Joint Task Offloading and Channel Allocation in Spatial-Temporal Dynamic for MEC Networks

TL;DR

This work tackles joint task offloading and channel allocation in spatial-temporal MEC networks with inter-task dependencies modeled as DAGs. It introduces TOICA, a two-stage framework combining a dynamic programming-based channel allocator (DCA) that maps subchannels via a grouped knapsack formulation and a D3QN-based offloading policy (DTO) that learns long-horizon decisions for multi-user, multi-server MEC. Key contributions include a priority-based DAG decoupling rule, NP-hard problem formulation, and the coupling of DP and deep RL to achieve real-time, scalable performance with demonstrated delay-energy cost reductions in dynamic scenarios. The approach enables adaptive resource utilization under mobility, channel fluctuations, and I/O interference, with practical implications for latency-sensitive MEC applications. Future work points to incorporating downlink latency, scaling to dense deployments, and distributed DRL training for large-scale MEC systems.

Abstract

Computation offloading and resource allocation are critical in mobile edge computing (MEC) systems to handle the massive and complex requirements of applications restricted by limited resources. In a multi-user multi-server MEC network, the mobility of terminals causes computing requests to be dynamically distributed in space. At the same time, the non-negligible dependencies among tasks in some specific applications impose temporal correlation constraints on the solution as well, leading the time-adjacent tasks to experience varying resource availability and competition from parallel counterparts. To address such dynamic spatial-temporal characteristics as a challenge in the allocation of communication and computation resources, we formulate a long-term delay-energy trade-off cost minimization problem in the view of jointly optimizing task offloading and resource allocation. We begin by designing a priority evaluation scheme to decouple task dependencies and then develop a grouped Knapsack problem for channel allocation considering the current data load and channel status. Afterward, in order to meet the rapid response needs of MEC systems, we exploit the double duel deep Q network (D3QN) to make offloading decisions and integrate channel allocation results into the reward as part of the dynamic environment feedback in D3QN, constituting the joint optimization of task offloading and channel allocation. Finally, comprehensive simulations demonstrate the performance of the proposed algorithm in the delay-energy trade-off cost and its adaptability for various applications.

Figures (9)

• Figure 1: Spatial and temporal dynamic MEC networks.
• Figure 2: DAG structure of task dependencies (Health monitoring application example).
• Figure 3: Architecture of D3QN-based Task Offloading.
• Figure 4: The structure of the TOICA algorithm.
• Figure 5: Progression of cumulative rewards.