AI 中文总结
该研究针对物联网-边缘-云连续体中任务卸载的拥塞与资源利用问题，提出联合确定任务执行位置与时序的控制策略，显著提升了任务满意度并降低了资源消耗与执行时间。
AI 中文摘要
自主移动、工业自动化等对延迟敏感的物联网应用，需要确定性保障以确保任务在严格截止期限内完成。支持6G的物联网-边缘-云连续体可通过利用设备、边缘及云基础设施的通信、计算与智能资源满足此类需求。但现有任务卸载策略主要聚焦于选择任务执行位置，通常假设任务到达后立即处理，这会在多个任务时间重合时引发瞬时拥塞，导致动态 workload 下资源利用效率低下。本文针对这些局限，提出一种确定性任务卸载的执行时序控制策略，联合确定任务的执行位置与开始时间，同时保证截止期限合规。核心思路是利用任务的延迟预算控制执行时序，实现 workload 随时间更均衡的分布，降低连续体中的峰值拥塞。评估结果显示，与现有基准相比，所提方法的满意度最高提升70%，通信资源使用量减少40%，峰值计算资源利用率降低15%，平均执行时间最多缩短77%。
英文摘要
Latency-critical IoT applications, such as autonomous mobility and industrial automation, require deterministic guarantees to ensure that tasks are completed within strict deadlines. The 6G-enabled IoT-edge-cloud continuum can support such requirements by leveraging communication, computation and intelligence resources across devices, edge, and cloud infrastructures. However, existing task offloading strategies mainly focus on selecting where tasks are executed and typically assume immediate processing upon task arrival. This leads to transient congestion when multiple tasks coincide in time and results in inefficient resource utilization under dynamic workloads. This paper addresses these limitations by introducing an execution timing control strategy for deterministic task offloading that jointly determines where tasks are executed and when their execution starts, while guaranteeing deadline compliance. The key idea is to exploit the latency budget of tasks to control their execution timing, enabling a more balanced distribution of workload over time and reducing peak congestion across the continuum. Evaluation results show that, compared to existing benchmarks, the proposed approach achieves up to 70% higher satisfaction ratio, reduces the communication resources usage by 40%, lowers peak computing resource utilization by 15%, and decreases average execution time by up to 77%.
