Decentralized Task Offloading in Collaborative Edge Computing: A Digital Twin Assisted Multi-Agent Reinforcement Learning Approach

Decentralized Edge Computing (DEC) has emerged as a computing paradigm leveraging computational resources of edge nodes for complex, data-intensive applications. Decentralized task offloading decides when and at which edge node each task is executed without a central coordinator. However, ensuring reliability for decentralized task offloading is crucial, especially in critical applications like video analytics. Existing centralized approaches often face single points of failure and high communication overhead. Current decentralized methods often ignore task dependencies and bandwidth allocation, leading to suboptimal resource utilization and low reliability. We address the Reliability-aware Dependent Task Offloading (RDTO) problem in DEC, jointly optimizing bandwidth allocation, to maximize task success rate. The challenge of RDTO lies in optimizing dynamic task offloading and bandwidth allocation with task dependencies. We propose a Digital Twin assisted Multi-agent Reinforcement Learning (DT-MARL) algorithm. Our approach integrates a novel digital twin model that provides real-time estimation of task completion time and edge node failure rates. By integrating digital twin with multi-agent reinforcement learning, we enable each edge node to make informed decisions for offloading strategies, effectively improving the task success rate. Extensive experiments using real-world and synthetic datasets demonstrate that DT-MARL outperforms state-of-the-art baselines on task success rate up to 32.00% and 32.43%, respectively.