Multi-Population Cooperative Elite Algorithm for Efficient Computation Offloading in Mobile Edge Computing

The Internet of Things (IoT) and mobile edge computing (MEC) technologies advance, more workloads are being transferred to edge servers for processing. The offloading strategy is a crucial aspect of this development, considering all relevant factors and requiring a rapid development approach. This research aims to develop and propose an innovative solution for fine-grained task offloading scheduling in the context of the evolving technologies of the Internet of Things (IoT) and mobile edge computing (MEC). The research addresses the challenges posed by task dependencies within user-generated applications processed across distributed edge servers. This study presents a solution for fine-grained task offloading scheduling by representing user-generated applications as a directed acyclic graph (DAG). We propose a multi-population cooperative elite algorithm (MCE-PSO) based on particle swarm optimization to address the challenge of offloading tasks with dependencies in MEC, reducing application execution time and energy consumption. The proposed method uses a Penalty-based algorithm to minimize energy usage. The results of our experiments show that MCE-PSO outperforms benchmark algorithms, reducing overhead by up to 82.6%, 36.6%, and 16.3%. This demonstrates the efficiency and reliability of our system.