IEEE Transactions on Network Science and Engineering最新文献

{"title":"Joint Task Coding and Transfer Optimization for Edge Computing Power Networks","authors":"Jiajia Liu;Yunlong Lu;Hao Wu;Bo Ai;Abbas Jamalipour;Yan Zhang","doi":"10.1109/TNSE.2025.3554100","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3554100","url":null,"abstract":"Driven by the exponential growth of the Internet of Everything (IoE) and substantial advancements in artificial intelligence, services based on deep learning have seen a significant increase in demand for computing resources. The existing edge computing paradigms struggle to handle the explosive growth in computing demands. They also face challenges in jointly optimizing the high transmission load and privacy concerns of task collaboration while failing to utilize computing resources efficiently in complex and dynamic computing power networks. In this paper, we investigate an edge computing power network framework that integrates heterogeneous computing resources from both horizontal and vertical dimensions. We formulate a collaborative task transfer problem to minimize the total execution time of multiple tasks by joint optimization task coding, computing-task association, and collaborative transfer computing strategies among nodes. To solve the formulated problem, we conduct in-depth theoretical analyses and design a two-layer multi-agent optimization algorithm. Specifically, the task coding problem is reformulated in the inner layer into a solvable form, and a closed-form expression for the task coding ratio is derived. Subsequently, we design an adaptive hybrid reward-based multi-agent deep reinforcement learning algorithm to address the sparsity challenges of single-layer rewards while ensuring efficient and stable training convergence. Numerical results show the superiority of our proposed algorithm.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2783-2796"},"PeriodicalIF":6.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492251","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}

{"title":"Delay-Aware Robust Edge Network Hardening Under Decision-Dependent Uncertainty","authors":"Jiaming Cheng;Duong Thuy Anh Nguyen;Ni Trieu;Duong Tung Nguyen","doi":"10.1109/TNSE.2025.3548020","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3548020","url":null,"abstract":"Edge computing promises to offer low-latency and ubiquitous computation to numerous devices at the network edge. For delay-sensitive applications, link delays significantly affect service quality. These delays can fluctuate substantially over time due to various factors such as network congestion, changing traffic conditions, cyberattacks, component failures, and natural disasters. Thus, it is crucial to efficiently harden the edge network to mitigate link delay variation and ensure a stable and improved user experience. To this end, we propose a novel robust model for optimal edge network hardening, considering link delay uncertainty. Unlike existing literature that treats uncertainties as exogenous, our model incorporates an endogenous uncertainty set to properly capture the impact of hardening and workload allocation decisions on link delays. However, the endogenous set introduces additional complexity to the problem due to the interdependence between decisions and uncertainties. To address this, we present two efficient methods to transform the problem into a solvable form. Extensive numerical results demonstrate the effectiveness of the proposed approach in mitigating delay variations and enhancing system performance.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"2388-2401"},"PeriodicalIF":6.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871101","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}

{"title":"DeepAW: A Customized DNN Watermarking Scheme Against Unreliable Participants","authors":"Shen Lin;Xiaoyu Zhang;Xu Ma;Xiaofeng Chen;Willy Susilo","doi":"10.1109/TNSE.2025.3553673","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3553673","url":null,"abstract":"Training DNNs requires large amounts of labeled data, costly computational resources, and tremendous human effort, resulting in such models being a valuable commodity. In collaborative learning scenarios, unreliable participants are widespread due to data collected from a diverse set of end-users that differ in quality and quantity. It is important to note that failure to take into account the contributions of all participants in the collaborative model training process when sharing the model with them could potentially result in a deterioration in collaborative efforts. In this paper, we propose a customized DNN watermarking scheme to safeguard the model ownership, namely <italic>DeepAW</i>, achieving robustness to model stealing attacks and collaborative fairness in the presence of unreliable participants. Specifically, <italic>DeepAW</i> leverages the tightly binding between the embedded watermarking and the model performance to defend against the model stealing attacks, resulting in the sharp decline of the model performance encountering any attempt at watermarking modification. <italic>DeepAW</i> achieves collaborative fairness by detecting unreliable participants and customizing the model performance according to the participants' contributions. Furthermore, we set up three model stealing attacks and four types of unreliable participants. The experimental results demonstrate the effectiveness, robustness, and collaborative fairness of <italic>DeepAW</i>.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2758-2769"},"PeriodicalIF":6.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502909","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}

{"title":"Privacy-Preserving Graph Inference Network for Multi-Entity Wind Power Forecast: A Federated Learning Approach","authors":"Xinxin Long;Yizhou Ding;Yuanzheng Li;Yang Li;Liang Gao;Zhigang Zeng","doi":"10.1109/TNSE.2025.3547227","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3547227","url":null,"abstract":"Data sharing is considered by many wind farm stakeholders as the cause of privacy issues and further financial risks, despite its potential to enhance the accuracy of multi-entity wind power forecasting (MWPF). Federated learning (FL) serves as a possible solution to preserve the privacy in MWPF, while the existing FL-based methods still struggle to obtain accurate prediction due to the intricate spatial dependencies and heterogeneous temporal dependencies. In response to these two challenges, this paper proposes a collaborative privacy-preserving framework (CPLF) for MWPF. Within the CPLF, a graph learning-based local model named graph inference network (GIN) is developed to learn local features and obtain the global ones through aggregation. In terms of the spatial dependencies, a structure-independent dynamic graph inference (SiDGI) block is designed to extract spatial features via learnable directed graph representation. Regarding the heterogeneous temporal dependencies, the GIN, with its encoder-decoder to distill general temporal pattern, is trained following a customized FL procedure to effectively extract entity-specific temporal features. This customization can mitigate the communication burden and reverse-engineer risks while yielding improvements in MWPF accuracy. Finally, the extensive experiments are implemented based on two datasets collected from the Northwest and Southeast of California. The superiority of the proposed privacy-preserving MWPF method is verified compared with some classical methods. Specially, for graph attention, MWPF achieves 6.8% and 14.9% average improvements in mean absolute percentage error (MAPE).","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2428-2444"},"PeriodicalIF":6.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492341","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}

{"title":"Accelerated Optimized Topology Design in Affine Formation Control Using ADMM","authors":"Yumeng Wang;Qingkai Yang;Fan Xiao;Hao Fang;Jie Chen","doi":"10.1109/TNSE.2025.3552979","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3552979","url":null,"abstract":"This paper studies the problem of topology design for activating affine formation control schemes. The affine formation control exhibits its unique feature as it relies on the stress matrix to dynamically maneuver the whole formation by controlling a small number of agents. Network properties of interest for this design problem generally give rise to optimization formulations within the framework of mixed-integer semidefinite programming (MISDP), resulting in computational inefficiency and NP-hardness. Firstly, to avoid introducing binary variables, the optimization of communication cost is modeled as an <inline-formula><tex-math>$l_{1}$</tex-math></inline-formula>-regularized network sparsity problem. In this way, an optimized topology design method accelerated by the alternating direction method of multipliers (ADMM) is proposed to obtain the stress matrix with low communication cost, fast convergence speed and high tolerance to time-delay. Furthermore, addressing scenarios irrespective of whether the minimum eigenvalue of the stress matrix is prescribed, we propose two enhanced ADMM-based algorithms with closed-form solutions. This is achieved through the transformation of semi-definite constraints in the subproblem into equality constraints. Finally, comparative simulations demonstrate the accelerated effects of the proposed scheme, showcasing its effectiveness in interaction topology construction and optimization for large-scale networks.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2694-2707"},"PeriodicalIF":6.7,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492419","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}

{"title":"DDPS: Dynamic Differential Pricing-Based Edge Offloading System With Energy Harvesting Devices","authors":"Hai Xue;Yun Xia;Neal N. Xiong;Di Zhang;Songwen Pei","doi":"10.1109/TNSE.2025.3550251","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3550251","url":null,"abstract":"Mobile edge computing (MEC) mitigates the energy and computation burdens on mobile users (MUs) by offloading tasks to the network edge. To optimize MEC server utilization through effective resource allocation, a well-designed pricing strategy is indispensable. In this paper, we propose a dynamic differential pricing scheme (DDPS) for an edge offloading scenario with energy harvesting devices, which determines prices based on computing resource usage to enhance edge server (ES) utilization. First, an offloading decision algorithm is proposed to balance harvested and consumed energy, determining whether and how much data to offload. Second, a Stackelberg game-based differential pricing algorithm is proposed to optimize computing resource allocation for MUs and reallocate surplus resources to delay-sensitive devices. Extensive simulations are conducted to demonstrate the effectiveness of the proposed DDPS scheme. Specifically, in comparison to the existing best-performing pricing scheme, for different task arrival rates, DDPS can achieve a 5.3% decrease in average execution delay, a 1.7% increase in ES utility (<inline-formula><tex-math>$U_{text{server}}$</tex-math></inline-formula>, which represents the payment from MUs minus penalties for discarded tasks), and a 2.1% increase in the average ratio of service for MUs. In addition, DDPS also improves 2.8% <inline-formula><tex-math>$U_{text{server}}$</tex-math></inline-formula> on average with different ES computation capacities.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2549-2565"},"PeriodicalIF":6.7,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492257","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}

{"title":"Enhanced ISAC Framework for Moving Target Assisted by Beyond-Diagonal RIS: Accurate Localization and Efficient Communication","authors":"Dawei Wang;Zijun Wang;Weichao Yang;Hongbo Zhao;Yixin He;Li Li;Zhongxiang Wei;Fuhui Zhou","doi":"10.1109/TNSE.2025.3571278","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3571278","url":null,"abstract":"This paper proposes an innovative Integrated Sensing and Communication (ISAC) framework for moving target detection by leveraging beyond-diagonal RIS (BD-RIS) to improve beamforming performance and control wireless propagation. In this framework, we first design a novel target-tracking method for moving target detection based on Extended Kalman Filtering (EKF) with accurate cooperative localization. In addition, to further improve the sensing accuracy, we minimize the joint posterior Cramér-Rao bound (PCRB) for both target position and velocity constrained by the communication performance requirements, and maintain the orthogonality and symmetry constraints of BD-RIS. Given the non-convex nature of the problem, we break it into two subproblems, which are solved iteratively using the proposed alternating optimization (AO) algorithm. The AO algorithm incorporates a semidefinite relaxation (SDR) method for beamforming and a penalty dual decomposition (PDD) approach for BD-RIS optimization. The simulation results demonstrate that: (1) the proposed prediction method accurately tracks the position and velocity of the target in dynamic environments; (2) the proposed AO algorithm is efficient and effective, exhibiting fast convergence and achieving a performance improvement of 6.7<inline-formula><tex-math>$%$</tex-math></inline-formula> compared to conventional diagonal RIS.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"4299-4315"},"PeriodicalIF":7.9,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891136","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}

{"title":"Quantum-Resistant Secure Communication Protocol for Digital Twin-Enabled Context-Aware IoT-Based Healthcare Applications","authors":"Basudeb Bera;Ashok Kumar Das;Biplab Sikdar","doi":"10.1109/TNSE.2025.3553044","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3553044","url":null,"abstract":"Digital Twins (DTs) play a crucial role in context-aware Internet of Things (IoT) applications within the healthcare sector, including the industrial healthcare domain, by facilitating the continuous sharing of sensitive and confidential patient data from physical objects in real time. This shared data is essential for treatment planning and decision-making processes, often being accessed remotely by authorized users. However, traditional security mechanisms, which rely on the integer factorization problem (IFP) and the elliptic curve discrete logarithm problem (ECDLP), are vulnerable to quantum attacks using algorithms like Shor's, posing significant risks to data protection. As a result, the healthcare sector faces several security challenges, including the vulnerability of sensitive patient data to cyberattacks, quantum threats, the risk of unauthorized access to medical devices and IoT systems, and the increasing sophistication of cybercriminals exploiting weak authentication methods. To address these issues, we propose a quantum-resistant protocol that safeguards data privacy in DT-enabled IoT healthcare applications, ensures secure transmission of information, maintains patient trust, supports long-term data confidentiality, and protects medical devices and IoT systems from potential breaches. By employing lattice-based cryptographic techniques, particularly the ring learning with errors (RLWE) problem, the proposed scheme effectively addresses contemporary security challenges, including those posed by quantum computing. Real-time experiments conducted on Raspberry Pi 4 devices, along with computational overhead analysis, demonstrate the protocol's efficiency. Additionally, formal security validation using the Scyther tool and security analysis with the RoR model reinforce the robustness of the proposed protocol. A comprehensive comparative evaluation against existing schemes highlights its lightweight, scalable, and efficient nature. Furthermore, performance evaluations in the context of unknown attacks show that the proposed scheme significantly outperforms current alternatives in terms of effectiveness.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2722-2738"},"PeriodicalIF":6.7,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492408","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}

{"title":"Timeliness-Aware Computation Offloading Strategies for IIoT Networks","authors":"Tan Zheng Hui Ernest;A S Madhukumar","doi":"10.1109/TNSE.2025.3570379","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3570379","url":null,"abstract":"This paper investigates the peak age of information (PAoI) violation probability and mean PAoI of computation offloading strategies in multi-access edge computing-enabled (MEC-enabled) industrial Internet-of-Things (IIoT) networks. In particular, a comprehensive PAoI analysis framework for computation offloading strategies is proposed in this work. Through closed-form cumulative distribution function (CDF) expressions derived for received signal-to-interference-plus-noise ratios (SINRs) and PAoI arising from tandem M/M/1 queues, new closed-form expressions for PAoI violation probability and mean PAoI are obtained for the uplink timeliness-aware (UTA), joint uplink-and-computing timeliness-aware (JUCTA), and cloud-only (CL) computation offloading strategies. Extensive analysis demonstrate that the proposed UTA and JUCTA strategies outperform the CL strategy in MEC-enabled IIoT networks and are thus viable to support mission-critical IIoT applications. Crucially, it is also shown that the PAoI violation probability and mean PAoI of the considered computation offloading strategies hinges greatly on computation delay, communications radius, and task generation rates.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"4239-4254"},"PeriodicalIF":7.9,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891289","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}

{"title":"Contrastive Learning for Multi-Layer Network Community Detection via Learnable Network Augmentation","authors":"Min Teng;Ze Yin;Jiajin Huang;Chao Gao;Xianghua Li;Vladimir Nekorkin;Zhen Wang","doi":"10.1109/TNSE.2025.3570354","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3570354","url":null,"abstract":"Community detection in multi-layer networks is crucial for revealing the functions of entities and understanding their connections across dimensions. However, existing semi-supervised methods often rely on manual labels, leading to the significant computational overhead in networks with complex structures. Moreover, unsupervised and self-supervised methods usually struggle to integrate the intra-layer and inter-layer features, as well as the local and global features of networks, resulting in the limited accuracy. To address these challenges, this paper proposes a self-supervised <underline>N</u>etwork <underline>A</u>ugmentation <underline>C</u>ontrastive <underline>C</u>onstraint (NACC) method for multi-layer network community detection. Leveraging the ideas of network augmentation and contrastive learning, NACC detects the community structure based on the rich features contained in datasets. Specifically, NACC first integrates the intra-layer and inter-layer features of the multi-layer network to generate a learnable feature-augmented network. Then, it encodes the node and topology features, capturing both the local and global features, and generating the low-dimensional node representations for multi-layer and augmented networks. Moreover, the contrastive learning among different layers is proposed to train the above node representations, further enhancing the fusion of features. Finally, consense communities are detected based on the trained node representation. Extensive experiments demonstrate the performance of NACC in handling networks with numerous layers and complex structures, showcasing its reliability in real-world applications.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"4227-4238"},"PeriodicalIF":7.9,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891290","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}