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.

Collaborative edge computing (CEC) has emerged as a promising paradigm, enabling edge nodes to collaborate and execute tasks from end devices. Task offloading is a fundamental problem in CEC that decides when and where tasks are executed upon the arrival of tasks. However, the mobility of users often results in unstable connections, leading to network failures and resource underutilization. Existing works have not adequately addressed joint mobility-aware dependent task offloading and network flow scheduling, resulting in network congestion and suboptimal performance. To address this, we formulate an online joint mobility-aware dependent task offloading and bandwidth allocation problem, to improve the quality of service by reducing task completion time and energy consumption. We introduce a Mobility-aware Digital Twin-assisted Deep Reinforcement Learning (MDT-DRL) algorithm. Our digital twin model equips the reinforcement learning process by providing future states of mobile users, enabling efficient offloading plans for adapting to the mobile CEC system. Experimental results on real-world and synthetic datasets show that MDT-DRL surpasses state-of-the-art baselines on average task completion time and energy consumption.

Collaborative edge computing (CEC) is an emerging computing paradigm in which edge nodes collaborate to perform tasks from end devices. Task offloading decides when and at which edge node tasks are executed. Most existing studies assume task profiles and network conditions are known in advance, which can hardly adapt to dynamic real-world computation environments. Some learning-based methods use online task offloading without considering task dependency and network flow scheduling, leading to underutilized resources and flow congestion. We study Online Dependent Task Offloading (ODTO) in CEC, jointly optimizing network flow scheduling to optimize quality of service by reducing task completion time and energy consumption. The challenge of ODTO lies in how to offload dependent tasks and schedule network flows in dynamic networks. We model ODTO as the Markov Decision Process (MDP) and propose an Asynchronous Deep Progressive Reinforcement Learning (ADPRL) approach that optimizes offloading and bandwidth decisions. We design a novel dependency-aware reward mechanism to address task dependency and dynamic networks. Extensive experiments on the Alibaba cluster trace dataset and synthetic dataset indicate that our algorithm outperforms heuristic and learning-based methods in average task completion time and energy consumption.