<p>Smart home users confront two major issues: constant power and expensive electricity. A demand-response analysis was used traditionally with different optimization and constraint-driven updation to ensure user comfort and control power consumption. The objective of the proposed model is to optimize power utilization and user satisfaction and reduce the electricity bill. A novel DPReDE model is presented in this research work by integrating an optimized lighted-weighted differential model to optimize the user comfort, power consumption, and electricity bill. Optimizing energy consumption in a smart home setting was the goal of this suggested model, which combined demand-pricing and response analysis with an improved Differential evolution approach. The EMPC controller and the AUDB and PSCDB are the local database that are linked to this model. The model learned about power wastage and expensive time slots. This slot-by-slot analysis of energy expenditure and price shifts the distribution of available resources. This model includes Enhanced Differential Evolution, which may be used to figure out when it is most cost-effective and convenient to use various appliances. Scheduling and slot switching are also optimized for performance concerning average delay, user comfort, and power consumption. Grey Wolf Optimization, Particle Swarm Optimization, Tri-objective scheduling model, price, demand Response adaptive scheduling model, Stochastic Mixed-Integer Linear Programming Framework, Fuzzy adaptive BAT scheduler, and Fuzzy compromised Game theory models are used to verify the model. In comparison to the models developed by Lee et al., Khalid et al., Makhdameh et al., Chamandoust et al., Liu et al., and Javedi et al., the proposed model reduced the average delay by 16.54%, 66.51%, 18.01%, 58.98%, and 56.19%, respectively. The proposed work is validated against normal and heavy load situations. With a score of 0.9399, the proposed model showed a considerable improvement in consumer comfort. As mentioned earlier, the DPReDE algorithm claims to have better power consumption than existing methods, using an average of 2.2537 kW. In normal load scenarios, the proposed model reduced the wait time value by up to 26.63%, while in heavy load situations, it reduced it by 61.36%. This outperformed all existing optimization methods. In both normal and heavy load scenarios, the PAR value was lowered by up to 41.77% and 78.62%, respectively, by the suggested approach, which beat all previous optimization models.</p>

A novel DPReDE model for optimizing demand-side power management in smart home

期刊论文
发表日期：

2025年3月7日

查看全文

Poonam Saroha,
Gopal Singh

摘要

Smart home users confront two major issues: constant power and expensive electricity. A demand-response analysis was used traditionally with different optimization and constraint-driven updation to ensure user comfort and control power consumption. The objective of the proposed model is to optimize power utilization and user satisfaction and reduce the electricity bill. A novel DPReDE model is presented in this research work by integrating an optimized lighted-weighted differential model to optimize the user comfort, power consumption, and electricity bill. Optimizing energy consumption in a smart home setting was the goal of this suggested model, which combined demand-pricing and response analysis with an improved Differential evolution approach. The EMPC controller and the AUDB and PSCDB are the local database that are linked to this model. The model learned about power wastage and expensive time slots. This slot-by-slot analysis of energy expenditure and price shifts the distribution of available resources. This model includes Enhanced Differential Evolution, which may be used to figure out when it is most cost-effective and convenient to use various appliances. Scheduling and slot switching are also optimized for performance concerning average delay, user comfort, and power consumption. Grey Wolf Optimization, Particle Swarm Optimization, Tri-objective scheduling model, price, demand Response adaptive scheduling model, Stochastic Mixed-Integer Linear Programming Framework, Fuzzy adaptive BAT scheduler, and Fuzzy compromised Game theory models are used to verify the model. In comparison to the models developed by Lee et al., Khalid et al., Makhdameh et al., Chamandoust et al., Liu et al., and Javedi et al., the proposed model reduced the average delay by 16.54%, 66.51%, 18.01%, 58.98%, and 56.19%, respectively. The proposed work is validated against normal and heavy load situations. With a score of 0.9399, the proposed model showed a considerable improvement in consumer comfort. As mentioned earlier, the DPReDE algorithm claims to have better power consumption than existing methods, using an average of 2.2537 kW. In normal load scenarios, the proposed model reduced the wait time value by up to 26.63%, while in heavy load situations, it reduced it by 61.36%. This outperformed all existing optimization methods. In both normal and heavy load scenarios, the PAR value was lowered by up to 41.77% and 78.62%, respectively, by the suggested approach, which beat all previous optimization models.