IMPACT：面向云边系统中SLO保障的微服务迁移的意图驱动多智能体策略
IMPACT: Intent-driven Multi-agent Policy with Attention for SLO-guaranteed Microservice Migration in Cloud-edge Systems
- Columbia University（哥伦比亚大学）
- Carnegie Mellon University（卡内基梅隆大学）
- Brandeis University（布兰迪斯大学）
- Georgetown University（乔治城大学）
- Georgia Institute of Technology（佐治亚理工学院）
- Stevens Institute of Technology（史蒂文斯理工学院）
- University of California San Diego（加州大学圣迭戈分校）
- University of California, Davis（加州大学戴维斯分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对云边系统中微服务迁移与带宽控制不协调导致SLO违规的问题，提出意图驱动多智能体框架IMPACT，通过双重注意力机制实现协同决策，显著降低延迟和尾延迟偏差。
AI中文摘要：
在动态移动边缘计算（MEC）系统中，确保严格的尾延迟服务级别目标（SLO）仍然具有挑战性，因为用户移动性、无线衰落、突发工作负载和部分可观测性共同破坏了可靠的云边编排。现有的微服务迁移方法主要优化平均延迟，并且通常将迁移与带宽控制解耦，导致决策不协调、队列振荡以及频繁的高百分位延迟违规。为解决此问题，我们提出了IMPACT，一种用于云边系统中协同微服务迁移和带宽控制的意图驱动Agentic AI框架。在集中训练与分散执行（CTDE）下，每个边缘云被建模为一个自主智能体，将局部SLO风险、迁移紧迫性和计算压力编码为紧凑的语义意图表示。IMPACT进一步引入了双重注意力机制，首先选择性地聚合相关同伴意图以实现高效的智能体间通信，然后过滤局部观测以强调目标相关的状态信息。该设计在部分可观测性下实现了稳健的协调，并联合优化了服务迁移和离散上行链路带宽分配。在5边缘和20边缘场景中的大量实验表明，与最先进的因子化多智能体强化学习（MARL）和启发式基线相比，IMPACT将平均延迟降低了30-50%，尾延迟偏差降低了40-70%，同时在严格阈值下实现了接近零的SLO违规率，能耗接近最佳启发式基线。这些结果表明，意图驱动的智能体协调为复杂云边智能系统中的SLO感知编排提供了一种有效且可扩展的解决方案。
英文摘要：
Ensuring strict tail-latency service-level objectives (SLOs) in dynamic mobile edge computing (MEC) systems remains challenging because user mobility, wireless fading, bursty workloads, and partial observability jointly undermine reliable cloud-edge orchestration. Existing microservice migration methods predominantly optimize average delay and often decouple migration from bandwidth control, leading to uncoordinated decisions, queue oscillation, and frequent high-percentile latency violations. To address this issue, we propose IMPACT, an intent-driven Agentic AI framework for cooperative microservice migration and bandwidth control in cloud-edge systems. Under centralized training with decentralized execution (CTDE), each edge cloud is modeled as an autonomous agent that encodes local SLO risk, migration urgency, and computational pressure into compact, semantic intent representations. IMPACT further introduces a double-attention mechanism that first selectively aggregates relevant peer intents for efficient inter-agent communication and then filters local observations to emphasize goal-relevant state information. This design enables robust coordination under partial observability and jointly optimizes service migration and discrete uplink bandwidth allocation. Extensive experiments in 5-edge and 20-edge scenarios show that IMPACT reduces mean latency by 30-50% and tail-latency deviation by 40-70% compared with state-of-the-art factorized multi-agent reinforcement learning (MARL) and heuristic baselines, while achieving near-zero SLO violation rates under tight thresholds and energy consumption close to the best heuristic baseline. These results demonstrate that intent-driven agentic coordination provides an effective and scalable solution for SLO-aware orchestration in complex cloud-edge intelligent systems.
