Review
Computer Science, Information Systems
Sukhpal Singh Gill, Minxian Xu, Carlo Ottaviani, Panos Patros, Rami Bahsoon, Arash Shaghaghi, Muhammed Golec, Vlado Stankovski, Huaming Wu, Ajith Abraham, Manmeet Singh, Harshit Mehta, Soumya K. Ghosh, Thar Baker, Ajith Kumar Parlikad, Hanan Lutfiyya, Salil S. Kanhere, Rizos Sakellariou, Schahram Dustdar, Omer Rana, Ivona Brandic, Steve Uhlig
Summary: Autonomic computing investigates how systems can achieve specified control outcomes on their own. Integrating AI/ML to improve resource autonomy and performance remains a fundamental challenge. Experts in the field discuss current research, potential future directions, and challenges and opportunities for leveraging AI and ML in emerging computing paradigms.
INTERNET OF THINGS
(2022)
Article
Engineering, Electrical & Electronic
Kunlun Wang, Jiong Jin, Yang Yang, Tao Zhang, Arumugam Nallanathan, Chintha Tellambura, Bijan Jabbari
Summary: With the development of next-generation wireless networks, the Internet of Things (IoT) is evolving towards the intelligent IoT (iIoT), where intelligent applications usually have stringent delay and jitter requirements. In order to provide low-latency services to heterogeneous users in the emerging iIoT, multi-tier computing was proposed by effectively combining edge computing and fog computing. This paper investigates key techniques and directions for wireless communications and resource allocation approaches to enable task offloading in multi-tier computing systems, and presents a detailed multi-tier computing model with its main functionality and optimization methods.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Aaisha Makkar, Uttam Ghosh, Pradip Kumar Sharma
Summary: The study introduces a cognitive intrusion security system to detect malicious images in web spam using edge intelligence, and validates the system's accuracy with deep learning algorithms, resulting in an accuracy of 98.77% when evaluated on a real-time collected dataset.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Information Systems
Syed Junaid Nawaz, Shree Krishna Sharma, Mohammad N. Patwary, Md Asaduzzaman
Summary: The paper discusses the upcoming technologies and services in the beyond 5G/6G wireless networks, emphasizing the importance of device-level design to efficiently support novel technologies. It introduces a novel edge computing-enabled e-URLLC framework to enhance consumer electronics advancements and initiates discussions on the need for the next-generation CE. The proposed ECCE framework, along with potential technologies and tools to enable its implementation, is described along with interesting open research topics and future recommendations.
Article
Computer Science, Artificial Intelligence
Hailin Feng, Liang Qiao, Zhihan Lv
Summary: The research aims to reduce network resource pressure, improve service quality and optimize network performance in cloud centers and edge nodes. A edge-cloud collaboration framework based on IoT is designed, using raspberry pi cards as working nodes. The framework consists of three layers, including edge RP, monitoring & scheduling RP, and CC. The task delay in the edge-cloud collaboration mode is the least among different working modes, and real-time object detection can be achieved.
APPLIED SOFT COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Fatemeh Aghaaliakbari, Zakaria Ait Hmitti, Marsa Rayani, Manel Gherari, Roch H. Glitho, Halima Elbiaze, Wessam Ajib
Summary: This article advocates the use of in-network computing (INC) paradigm to tackle the high bandwidth and low latency challenges of holographic applications, instead of the previously used edge computing paradigm. An architecture is proposed for provisioning INC-enabled slices for holographic-type application deployment, which is validated through a proof of concept and extensive simulations. Experimental results show that INC outperforms edge computing in addressing these key challenges, while maintaining low jitter for hologram stability.
IEEE COMMUNICATIONS MAGAZINE
(2023)
Article
Computer Science, Theory & Methods
Hao Zhou, Geng Yang, Yuxian Huang, Hua Dai, Yang Xiang
Summary: This paper proposes a privacy-preserving and verifiable federated learning (PVFL) method with low communication and computation overhead for edge computing. It is theoretically and experimentally demonstrated that PVFL has the properties of communication overhead independent of dropouts and parameter vector dimension, computation overhead independent of dropouts, and a negative correlation between the loss function value and the number of dropouts.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Computer Science, Hardware & Architecture
Zaiwar Ali, Ziaul Haq Abbas, Ghulam Abbas, Abdullah Numani, Muhammad Bilal
Summary: The limited battery and computing resources of mobile devices result in performance limitations in mobile edge computing networks. Computational offloading allows MDs to outsource resource-intensive tasks to nearby MES for execution. However, due to varying network conditions and limited computing resources at MES, the offloading decisions may not always be the most cost-effective. This paper proposes an energy efficient and faster deep learning based offloading technique (EFDOT) to minimize the overall cost of MDs by training a DNN for faster decision-making and fine-grained offloading optimization. Simulation results demonstrate the high accuracy of the DNN and improved performance of EFDOT in terms of energy consumption, service delay, and battery life.
Article
Computer Science, Information Systems
Erik Daniel, Florian Tschorsch
Summary: This survey paper provides a technical overview of the next generation data networks, introducing select data networks and highlighting new developments such as the Interplanetary File System. It identifies common building blocks and outlines future research goals regarding data networks.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2022)
Article
Computer Science, Hardware & Architecture
Ahmad M. Nagib, Hatem Abou-zeid, Hossam S. Hassanein
Summary: Deep reinforcement learning algorithms have potential in wireless networks, but face challenges in commercial applications. This article discusses the practical challenges of slow convergence and performance instability and reviews methods to address them. A case study demonstrates the importance of safe and accelerated DRL in wireless networks.
Article
Engineering, Multidisciplinary
Shunpu Tang, Lunyuan Chen, Ke He, Junjuan Xia, Lisheng Fan, Arumugam Nallanathan
Summary: This paper investigates the deployment of computational intelligence and deep learning in edge-enabled industrial IoT networks. A multi-exit-based federated edge learning framework is proposed to address the limited resources issue. Simulation experiments show that the proposed framework achieves significant accuracy improvement in industrial IoT networks.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Rangeet Mitra, Georges Kaddoum, Daniel Benevides da Costa
Summary: Information theoretic learning criteria are useful for mitigating degradations caused by unknown non-Gaussian noise processes in wireless communication systems. The reproducing kernel Hilbert space (RKHS) based approaches relying on these criteria provide near-optimal mitigation of unknown hardware impairments and non-Gaussian noises. Among these criteria, the minimum error entropy with fiducial points (MEEF) shows promising results, but depends on an accurate kernel-width initialization. To remove this dependency, a hyperparameter-free MEEF based adaptive algorithm is derived, which is validated through computer simulations.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Muralikrishnan Srinivasan, Sarath Gopi, Sheetal Kalyani, Xiaojing Huang, Lajos Hanzo
Summary: A high-rate yet low-cost air-to-ground communication backbone is proposed, utilizing passenger planes or high altitude platforms as mobile base stations and millimetre wave communication. Different beamforming techniques are used for transmission to achieve high directional gain and minimize interference, with approximate spectral efficiency and area spectral efficiency expressions derived for diverse system parameters.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Computer Science, Hardware & Architecture
Xiaoxia Xu, Yuanwei Liu, Xidong Mu, Qimei Chen, Hao Jiang, Zhiguo Ding
Summary: This article focuses on the application of artificial intelligence (AI) in non-orthogonal multiple access (NOMA) for achieving automated, adaptive, and high-efficiency multi-user communications. It proposes a novel cluster-free NOMA framework and identifies promising machine learning solutions to enable scenario-adaptive NOMA communications. The article also discusses the interplays between cluster-free NOMA and emerging wireless techniques.
IEEE WIRELESS COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Ling Hou, Mark A. Gregory, Shuo Li
Summary: This article provides a comprehensive review of Multi-access Edge Computing (MEC) enabled vehicular networks, which has become a crucial capability in the era of 5G and the Internet of Things. The paper introduces MEC by discussing its definition, architecture, applications, and challenges, and explores its support for vehicular network applications and services, as well as current research and future challenges.
Article
Computer Science, Artificial Intelligence
Jingcai Guo, Song Guo, Shiheng Ma, Yuxia Sun, Yuanyuan Xu
Summary: This research focuses on the recognition of both known and unknown malware families, and proposes a new model that uses generative adversarial networks to synthesize malware instances to better train the classifier and improve recognition performance. Additionally, a large-scale malware dataset (MAL-100) is built to address the lack of existing benchmark datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Jing Li, Weifa Liang, Yuchen Li, Zichuan Xu, Xiaohua Jia, Song Guo
Summary: Mobile Edge Computing (MEC) is a promising paradigm that offloads compute-intensive tasks to MEC networks, providing high-performance processing for mobile applications. This study focuses on the acceleration of DNN inference in MEC networks through DNN partitioning and multi-thread execution parallelism. The research develops novel algorithms for maximizing the number of delay-aware DNN service requests admitted, both in offline and online scenarios. Experimental simulations demonstrate the promising performance of the proposed algorithms.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Information Systems
Zhaolong Ning, Yuxuan Yang, Xiaojie Wang, Lei Guo, Xinbo Gao, Song Guo, Guoyin Wang
Summary: In this paper, a MEC network enabled by UAVs is investigated, considering multi-user computation offloading and edge server deployment to minimize system-wide computation cost under a dynamic environment. The problem is decomposed into two stochastic games and it is proven that each game has at least one Nash Equilibrium. Two learning algorithms are proposed to reach the Nash Equilibriums. These algorithms are further incorporated into an asynchronous updating algorithm to solve the system-wide computation cost minimization problem. Performance evaluations based on real-world data are conducted, showing the proposed algorithms can achieve efficient computation offloading and server deployment under dynamic environments.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Information Systems
Chao Wang, Chunxiao Jiang, Jingjing Wang, Shigen Shen, Song Guo, Peiying Zhang
Summary: This article proposes a blockchain-enabled resource orchestration scheme for IoT using deep reinforcement learning. The scheme allows the IoT edge server and end user to reach a consensus on network resource allocation based on blockchain theory. By utilizing a policy network, the intelligent agent can perceive changes in the network's state and make dynamic resource allocation decisions. Simulation results demonstrate that the proposed scheme performs better than other security resource allocation algorithms, with average revenue, user request acceptance rate, and profitability increased by 8.5%, 1.8%, and 11.9%, respectively.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Xiaojie Wang, Zhaolong Ning, Lei Guo, Song Guo, Xinbo Gao, Guoyin Wang
Summary: This paper investigates a practical scenario with multiple Service Providers (SPs) managing servers of different capacities and prices in the context of blockchain. It proposes a learning-based offloading algorithm that integrates Deep Reinforcement Learning (DRL) and Mean Field Theory (MFT) to maximize utilities of miners. Theoretical and performance results demonstrate the superiority of the proposed algorithm in terms of average miner utilities and algorithm convergence time compared to other representative algorithms.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Theory & Methods
Yuchen Li, Weifa Liang, Jing Li, Xiuzhen Cheng, Dongxiao Yu, Albert Y. Zomaya, Song Guo
Summary: The rise of deep learning brings new vitality to the future of intelligent IoT, and the emergence of edge intelligence enables real-time DNN inference services for mobile users. To ensure efficient and secure DNN model training in edge computing, federated learning is proposed as an ideal learning paradigm. This article focuses on energy-aware DNN model training in edge computing and proposes an algorithm to optimize the global loss of the training model while considering bandwidth and energy constraints.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Rongxin Han, Dezhi Chen, Song Guo, Jingyu Wang, Qi Qi, Lu Lu, Jianxin Liao
Summary: This article focuses on the parallel deployment of multi-service providers (SPs) in network slicing in the edge network. It proposes a multi-SP network slicing mechanism using multi-agent deep reinforcement learning to solve resource conflicts through network resource coordination. It demonstrates scalability and fast model convergence in dealing with dynamic edge networks.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Hao Dong, Cunqing Hua, Lingya Liu, Wenchao Xu, Song Guo, Rahim Tafazolli
Summary: This paper investigates the spectrum sharing problem in integrated terrestrial satellite networks and proposes an optimization framework that jointly considers terrestrial beamformer design and satellite user scheduling. The optimization problems are decomposed into three sub-problems and solved using deep clustering, second-order cone programming (SOCP), and linear programming. The proposed algorithm is demonstrated to be effective through simulation results.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Zeyu Qin, Haipeng Yao, Tianle Mai, Di Wu, Ni Zhang, Song Guo
Summary: LEO satellite networks serve as a necessary supplement to terrestrial networks, especially in areas where the latter are limited. However, the increasing demand for computation-intensive IoT applications poses challenges in terms of efficient communication and computing capabilities. The combination of LEO networks and edge computing offers significant opportunities to address these problems.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Hardware & Architecture
Huawei Huang, Xiaowen Peng, Yue Lin, Miaoyong Xu, Guang Ye, Zibin Zheng, Song Guo
Summary: In a sharded blockchain, transactions are processed by parallel committees, boosting the transaction throughput. However, latency in committee formation and imbalanced consensus latency degrade the throughput. This paper proposes an algorithm to balance the tradeoff between throughput and cumulative age of transactions in a large-scale sharded blockchain, improving system utility, latency, and throughput performance.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Hardware & Architecture
Xiaolong Wang, Haipeng Yao, Tianle Mai, Song Guo, Yunjie Liu
Summary: With the rapid development of the Industrial Internet of Things (IIoT), the integration of time-sensitive networking (TSN) and fifth-generation (5G) wireless communication technology (TSN-5G networks) is considered the most promising solution to address the challenges posed by industrial networks. TSN can provide deterministic latency and reliability for real-time applications in wired networks, while 5G supports ultra-reliable and low-latency communications (uRLLC) in wireless networks. This paper focuses on the end-to-end traffic scheduling problem in TSN-5G networks and proposes a novel integrated TSN and 5G industrial network architecture, as well as a Double Q-learning based hierarchical particle swarm optimization algorithm (DQHPSO) to search for the optimal scheduling solution. Extensive simulations show that the DQHPSO algorithm improves the scheduling success ratio of time-triggered flows compared to other algorithms.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Information Systems
Tianle Mai, Haipeng Yao, Ni Zhang, Lexi Xu, Mohsen Guizani, Song Guo
Summary: The exponential growth of IoT devices and applications has brought both economic opportunities and challenges. The integration of IoT and blockchain technology is considered a promising solution to address privacy and security vulnerabilities. In this article, a cloud mining pool-aided BCoT architecture is proposed to overcome the computation and energy cost issue of blockchain. Furthermore, mining pool selection algorithms and a lightweight distributed reinforcement learning algorithm are introduced.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Information Systems
Fahao Chen, Peng Li, Deze Zeng, Song Guo
Summary: Short video apps like TikTok have gained popularity by providing users with fresh and short video contents that match their preferences. However, the growth of these apps poses technical challenges on the existing infrastructure. This article proposes an edge-assisted short video sharing framework that caches popular videos on edge servers for fast access through high-speed network connections.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Information Systems
Ziming Liu, Song Guo, Jingcai Guo, Yuanyuan Xu, Fushuo Huo
Summary: Multi-label zero-shot learning aims at recognizing multiple unseen labels for each input sample, but existing methods often neglect minor classes and result in inadequate attention. This paper proposes a novel unbiased framework that balances the training process by considering class-specific regions and strengthens the correlation among semantic representations.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Jing Li, Weifa Liang, Wenzheng Xu, Zichuan Xu, Xiaohua Jia, Albert Y. Zomaya, Song Guo
Summary: This article investigates the issue of user satisfaction on services provided by a Mobile Edge Computing (MEC) network and introduces a submodular function based metric to measure user satisfaction. It formulates a novel user satisfaction problem and proposes approximation algorithms with provable approximation ratios to maximize the accumulative user satisfaction and consider resource budget constraints.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
