Cost-efficient smart home energy management with hybrid quadratic interpolation tuna swarm optimization

As advanced technologies continue to evolve, the use of automated devices in homes is growing rapidly. Consequently, developing new strategies for managing electricity consumption is essential to ensuring the safety of household installations. Demand Side Management (DSM) is one proposed solution to address residential electricity demand, significantly contributing to the development of small-scale and smart grid systems. Through DSM programs, consumers can communicate with grid operators, aiding in decision-making and helping utilities reduce peak power demand. This study introduces a hybrid optimization algorithm for energy scheduling in smart homes called Quadratic Interpolation Tuna Swarm Optimization (QITSO). This algorithm aims to improve solution precision by enhancing solution diversity through the optimization process, effectively balancing the exploration and exploitation phases. The proposed model operates in two varying operational time frames: 60 min and 15 min. Additionally, user demand and behavior were analyzed under two electricity pricing systems: Critical Peak Pricing (CPP) and Real-Time Pricing (RTP). Simulation results show that the proposed model efficiently schedules devices, reducing peak demands and electricity costs while maintaining consumer comfort. Specifically, the performance of the hybrid algorithm is highlighted, demonstrating significant cost savings of 73.04% in RTP and 42.56% in CPP over a 60-min operating time interval. Additionally, the results show a 46.99% savings in PAR for RTP and 45.11% in cost for CPP. For a 15-min operating time interval, QITSO achieves 29.03% in RTP and an impressive 75.71% in CPP, underscoring its effectiveness compared to the QITSO algorithm over Tuna Swarm Optimization (TSO). Thus, the superiority of the QITSO algorithm over TSO and QIO techniques is clearly demonstrated.