Predicting Household Electricity Consumption Through Weather Variables: A Quantitative Approach

Abstract

This study analyzes the influence of weather variables on household electricity consumption using a quantitative correlation research design. Twelve months of secondary data, including electricity usage, temperature, relative humidity, and rainfall, were examined to identify consumption patterns and investigate the statistical connection between these meteorological parameters and energy demand. Descriptive statistics showed a mean monthly consumption of 365.00 kWh with a standard deviation of 87.31 kWh, indicating significant seasonal variability in household energy needs. Temperature emerged as the dominant driver of consumption (), followed by a moderate relationship with relative humidity (%), while rainfall showed only a weak positive correlation (mm). The resulting multiple linear regression model quantifies these impacts, revealing that each increase in temperature raises consumption by approximately 22.54 kWh. Humidity further amplifies this effect by increasing thermal discomfort, which prompts households to operate cooling systems for extended periods. Findings conclude that cooling needs during hot and humid periods are the primary cause of significant energy spikes. These results provide a precision tool for demand forecasting, guiding utility providers in maintaining grid stability during peak loads and assisting households in adopting energy-efficient practices to reduce expenses. Integrating weather-aware models is essential for achieving a sustainable and resilient energy future by reducing energy wastage and lowering carbon emissions as the climate continues to shift.