Characterizing Residential Load Patterns by Household Demographic and Socioeconomic Factors
This work addresses the need for better insights into energy consumption drivers for utility companies and policymakers, but it is incremental as it builds on existing smart-meter analysis methods.
This paper tackled the problem of understanding the drivers of residential energy consumption by characterizing load patterns based on household demographic and socioeconomic factors, using a deep neural network to analyze real-world data and demonstrate connections between these features and consumption behaviors.
The wide adoption of smart meters makes residential load data available and thus improves the understanding of the energy consumption behavior. Many existing studies have focused on smart-meter data analysis, but the drivers of energy consumption behaviors are not well understood. This paper aims to characterize and estimate users' load patterns based on their demographic and socioeconomic information. We adopt the symbolic aggregate approximation (SAX) method to process the load data and use the K-Means method to extract key load patterns. We develop a deep neural network (DNN) to analyze the relationship between users' load patterns and their demographic and socioeconomic features. Using real-world load data, we validate our framework and demonstrate the connections between load patterns and household demographic and socioeconomic features. We also take two regression models as benchmarks for comparisons.