AI 中文总结
该研究针对自动驾驶车辆边缘MEC的混合关键度任务调度，构建强启发式算法，发现LLM控制平面仅在安全关键任务激增时优于静态启发式算法。
AI 中文摘要
自动驾驶车辆将延迟敏感的感知任务卸载到附近的移动边缘计算（MEC）服务器，在该服务器上，错过安全关键任务会导致不安全后果，而非性能下降。大语言模型（LLM）越来越被提议作为自适应、可解释的调度器，但关于它们何时有用的证据却很少。我们研究异构MEC服务器上的感知期限感知混合关键度调度，其中时间关键（TC）任务必须以对尽力而为流量的可控成本得到保护，并探究多智能体LLM控制层是否优于强启发式算法。我们分两步回答：首先，我们构建启发式算法：窗口式合同网拍卖，该拍卖按最早截止时间对每个准入窗口的时间关键任务优先排序，并按最早完成时间放置任务。在三个拓扑的60个实例和15个基准下，在相同在线约束下，它达到0.902的TC完成率，高于所有基准（Holm校正p<0.001；最佳基准为0.838），达到CP-SAT上限的0.87。其次，我们添加LLM控制平面。受控分解将调度器的优势追溯到两个普通因素：批处理范围和时间关键优先排序；当负载平稳时，拍卖、每窗口LLM策略和在线适应性没有增益，此时启发式算法已接近最优。在运行中期安全关键任务激增时，情况发生变化，LLM控制平面显著优于静态启发式算法和老虎机算法。因此，LLM编排仅在非平稳性打开固定策略无法利用的空间时才值得其成本。我们报告控制平面延迟和理由，并发布所有代码和带种子的实例。
英文摘要
Autonomous vehicles offload latency-sensitive perception tasks to nearby mobile edge computing (MEC) servers, where a missed safety-critical task is unsafe rather than merely degraded. Large language models (LLMs) are increasingly proposed as adaptive, explainable schedulers, yet evidence of when they help is scarce. We study deadline-aware, mixed-criticality scheduling on heterogeneous MEC servers, where time-critical (TC) tasks must be protected at a controlled cost to best-effort traffic, and ask whether a multi-agent LLM control layer improves on a strong heuristic. We answer in two steps. First we build the heuristic: a windowed contract-net auction that orders each admission window time-critical-first by earliest deadline and places tasks by earliest-finish-time. Across 60 instances on three topologies and 15 baselines under an identical online constraint, it attains a TC completion rate of 0.902, above every baseline (Holm-corrected p < 0.001; best baseline 0.838) and at 0.87 of a CP-SAT upper bound. Second, we add the LLM control plane. A controlled decomposition traces the scheduler's advantage to two ordinary factors, the batching horizon and time-critical-first ordering; the auction, the per-window LLM policy, and online adaptation add nothing while the load is stationary, where the heuristic is already near-optimal. Under a mid-run surge of safety-critical tasks the picture changes, and the LLM control plane gains significantly over both the static heuristic and the bandit. LLM orchestration therefore earns its cost only when non-stationarity opens headroom a fixed policy cannot use. We report control-plane latency and rationale, and release all code and seeded instances.
Comments8 pages, 5 figures, and 4 tables
