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

2025-05-07

AI Summary

This paper addresses the spatiotemporal dynamics in mobile edge computing (MEC) arising from user mobility and task temporal dependencies, focusing on joint task offloading and wireless resource allocation for multi-user, multi-server scenarios to minimize long-term delay-energy weighted cost. We propose a two-layer modeling framework: an upper layer that decouples offloading decisions based on task priority, and a lower layer formulated as a grouped knapsack problem for channel allocation. To enable real-time adaptive optimization under dynamic conditions, we design a Double Dueling Deep Q-Network (D3QN) algorithm that embeds channel allocation into the reward function. Experimental results demonstrate that our approach improves energy efficiency by 32.7% over baseline methods under high-mobility and strongly interdependent task workloads, while exhibiting robustness and rapid responsiveness.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Mechanism Design

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• Optimize task offloading and channel allocation in MEC networks
• Address spatial-temporal dynamics in multi-user multi-server systems
• Minimize long-term delay-energy trade-off cost via D3QN

Innovation

• Priority evaluation scheme decouples task dependencies
• Grouped Knapsack problem optimizes channel allocation
• D3QN integrates offloading and channel allocation dynamically