Sustainable Dependent Sub-Tasks Orchestration at Extreme Edge Computing: A Partitioning-based Deep Reinforcement Learning Approach

Extreme Edge Computing (EEC) promotes sustainable computing by reducing reliance on centralized data centres and decreasing their environmental impact. By using extreme edge devices to handle computing requests, the EEC reduces the energy demands for data transmission and execution, thereby reducing carbon footprints. However, EEC introduces challenges due to the mobile, heterogeneous, and resource-limited nature of these devices. Additionally, tasks are often complex and interdependent, complicating offloading and workload orchestration. The dynamicity of EEC systems, where both task generation and resources can be mobile, alongside task inter-dependencies, escalates the complexity of task offloading and workload management. To tackle these complexities, task partitioning emerges as a viable strategy. Moreover, in dynamic edge computing scenarios, resource demand remains unpredictable, emphasizing the critical need to optimize resource utilization efficiently. In this article, we investigate the problem of tasks with inter-dependencies offloading in an EEC environment where mobile and resource-constrained edge devices are employed as computing resources. In this regard, a partitioning-based Deep Reinforcement Learning (DRL) for Dependent sub-Task Orchestration (DeTOrch) model is proposed. DeTOrch uses a state-of-the-art partitioning method for decomposing tasks and proposes a novel mobility task-orchestration mechanism to minimize the task completion time and maximize the use of edge devices’ resource. The simulation results show that the proposed model can significantly improve the task success rate and decrease task completion time. In addition, in various scenarios with different levels of mobility, the proposed model outperforms the baselines while utilizing the resource of edge devices.