Hybrid Bacterial Colony Optimization and Particle Swarm Optimization for load balancing in fog computing

Fog computing minimizes latency and bandwidth consumption by processing data near the source, but it has the challenge of workload balancing across the dynamic and resource limited fog nodes. Uneven task assignment can result in bottlenecks, idle resources, and lowered Quality of Service (QoS) standards. In this work, we introduce a hybrid metaheuristic load balancing algorithm for fog computing by combining the Bacterial Colony Optimization (BCO) and the Particle Swarm Optimization (PSO) techniques to enhance load balancing. BCO has good solution space exploration capabilities, whereas PSO has the advantage of quick convergence; the hybrid takes advantage from both to achieve reduced makespan with better VM usage. The proposed algorithm has been developed in the Python language, with original BCO and hybrid modules, along with a standard PSO executable. The program has been tested on a synthetic offline task–VM dataset generated by CloudSim 6.0 with size ranges from 100 to 10,000 tasks and poison distribution of variety of tasks arriving, with identical experiment settings. The results indicate the hybrid BCO–PSO to exhibit significant makespan reduction with increased VM utilization compared to the individual BCO, PSO, as well as the Adaptive Inertia Weight Particle Swarm Optimization (AIW–PSO) algorithms for most test scenarios, with faster convergence for high workload scenarios. In the high-load cases, the hybrid reduced makespan by 32.76% compared to AIW–PSO for 5000 tasks and by 35.79% compared to AIW–PSO for 10000 tasks. These experimental results indicate that the proposed hybrid algorithm can be an effective, adaptive solution for task allocation in fog-inspired computational scheduling scenarios. This evaluation focuses on computation-side task scheduling using a synthetic task–VM model and keeping network-level factors such as latency or bandwidth idle.