[论文解读] Edge Intelligence: Architectures, Challenges, and Applications

Dianlei Xu, Tong Li+6 more|arXiv (Cornell University)|Mar 26, 2020

Privacy-Preserving Technologies in Data参考文献 336被引用 123

一句话总结

一个全面的综述，识别四个核心的边缘智能组成部分——edge caching、edge training、edge inference 和 edge offloading，并提供多维度的架构、技术和未解决挑战的分类法。

ABSTRACT

Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis in locations close to where data is captured based on artificial intelligence. The aim of edge intelligence is to enhance the quality and speed of data processing and protect the privacy and security of the data. Although recently emerged, spanning the period from 2011 to now, this field of research has shown explosive growth over the past five years. In this paper, we present a thorough and comprehensive survey on the literature surrounding edge intelligence. We first identify four fundamental components of edge intelligence, namely edge caching, edge training, edge inference, and edge offloading, based on theoretical and practical results pertaining to proposed and deployed systems. We then aim for a systematic classification of the state of the solutions by examining research results and observations for each of the four components and present a taxonomy that includes practical problems, adopted techniques, and application goals. For each category, we elaborate, compare and analyse the literature from the perspectives of adopted techniques, objectives, performance, advantages and drawbacks, etc. This survey article provides a comprehensive introduction to edge intelligence and its application areas. In addition, we summarise the development of the emerging research field and the current state-of-the-art and discuss the important open issues and possible theoretical and technical solutions.

研究动机与目标

• 推动 edge-enabled AI 以降低延迟、节省带宽并保护隐私。
• 系统性地对四个 edge intelligence 组成部分：caching、training、inference 和 offloading，进行现状分门别类。
• 将 edge 方法与传统的 cloud-centric intelligence 进行比较并讨论权衡。
• 总结开放问题并在数据、模型、隐私和激励方面勾勒未来的研究方向。

提出的方法

• 提出一个四组件框架：edge caching、edge training、edge inference 和 edge offloading。
• 为每个组成部分提供多维分类法，包括实际问题、技术、目标、性能和缺点。
• 从应用场景、方法论和结果的角度分析文献。
• 讨论开放问题与未来研究方向，包括数据稀缺性、数据一致性、模型/算法的适应性、隐私与安全以及激励机制。

实验结果

研究问题

• RQ1 边缘智能的基本组成部分与架构是什么，它们如何相互作用？
• RQ2 哪些实际问题、技术和目标描述了 edge caching、edge training、edge inference 与 edge offloading？
• RQ3 在延迟、隐私和带宽方面，edge intelligence 与传统 cloud-centric intelligence 有何不同？
• RQ4 数据、模型/算法、隐私、安全与激励等方面有哪些关键的开放问题和未来方向？

主要发现

• 识别出边缘智能的四个关键组成部分：edge caching、edge training、edge inference 和 edge offloading。
• 为每个组成部分提供系统性的、多维度的分类与分类法。
• 记录开放问题并提出五条未来研究方向：数据稀缺性、数据一致性、模型/算法的适应性、隐私与安全、以及激励机制。
• 回顾增长趋势与动机，指出自2014年以来 edge training、inference 和 offloading 的迅速上升。
• 强调边缘计算通过 edge-cloud 合作实现超低延迟、降低终端设备能耗、并实现可扩展部署。