Skip to main content
QUICK REVIEW

[论文解读] A Survey on Offloading in Federated Cloud-Edge-Fog Systems with Traditional Optimization and Machine Learning

Binayak Kar, Widhi Yahya|arXiv (Cornell University)|Feb 22, 2022
IoT and Edge/Fog Computing被引用 14
一句话总结

本文全面综述了联邦云边雾计算系统中的任务卸载技术,对比了传统优化方法与机器学习(尤其是强化学习)方法。提出了一种新颖的联邦分类与研究路线图,表明基于机器学习的卸载能够在传统优化因计算开销过大而失效的动态、高维环境中实现低延迟、自适应的决策。

ABSTRACT

The huge amount of data generated by the Internet of things (IoT) devices needs the computational power and storage capacity provided by cloud, edge, and fog computing paradigms. Each of these computing paradigms has its own pros and cons. Cloud computing provides enhanced data storage and computing power but causes high communication latency. Edge and fog computing provide similar services with lower latency but with limited capacity, capability, and coverage. A single computing paradigm cannot fulfil all the requirements of IoT devices and a federation between them is needed to extend their capacity, capability, and services. This federation is beneficial to both subscribers and providers and also reveals research issues in traffic offloading between clouds, edges, and fogs. Optimization has traditionally been used to solve the problem of traffic offloading. However, in such a complex federated system, traditional optimization cannot keep up with the strict latency requirements of decision making, ranging from milliseconds to sub-seconds. Machine learning approaches, especially reinforcement learning, are consequently becoming popular because they can quickly solve offloading problems in dynamic environments with large amounts of unknown information. This study provides a novel federal classification between cloud, edge, and fog and presents a comprehensive research roadmap on offloading for different federated scenarios. We survey the relevant literature on the various optimization approaches used to solve this offloading problem, and compare their salient features. We then provide a comprehensive survey on offloading in federated systems with machine learning approaches and the lessons learned as a result of these surveys. Finally, we outline several directions for future research and challenges that have to be faced in order to achieve such a federation.

研究动机与目标

  • 解决单层次计算(云、边缘、雾)在处理多样化、动态的物联网工作负载时,面对严格延迟和资源约束的局限性。
  • 基于联邦类型(垂直、水平、混合)和卸载方向,对联邦云边雾系统中的卸载技术进行分析与分类。
  • 对比在复杂、动态环境中,传统优化与基于机器学习的卸载决策方法。
  • 识别联邦系统中的关键挑战,如延迟、可靠性、能效以及性能退化问题。
  • 勾勒未来研究方向,以实现在联邦边缘-云-雾生态系统中可扩展、自适应且可靠的卸载。

提出的方法

  • 提出一种新颖的三层次联邦系统分类:云(顶层)、边缘(中层)和雾(底层),明确其在数据处理与服务交付中的不同角色。
  • 根据联邦结构和计算迁移方向,将卸载分类为垂直(跨层级)、水平(同层级内)和混合(组合)三种类型。
  • 回顾传统优化技术(如整数规划、启发式算法)在卸载中的应用,指出其在实时场景中存在高计算成本和延迟问题。
  • 分析基于机器学习的方法,特别是强化学习(RL),其通过环境反馈学习最优卸载策略,无需标注数据或穷举搜索。
  • 评估强化学习模型在快速推理和实时决策中的表现,实现亚秒级响应时间,这对延迟敏感的物联网应用至关重要。
  • 通过系统性文献综述,对比优化与基于机器学习的卸载方法的关键特性、优势与局限性。

实验结果

研究问题

  • RQ1联邦云边雾系统如何克服单一计算范式在延迟、容量和覆盖范围方面的局限性?
  • RQ2在动态、大规模物联网环境中,传统优化与基于机器学习的卸载在关键差异与权衡方面有何不同?
  • RQ3为何强化学习特别适用于具有未知或变化参数且具有严格延迟约束的系统中的卸载决策?
  • RQ4在联邦卸载架构中,确保可靠性、低能耗和性能隔离面临哪些开放挑战?
  • RQ5为实现异构、联邦化的云边雾系统中可扩展、自适应且安全的任务卸载,未来研究需关注哪些方向?

主要发现

  • 传统优化方法在卸载中计算开销大,在动态物联网环境中常违反实时控制平面的延迟要求。
  • 机器学习,特别是强化学习,可通过从环境反馈中学习,实现快速、自适应的卸载决策,且无需标注数据或穷举搜索。
  • 强化学习模型即使在输入参数不完整或未知的情况下,也能实现实时近似最优的卸载决策,使其成为动态、大规模系统的理想选择。
  • 同层级内(如边缘到边缘)的水平卸载在现有研究中仍被严重忽视,但对联邦系统中的负载均衡和资源利用率至关重要。
  • 联邦系统可带来降低延迟、通过地理多样性提升可靠性以及增强服务可用性的优势,但需谨慎管理以避免因过度订阅或误报导致的性能退化。
  • 将机器学习与联邦卸载相结合,可实现跨云、边缘和雾层级的可扩展、低延迟且节能的任务分发,尤其适用于对延迟和计算敏感的应用。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。