AI-Enhanced Offloading in Edge Computing: When Machine Learning Meets Industrial IoT

By Wen Sun, Jiajia Liu, Yanlin Yue. 2019

162 citations recorded by the source corpus.

The Industrial Internet of Things (IIoT) enables intelligent industrial operations by incorporating artificial intelligence (AI) and big data technologies. An AI-enabled framework typically requires prompt and private cloud-based service to process and aggregate manufacturing data. Thus, integrating intelligence into edge computing is without doubt a promising development trend. Nevertheless, edge intelligence brings heterogeneity to the edge servers, in terms of not only computing capability, but also service accuracy. Most works on offloading in edge computing focus on finding the power-delay trade-off, ignoring service accuracy provided by edge servers as well as the accuracy required by IIoT devices. In this vein, in this article we introduce an intelligent computing architecture with cooperative edge and cloud computing for IIoT. Based on the computing architecture, an AI enhanced offloading framework is proposed for service accuracy maximization, which considers service accuracy as a new metric besides delay, and intelligently disseminates the traffic to edge servers or through an appropriate path to remote cloud. A case study is performed on transfer learning to show the performance gain of the proposed framework.

Subfields: Computer Networks and Communications, Information Systems, ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. H. Vincent Poor
2. Howard H. Yang
3. Tony Q. S. Quek
4. Jun Li
5. Ming Ding
6. Wen Sun
7. Shi Jin
8. Yan Zhang

In Information Systems

1. Jun Li
2. Ming Ding
3. H. Vincent Poor
4. Yan Zhang

In ML Systems & Hardware

1. H. Vincent Poor
2. Tony Q. S. Quek
3. Howard H. Yang
4. Mingzhe Chen
5. Walid Saad

Citations in the corpus

• Federated Learning With Differential Privacy: Algorithms and Performance Analysis (2019, methodology): “When integrating AI into a variety of IoT applications, distributed machine learning (ML) is preferred for many data processing tasks by defining parametrized functions from inputs to outputs as compositions of basic building blocks [4], [5].”
• Reducing Offloading Latency for Digital Twin Edge Networks in 6G (2020, background): “Most existing works in MEC focus on offloading decision using game theory or machine learning methods to reduce the computational latency and energy consumption [14], [15].”
• AI for Next Generation Computing: Emerging Trends and Future Directions (2022, unknown): “• Only by fully integrating edge computing into existing cloud architecture can its full potential be realised using AI, making edge computing the crucial missing connection between data sources (the devices) and cloud computing (core network) [107] because edge nodes have a limited storage and comp”