Article
Computer Science, Interdisciplinary Applications
Rojia Nikbazm, Mahmood Ahmadi
Summary: The rapid advancement of networking and computing technologies has brought new challenges in the provision and management of network services. SDN and NFV technologies, along with the use of knowledge-based systems, are effective solutions. However, the lack of a simulation framework with knowledge concept has been a gap in the NFV and SDN field. In this paper, a highly extensible, interoperable, and scalable simulation framework for developing knowledge-based methods is proposed. Additionally, a new auto-scaling method based on machine learning is proposed and simulated, showing its effectiveness and efficiency in resource prediction and VNF auto-scaling.
SIMULATION MODELLING PRACTICE AND THEORY
(2022)
Article
Computer Science, Information Systems
Marwa A. Abdelaal, Gamal A. Ebrahim, Wagdy R. Anis
Summary: The VNFRP approach aims to achieve load balancing over core links in NFV by considering multiple resource constraints. It significantly improves load balancing, reduces network energy consumption by more than 54%, and efficiently decreases SFC placement cost by over 67%.VNFRP is a scalable solution for large networking environments with fast response time and rapid convergence.
Article
Computer Science, Hardware & Architecture
Deborsi Basu, Soumyadeep Kal, Uttam Ghosh, Raja Datta
Summary: This research proposes a programmable network solution that improves the efficiency of overall network performance by using dedicated network slices for communication. By using service-specific learning models on shared network slices, the error in resource allocation is reduced, leading to fewer service denials for critical applications.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Computer Science, Hardware & Architecture
Nour el Houda Nouar, Sami Yangui, Noura Faci, Khalil Drira, Said Tazi
Summary: NFV is gaining importance in addressing emerging networking challenges by running VNF on generic hardware. Existing VNF description models lack accuracy and precision, leading to the proposal of VIKING and a semantic-based matchmaking algorithm. Experimental validation in the CDN domain demonstrates the effectiveness and value of the proposed approach.
Article
Chemistry, Analytical
Anwei Dong, Xingwei Wang, Bo Yi, Qiang He, Min Huang
Summary: This paper presents a blockchain-based framework for resource sharing and access control in the realm of NFV, with a focus on ensuring profitability during VNF instantiation. The framework introduces a resource sharing game model and a greedy matching algorithm to optimize the benefits for both VNF instances and infrastructure resource providers. Additionally, a blockchain-based access control mechanism is designed to securely store keys and provide fine-grained access control.
Article
Engineering, Electrical & Electronic
Xinran Liu, Yonghong Hou, Hongchen Liu
Summary: This paper investigates the joint VNF deployment and resource allocation problems and proposes a discrete spider monkey optimization algorithm to solve them. By simulating the behavior of spider monkey groups, this algorithm effectively reduces the end-to-end latency of services in NFV-enabled networks.
INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Deborsi Basu, Soumyadeep Kal, Uttam Ghosh, Raja Datta
Summary: The network slicing technique is reshaping communication networks, and this paper proposes a multilayered SFC formation method for adaptive VNF allocation and an intelligent VNF selection mechanism using machine learning techniques. The performance evaluation shows that dynamic VNF selection can reduce resource usage by half compared to static allocations.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Jie Sun, Feng Liu, Huandong Wang, Dapeng Oliver Wu
Summary: Emerging network-softwarization technologies, such as software-defined networking and network function virtualization, have significant roles in 5G communication and future networks. One of the critical challenges is the appropriate placement of virtual network functions (VNFs) in softwarized networks. This study focuses on the joint optimization problem of VNF Placement, CPU Allocation, and flow Routing (VNFPAR) in scenarios with dynamically changing VNF traffic. The proposed algorithms, including an optimal algorithm and heuristic algorithms, demonstrate their effectiveness in solving VNFPAR problems and achieving a tradeoff between solution quality and execution time.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Marwa A. Abdelaal, Gamal A. Ebrahim, Wagdy R. Anis
Summary: NFV, a promising innovation in telecommunication networks, leverages ILP and heuristic algorithms to reduce link utilization and bandwidth consumption while ensuring high availability, facilitating quick response to network failures.
Article
Computer Science, Theory & Methods
Qi Li, Xinhao Deng, Zhuotao Liu, Yuan Yang, Xiaoyue Zou, Qian Wang, Mingwei Xu, Jianping Wu
Summary: NFV is a new networking paradigm focusing on dynamic network function deployment, but existing studies lack effective solutions for security function enforcement. FuncE proposes a method for efficient real-time security function enforcement through unified dynamic flow and function scheduling, achieving near-optimal solutions and significantly reducing latency compared to existing solvers.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Computer Science, Artificial Intelligence
Hejun Xuan, Yi Zhou, Xuelin Zhao, Zhenghui Liu
Summary: Network function virtualization decouples traditional network function from dedicated hardware and promotes the transformation of network service deployment. This paper investigates the deployment problem of VNF service chain in SDN/NFV-Enabled Networks and proposes a real-time algorithm based on multi-agent deep reinforcement learning with self-adaption division strategy (MDRL-SaDS) to minimize energy consumption.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Information Systems
Junling Li, Weisen Shi, Huaqing Wu, Shan Zhang, Xuemin Shen
Summary: This article investigates the online dynamic virtual network function (VNF) mapping and scheduling in Space-air-ground-integrated networks (SAGINs), considering the dynamicity of Internet of Vehicles (IoV) services. The proposed solution enables VNF live migration, reinstantiation, and rescheduling to increase service acceptance ratio and service provider's profits. Two Tabu search (TS)-based algorithms are proposed to efficiently solve the mixed-integer linear programming (MILP) problem. Simulation results show that the proposed solution outperforms existing works in terms of multiple performance metrics.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Mahsa Moradi, Mahmood Ahmadi, Rojia Nikbazm
Summary: Network Function Virtualization (NFV) is an architecture that separates software from hardware using virtualization technology. One of the challenges in NFV is managing the resources of virtualized network functions (VNFs). Due to the dynamic nature of NFV, resource allocation to VNFs needs to be adjusted based on incoming traffic variations. This paper analyzes and compares three machine learning algorithms, Support Vector Regression (SVR), Decision Tree (DT), and k-Nearest Neighbor (KNN), in terms of resource prediction. The results show that all three algorithms achieve an error less than one in predicting resources, with SVR having a longer execution time compared to the other two algorithms.
JOURNAL OF NETWORK AND SYSTEMS MANAGEMENT
(2022)
Article
Engineering, Electrical & Electronic
Ammara Anjum Khan, Mehran Abolhasan, Wei Ni, Justin Lipman, Abbas Jamalipour
Summary: The paper describes a comprehensive network slicing framework that utilizes SDN, NFV, and Edge Computing technologies to manage the cooperation of RAN and Core Network in achieving QoS provisioning in 5G-driven VANETs. The proposed dynamic radio resource slice optimization scheme solves the problem using Genetic Algorithm and demonstrates the framework's ability to optimize resources and meet performance metrics for mission critical communication.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Chemistry, Analytical
Alejandro Llorens-Carrodeguas, Irian Leyva-Pupo, Cristina Cervello-Pastor, Luis Pineiro, Shuaib Siddiqui
Summary: This paper investigates dynamic scaling and load balancing of transparent virtualized network functions (VNFs) and proposes a SDN-based solution. Through experiments, the feasibility of the solution was validated, showing that SDN controllers and OFS offer flexibility to implement various strategies for load balancing, scaling, and monitoring.
Article
Automation & Control Systems
Weisen Shi, Junling Li, Peng Yang, Qiang Ye, Weihua Zhuang, Xuemin Shen, Xu Li
Summary: This article proposes a two-level soft-slicing scheme for 5G-and-beyond radio access networks, which supports ultrareliable and low-latency communications (URLLC) and enhanced mobile broadband (eMBB) services. It achieves this by allocating resources at the network level and scheduling resources at the gNodeB level, meeting the delay/reliability and throughput requirements for URLLC and eMBB services respectively.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Hardware & Architecture
Wen Wu, Conghao Zhou, Mushu Li, Huaqing Wu, Haibo Zhou, Ning Zhang, Xuemin Sherman Shen, Weihua Zhuang
Summary: This article presents an AI-native network slicing architecture for 6G networks to facilitate intelligent network management and support emerging AI services.
IEEE WIRELESS COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Zhibin Wang, Yong Zhou, Yuanming Shi, Weihua Zhuang
Summary: This paper investigates federated learning over a multi-cell wireless network, where each cell performs a different FL task and utilizes air computation for fast uplink gradient aggregation. The study reveals that inter-cell interference hinders the convergence of FL. To address this issue, a cooperative multi-cell FL optimization framework is proposed to manage interference and design efficient downlink and uplink transmissions.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Wen Wu, Mushu Li, Kaige Qu, Conghao Zhou, Xuemin Shen, Weihua Zhuang, Xu Li, Weisen Shi
Summary: This paper proposes a novel Split learning (SL) scheme called Cluster-based Parallel SL (CPSL) to reduce training latency by parallelizing device-side model training and sequentially training the whole AI model. A resource management algorithm is also proposed to consider device heterogeneity and network dynamics. Extensive simulation results demonstrate that the proposed solution greatly reduces training latency and adapts to network dynamics compared with existing SL benchmarks.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Editorial Material
Engineering, Electrical & Electronic
Weihua Zhuang
IEEE VEHICULAR TECHNOLOGY MAGAZINE
(2023)
Article
Engineering, Electrical & Electronic
Yufeng Li, Qi Liu, Weihua Zhuang, Yiqing Zhou, Chenhong Cao, Jiangxing Wu
Summary: This article proposes a dynamic heterogeneous redundancy (DHR) scheme for connected automated vehicles (CAVs) to achieve both safety and security in the presence of functional failures or cyberattacks. The DHR architecture, employing multiple heterogeneous executors with the same function, ensures functional safety by providing redundancy and enhances security by detecting abnormal executors caused by cyberattacks. Test results on an automated bus demonstrate the effectiveness of the proposed DHR in enhancing both safety and security for CAVs.
IEEE VEHICULAR TECHNOLOGY MAGAZINE
(2023)
Editorial Material
Engineering, Electrical & Electronic
Weihua Zhuang
Summary: The IEEE Vehicular Technology Society is excited for the upcoming 97th Annual Vehicular Technology Conference in Florence, Italy. The conference organizers and committee members are acknowledged for their efforts.
IEEE VEHICULAR TECHNOLOGY MAGAZINE
(2023)
Editorial Material
Engineering, Electrical & Electronic
Weihua Zhuang
Summary: This time of year is significant for the IEEE Vehicular Technology Society (VTS) as it holds the VTS Award ceremony during the 98th Annual IEEE Vehicular Technology Conference in Hong Kong (VTC2023-Fall) and brings professionals together at the 2023 IEEE Vehicle Power and Propulsion Conference in Milan, Italy.
IEEE VEHICULAR TECHNOLOGY MAGAZINE
(2023)
Article
Computer Science, Information Systems
Kaige Qu, Weihua Zhuang, Wen Wu, Mushu Li, Xuemin Shen, Xu Li, Weisen Shi
Summary: This paper focuses on deep neural network (DNN)-based classification tasks and investigates how to improve the confidence level and delay performance of DNN inference through device-edge collaboration. By developing a stochastic cumulative DNN inference scheme and a computation-efficient DNN model deployment strategy, an adaptive device-edge collaboration scheme is proposed to support cumulative DNN inference for multiple devices. Simulation results demonstrate the effectiveness of this scheme.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Automation & Control Systems
Hiroaki Mukaidani, Shunpei Irie, Hua Xu, Weihua Zhuang
Summary: In this paper, the authors discuss linear-quadratic mean-field social control problems for a specific class of stochastic systems with ordinary and delay control inputs. They introduce a stabilization problem using a memoryless static output feedback (SOF) strategy and use the guaranteed cost control theory to minimize the upper bound of the cost function. The study reveals that minimizing the upper bound of the cost function is not achievable with only a delay control input. They also prove the impossibility of implementing a mean-field SOF strategy and establish the necessary conditions for sub-optimality using stochastic cross-coupled matrix equations (SCCMEs) and the Karush-Kuhn-Tucker condition. Lastly, the authors investigate the performance and usefulness of their proposed strategy using an order-reduced scheme based on the direct method.
IEEE CONTROL SYSTEMS LETTERS
(2023)
Article
Computer Science, Information Systems
Wei Quan, Ziheng Xu, Mingyuan Liu, Nan Cheng, Gang Liu, Deyun Gao, Hongke Zhang, Xuemin Shen, Weihua Zhuang
Summary: This paper presents a survey on the recent research in AI-driven packet forwarding with programmable data plane (PDP). Two representative frameworks of packet forwarding, traditional AI-driven forwarding and PDP-assisted forwarding, are described. The capacity of packet forwarding under these frameworks is evaluated in terms of delay, throughput, security, and reliability. The paper also identifies three directions in the development of AI-driven packet forwarding and highlights challenges and issues in future research.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2023)
Article
Computer Science, Information Systems
Xiaozhen Lu, Liang Xiao, Pengmin Li, Xiangyang Ji, Chenren Xu, Shui Yu, Weihua Zhuang
Summary: Sixth-generation (6G) cellular systems are vulnerable to PHY-layer attacks and privacy leakage due to large-scale networks and time-sensitive applications. Optimized security schemes suffer performance degradation in 6G systems, and reinforcement learning (RL) algorithms can enhance security against smart attacks without relying on attack models. This article provides a comprehensive survey on RL-based 6G PHY cross-layer security and privacy protection.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2023)
Review
Computer Science, Interdisciplinary Applications
Xuemin (Sherman) Shen, Jie Gao, Mushu Li, Conghao Zhou, Shisheng Hu, Mingcheng He, Weihua Zhuang
Summary: The sixth generation (6G) networks are expected to revolutionize communication by enabling immersive experiences through the integration of extended reality, holography, and haptics. However, the high demand for data transmission rate and stringent requirements for latency and reliability pose challenges for 6G networks to support immersive communications. This survey article presents the prospects and challenges of immersive communications in 6G networks, along with emerging solutions to address these challenges.
FRONTIERS IN COMPUTER SCIENCE
(2023)
Article
Engineering, Electrical & Electronic
Mushu Li, Jie Gao, Conghao Zhou, Xuemin Shen, Weihua Zhuang
Summary: In this article, a novel approach for content caching and delivery in mobile virtual reality (VR) video streaming is presented. The proposed approach aims to maximize VR video streaming performance by proactively caching popular VR video chunks and adaptively scheduling computing resources at an edge server based on user and network dynamics. The approach includes a scalable content placement scheme and a machine learning-assisted VR video delivery scheme to improve video delivery efficiency and reduce frame missing rate.
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING
(2023)
Article
Computer Science, Information Systems
Qi Cheng, Hangguan Shan, Weihua Zhuang, Tony Q. S. Quek, Zhaoyang Zhang, Fen Hou
Summary: This study explores the cooperation between e-commerce platform companies and network operators as virtual network operators in China and proposes an incentive mechanism based on mobile data reward to maximize profits for network players. It introduces a three-stage static Stackelberg game and a deep Q-network based algorithm to derive optimal strategies. Simulation results demonstrate the impact of system parameters on game players and social welfare.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
