HHBA-GA: Hybrid Hitchcock Bird Algorithm and Genetic Algorithm Based Dynamic Task Scheduling in Edge-Cloud Computing
TL;DR
Experiments indicate that HHBA-GA achieves the best performance in makespan, energy consumption, and cost efficiency compared with GA, PSO, and standalone HHBA, and the model significantly enhances resource usage, proving its effectiveness in large-scale edge-cloud applications.
Abstract
: Edge computing, a geographically distributed set of computing platforms, is crucial in modern IoT applications for faster processing and application execution. Effective task scheduling in edge-cloud computing enhances resource utilization, lowers makespan, reduces energy consumption, and achieves cost-effectiveness, meeting new time measure requirements for the modern world. This paper presents a new Hybrid Hitchcock Bird Algorithm (HHBA) and Genetic Algorithm (GA)-based dynamic task scheduling method that combines the advantages of HHBA and GA algorithms. While GA operates on the solution space to evolve a more effective solution through selection and mutation operations, refining the task allocation by promoting the use of two-point crossover and uniform crossover for the topic planning in trades, HHBA can be considered as the optimizer, honing in on the set of sub-tasks through local comparisons while ensuring an equal workload among the resources. Experiments indicate that HHBA-GA achieves the best performance in makespan, energy consumption, and cost efficiency compared with GA, PSO, and standalone HHBA. The proposed pathway leads to an increase in energy savings of up to 24% and a reduction in cost reduction of about 22% when compared to traditional approaches. Furthermore, the model significantly enhances resource usage, proving its effectiveness in large-scale edge-cloud applications.