Article
Computer Science, Information Systems
Chao-Chao Wang, Xinwei Yao, Wan-Laing Wang, Josep Miquel Jornet
Summary: This paper proposes a multi-hop deflection routing algorithm based on reinforcement learning (MDR-RL) for the design of routing protocols in nanonetworks. By implementing new routing and deflection tables in nano-nodes and designing different updating schemes, dynamic and efficient routing path exploration is achieved. Simulation results show that MDR-RL can significantly increase the packet delivery ratio and number of delivered packets while reducing the packet average hop count.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2022)
Article
Engineering, Civil
Kashif Naseer Qureshi, Muhammad Ahmed, Gwanggil Jeon, Francesco Piccialli
Summary: Internet of connected vehicles (IoCV) is a popular form of vehicle ad hoc networks based on the new Internet, 5G, cloud, and edge computing, where vehicle nodes can exchange information with or without infrastructure. The Intersection Gateway and Connectivity based Routing (IGCR) protocol is proposed to address issues in existing routing protocols and has shown better performance in data delivery, delay, and throughput based on experimental results.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Information Systems
Khuram Khalid, Isaac Woungang, Sanjay K. Dhurandher, Jagdeep Singh
Summary: In this paper, a novel routing scheme called Reinforcement Learning-based Fuzzy Geocast Routing Protocol (RLFGRP) for Opportunistic networks is proposed. By utilizing node's Q-value, reward value and remaining buffer space, the fuzzy controller determines the likelihood of a node being selected as a suitable forwarder. Through simulations, RLFGRP outperforms established routing protocols in terms of overhead ratio, delivery ratio, and average latency.
INTERNET OF THINGS
(2021)
Article
Engineering, Multidisciplinary
M. Khalid Diaa, I. Samer Mohamed, M. Ayman Hassan
Summary: This paper presents an obstacle prediction-based routing protocol for Vehicular Ad-hoc Networks (VANETs) that utilizes vehicle kinematics and mobility prediction to achieve reliable communication and data transmission in the network.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Computer Science, Information Systems
Gagan Deep Singh, Manish Prateek, Sunil Kumar, Madhushi Verma, Dilbag Singh, Heung-No Lee
Summary: Vehicular Adhoc Networks (VANETs) face challenges in node management, security, and routing. This paper proposes a Hybrid Genetic Firefly Algorithm-based Routing Protocol (HGFA) for faster communication in VANET. Extensive comparative analysis shows that the proposed HGFA algorithm outperforms other algorithms in different network scenarios.
Article
Telecommunications
Chen Chen, Huan Li, Xi'ang Li, Jianlong Zhang, Hong Wei, Hao Wang
Summary: The TLBGR protocol proposed in this paper addresses the problem of data acquisition in traditional trunk coordinated control systems in VANETs. By utilizing the traffic flow of trunk lines and surrounding road networks, it provides real-time data transmission routing scheme to avoid data congestion and local optimum problems, ultimately increasing data packet delivery rate. Simulation results demonstrate that TLBGR outperforms other IoT routing protocols in terms of end-to-end delay, delivery rate, and routing cost in the scenario of urban traffic trunk lines.
DIGITAL COMMUNICATIONS AND NETWORKS
(2021)
Article
Telecommunications
Omid Jafarzadeh, Mehdi Dehghan, Hadi Sargolzaey, Mohammad Mehdi Esnaashari
Summary: Vehicular Ad Hoc Network (VANET) utilizes wireless technologies in vehicles for various applications like emergency, safety, and entertainment, and is a key component of intelligent transportation systems. Challenges in VANET routing due to dynamic environments can be addressed by using machine learning techniques such as Multi-Agent Reinforcement Learning (MARL). By developing a model-based Reinforcement Learning scheme and utilizing Fuzzy Logic for link evaluation, improvements in routing metrics have been achieved.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Juan Xu, Yan Zhang, Jiaolong Jiang, Jiali Kan
Summary: The study introduced a multi-hop routing protocol called MRLSP based on link state prediction, utilizing Kalman filtering for link state estimation. It also incorporated an ultrasonic energy harvesting system and established a fuzzy system for selecting the next hop node to ensure successful packet transmission with fewer hops.
Article
Engineering, Civil
Tao Zhang, Changqiao Xu, Bingchi Zhang, Jiahao Shen, Xiaohui Kuang, Luigi Alfredo Grieco
Summary: This paper investigates the issue of route mutation in vehicular ad hoc networks (VANETs) and proposes a grid-based extended joint action learning approach (Grid-eJAL) to mitigate attacks. By sharing parameters in learning, Grid-eJAL improves convergence speed and its convergence is theoretically proved. Extensive simulation results demonstrate the effectiveness of Grid-eJAL compared to other solutions.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Saeed Shokrollahi, Mahtab Dehghan
Summary: This paper proposes a trust-based geographic routing protocol (TGRV) for Vehicular ad-hoc networks (VANETs) to improve the routing correctness by limiting the participation of malicious vehicles. TGRV utilizes a monitoring system for vehicles to monitor the correct packet forwarding rate of the next-hop and updates the direct trust and recommendation trust accordingly. Extensive simulations on OMNeT++ show that TGRV performs well in terms of packet delivery ratio, end-to-end delay, and average hop count compared to other protocols.
Article
Social Sciences, Interdisciplinary
Rana Muhammad Amir Latif, Muhammad Jamil, Jinliao He, Muhammad Farhan
Summary: City zones are overcrowded due to population growth and swift relocation. This research proposes an improved authentication and communication protocol for an Intelligent Transportation System in VANET. Cluster-based routing protocols optimize resource sharing in vehicular communication and address security concerns. The protocols focus on short-range P2P wireless communication and offer secure authentication and enhanced performance.
Article
Computer Science, Information Systems
Chen Wang, Rui Huang, Jian Shen, Jianwei Liu, Pandi Vijayakumar, Neeraj Kumar
Summary: This article proposes a novel lightweight authentication protocol to avoid emergency vehicles in VANETs. The protocol is efficient in reducing mission delays caused by traffic congestion.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Ying Zhang, Zheming Zhang, Lei Chen, Xinheng Wang
Summary: This paper proposes a reinforcement learning-based opportunistic routing protocol (RLOR) for underwater acoustic sensor networks, which comprehensively considers nodes' peripheral status to select appropriate relay nodes and employs a recovery mechanism to improve data delivery rates. In underwater dynamic network environments, RLOR performs well in terms of end-to-end delay, reliability, and energy efficiency.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Kennedy Chinedu Okafor, Bamidele Adebisi, Kelvin Anoh
Summary: Data transmission over PLC infrastructure will increase IoT nodes in 5G and 6G networks. A lightweight multi-hop routing protocol (LMRP) is needed at the edges of PLC networks for optimal routing. The proposed LMRP reduces path loss and offers a lightweight routing performance compared to similar schemes.
INTERNET OF THINGS
(2023)
Article
Telecommunications
Mishri Saleh AlMarshoud, Ali H. Al-Bayatti, Mehmet Sabir Kiraz
Summary: This paper introduces a new and efficient end-to-end anonymous key exchange protocol based on self-blindable signatures to address the security and privacy issues in vehicular ad hoc networks (VANETs). By privately blinding private certificates and computing anonymous shared keys using zero-knowledge proof, the protocol can generate shared keys without requiring further external information. Compared to existing schemes, this protocol achieves higher efficiency.
VEHICULAR COMMUNICATIONS
(2022)
Article
Engineering, Civil
Wei Gao, Celimuge Wu, Lei Zhong, Kok-Lim Alvin Yau
Summary: Vehicle platoons are closely connected groups of vehicles moving in the same direction at a certain speed. In order to address communication challenges within platoons, a spectrum sensing scheduling scheme is proposed. This scheme establishes a three-level platoon architecture and utilizes a greedy algorithm and vehicle-to-vehicle communication to minimize platoon delay and improve safety.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Xuelin Cao, Bo Yang, Yulong Shen, Chau Yuen, Yan Zhang, Zhu Han, H. Vincent Poor, Lajos Hanzo
Summary: Sixth-Generation (6G) technologies will revolutionize the wireless ecosystem through satellite-terrestrial integrated networks (STINs). This research investigates the application of edge computing paradigm to low Earth orbit satellite (LEOS) networks for supporting computation-intensive and delay-sensitive services. A LEOS edge-assisted multi-layer multi-access edge computing (MEC) system is proposed, which enhances the coverage and solves computing problems in congested and isolated areas. Optimization problems are formulated and solved using an alternating optimization (AO) method to achieve low computing latency and energy dissipation.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Automation & Control Systems
Haijun Liao, Zhenyu Zhou, Nian Liu, Yan Zhang, Guangyuan Xu, Zhenti Wang, Shahid Mumtaz
Summary: Digital twin (DT) is a cutting-edge technology for intelligent optimization of electrical equipment management, but it still faces reliability and communication efficiency problems. This paper proposes a Cloud-edge-device Collaborative reliable and Communication-efficient DT named C-3-FLOW. By jointly optimizing device scheduling, channel allocation, and computational resource allocation, C-3-FLOW minimizes the long-term global loss function and time-average communication cost. Simulation results verify its superior performance in loss function, communication efficiency, and carbon emission reduction.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Liwen Niu, Xianfu Chen, Ning Zhang, Yongdong Zhu, Rui Yin, Celimuge Wu, Yangjie Cao
Summary: Mobile-edge computing (MEC) enables computation offloading from resource-constrained mobile devices to nearby servers. However, spectrum congestion poses a challenge to computation task scheduling, affecting the quality of computation experience. This article investigates computation task scheduling in a heterogeneous cellular and WiFi MEC system, considering both licensed and unlicensed spectrum opportunities.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Yu Gu, Huan Yan, Xiang Zhang, Yantong Wang, Jinyang Huang, Yusheng Ji, Fuji Ren
Summary: The use of WiFi sensing technology in applications such as gait and gesture recognition has gained attention. The challenge lies in effectively utilizing the amplitude and phase information of channel state information (CSI) from WiFi devices for sensing tasks. To address this, an attention-based framework is developed to track the importance of amplitude and phase information and extract features related to gestures. Experimental results show that the proposed method achieves high recognition accuracy in different conditions.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Yu Gong, Yifei Wei, Zhiyong Feng, F. Richard Yu, Yan Zhang
Summary: This paper proposes a holistic network virtualization architecture that integrates digital twin and network slicing for service-centric and user-centric network management. It also introduces a new environment aware offloading mechanism based on the integrated sensing and communication system to solve the joint optimization problem of task scheduling and resource allocation. Simulation results demonstrate the effectiveness and superiority of the proposed schemes.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Wen Sun, Zongjun Li, Qubeijian Wang, Yan Zhang
Summary: In this article, a wireless computing power network (WCPN) is proposed to orchestrate the computing and networking resources of heterogeneous nodes for specific computing tasks. A task and resource-aware federated learning model (FedTAR) is designed to optimize the energy consumption of computing nodes through the joint optimization of computing strategies and collaborative learning strategies. An energy-efficient asynchronous aggregation algorithm is also proposed to accelerate the convergence speed of federated learning in WCPN.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Telecommunications
Bingyi Liu, Yang Sheng, Xun Shao, Yusheng Ji, Weizhen Han, Enshu Wang, Shengwu Xiong
Summary: Green Internet of Vehicles (IoV) is a new research area that focuses on reducing networking overhead and improving communication efficiency in future vehicular cyber-physical systems (VCPS). In this paper, we propose a vehicle density prediction-based routing protocol called VDPGrid. We introduce a vehicle density prediction model and a routing path evaluation scheme that considers vehicle density, link quality, and routing length. Experimental results using real-world vehicle trajectories validate the effectiveness of our method.
IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING
(2023)
Article
Automation & Control Systems
Anh Duy Nguyen, Viet Hung Vu, Duc Viet Hoang, Thuy Dung Nguyen, Kien Nguyen, Phi Le Nguyen, Yusheng Ji
Summary: This research introduces a novel deep learning-based method for forecasting discharge and water levels. To overcome data scarcity and noise existence, the study leverages the strengths of 1D-CNN, LSTM, and ensemble learning. In addition, the application of SSA helps eliminate noise-like components while retaining essential parts, and the attention mechanism assigns higher weights to more important features, further enhancing accuracy.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Jia Xu, Zhuangye Luo, Chengcheng Guan, Dejun Yang, Linfeng Liu, Yan Zhang
Summary: This paper proposes a two-tiered social crowdsourcing architecture to address the insufficient participation problem in budget-constrained online crowdsourcing systems. Through theoretical analysis and simulations, the incentive mechanisms are shown to achieve computational efficiency, individual rationality, budget feasibility, cost truthfulness, and time truthfulness. The proposed mechanisms outperform offline algorithms in terms of value.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Peng Wang, Wen Sun, Haibin Zhang, Wenqiang Ma, Yan Zhang
Summary: This article proposes a provable secure and decentralized federated learning based on blockchain for Wireless Computing Power Network (WCPN). It integrates a blockchain with proof-of-accuracy (PoAcc) consensus scheme to prioritize high-accuracy local models in the federated learning process, accelerating convergence and improving efficiency. Experimental results show that the proposed scheme ensures consistency and security while outperforming benchmarks in terms of model accuracy and resource consumption.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Caijuan Chen, Yi-Han Chiang, Hai Lin, John C. S. Lui, Yusheng Ji
Summary: This study aims to address the issue of client selection and receive beamforming optimization in OTA FL, and proposes a mixed-integer nonlinear programming method for optimization.
IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY
(2023)
Article
Computer Science, Information Systems
Kok-Lim Alvin Yau, Yung-Wey Chong, Xiumei Fan, Celimuge Wu, Yasir Saleem, Phei-Ching Lim
Summary: This paper presents the application of various variants of reinforcement learning (RL) in diabetes management. It focuses on improving blood glucose levels and the similarity between RL and physician's policies. The paper discusses the attributes of RL, essential training elements, representation of diabetes attributes, and different types of RL algorithms. It also explores open issues and potential future developments in using RL for diabetes management.
Article
Computer Science, Hardware & Architecture
Xing An, Celimuge Wu, Yangfei Lin, Min Lin, Tsutomu Yoshinaga, Yusheng Ji
Summary: Multi-robot systems are gaining attention due to their lower cost, better robustness, and higher scalability compared to single-robot systems. Cooperative object transport is a well-known use case of multi-robot systems and has great potential in real-world applications. However, recent studies focus more on coordination and task allocation problems, with less emphasis on communication among multiple robots.
IEEE OPEN JOURNAL OF THE COMPUTER SOCIETY
(2023)
