The increasing variation in residential electricity demand has created a need for accurate electrical load forecasting to support efficient power system operation, demand-side management, and energy utilization in smart homes. This review paper presents a comprehensive study of Artificial Intelligence (AI)-based residential electrical load forecasting techniques used for predicting household power demand. The study examines the use of historical load profiles, time-related parameters, weather conditions, occupancy patterns, and appliance-level electricity consumption for improving forecasting performance. The reviewed techniques are analyzed in terms of their ability to predict short-term residential load variations, peak demand, and daily consumption patterns. Accurate load forecasting can assist in load scheduling, peak-load reduction, demand response, distributed energy resource management, and integration of renewable energy sources within smart residential networks. The paper also discusses major challenges such as load variability, forecasting uncertainty, data availability, computational requirements, and changing consumer behavior. Finally, future research directions are identified toward developing reliable AI-based forecasting frameworks for efficient residential energy management and improved smart-grid operation.