Home energy management system (HEMS) is a section of demand response (DR), that plays an imperative role in the residential areas towards appliance management for the enhancement of energy efficiency and grid stability. In this article, a methodical home energy management system (Methodical-HEMS) was proposed based upon K-means, a machine learning algorithm and satin bowerbird optimization (SBO) algorithm to optimize the scheduling of appliances within a 24-h period. The K-means algorithm is used for defining the discrete comfort window (DCW) for schedulable appliance, while SBO algorithm is used for defining the suitable time slots for the schedulable appliance to operate within the DCW. Methodical-HEMS is considered for a single home with the day ahead time of use pricing, to minimize the overall electricity bill (EB) and to satisfy the consumer’s comfort. The performance of Methodical-HEMS is evaluated with other heuristic algorithms, including a particle swarm optimization algorithm, grey wolf optimization algorithm, artificial bee colony algorithm and genetic algorithm. The simulation outcomes demonstrate that, the SBO based HEMS algorithm effectually reduces the overall EB from ₹ 29.14/day to ₹ 22.84/day, minimizes the peak-to-average ratio by 10.28% and remains uncompromising on the consumer’s comfort.