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

2025-01-25

AI Summary

To address the challenge of low-latency task offloading in dynamic Industrial Internet of Things (IIoT) edge computing environments—characterized by human–machine interaction and sudden workload fluctuations—this paper proposes a reinforcement learning (RL)-driven collaborative framework integrating Adaptive Particle Swarm Optimization (APSO) and Soft Actor-Critic (SAC). The dynamic offloading decision problem is formulated as a joint optimization task, where SAC enables online policy learning under uncertainty, APSO ensures efficient global search, and a dynamic load-aware mechanism enhances environmental adaptability. Compared to conventional static or heuristic approaches, the proposed framework achieves significantly faster convergence (+37%), reduced end-to-end latency, improved resource utilization, and enhanced service reliability. To the best of our knowledge, this work represents the first deep integration of RL and adaptive swarm intelligence for IIoT edge task offloading, establishing a new paradigm for adaptive, real-time decision-making in dynamic industrial edge systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Learning & Optimization for ROB
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

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.

Problem

• Edge Computing
• Task Allocation
• Dynamic Optimization

Innovation

• Adaptive Particle Swarm Optimization (APSO)
• Soft Actor-Critic (SAC)
• Industrial Internet of Things (IIoT) Edge Computing