Pub Date : 2025-12-26DOI: 10.1109/TNSE.2025.3648844
Changbing Bi;Yue Cao;Yanzhen Ren;Youliang Tian;Lin Wan;Wei Ke
With the rapid development of the Electric Vehicle (EV) market, the growing demand for electricity charging has driven the evolution of private charging infrastructure toward shared deployment. Shared Charging Systems (SCSs) play a vital role in integrating both private and public Charging Piles (CPs), thereby improving overall resource utilization. However, such multi-party SCSs introduce challenges in security and fairness. EVs and CPs exchange parameters via wireless communication to optimize the charging process, which may exposes various threats such as tampering, eavesdropping, replay, and deletion attacks. Meanwhile, the distributed deployment of CPs complicates charging fee calculation management and may lead to issues such as malicious overcharging. To address these challenges, we propose a blockchain-enabled secure authentication and fair trading scheme, ensuring secure communication while guaranteeing transparency and fairness for SCSs. First, we design a pairing-free heterogeneous signcryption algorithm that supports distributed key generation. It realizes efficient mutual authentication based on this algorithm while preventing information leakage during the process. We provide a rigorous security proof under the Random Oracle Model (ROM) to establish its security. Second, we develop a blockchain-based smart contract mechanism to enable decentralized and transparent charging fee calculation, as well as automated payments. By eliminating third-party intermediaries, our solution reduces trading costs whle effectively addresses challenges such as charging fee calculation difficulties and malicious overcharging in distributed CP deployments. Experimental results show that the proposed scheme outperforms existing approaches in terms of both computational and communication overhead. Additionally, our smart contracts incur extremely low gas costs, enhancing the feasibility of the scheme.
{"title":"A Blockchain-Enabled Secure Authentication and Fair Trading Scheme for Shared Charging Systems","authors":"Changbing Bi;Yue Cao;Yanzhen Ren;Youliang Tian;Lin Wan;Wei Ke","doi":"10.1109/TNSE.2025.3648844","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3648844","url":null,"abstract":"With the rapid development of the Electric Vehicle (EV) market, the growing demand for electricity charging has driven the evolution of private charging infrastructure toward shared deployment. Shared Charging Systems (SCSs) play a vital role in integrating both private and public Charging Piles (CPs), thereby improving overall resource utilization. However, such multi-party SCSs introduce challenges in security and fairness. EVs and CPs exchange parameters via wireless communication to optimize the charging process, which may exposes various threats such as tampering, eavesdropping, replay, and deletion attacks. Meanwhile, the distributed deployment of CPs complicates charging fee calculation management and may lead to issues such as malicious overcharging. To address these challenges, we propose a blockchain-enabled secure authentication and fair trading scheme, ensuring secure communication while guaranteeing transparency and fairness for SCSs. First, we design a pairing-free heterogeneous signcryption algorithm that supports distributed key generation. It realizes efficient mutual authentication based on this algorithm while preventing information leakage during the process. We provide a rigorous security proof under the Random Oracle Model (ROM) to establish its security. Second, we develop a blockchain-based smart contract mechanism to enable decentralized and transparent charging fee calculation, as well as automated payments. By eliminating third-party intermediaries, our solution reduces trading costs whle effectively addresses challenges such as charging fee calculation difficulties and malicious overcharging in distributed CP deployments. Experimental results show that the proposed scheme outperforms existing approaches in terms of both computational and communication overhead. Additionally, our smart contracts incur extremely low gas costs, enhancing the feasibility of the scheme.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"5603-5621"},"PeriodicalIF":7.9,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026430","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}
Pub Date : 2025-12-23DOI: 10.1109/TNSE.2025.3647512
Rong Wang;Runyu Mao;Tao Wen;Shihong Wei;Qian Li;Yunpeng Xiao
In social networks, the accurate detection of guided topics is of great significance for maintaining the healthy order of the network. Aiming at the high-dimensionality of its feature space and the hiddenness of users' emotions, a guided topic detection method based on data enhancement and feature representation is proposed. Firstly, to address the problem of sparse effective data and high-dimensional heterogeneity in the early stage of guided topic, GAN network is introduced to realize homomorphic compensation of data and enhance data diversity. Meanwhile, the SC2vec method is designed to realize the low-rank densification of data. In addition, random wandering is introduced to mine the implicit association network among users and to realize the fusion of multi-dimensional information. Secondly, to address the problem of the hidden nature of users' emotional polarity, the internal attributes and external influences of users are mined. The fine-grained emotional influence factors based on linear multiple regression are constructed. At the same time, the evolutionary game theory is introduced to build an emotional interaction game model between users to reveal the dynamic evolution law of users' emotions. The experimental results show that the method not only successfully realizes the low-rank densification of data and the deep mining of implicit user emotions, but also achieves significant improvement in the accuracy of guided topic detection.
{"title":"A Guided Topic Detection Model Based on Data Augmentation and Feature Representation","authors":"Rong Wang;Runyu Mao;Tao Wen;Shihong Wei;Qian Li;Yunpeng Xiao","doi":"10.1109/TNSE.2025.3647512","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3647512","url":null,"abstract":"In social networks, the accurate detection of guided topics is of great significance for maintaining the healthy order of the network. Aiming at the high-dimensionality of its feature space and the hiddenness of users' emotions, a guided topic detection method based on data enhancement and feature representation is proposed. Firstly, to address the problem of sparse effective data and high-dimensional heterogeneity in the early stage of guided topic, GAN network is introduced to realize homomorphic compensation of data and enhance data diversity. Meanwhile, the SC2vec method is designed to realize the low-rank densification of data. In addition, random wandering is introduced to mine the implicit association network among users and to realize the fusion of multi-dimensional information. Secondly, to address the problem of the hidden nature of users' emotional polarity, the internal attributes and external influences of users are mined. The fine-grained emotional influence factors based on linear multiple regression are constructed. At the same time, the evolutionary game theory is introduced to build an emotional interaction game model between users to reveal the dynamic evolution law of users' emotions. The experimental results show that the method not only successfully realizes the low-rank densification of data and the deep mining of implicit user emotions, but also achieves significant improvement in the accuracy of guided topic detection.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"5110-5127"},"PeriodicalIF":7.9,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929381","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}
Pub Date : 2025-12-22DOI: 10.1109/TNSE.2025.3645073
Qianqian Cai;Tong Wang;Mali Xing;Yanyan Ye;Minyue Fu
Community detection is capable of uncovering the inherent structure and functional organization within complex networks by analyzing multi-scale topological features. According to the brief survey, local detection methods demonstrate notable strengths, but challenges persist in selecting suitable seeds, identifying community cores, and precisely extending communities. Therefore, in this paper, a local community detection algorithm based on identifying high-quality core region is proposed. Specifically, at the seed selection stage, a core cohesiveness index is constructed to quantify the node importance, with two-step filtering strategy implemented to refine the selection of suitable seeds. After that, a hierarchical affinity evaluation mechanism is proposed on the basis of node-core affinity values to ensure the formation of high-quality core region (i.e., high-quality initial community). Community extension is then achieved by using the enhanced objective function combined with an incremental update strategy, it preserves structural cohesion and reduces computational costs. Finally, the membership assignments of the remaining nodes will be further processed through community optimization to refine community boundaries. Experimental results demonstrate that our proposed algorithm outperforms other community detection algorithms with relatively low time complexities across multi-scale real-world and synthetic networks.
{"title":"Local Community Detection in Complex Networks: A Brief Survey and an Algorithm Based on Identifying High-Quality Core Region","authors":"Qianqian Cai;Tong Wang;Mali Xing;Yanyan Ye;Minyue Fu","doi":"10.1109/TNSE.2025.3645073","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3645073","url":null,"abstract":"Community detection is capable of uncovering the inherent structure and functional organization within complex networks by analyzing multi-scale topological features. According to the brief survey, local detection methods demonstrate notable strengths, but challenges persist in selecting suitable seeds, identifying community cores, and precisely extending communities. Therefore, in this paper, a local community detection algorithm based on identifying high-quality core region is proposed. Specifically, at the seed selection stage, a core cohesiveness index is constructed to quantify the node importance, with two-step filtering strategy implemented to refine the selection of suitable seeds. After that, a hierarchical affinity evaluation mechanism is proposed on the basis of node-core affinity values to ensure the formation of high-quality core region (i.e., high-quality initial community). Community extension is then achieved by using the enhanced objective function combined with an incremental update strategy, it preserves structural cohesion and reduces computational costs. Finally, the membership assignments of the remaining nodes will be further processed through community optimization to refine community boundaries. Experimental results demonstrate that our proposed algorithm outperforms other community detection algorithms with relatively low time complexities across multi-scale real-world and synthetic networks.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"5489-5504"},"PeriodicalIF":7.9,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026475","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}
Space-Air-Ground Integrated Networks (SAGIN) have been recognized as key enablers of 6G systems for ubiquitous service provisioning, unlocking Internet of Things (IoT) applications in geographically dispersed areas. In this paper, we study the problem of computation task offloading for remotely deployed IoT devices to either a limited-capability Uncrewed Aerial Vehicle (UAV)-mounted Multi-access Edge Computing (MEC) server or a cloud server via satellite relaying. The problem is formulated as a non-cooperative game, where each IoT device autonomously determines the percentage of task offloaded to each server to minimize the aggregate time and energy overhead due to transmissions and remote processing. Diverging from the prevailing literature, in this paper, we model the IoT devices' risk-seeking and loss-averse behavior in sharing the common pools of computing resources, i.e., cloud and MEC server. By incorporating risk-consciousness in their computation offloading decision-making, IoT devices strive to balance the total incurred overhead with the likelihood of task rejection due to overexploitation of limited shared edge resources. To this end, the IoT devices' utility function is modeled using Prospect Theory and Tragedy of the Commons. Two solutions based on normal and satisfaction-form games are derived, targeting to maximize or achieve a minimum value for the prospect-theoretic utility, providing insights from both device and system perspectives, respectively. Numerical results show the effectiveness of the overall risk-conscious computing framework in the achieved time and energy overhead, as well as task probability of failure.
{"title":"Risk-Conscious Computing in Space-Air-Ground IoT Networks: A Prospect-Theoretic Game Perspective","authors":"Panagiotis Charatsaris;Maria Diamanti;Eirini Eleni Tsiropoulou;Symeon Papavassiliou","doi":"10.1109/TNSE.2025.3647157","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3647157","url":null,"abstract":"Space-Air-Ground Integrated Networks (SAGIN) have been recognized as key enablers of 6G systems for ubiquitous service provisioning, unlocking Internet of Things (IoT) applications in geographically dispersed areas. In this paper, we study the problem of computation task offloading for remotely deployed IoT devices to either a limited-capability Uncrewed Aerial Vehicle (UAV)-mounted Multi-access Edge Computing (MEC) server or a cloud server via satellite relaying. The problem is formulated as a non-cooperative game, where each IoT device autonomously determines the percentage of task offloaded to each server to minimize the aggregate time and energy overhead due to transmissions and remote processing. Diverging from the prevailing literature, in this paper, we model the IoT devices' risk-seeking and loss-averse behavior in sharing the common pools of computing resources, i.e., cloud and MEC server. By incorporating risk-consciousness in their computation offloading decision-making, IoT devices strive to balance the total incurred overhead with the likelihood of task rejection due to overexploitation of limited shared edge resources. To this end, the IoT devices' utility function is modeled using Prospect Theory and Tragedy of the Commons. Two solutions based on normal and satisfaction-form games are derived, targeting to maximize or achieve a minimum value for the prospect-theoretic utility, providing insights from both device and system perspectives, respectively. Numerical results show the effectiveness of the overall risk-conscious computing framework in the achieved time and energy overhead, as well as task probability of failure.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"5056-5073"},"PeriodicalIF":7.9,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929526","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}
Pub Date : 2025-12-18DOI: 10.1109/TNSE.2025.3645935
Anh-Tien Tran;Thanh Phung Truong;Dongwook Won;Nhu-Ngoc Dao;Sungrae Cho
Rate-splitting multiple access (RSMA) and successive interference cancellation (SIC) are essential approaches in the next-generation communication systems that boost spectrum efficiency by effectively managing and mitigating interference between multiple signals. However, a challenge arises in ensuring that users can distinguish the common message from the remaining non-decoded private messages without considering a separate SIC constraint per user. This imperfection cancellation leads to residual interference from the common stream that remains in the received signal. This work investigates the maximization of the weighted sum-rate (WSR) in single-layer RSMA multiple input single output (MISO) downlink network by proposing explicit SIC constraints. In particular, we suggest an approach that initially addresses the critical problem of allocating power and precoding vectors for streams using a deep reinforcement learning (DRL) method, and then determines the user-specific allocations within the common rate to meet the criteria of users’ minimum rate by solving a linear programming problem. Simulation results exhibit the supremacy of the proposed DRL framework over SDMA and other DRL approaches in terms of spectral efficiency leading to an improvement of approximately 30% of WSR in several scenarios.
{"title":"Weighted Sum-Rate Maximization in Rate-Splitting MISO Downlink Systems","authors":"Anh-Tien Tran;Thanh Phung Truong;Dongwook Won;Nhu-Ngoc Dao;Sungrae Cho","doi":"10.1109/TNSE.2025.3645935","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3645935","url":null,"abstract":"Rate-splitting multiple access (RSMA) and successive interference cancellation (SIC) are essential approaches in the next-generation communication systems that boost spectrum efficiency by effectively managing and mitigating interference between multiple signals. However, a challenge arises in ensuring that users can distinguish the common message from the remaining non-decoded private messages without considering a separate SIC constraint per user. This imperfection cancellation leads to residual interference from the common stream that remains in the received signal. This work investigates the maximization of the weighted sum-rate (WSR) in single-layer RSMA multiple input single output (MISO) downlink network by proposing explicit SIC constraints. In particular, we suggest an approach that initially addresses the critical problem of allocating power and precoding vectors for streams using a deep reinforcement learning (DRL) method, and then determines the user-specific allocations within the common rate to meet the criteria of users’ minimum rate by solving a linear programming problem. Simulation results exhibit the supremacy of the proposed DRL framework over SDMA and other DRL approaches in terms of spectral efficiency leading to an improvement of approximately 30% of WSR in several scenarios.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"5522-5538"},"PeriodicalIF":7.9,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026386","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}
Pub Date : 2025-12-18DOI: 10.1109/TNSE.2025.3645802
Zeyu Liu;Shuai Wang;Rui Zhang;Zhe Song;Gaofeng Pan
With the deep evolution of satellite communication technologies and hierarchical hybrid networks (HHSNs), modern communication satellites have transformed from single-function relay nodes into core hubs enabling global interconnectivity. The dynamic topology, open-channel environment, and resource limitations inherent to HHSN expose satellite routing protocols to the challenges of the Reliability-Security-Efficiency (RSE) trilemma. In this paper, we provide a systematic review of advancements in HHSN routing research, analyzing core technical challenges through the lens of typical application scenarios while highlighting the divergent performance of various solutions under the RSE trilemma. To the best of our knowledge, we are the first to analyze the performance of HHSN routing protocols within the framework of the RSE theory. Existing reviews either treat routing merely as a component of broader surveys or lack analysis based on the RSE trilemma framework. Building on our review of HHSN routing protocols, we discuss the topology description and security aspects of HHSN and propose potential directions for future HHSN routing research.
{"title":"Routing in Hierarchical Hybrid Satellite Networks: A Survey","authors":"Zeyu Liu;Shuai Wang;Rui Zhang;Zhe Song;Gaofeng Pan","doi":"10.1109/TNSE.2025.3645802","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3645802","url":null,"abstract":"With the deep evolution of satellite communication technologies and hierarchical hybrid networks (HHSNs), modern communication satellites have transformed from single-function relay nodes into core hubs enabling global interconnectivity. The dynamic topology, open-channel environment, and resource limitations inherent to HHSN expose satellite routing protocols to the challenges of the Reliability-Security-Efficiency (RSE) trilemma. In this paper, we provide a systematic review of advancements in HHSN routing research, analyzing core technical challenges through the lens of typical application scenarios while highlighting the divergent performance of various solutions under the RSE trilemma. To the best of our knowledge, we are the first to analyze the performance of HHSN routing protocols within the framework of the RSE theory. Existing reviews either treat routing merely as a component of broader surveys or lack analysis based on the RSE trilemma framework. Building on our review of HHSN routing protocols, we discuss the topology description and security aspects of HHSN and propose potential directions for future HHSN routing research.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"4883-4911"},"PeriodicalIF":7.9,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145879961","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}
The Internet of Medical Things (IoMT) consists of many resource-constrained medical devices that provide patients with medical services anytime and anywhere. In such an environment, the collection and sharing of medical records raise serious security concerns. Although various cryptographic schemes have been proposed, most fail to address two critical threats simultaneously: (i) sensitive data exposure caused by external cloud servers and/or open network environments; (ii) algorithm substitution attacks (ASAs) by internal adversaries. Furthermore, when data owners (e.g., delegators) are inconvenient to process their data, it is desirable to establish a more fine-grained way to delegate encryption rights. To tackle these issues, we propose a subversion-resistant autonomous path proxy re-encryption with an equality test function (SRAP-PRET). Specifically, our scheme allows the delegator to create a multi-hop delegation path in advance with the delegator's preferences, effectively preventing unauthorized access. By deploying a cryptographic reverse firewall zone, SRAP-PRET addresses the problem of information leakage caused by adversaries initiating ASAs. Additionally, SRAP-PRET also supports secure deduplication and efficient data decryption. Security analysis shows that SRAP-PRET provides resistance against ASAs and security against chosen plaintext attacks. Performance evaluations demonstrate that SRAP-PRET offers enhanced security properties without sacrificing efficiency.
{"title":"Subversion-Resistant Autonomous Path Proxy Re-Encryption With Secure Deduplication for IoMT","authors":"Jiasheng Chen;Zhenfu Cao;Lulu Wang;Jiachen Shen;Zehui Xiong;Xiaolei Dong","doi":"10.1109/TNSE.2025.3645991","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3645991","url":null,"abstract":"The Internet of Medical Things (IoMT) consists of many resource-constrained medical devices that provide patients with medical services anytime and anywhere. In such an environment, the collection and sharing of medical records raise serious security concerns. Although various cryptographic schemes have been proposed, most fail to address two critical threats simultaneously: (i) sensitive data exposure caused by external cloud servers and/or open network environments; (ii) algorithm substitution attacks (ASAs) by internal adversaries. Furthermore, when data owners (e.g., delegators) are inconvenient to process their data, it is desirable to establish a more fine-grained way to delegate encryption rights. To tackle these issues, we propose a subversion-resistant autonomous path proxy re-encryption with an equality test function (SRAP-PRET). Specifically, our scheme allows the delegator to create a multi-hop delegation path in advance with the delegator's preferences, effectively preventing unauthorized access. By deploying a cryptographic reverse firewall zone, SRAP-PRET addresses the problem of information leakage caused by adversaries initiating ASAs. Additionally, SRAP-PRET also supports secure deduplication and efficient data decryption. Security analysis shows that SRAP-PRET provides resistance against ASAs and security against chosen plaintext attacks. Performance evaluations demonstrate that SRAP-PRET offers enhanced security properties without sacrificing efficiency.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"5551-5567"},"PeriodicalIF":7.9,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026403","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}
With the increasing deployment of environment-aware services in the Internet of Vehicles (IoV), vehicles are required to execute multiple computational tasks in real time. However, resource allocation and task offloading in unmanned aerial vehicles (UAVs)-assisted IoV systems remain challenging due tothe growing number of vehicle terminals (VTs), potential privacy leakage, and resource-constrained edge devices. This paper proposes a digital twin (DT) and generative artificial intelligence (GAI)-powered hierarchical aerial-ground cooperative architecture (DTG-HACA) that achieves dynamic resource optimization through a three-layer framework. The DT layer enables real-time synchronization of vehicle/UAV states and simulated trajectory planning. The high altitude platforms (HAPs) layer provides low-latency offloading channels through stratospheric wide-area coverage and solar-powered endurance, while the physical entity layer executes energy-efficient edge computing via UAV-vehicle-roadside units (RSUs) collaboration. For UAV trajectory optimization, we introduce the multi-agent deep deterministic policy gradient (MADDPG)-improved prioritized experience replay (MADDPG-IPER) algorithm that minimizes communication overhead and energy consumption while integrating DT-simulated trajectory planning. For the joint challenge of edge caching and task offloading under privacy preservation constraints, we develop a federated deep reinforcement learning (FDRL) based generative adversarial network (FDRL-GAN) algorithm. This solution addresses critical challenges in dynamic task offloading and resource allocation for UAV-assisted IoV by leveraging GAI to predict task demands for cache hit rate optimization, while implementing FDRL for distributed privacy-preserving decision-making without raw data sharing, thereby achieving global resource allocation optimality. Extensive simulation experiments confirm that our proposed scheme demonstrates significant advantages over existing benchmark algorithms across five critical performance metrics, including training stability, computational capacity, task offloading efficiency, cache hit rate, and energy consumption.
{"title":"UAV-Assisted Task Offloading and Resource Allocation in Internet of Vehicles: An Integration of Digital Twin and Generative AI","authors":"Xing Wang;Chao He;Wenhui Jiang;Wanting Wang;Leida Li;Xin Xie","doi":"10.1109/TNSE.2025.3645844","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3645844","url":null,"abstract":"With the increasing deployment of environment-aware services in the Internet of Vehicles (IoV), vehicles are required to execute multiple computational tasks in real time. However, resource allocation and task offloading in unmanned aerial vehicles (UAVs)-assisted IoV systems remain challenging due tothe growing number of vehicle terminals (VTs), potential privacy leakage, and resource-constrained edge devices. This paper proposes a digital twin (DT) and generative artificial intelligence (GAI)-powered hierarchical aerial-ground cooperative architecture (DTG-HACA) that achieves dynamic resource optimization through a three-layer framework. The DT layer enables real-time synchronization of vehicle/UAV states and simulated trajectory planning. The high altitude platforms (HAPs) layer provides low-latency offloading channels through stratospheric wide-area coverage and solar-powered endurance, while the physical entity layer executes energy-efficient edge computing via UAV-vehicle-roadside units (RSUs) collaboration. For UAV trajectory optimization, we introduce the multi-agent deep deterministic policy gradient (MADDPG)-improved prioritized experience replay (MADDPG-IPER) algorithm that minimizes communication overhead and energy consumption while integrating DT-simulated trajectory planning. For the joint challenge of edge caching and task offloading under privacy preservation constraints, we develop a federated deep reinforcement learning (FDRL) based generative adversarial network (FDRL-GAN) algorithm. This solution addresses critical challenges in dynamic task offloading and resource allocation for UAV-assisted IoV by leveraging GAI to predict task demands for cache hit rate optimization, while implementing FDRL for distributed privacy-preserving decision-making without raw data sharing, thereby achieving global resource allocation optimality. Extensive simulation experiments confirm that our proposed scheme demonstrates significant advantages over existing benchmark algorithms across five critical performance metrics, including training stability, computational capacity, task offloading efficiency, cache hit rate, and energy consumption.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"5038-5055"},"PeriodicalIF":7.9,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929393","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}
Pub Date : 2025-12-17DOI: 10.1109/TNSE.2025.3645282
Lijun He;Zheyuan Li;Juncheng Wang;Ziye Jia;Yanting Wang;Chau Yuen;Zhu Han
The rapid expansion of Low Earth Orbit (LEO) satellites inescapably leads to the explosive growth of space data in LEO Satellite Networks (LSNs). The stochastic nature of space data arrivals and the intrinsically time-varying satellite-ground links in LSNs pose significant challenges for offloading substantial volumes of space data from LSNs to the ground stations. To overcome these challenges, we systematically study the joint online optimization of power allocation and task scheduling for data offloading in LSNs. Firstly, we remove the constraint of mean rate queue stability from the formulated joint online optimization problem and leverage Lyapunov optimization to decouple it into a set of per-time-slot subproblems. Each subproblem is then divided into a task scheduling problem and a power allocation problem. Subsequently, we derive a closed-form optimal solution for the power allocation problem, and a multi-armed bandit-based quasi-optimal solution for the task scheduling problem. Furthermore, we extend the aforementioned solutions to address the original joint online optimization problem. Through theoretical analyses, we show that the proposed algorithms consistently attain a sublinear time-averaged regret. Extensive simulation results demonstrate that our proposed algorithms exhibit superior performance over other benchmarks.
{"title":"Joint Online Optimization of Power Allocation and Task Scheduling for Data Offloading in LEO Satellite Networks","authors":"Lijun He;Zheyuan Li;Juncheng Wang;Ziye Jia;Yanting Wang;Chau Yuen;Zhu Han","doi":"10.1109/TNSE.2025.3645282","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3645282","url":null,"abstract":"The rapid expansion of Low Earth Orbit (LEO) satellites inescapably leads to the explosive growth of space data in LEO Satellite Networks (LSNs). The stochastic nature of space data arrivals and the intrinsically time-varying satellite-ground links in LSNs pose significant challenges for offloading substantial volumes of space data from LSNs to the ground stations. To overcome these challenges, we systematically study the joint online optimization of power allocation and task scheduling for data offloading in LSNs. Firstly, we remove the constraint of mean rate queue stability from the formulated joint online optimization problem and leverage Lyapunov optimization to decouple it into a set of per-time-slot subproblems. Each subproblem is then divided into a task scheduling problem and a power allocation problem. Subsequently, we derive a closed-form optimal solution for the power allocation problem, and a multi-armed bandit-based quasi-optimal solution for the task scheduling problem. Furthermore, we extend the aforementioned solutions to address the original joint online optimization problem. Through theoretical analyses, we show that the proposed algorithms consistently attain a sublinear time-averaged regret. Extensive simulation results demonstrate that our proposed algorithms exhibit superior performance over other benchmarks.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"5018-5037"},"PeriodicalIF":7.9,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929383","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}
Pub Date : 2025-12-16DOI: 10.1109/TNSE.2025.3644931
Zhangfei Zhou;Youguo Wang;Qiqing Zhai;Jun Yan
Source localization, the inverse problem of diffusion processes, is crucial for tracking social rumors, identifying epidemic spreaders, and detecting computer viruses. Multi-source localization based on snapshot observation has garnered significant attention due to its low cost and ease of acquisition. However, challenges such as ill-posedness and heavy dependence on diffusion models hinder effective solutions. Existing methods often rely on deterministic techniques that require searching the entire graph space, struggle to effectively encode topological information, and are limited to a single diffusion model. To address these limitations, we propose Source Localization based on Representation Learning and Bayesian Optimization (SL-RLBO), a generic framework that quantifies source uncertainty via Monte Carlo simulation. Specifically, we first develop a novel algorithm to simultaneously estimate diffusion parameters and time from a single snapshot. Then, we utilize a multi-source reverse infection algorithm to identify candidate sources and leverage graph representation learning techniques to capture latent topological features. Finally, we formulate an objective function applicable to various diffusion models and efficiently optimize it using Bayesian optimization. Extensive experiments and case studies conducted on two synthetic and six real-world datasets show that SL-RLBO consistently outperforms four state-of-the-art baselines across different diffusion models, reducing error distance by an average of 18.94%.
{"title":"Multi-Source Localization Based on Graph Representation Learning and Bayesian Optimization","authors":"Zhangfei Zhou;Youguo Wang;Qiqing Zhai;Jun Yan","doi":"10.1109/TNSE.2025.3644931","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3644931","url":null,"abstract":"Source localization, the inverse problem of diffusion processes, is crucial for tracking social rumors, identifying epidemic spreaders, and detecting computer viruses. Multi-source localization based on snapshot observation has garnered significant attention due to its low cost and ease of acquisition. However, challenges such as ill-posedness and heavy dependence on diffusion models hinder effective solutions. Existing methods often rely on deterministic techniques that require searching the entire graph space, struggle to effectively encode topological information, and are limited to a single diffusion model. To address these limitations, we propose <underline>S</u>ource <underline>L</u>ocalization based on <underline>R</u>epresentation <underline>L</u>earning and <underline>B</u>ayesian <underline>O</u>ptimization (SL-RLBO), a generic framework that quantifies source uncertainty via Monte Carlo simulation. Specifically, we first develop a novel algorithm to simultaneously estimate diffusion parameters and time from a single snapshot. Then, we utilize a multi-source reverse infection algorithm to identify candidate sources and leverage graph representation learning techniques to capture latent topological features. Finally, we formulate an objective function applicable to various diffusion models and efficiently optimize it using Bayesian optimization. Extensive experiments and case studies conducted on two synthetic and six real-world datasets show that SL-RLBO consistently outperforms four state-of-the-art baselines across different diffusion models, reducing error distance by an average of 18.94%.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"4815-4832"},"PeriodicalIF":7.9,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886569","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：