Reinforcement Learning Controlled Adaptive PSO for Task Offloading in IIoT Edge Computing

TL;DR

The paper addresses efficient task offloading in IIoT-enabled MEC under dynamic conditions. It introduces a hybrid APSO-SAC method that uses Soft Actor Critic to adaptively tune the hyperparameters of Adaptive Particle Swarm Optimization, balancing exploration and exploitation in changing environments. Experiments on large-scale simulations (250 devices, 20 MEC servers) show APSO-SAC achieving the lowest best cost compared with baseline PSO and other RL-based approaches, demonstrating improved latency and energy efficiency. The approach is implemented with open-source code, enabling reproducibility and practical deployment in IIoT edge computing scenarios.

Abstract

Industrial Internet of Things (IIoT) applications demand efficient task offloading to handle heavy data loads with minimal latency. Mobile Edge Computing (MEC) brings computation closer to devices to reduce latency and server load, optimal performance requires advanced optimization techniques. We propose a novel solution combining Adaptive Particle Swarm Optimization (APSO) with Reinforcement Learning, specifically Soft Actor Critic (SAC), to enhance task offloading decisions in MEC environments. This hybrid approach leverages swarm intelligence and predictive models to adapt to dynamic variables such as human interactions and environmental changes. Our method improves resource management and service quality, achieving optimal task offloading and resource distribution in IIoT edge computing.

Figures (4)

• Figure 1: Environment of Smart Factory
• Figure 2: Baseline PSO
• Figure 3: Adaptive PSO
• Figure 4: APSOSAC