A pattern recognition methodology for analyzing residential customers load data and targeting demand response applications

•Specific time intervals of the day are determined based on the analysis of data.•Data size reduction of load data is performed using a modified symbolic aggregate approximation method.•The data is clustered using a hierarchical algorithm and its underlying patterns are analyzed.•Stability of user's consumption behavior over time is determined using the entropy concept.•A thorough literature review is provided and the related concepts are described in detail.