Classification of consumers and analysis of electricity consumption patterns based on variance analysis methods

Relevance. The increasing electricity consumption in the private residential sector, driven in part by the growing use of electric heating, is leading to higher loads on 0.4 kV power transmission lines. Traditional standardized load profiles do not always reflect modern consumption patterns and conditions, which creates risks of inaccurate assessments of the electrical grid’s capacity and necessitates more precise modeling of grid operating conditions. Purpose . To develop approaches for classifying consumers and identifying statistically significant patterns in electricity consumption in private residential areas for subsequent calculation of grid operating conditions. Methods . The analysis was based on half-hourly electricity consumption data from 42 private houses, collected via an Automated Meter Reading and Management System (AMRMS). The data was cleaned using the three-sigma rule to remove gaps and outliers, and heat maps were used to identify non-representative consumers. The statistical significance of differences was determined using analysis of variance (ANOVA) and Tukey’s test. Based on median consumption values, consumer groups were formed (low and high electricity consumption). Data processing and visualization were performed using MS Excel, Python (Pandas, NumPy, SciPy libraries), and the Statistica software package. Results. The analysis confirmed statistically significant differences in electricity consumption between most of the houses (F = 2065.4, p < 0.001). Tukey’s test showed that within each group, homes exhibited relatively stable energy consumption values, while intergroup comparisons revealed substantial variations in electricity usage. As a result of the study, two consumer types were identified: "low" and "high" consumption groups. The high-consumption group exhibited distinct evening peaks (18:00–22:00), whereas the low-consumption group had a more evenly distributed load profile. Conclusion. The application of statistical analysis methods to electricity consumption data enabled the simplification of household classification into two main groups and the development of typical consumption profiles. These results were integrated into the LineCapacity software, facilitating grid operation calculations and reducing the risk of misjudging the available power transmission capacity. A promising research direction is planned, focusing on expanding the dataset on residential electricity consumption. This will allow for the consideration of seasonal factors and the development of simulation modeling mechanisms for various consumer groups.