MHDORA-LBA: Dynamic and Optimized Resource-Aware Load Balancing Approach for Resource Allocation

This paper discusses the LB approach as an optimization-based method for dynamic resource allocation and its impacts on stability and profit. Artificial Bee Colony (ABC), which is a swarm intelligence, was founded based on the foraging behaviour of honey bees (HB) to optimise problems. A newly developed strategy based on this concept is the Differential Evolution Optimized (DEO) Dynamic Resource-Aware LB Method that draws from the HB. It operates by integrating two schemas, DRALBA and Hybrid Modified Honey Bee, via DE Algorithm known as HyMHBDE. The resource allocation in this paper is done dynamically with the help of DRALBA. It presents a novel HB that employs the DEO strategy, borrowed from scout bees, to enhance the performance of the standard ABC in exploration. This method modifies the traditional ABC scout-bee phase by employing the crossover and mutation operators of the DEO algorithm. To authenticate the performance and efficiency of the MHDORA-LBA technique, an experimental examination and comparative study are performed. Findings are shown on both GoCJ and synthetic data, and comparisons are made to the DRALBA or DRABC-LB procedures to see how successful the suggested method is. Based on the simulation findings, it is clear that the suggested strategy maximises throughput and resource utilisation while improving LB stability via task allocation that decreases response time and makespan.