Multi-Objective Demand Response Scheduling Using Fire Hawk Optimization for Smart Microgrid Systems

Abstract

The use of renewable energy resources and distributed energy resources has added complexity to the energy management of smart microgrids, thus the importance of efficient demand response scheduling has come into play to guarantee energy grid stability, decrease operational costs, and enhance the usage of renewable energy resources. Optimization techniques used in traditional approaches can be difficult to apply in dynamic load scenarios due to premature convergence, longer scheduling delays, and poor load balancing. In this regard, this paper introduces a fire hawk optimization (FHO) algorithm for the demand response scheduling problem, inspired by the fire hawk swarm and their natural hunting habits. The proposed framework aims at minimizing the cost of energy consumption, transmission power loss, scheduling delay, peak to average ratio while increasing the accuracy of scheduling and maximizing renewable energy utilization. The model was designed and run in MATLAB 2024a and tested with smart grid data from the UCI Machine Learning Repository. Experimental test showed that the proposed method reported a minimum peak to average ratio of 2.18, 8.42 kW of transmission power loss and a scheduling delay of 29ms with a maximum scheduling accuracy of 98.14%. Through comparative analysis it was also observed that the FHO algorithm is faster to converge and better than the other algorithms (GA, PSO, GWO), and it is considered an effective, scalable and reliable algorithm for intelligent demand response scheduling in next-generation smart microgrid systems.