Building Electricity Consumption Analysis: Data-Driven Approach with Preprocessing, Visualization, and Cluster Analysis

Electricity consumption data for the building for the period September 2021 to March 2023 were processed and analyzed for this study. The dataset consists of electricity consumption data at 96 time points per day, covering 31 consecutive months. The goal of this study is to provide a comprehensive analysis of the electricity consumption behavior of buildings, exploring temporal patterns, and extracting potential electricity consumption patterns. First, the data are preprocessed, including data cleaning, handling of missing values and outliers, and data normalization to ensure data accuracy and consistency. Then, through data visualization and statistical analysis, the periodicity of electricity consumption in buildings and the characteristics of electricity consumption during peak and trough hours are revealed. Based on this, cluster analysis was applied to group similar power usage patterns and identify different power usage characteristics. The results of the study provide important references and guidance for building energy management and energy saving optimization, and are expected to help building operators use energy resources more efficiently, reduce the cost of energy consumption, and reduce the impact on the environment. The study is of positive significance for the promotion of sustainable development and the development of intelligent buildings.