Edge Intelligence: Architectures, Challenges, and Applications
University of Helsinki（赫尔辛基大学）；Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Hong Kong University of Science and Technology（香港科技大学）；Huazhong University of Science and Technology（华中科技大学）；University of Cambridge（剑桥大学）
Dianlei Xu, Tong Li, Yong Li, Xiang Su, Sasu Tarkoma, Tao Jiang, Jon Crowcroft, Pan Hui
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.
Toshiba Europe Ltd.（东芝欧洲有限公司）；Bristol Research and Innovation Laboratory（布里斯托尔研究与创新实验室）
Time-critical control applications typically pose stringent connectivity requirements for communication networks. The imperfections associated with the wireless medium such as packet losses, synchronization errors, and varying delays have a detrimental effect on performance of real-time control, often with safety implications. This paper introduces multi-service edge-intelligence as a new paradigm for realizing time-critical control over wireless. It presents the concept of multi-service edge-intelligence which revolves around tight integration of wireless access, edge-computing and machine le…
Sun Yat-sen University（中山大学）；Arizona State University（亚利桑那州立大学）
With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet-of-Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions Bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet th…
Huazhong University of Science and Technology（华中科技大学）；Xidian University（西安电子科技大学）；Virginia Tech（弗吉尼亚理工大学）；Princeton University（普林斯顿大学）
Edge intelligence, also called edge-native artificial intelligence (AI), is an emerging technological framework focusing on seamless integration of AI, communication networks, and mobile edge computing. It has been considered to be one of the key missing components in the existing 5G network and is widely recognized to be one of the most sought-after functions for tomorrow's wireless 6G cellular systems. In this article, we identify the key requirements and challenges of edge-native AI in 6G. A self-learning architecture based on self-supervised Generative Adversarial Nets (GANs) is introduced…
Along with the rapid developments in communication technologies and the surge in the use of mobile devices, a brand-new computation paradigm, Edge Computing, is surging in popularity. Meanwhile, Artificial Intelligence (AI) applications are thriving with the breakthroughs in deep learning and the many improvements in hardware architectures. Billions of data bytes, generated at the network edge, put massive demands on data processing and structural optimization. Thus, there exists a strong demand to integrate Edge Computing and AI, which gives birth to Edge Intelligence. In this paper, we divid…
University of Waterloo（滑铁卢大学）；Marquette University（马凯特大学）；Peng Cheng Laboratory（鹏城实验室）
In this tutorial paper, we look into the evolution and prospect of network architecture and propose a novel conceptual architecture for the 6th generation (6G) networks. The proposed architecture has two key elements, i.e., holistic network virtualization and pervasive artificial intelligence (AI). The holistic network virtualization consists of network slicing and digital twin, from the aspects of service provision and service demand, respectively, to incorporate service-centric and user-centric networking. The pervasive network intelligence integrates AI into future networks from the perspec…
Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence
Sun Yat-sen University（中山大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Tsinghua University（清华大学）；Midea Group（美的集团）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Peng Cheng Laboratory（鹏城实验室）；Terminus Group（特斯联集团）；The University of Waterloo（滑铁卢大学）
Edge computing has become a popular paradigm where services and applications are deployed at the network edge closer to the data sources. It provides applications with outstanding benefits, including reduced response latency and enhanced privacy protection. For emerging advanced applications, such as autonomous vehicles, industrial IoT, and metaverse, further research is needed. This is because such applications demand ultra-low latency, hyper-connectivity, and dynamic and reliable service provision, while existing approaches are inadequate to address the new challenges. Hence, we envision tha…
University of Oulu（奥卢大学）；Capobianco（卡波比安科公司）；Huawei（华为）；TU Delft（代尔夫特理工大学）；University of Vigo（维戈大学）；VTT Technical Research Centre of Finland（芬兰技术研究中心）；Poznan University of Technology（波兹南理工大学）；University of Helsinki（赫尔辛基大学）；Pengcheng Laboratory（鹏城实验室）
In this white paper we provide a vision for 6G Edge Intelligence. Moving towards 5G and beyond the future 6G networks, intelligent solutions utilizing data-driven machine learning and artificial intelligence become crucial for several real-world applications including but not limited to, more efficient manufacturing, novel personal smart device environments and experiences, urban computing and autonomous traffic settings. We present edge computing along with other 6G enablers as a key component to establish the future 2030 intelligent Internet technologies as shown in this series of 6G White P…
Huazhong University of Science and Technology（华中科技大学）；Dalian University of Technology（大连理工大学）；Wuhan University（武汉大学）
With the development of intelligent applications (e.g., self-driving, real-time emotion recognition, etc), there are higher requirements for the cloud intelligence. However, cloud intelligence depends on the multi-modal data collected by user equipments (UEs). Due to the limited capacity of network bandwidth, offloading all data generated from the UEs to the remote cloud is impractical. Thus, in this article, we consider the challenging issue of achieving a certain level of cloud intelligence while reducing network traffic. In order to solve this problem, we design a traffic control algorithm …
Resource-Aware LLM Reasoning for Mobile Edge General Intelligence
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen（清华大学深圳国际研究生院，清华大学，深圳）；College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学 computing 和数据科学学院，新加坡）；Department of Electronic Engineering, Tsinghua University, Beijing（清华大学电子工程系，北京）；State Key Laboratory of Space Network and Communications, Tsinghua University, Beijing（空间网络与通信国家重点实验室，清华大学，北京）；Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing（北京信息科学与技术国家研究中心，清华大学，北京）；Department of Electrical and Computer Engineering, Auburn University, Auburn, USA（阿伯丁大学电气与计算机工程系，阿伯丁，美国）
Beijing Jiaotong University（北京交通大学）；Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Edge intelligence is an emerging paradigm for real-time training and inference at the wireless edge, thus enabling mission-critical applications. Accordingly, base stations (BSs) and edge servers (ESs) need to be densely deployed, leading to huge deployment and operation costs, in particular the energy costs. In this article, we propose a new framework called Mobility-Enhanced Edge inTelligence (MEET), which exploits the sensing, communication, computing, and self-powering capabilities of intelligent connected vehicles for the smart and green 6G networks. Specifically, the operators can incorp…
School of Data and Computer Science（数据与计算机科学学院）；Sun Yat-sen University（中山大学）
As the backbone technology of machine learning, deep neural networks (DNNs) have have quickly ascended to the spotlight. Running DNNs on resource-constrained mobile devices is, however, by no means trivial, since it incurs high performance and energy overhead. While offloading DNNs to the cloud for execution suffers unpredictable performance, due to the uncontrolled long wide-area network latency. To address these challenges, in this paper, we propose Edgent, a collaborative and on-demand DNN co-inference framework with device-edge synergy. Edgent pursues two design knobs: (1) DNN partitioning…
Dubbed "the successor to the mobile Internet", the concept of the Metaverse has recently exploded in popularity. While there exists lite versions of the Metaverse today, we are still far from realizing the vision of a seamless, shardless, and interoperable Metaverse given the stringent sensing, communication, and computation requirements. Moreover, the birth of the Metaverse comes amid growing privacy concerns among users. In this article, we begin by providing a preliminary definition of the Metaverse. We discuss the architecture of the Metaverse and mainly focus on motivating the convergence…
This paper studies an edge intelligence-based IoT network in which a set of edge servers learn a shared model using federated learning (FL) based on the datasets uploaded from a multi-technology-supported IoT network. The data uploading performance of IoT network and the computational capacity of edge servers are entangled with each other in influencing the FL model training process. We propose a novel framework, called federated edge intelligence (FEI), that allows edge servers to evaluate the required number of data samples according to the energy cost of the IoT network as well as their loc…
Artificial intelligence (AI) technology makes mobile devices become intelligent objects which can learn and act automatically. Although AI will bring great opportunities for mobile applications, little work has focused on the architecture and the interaction with the cloud. In this article, we present three existing architectures of mobile intelligence in detail and introduce its broad application prospects. Furthermore, we conduct a series of experiments to evaluate the performance of the prevalent commercial applications and intelligent frameworks. Our results show that there is a big gap be…
Tianjin University（天津大学）；Shenzhen University（深圳大学）；University of British Columbia（不列颠哥伦比亚大学）；Nanyang Technological University（南洋理工大学）；Huawei Technologies（华为技术有限公司）；Sun Yat-sen University（中山大学）
Ubiquitous sensors and smart devices from factories and communities are generating massive amounts of data, and ever-increasing computing power is driving the core of computation and services from the cloud to the edge of the network. As an important enabler broadly changing people's lives, from face recognition to ambitious smart factories and cities, developments of artificial intelligence (especially deep learning, DL) based applications and services are thriving. However, due to efficiency and latency issues, the current cloud computing service architecture hinders the vision of "providing…
In a level-5 autonomous driving system, the autonomous driving vehicles (AVs) are expected to sense the surroundings via analyzing a large amount of data captured by a variety of onboard sensors in near-real-time. As a result, enormous computing costs will be introduced to the AVs for processing the tasks with the deployed machine learning (ML) model, while the inference accuracy may not be guaranteed. In this context, the advent of edge intelligence (EI) and sixth-generation (6G) wireless networking are expected to pave the way to more reliable and safer autonomous driving by providing multi-…
The development of emerging applications, such as autonomous transportation systems, are expected to result in an explosive growth in mobile data traffic. As the available spectrum resource becomes more and more scarce, there is a growing need for a paradigm shift from Shannon's Classical Information Theory (CIT) to semantic communication (SemCom). Specifically, the former adopts a "transmit-before-understanding" approach while the latter leverages artificial intelligence (AI) techniques to "understand-before-transmit", thereby alleviating bandwidth pressure by reducing the amount of data to b…
Edge intelligence leverages computing resources on network edge to provide artificial intelligence (AI) services close to network users. As it enables fast inference and distributed learning, edge intelligence is envisioned to be an important component of 6G networks. In this article, we investigate AI service provisioning for supporting edge intelligence. First, we present the features and requirements of AI services. Then, we introduce AI service data management, and customize network slicing for AI services. Specifically, we propose a novel resource pooling method to jointly manage service …
The number of internet-connected devices has been exponentially growing with the massive volume of heterogeneous data generated from various devices, resulting in a highly intertwined cyber-physical system. Currently, the Edge Intelligence System (EIS) concept that leverages the merits of edge computing and Artificial Intelligence (AI) is utilized to provide smart cloud services with powerful computational processing and reduce decision-making delays. Thus, EIS offers a possible solution to realizing future Intelligent Transportation Systems (ITS), especially in a vehicular network framework. …
The mobile communication system has transformed to be the fundamental infrastructure to support digital demands from all industry sectors, and 6G is envisioned to go far beyond the communication-only purpose. There is coming to a consensus that 6G will treat Artificial Intelligence (AI) as the cornerstone and has a potential capability to provide "intelligence inclusion", which implies to enable the access of AI services at anytime and anywhere by anyone. Apparently, the intelligent inclusion vision produces far-reaching influence on the corresponding network architecture design in 6G and dese…
Leveraging recent advances on mobile edge computing (MEC), edge intelligence has emerged as a promising paradigm to support mobile artificial intelligence (AI) applications at the network edge. In this paper, we consider the AI service placement problem in a multi-user MEC system, where the access point (AP) places the most up-to-date AI program at user devices to enable local computing/task execution at the user side. To fully utilize the stringent wireless spectrum and edge computing resources, the AP sends the AI service program to a user only when enabling local computing at the user yield…
Machine Intelligence (MI) technologies have revolutionized the design and applications of computational intelligence systems, by introducing remarkable scientific and technological enhancements across domains. MI can improve Internet of Things (IoT) in several ways, such as optimizing the management of large volumes of data or improving automation and transmission in large-scale IoT deployments. When considering MI in the IoT context, MI services deployment must account for the latency demands and network bandwidth requirements. To this extent, moving the intelligence towards the IoT end-devic…
The air-ground integrated network is a key component of future sixth generation (6G) networks to support seamless and near-instant super-connectivity. There is a pressing need to intelligently provision various services in 6G networks, which however is challenging. To meet this need, in this article, we propose a novel architecture called UaaS (UAVs as a Service) for the air-ground integrated network, featuring UAV as a key enabler to boost edge intelligence with the help of machine learning (ML) techniques. We envision that the proposed UaaS architecture could intelligently provision wireless…
North Carolina State University（北卡罗来纳州立大学）；Old Dominion University（欧道明大学）；Utah State University（犹他州立大学）
Edge caching is a new paradigm that has been exploited over the past several years to reduce the load for the core network and to enhance the content delivery performance. Many existing caching solutions only consider homogeneous caching placement due to the immense complexity associated with the heterogeneous caching models. Unlike these legacy modeling paradigms, this paper considers heterogeneous content preference of the users with heterogeneous caching models at the edge nodes. Besides, aiming to maximize the cache hit ratio (CHR) in a two-tier heterogeneous network, we let the edge nodes…
The Internet of Vehicles (IoV) is an emerging paradigm, driven by recent advancements in vehicular communications and networking. Advances in research can now provide reliable communication links between vehicles, via vehicle-to-vehicle communications, and between vehicles and roadside infrastructures, via vehicle-to-infrastructure communications. Meanwhile, the capability and intelligence of vehicles are being rapidly enhanced, and this will have the potential of supporting a plethora of new exciting applications, which will integrate fully autonomous vehicles, the Internet of Things (IoT), a…
Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；East China Normal University（华东师范大学）；Nantong University（南通大学）；National Mobile Communications Research Laboratory（移动通信国家重点实验室）；Southeast University（东南大学）；National Key Laboratory on Communications（通信抗干扰技术国家级重点实验室）；University of Electronic Science and Technology of China（电子科技大学）
Mobile edge computing (MEC) is considered a novel paradigm for computation-intensive and delay-sensitive tasks in fifth generation (5G) networks and beyond. However, its uncertainty, referred to as dynamic and randomness, from the mobile device, wireless channel, and edge network sides, results in high-dimensional, nonconvex, nonlinear, and NP-hard optimization problems. Thanks to the evolved reinforcement learning (RL), upon iteratively interacting with the dynamic and random environment, its trained agent can intelligently obtain the optimal policy in MEC. Furthermore, its evolved versions, …
Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
The Hong Kong University of Science and Technology（香港科技大学）；Peng Cheng Laboratory（鹏城实验室）；ShanghaiTech University（上海科技大学）；Huawei Technologies Co., Ltd.（华为技术有限公司）；Tsinghua University（清华大学）
The use of Artificial Intelligence (AI) is becoming increasingly pervasive and relevant in many different application areas. Researchers are putting a considerable effort to take full advantage of the power of AI, while trying to overcome the technical challenges that are intrinsically linked to almost any domain area of application, such as the Internet of Things (IoT). One of the biggest problems related to the use of AI in IoT is related to the difficulty of coping with the wide variety of protocols and software technologies used, as well as with the heterogeneity of the hardware resources …
Mobile Edge Computing (MEC) has emerged as a promising supporting architecture providing a variety of resources to the network edge, thus acting as an enabler for edge intelligence services empowering massive mobile and Internet of Things (IoT) devices with AI capability. With the assistance of edge servers, user equipments (UEs) are able to run deep neural network (DNN) based AI applications, which are generally resource-hungry and compute-intensive, such that an individual UE can hardly afford by itself in real time. However the resources in each individual edge server are typically limited.…
Web 3.0 enables user-generated contents and user-selected authorities. With decentralized wireless edge computing architectures, Web 3.0 allows users to read, write, and own contents. A core technology that enables Web 3.0 goals is blockchain, which provides security services by recording content in a decentralized and transparent manner. However, the explosion of on-chain recorded contents and the fast-growing number of users cause increasingly unaffordable computing and storage resource consumption. A promising paradigm is to analyze the semantic information of contents that can convey preci…
University of Oulu（奥卢大学）；CentraleSupélec（中央理工-高等电力学院）；Université Paris-Saclay（巴黎-萨克雷大学）
Fueled by the availability of more data and computing power, recent breakthroughs in cloud-based machine learning (ML) have transformed every aspect of our lives from face recognition and medical diagnosis to natural language processing. However, classical ML exerts severe demands in terms of energy, memory and computing resources, limiting their adoption for resource constrained edge devices. The new breed of intelligent devices and high-stake applications (drones, augmented/virtual reality, autonomous systems, etc.), requires a novel paradigm change calling for distributed, low-latency and r…
