Communication-Efficient Edge AI Inference Over Wireless Networks
- URL: http://arxiv.org/abs/2004.13351v1
- Date: Tue, 28 Apr 2020 08:04:06 GMT
- Title: Communication-Efficient Edge AI Inference Over Wireless Networks
- Authors: Kai Yang, Yong Zhou, Zhanpeng Yang, Yuanming Shi
- Abstract summary: We present the principles of efficient deployment of model inference at network edge to provide low-latency and energy-efficient AI services.
This includes the wireless distributed computing framework for low-latency device distributed model inference as well as the wireless cooperative transmission strategy for energy-efficient edge cooperative model inference.
- Score: 33.1306043471745
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Given the fast growth of intelligent devices, it is expected that a large
number of high-stake artificial intelligence (AI) applications, e.g., drones,
autonomous cars, tactile robots, will be deployed at the edge of wireless
networks in the near future. As such, the intelligent communication networks
will be designed to leverage advanced wireless techniques and edge computing
technologies to support AI-enabled applications at various end devices with
limited communication, computation, hardware and energy resources. In this
article, we shall present the principles of efficient deployment of model
inference at network edge to provide low-latency and energy-efficient AI
services. This includes the wireless distributed computing framework for
low-latency device distributed model inference as well as the wireless
cooperative transmission strategy for energy-efficient edge cooperative model
inference. The communication efficiency of edge inference systems is further
improved by building up a smart radio propagation environment via intelligent
reflecting surface.
Related papers
- Distributed Swarm Learning for Edge Internet of Things [28.125744688546842]
The rapid growth of the Internet of Things (IoT) has led to the widespread deployment of smart computation devices at wireless edge for machine learning tasks.
This article explores the risks of swarm security, non-constrained wireless communication and privacy issues.
It combines biological intelligence in a holistic manner to provide efficient solutions for large-scale IoT at the edge wireless networks.
arXiv Detail & Related papers (2024-03-29T14:05:40Z) - A Wireless AI-Generated Content (AIGC) Provisioning Framework Empowered by Semantic Communication [53.78269720999609]
Generative AI applications have been recently catering to a vast user base by creating diverse and high-quality AI-generated content (AIGC)
It is challenging to provide qualified AIGC services in wireless networks with unstable channels, limited bandwidth resources, and unevenly distributed computational resources.
We propose a semantic communication (SemCom)-empowered AIGC (SemAIGC) generation and transmission framework.
arXiv Detail & Related papers (2023-10-26T18:05:22Z) - Large Language Models Empowered Autonomous Edge AI for Connected
Intelligence [51.269276328087855]
Edge artificial intelligence (Edge AI) is a promising solution to achieve connected intelligence.
This article presents a vision of autonomous edge AI systems that automatically organize, adapt, and optimize themselves to meet users' diverse requirements.
arXiv Detail & Related papers (2023-07-06T05:16:55Z) - Task-Oriented Integrated Sensing, Computation and Communication for
Wireless Edge AI [46.61358701676358]
Edge artificial intelligence (AI) has been proposed to provide high-performance computation of a conventional cloud down to the network edge.
Recently, convergence of wireless sensing, computation and communication (SC$2$) for specific edge AI tasks, has aroused paradigm shift.
It is paramount importance to advance fully integrated sensing, computation and communication (I SCC) to achieve ultra-reliable and low-latency edge intelligence acquisition.
arXiv Detail & Related papers (2023-06-11T06:40:51Z) - Pervasive Machine Learning for Smart Radio Environments Enabled by
Reconfigurable Intelligent Surfaces [56.35676570414731]
The emerging technology of Reconfigurable Intelligent Surfaces (RISs) is provisioned as an enabler of smart wireless environments.
RISs offer a highly scalable, low-cost, hardware-efficient, and almost energy-neutral solution for dynamic control of the propagation of electromagnetic signals over the wireless medium.
One of the major challenges with the envisioned dense deployment of RISs in such reconfigurable radio environments is the efficient configuration of multiple metasurfaces.
arXiv Detail & Related papers (2022-05-08T06:21:33Z) - Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and
Applications [39.223546118441476]
6G will revolutionize the evolution of wireless from "connected things" to "connected intelligence"
Deep learning and big data analytics based AI systems require tremendous computation and communication resources.
edge AI stands out as a disruptive technology for 6G to seamlessly integrate sensing, communication, computation, and intelligence.
arXiv Detail & Related papers (2021-11-24T11:47:16Z) - Distributed Learning in Wireless Networks: Recent Progress and Future
Challenges [170.35951727508225]
Next-generation wireless networks will enable many machine learning (ML) tools and applications to analyze various types of data collected by edge devices.
Distributed learning and inference techniques have been proposed as a means to enable edge devices to collaboratively train ML models without raw data exchanges.
This paper provides a comprehensive study of how distributed learning can be efficiently and effectively deployed over wireless edge networks.
arXiv Detail & Related papers (2021-04-05T20:57:56Z) - Deep Reinforcement Learning-Aided RAN Slicing Enforcement for B5G
Latency Sensitive Services [10.718353079920007]
This paper presents a novel architecture that leverages Deep Reinforcement Learning at the edge of the network in order to address Radio Access Network Slicing and Radio Resource Management.
The effectiveness of our proposal against baseline methodologies is investigated through computer simulation, by considering an autonomous-driving use-case.
arXiv Detail & Related papers (2021-03-18T14:18:34Z) - Intelligent Reflecting Surface Aided Wireless Communications: A Tutorial [64.77665786141166]
Intelligent reflecting surface (IRS) is an enabling technology to engineer the radio signal prorogation in wireless networks.
IRS is capable of dynamically altering wireless channels to enhance the communication performance.
Despite its great potential, IRS faces new challenges to be efficiently integrated into wireless networks.
arXiv Detail & Related papers (2020-07-06T13:59:09Z) - Federated Machine Learning for Intelligent IoT via Reconfigurable
Intelligent Surface [35.64178319119883]
We develop an over-the-air based communication-efficient federated machine learning framework for intelligent IoT networks.
We exploit the waveform superposition property of a multi-access channel to reduce the model aggregation error.
arXiv Detail & Related papers (2020-04-13T09:48:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.