IEEE Transactions on Network Science and Engineering最新文献_第5页

LooP: A Low-Overhead Path Reconstruction for Large-Scale IoTs

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-13 DOI: 10.1109/TNSE.2025.3535806

Luwei Fu;Zhiwei Zhao;Zhuoliu Liu;Geyong Min

{"title":"LooP: A Low-Overhead Path Reconstruction for Large-Scale IoTs","authors":"Luwei Fu;Zhiwei Zhao;Zhuoliu Liu;Geyong Min","doi":"10.1109/TNSE.2025.3535806","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3535806","url":null,"abstract":"Internet of Things (IoT) plays a vital role in various smart applications due to its cost-efficiency and good scalability. For safety and management of a large-scale IoT with many gateways, packet-level path reconstruction which exactly reveals the transmission path of each packet is desired. However, the existing path reconstruction schemes rely on correlation between diverse packets, which results in either considerable overhead or poor accuracy. It is particularly difficult to reconstruct the paths by affordable overhead under the intensive deployment, constrained resource, and weak correlation of IoT devices. To this end, we propose a <bold>Lo</b>w-<bold>o</b>verhead <bold>P</b>ath reconstruction (LooP) for large-scale IoT. The proposed scheme exploits the nature of incremental update that each node only identifies the changes of its one-hop topology for diverse gateways. The gateway nodes then iteratively recover the complete path of each received packet according to the reported changes and historical information. It removes much redundant overhead (e.g., the common paths information) while guaranteeing the accurate reconstruction in a large scale and dynamic topology network. We analyze the information entropy of LooP and several existing schemes to theoretically prove the superiority of our proposal. The experimental results also demonstrate LooP can achieve 98% reconstruction accuracy on average and at least 3x gain-cost-ratio of the sub-optimal rival.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1623-1634"},"PeriodicalIF":6.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Joint Content Caching and Request Routing for User-Centric Many-Objective Metaverse Services

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-13 DOI: 10.1109/TNSE.2025.3541746

Zhaoming Hu;Chao Fang;Zhuwei Wang;Jining Chen;Shu-Ming Tseng;Mianxiong Dong

{"title":"Joint Content Caching and Request Routing for User-Centric Many-Objective Metaverse Services","authors":"Zhaoming Hu;Chao Fang;Zhuwei Wang;Jining Chen;Shu-Ming Tseng;Mianxiong Dong","doi":"10.1109/TNSE.2025.3541746","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3541746","url":null,"abstract":"Metaverse, as a revolutionary technology that changes the way of human interaction, brings new challenges to content delivery services due to the extensive data transmission and personalized service requirements. To ensure a personalized user experiences while improving the utilization of heterogeneous network resources, a user-centric many-objective metaverse content delivery framework is proposed to optimize content delivery through user attention awareness. This framework addresses two key subproblems in metaverse content delivery by investigating user-centric many-objective cooperative content caching and deep reinforcement learning (DRL)-based request routing. The user-centric many-objective cooperative content caching is proposed to dynamically combine three basic preference prediction results to predict user preferences and control network resource allocation, which can simultaneously optimize prediction precision, delay, offloaded traffic, and load balancing. In DRL-based request routing, the reward function is designed to enable the optimization of multiple objectives. The multi-objective DRL routing algorithm is employed to continuously observe network states and make adaptive routing decisions in response to user requests. In the simulation, a movie dataset is employed to simulate user requests and support user attention awareness. The results show that the proposed content delivery framework outperforms existing basic prediction algorithms and other content delivery algorithms on four evaluation indicators.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1911-1925"},"PeriodicalIF":6.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving Matching Models With Contextual Attention for Multi-Turn Response Selection in Retrieval-Based Chatbots

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-13 DOI: 10.1109/TNSE.2025.3532663

Jingyu Wang;Bing Ma;Yafeng Nan;Yixiao He;Haifeng Sun;Cong Liu;Shimin Tao;Qi Qi;Jianxin Liao

{"title":"Improving Matching Models With Contextual Attention for Multi-Turn Response Selection in Retrieval-Based Chatbots","authors":"Jingyu Wang;Bing Ma;Yafeng Nan;Yixiao He;Haifeng Sun;Cong Liu;Shimin Tao;Qi Qi;Jianxin Liao","doi":"10.1109/TNSE.2025.3532663","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3532663","url":null,"abstract":"Multi-turn response selection is an important task in artificial intelligence. Early methods match each utterance with a response to obtain the matching information between utterance and response, then aggregate the matching vectors in chronological order. They are lightweight but ignore the dependencies between utterances, which is very important for mining useful matching information in utterance-response pair. Recently, some PLM-based methods can consider both relations between utterance and response and relations within utterances. However, they cost huge computational resource and suffer from loss of information due to the maximum length limit. In this research, we propose a lightweight, effective and low-loss method, CSMN. We initially expand the traditional attention to context-aware attention, making the model to dynamically learn complete matching information from response, utterance and context during the utterance-response matching. A hierarchical context-aware aggregation network is then applied for the further improvement of the proposed model. Experimental results on three large-scale dialogue datasets collected from social networks demonstrate the effectiveness of our proposed model. CSMN outperforms all traditional methods and is comparable to existing PLM-based methods with a extremely low cost of computational resource, which improves the response quality and user experience in multi-turn dialogue systems, and has important practical applications in resource-constrained environments.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1497-1509"},"PeriodicalIF":6.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic Event-Triggered Optimal Control for Heterogeneous Vehicle Platoon Based on Integral Reinforcement Learning

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-12 DOI: 10.1109/TNSE.2025.3540993

Yongming Li;Ying Xu;Kewen Li

引用次数: 0

Network Representation of Higher-Order Interactions Based on Information Dynamics

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-11 DOI: 10.1109/TNSE.2025.3540982

Gorana Mijatovic;Yuri Antonacci;Michal Javorka;Daniele Marinazzo;Sebastiano Stramaglia;Luca Faes

{"title":"Network Representation of Higher-Order Interactions Based on Information Dynamics","authors":"Gorana Mijatovic;Yuri Antonacci;Michal Javorka;Daniele Marinazzo;Sebastiano Stramaglia;Luca Faes","doi":"10.1109/TNSE.2025.3540982","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3540982","url":null,"abstract":"Many complex systems in science and engineering are modeled as networks whose nodes and links depict the temporal evolution of each system unit and the dynamic interaction between pairs of units, which are assessed respectively using measures of auto- and cross-correlation or variants thereof. However, a growing body of work is documenting that this standard network representation can neglect potentially crucial information shared by three or more dynamic processes in the form of higher-order interactions (HOIs). While several measures, mostly derived from information theory, are available to assess HOIs in network systems mapped by multivariate time series, none of them is able to provide a compact yet detailed representation of higher-order interdependencies. In this work, we fill this gap by introducing a framework for the assessment of HOIs in dynamic network systems at different levels of resolution. The framework is grounded on the dynamic implementation of the O-information, a new measure assessing HOIs in dynamic networks, which is here used together with its local counterpart and its gradient to quantify HOIs respectively for the network as a whole, for each link, and for each node. The integration of these measures into the conventional network representation results in a tool for the representation of HOIs <italic>as networks</i>, which is defined formally using measures of information dynamics, implemented in its linear version by using vector regression models and statistical validation techniques, illustrated in simulated network systems, and finally applied to an illustrative example in the field of network physiology.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1872-1884"},"PeriodicalIF":6.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Two-Timescale Hierarchical Contract for Joint Computation Offloading and Energy Management in Edge Computing System

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-11 DOI: 10.1109/TNSE.2025.3538779

Min Yan;Li Wang;Lianming Xu;Luyang Hou;Zhu Han

{"title":"Two-Timescale Hierarchical Contract for Joint Computation Offloading and Energy Management in Edge Computing System","authors":"Min Yan;Li Wang;Lianming Xu;Luyang Hou;Zhu Han","doi":"10.1109/TNSE.2025.3538779","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3538779","url":null,"abstract":"To mitigate the rising energy costs in edge computing, edge servers (ESs) can receive revenues from reducing their energy usage by contracting with virtual power plant (VPP). ESs also respond to user equipment (UE) by providing computation offloading services. However, such two-layer coordinated trading of computation offloading and energy management in a VPP-ES-UE architecture should address the information asymmetry issue and uncertain task arrivals, posing challenges to maximizing the stakeholders' utility. In this paper, we formulate the two-layer coordinated trading as a hierarchical contracting problem, which addresses the information asymmetry using two contract models. We design a VPP-ES energy contract on a large timescale and an ES-UE computation contract on a small timescale, where ESs need to coordinate the future task arrivals under the energy reduction target assigned by VPP. We construct a two-timescale virtual queue to achieve the energy reduction goal by the long-term queue stability constraint and employ Lyapunov optimization to transform the original problem into an online optimization problem without requiring future information. An online two-timescale hierarchical contract optimization algorithm is proposed to solve the transformed problem. The simulation results demonstrate that our method achieves higher social welfare compared to other benchmarks.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1745-1760"},"PeriodicalIF":6.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Federated Learning-Based Offset-Free Distributed Control of Nonlinear Networked Systems With Application to IIoT

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-11 DOI: 10.1109/TNSE.2025.3540643

Zeyuan Xu;Yujia Wang;Zhe Wu;Wei Xing Zheng;Cheng Hu

{"title":"Federated Learning-Based Offset-Free Distributed Control of Nonlinear Networked Systems With Application to IIoT","authors":"Zeyuan Xu;Yujia Wang;Zhe Wu;Wei Xing Zheng;Cheng Hu","doi":"10.1109/TNSE.2025.3540643","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3540643","url":null,"abstract":"Preserving data privacy in data-driven modeling for the Industrial Internet of Things (IIoT) has become critically important due to the susceptibility of communication data from numerous devices to cyber-attacks. Given its multi-subsystem integration, nonlinear interactions, and networking characteristics, IIoT can be modeled as nonlinear networked systems (NNSs). This paper presents a federated learning-based offset-free distributed control (FL-OFDC) method for NNSs with multiple subsystems to preserve data privacy and achieve offset-free control, with potential applications to IIoT. First, a novel FL algorithm with personalized optimization (FLPO) is proposed to simultaneously obtain global and local models using a simple algorithm framework, which can preserve data privacy and address the heterogeneity issue among subsystems. Subsequently, a novel information-theoretic bound for the generalization error of the FLPO algorithm with iteration properties is constructed using individual sample mutual information. Next, an FL-OFDC scheme for NNSs under external disturbances is developed to eliminate the offset, and its closed-loop stability criteria are derived. Finally, a chemical process network, that is, a specific case of IIoT, is employed to demonstrate the practicality of the FLPO and FL-OFDC methods.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1859-1871"},"PeriodicalIF":6.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tackling Data Mining Risks: A Tripartite Covert Channel Merging Blockchain and IPFS

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-10 DOI: 10.1109/TNSE.2025.3539909

Zhuo Chen;Liehuang Zhu;Peng Jiang;Jialing He;Zijian Zhang

{"title":"Tackling Data Mining Risks: A Tripartite Covert Channel Merging Blockchain and IPFS","authors":"Zhuo Chen;Liehuang Zhu;Peng Jiang;Jialing He;Zijian Zhang","doi":"10.1109/TNSE.2025.3539909","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3539909","url":null,"abstract":"Blockchain-based covert communication enables undetectable data transmission by constructing covert channels in blockchain networks. However, extant approaches require transactions carrying secret data to be permanently preserved in the public ledger, which cannot resist data mining. Besides, these solutions cost up to $48,169 to transmit 1-MegaByte (MB) data. In this paper, we introduce a Tripartite Covert Communication Model (TCCM), which amalgamates blockchain and the Inter Planetary File System (IPFS) to facilitate the transfer of MB-level files while simultaneously circumventing data mining. TCCM comprises an IPFS covert channel, a ledger-layer covert channel, and a network-layer covert channel. The IPFS covert channel transmits the initial secret data. The ledger-layer covert channel embeds a timestamp into the blockchain transaction, which governs the construction time of the network-layer covert channel. The network-layer covert channel conveys the content identifier of the secret data utilizing Bitcoin's inventory message. We further present a TCCM instantiation and formally prove its unobservability. We instant TCCM to evaluate its performance on the Bitcoin mainnet. We also discuss its scalability, real-world use cases, and ethical considerations. Experimental outcomes demonstrate that the proposed instantiation is unobservable and able to transmit 100-MB files at a cost of $1.47.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1831-1848"},"PeriodicalIF":6.7,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Model-Driven Deep Learning-Based Optimization of Downlink Precoding and Fronthaul Compression in Cell-Free MIMO Systems

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-10 DOI: 10.1109/TNSE.2025.3539824

Yijie Chen;Wenchao Xia;Shu Cai;Gan Zheng;Hongbo Zhu

{"title":"Model-Driven Deep Learning-Based Optimization of Downlink Precoding and Fronthaul Compression in Cell-Free MIMO Systems","authors":"Yijie Chen;Wenchao Xia;Shu Cai;Gan Zheng;Hongbo Zhu","doi":"10.1109/TNSE.2025.3539824","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3539824","url":null,"abstract":"Cell-free multiple-input multiple-output (MIMO) system is a promising solution for wireless communications. However, the potential in improving system performance is restricted due to the capacity-limited fronthaul links. To tackle this problem, we utilize the compress-and forward approach, which leverages various compression and encoding techniques to reduce the fronthaul overhead. Thus, jointly optimizing precoding and fronthaul compression presents a significant challenge. However, current optimization algorithms frequently entail high computational complexity because of their iterative processes, rendering impractical for real-time use. To overcome this challenge, we present a model-driven deep learning-based framework to characterize the structure of precoding vectors and the compression matrix via low-dimensional parameters, leveraging the uplink-downlink duality as the expert knowledge. A deep neural network can learn these low-dimensional “key features” from channel state information. Simulation results indicate that our approach achieves performance comparable to the optimal algorithm and substantially reduces complexity.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1804-1817"},"PeriodicalIF":6.7,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Communication-Efficient and Utility-Enhanced Local Differential Privacy-Based Personalized Federated Compressed Learning

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-07 DOI: 10.1109/TNSE.2025.3539008

Min Li;Di Xiao

{"title":"Communication-Efficient and Utility-Enhanced Local Differential Privacy-Based Personalized Federated Compressed Learning","authors":"Min Li;Di Xiao","doi":"10.1109/TNSE.2025.3539008","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3539008","url":null,"abstract":"With the deeper and broader research on federated learning (FL), several inescapable challenges arise when putting FL into practice. However, existing research works predominately concentrate on addressing one or two challenges. This paper seeks to provide a comprehensive exploration of four fundamental issues, namely privacy, utility, communication efficiency and data heterogeneity. To simultaneously address these issues, we propose a communication-efficient and utility-enhanced local differential privacy (LDP)-based personalized federated compressed learning (FCL) method, called CUEL-PFCL. First and foremost, a general FCL framework is proposed to compress local visual data (e.g., images) while preserving data learnability, which can provide a certain degree of visual-level privacy protection and improve the communication efficiency. Subsequently, an analytically tractable Gaussian differential privacy is applied to enhance the trade-off between privacy and utility. Meanwhile, compressed sensing and SIGNSGD are respectively used to compress and quantify model gradients to further reduce the communication overhead. Besides, we keep the head representation locally to reduce communication costs, achieve the privacy amplification effect and solve the issue of data heterogeneity. Theoretical privacy analysis, experimental simulations and comprehensive comparisons all demonstrate that CUEL-PFCL has four advantages, i.e., strong privacy, enhanced utility, efficient communication and various personalized models.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1776-1790"},"PeriodicalIF":6.7,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0