Residential Electricity Consumption

Aligning and designing effective demand management and energy efficiency strategies for households is a difficult task due to different electricity consumption patterns. To tackle this problem, this study try to explores the identification of residential electricity consumption patterns using time series clustering and Jensen-Shannon Divergency(JSD)-based variability analysis. By analyzing data from smart meters, distinct customer profiles were derived, revealing varying degrees of stability and predictability in consumption behaviors. These characteristics help to understand the diversity of load shapes. Depending on the different characteristics, the results show that some consumers with a certain distinct consumption can easily be considered as potential for demand flexibility, while others should be carefully assessed for program offers. The results highlight the critical importance of understanding detailed consumption patterns to design effective Demand Response(DR) programs, leading to optimized energy management and enhanced grid stability and economic.