{"title":"Task Dependency Aware Optimal Resource Allocation for URLLC Edge Network: A Digital Twin Approach Using Finite Blocklength","authors":"Muhammad Awais;Haris Pervaiz;Qiang Ni;Wenjuan Yu","doi":"10.1109/TGCN.2024.3425442","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3425442","url":null,"abstract":"Next-generation wireless networks envision ubiquitous access and computational capabilities by seamlessly integrating aerial and terrestrial networks. Digital twin (DT) technology emerges as a proactive and cost-effective approach for resource-limited networks. Mobile edge computing (MEC) is pivotal in facilitating mobile offloading, particularly under the demanding constraints of ultra-reliable and low-latency communication (URLLC). This study proposes an advanced bisection sampling-based stochastic solution enhancement (BSSE) algorithm to minimize the system’s overall energy-time cost by jointly optimizing task offloading and resource allocation strategies. The formulated problem is a mixed-integer nonlinear programming problem due to its inherently combinatorial linkage with task-offloading decisions and strong correlation with resource allocation. The proposed algorithm operates iteratively through the following steps: 1) narrowing the search space through a one-climb policy, 2) developing a closed-form solution for optimal CPU frequency and transmit power, and 3) implementing randomized task offloading, which updates it in the direction of reducing objective value. The scalability of the proposed algorithm is also analyzed for a two-device model, which is subsequently extended to multiple devices. Comparative analysis against benchmark schemes reveals that our approach reduces total energy-time cost by 15.35% to 33.12% when weighting parameter <inline-formula> <tex-math>$partial ^{lambda }_{k_{2}}$ </tex-math></inline-formula> is increased from 0.1 to 0.3, respectively.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"177-190"},"PeriodicalIF":5.3,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430350","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":"Multi-Round Stackelberg Game-Based Pricing and Offloading in Containerized MEC Networks","authors":"Mingxiong Zhao;Zhaojie Yang;Zhenli He;Fanhao Xue;Xianqi Zhang","doi":"10.1109/TGCN.2024.3425643","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3425643","url":null,"abstract":"Mobile Edge Computing (MEC) tackles the challenges associated with the rapid proliferation of User Equipment (UE) and limited computing resources. Containerization, essential for MEC deployments, encapsulates applications and dependencies, optimizing resource utilization. In containerized MEC networks, UEs offload computational tasks to edge server containers, enabling service providers to profit from offering scalable and portable services, thereby establishing a symbiotic economic ecosystem. However, traditional models, which often separate cost and delay assessments, fail to consider these factors holistically. Furthermore, they underutilize the potential of container images’ hierarchical structure, which could optimize storage and reduce costs. Our research introduces a novel multi-round Stackelberg game framework that incorporates the hierarchical structure of container images to enhance resource management in MEC networks. Additionally, we integrate discount rates to model long-term economic interactions accurately, and develop two innovative algorithms: the Distributed Ant Colony Pricing (DACP) and the Multi-Round Simulated Annealing Pricing (MRSAP). These algorithms account for both immediate and long-term impacts, redefining user utility and significantly improving system efficiency. Simulation results validate the effectiveness of our algorithms in optimizing resource allocation and enhancing efficiency in dynamic MEC scenarios.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"191-206"},"PeriodicalIF":5.3,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430355","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":"Federated Learning-Enabled Jamming Detection for Stochastic Terrestrial and Non-Terrestrial Networks","authors":"Aida Meftah;Tri Nhu Do;Georges Kaddoum;Chamseddine Talhi","doi":"10.1109/TGCN.2024.3425792","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3425792","url":null,"abstract":"In this paper, we present a novel federated learning (FL) algorithm, named Aggregated and Augmented Training Federated (AAT-Fed), tailored for stochastic, distributed, tactical terrestrial and non-terrestrial (SDT-TNT) network environments. Focusing on an SDT-TNT network with multiple clusters and potential unknown jammers, our approach addresses jammer detection through convolutional variational autoencoders (C-VAEs) within the FL framework. Leveraging the spectral correlation function (SCF) of the in-phase and quadrature (I/Q) representation of received signals, our method extracts discriminating features for jammer detection in the absence of prior knowledge about the jammers. AAT-Fed excels at managing the unique characteristics of the tactical TNT network, considering its stochastic nature and the heterogeneity in data distribution between network cells, leading to enhanced jamming detection accuracy. Comparative simulation results demonstrate AAT-Fed’s superior performance over FL and non-FL approaches, showcasing its effectiveness in providing accurate jamming detection at a low jamming-to-noise ratio.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"271-290"},"PeriodicalIF":5.3,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430401","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":"Joint Optimization of Semi-Passive IRS Phase Shifts and NOMA Power Coefficients for Cooperative CRNs","authors":"Mohsin Khan;Jawad Mirza;Bakhtiar Ali;Muhammad Awais Javed;Kapal Dev;Lewis Nkenyereye;Paolo Bellavista","doi":"10.1109/TGCN.2024.3426305","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3426305","url":null,"abstract":"We investigate the incorporation of an intelligent reflecting surface (IRS) into cooperative spectrum-sharing cognitive radio networks (CRNs). The CRN consists of a primary user (PU) and multiple secondary users (SUs). There are two transmission phases. In the first phase, the primary transmitter is assisted by an IRS to serve the primary user (PU). This arrangement allows the primary network to allocate a part of its spectrum to the users within the secondary network. In the subsequent phase, the secondary transmitter (ST) employs a non-orthogonal multiple access (NOMA) transmission technique to simultaneously serve the PU and secondary users (SUs). By utilizing a semi-passive IRS, both data transmission to the PU and channel estimation of SUs are performed simultaneously during the first transmission phase. The main objective is to improve the weighted sum-rate of the CRN through a joint optimization of the NOMA power coefficients and IRS phase adjustments during the second transmission phase. We propose an effective algorithm that breaks down the primary sum-rate maximization problem into two sub-problems where IRS phase shifts are computed once at the beginning of the algorithm. Through simulations, we demonstrate that the proposed algorithm yields substantial gains in the sum-rate performance compared to existing methods.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"380-391"},"PeriodicalIF":5.3,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403784","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":"AoI-Aware Energy Efficiency Resource Allocation for Integrated Satellite-Terrestrial IoT Networks","authors":"Qingming Wang;Xiao Liang;Hua Zhang;Linghui Ge","doi":"10.1109/TGCN.2024.3425848","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3425848","url":null,"abstract":"Integrated satellite and terrestrial network (ISTN) is a potential technology to achieve ubiquitous and reliable broadband communication for Internet of Things (IoT) devices. Timely delivery of information updates represents a pivotal metric in IoT networks. However, due to the limited satellite transmission resources and the huge propagation delay caused by long distance from satellites to the Earth, ISTN faces great challenges in ensuring such freshness. Moreover, energy efficiency (EE) is also a crucial factor in ISTN with multiple antennas serving multiple users. In this research, we incorporate Age of Information (AoI) as a metric to ensure the information freshness of all IoT devices and design an AoI-aware EE resource allocation scheme. We maximize the system average EE by jointly optimizing the beamforming of Low Earth Orbit (LEO) satellites and base station (BS), and scheduling while maintaining the maximum AoI constraints of all IoT devices. To solve such a difficult problem, a Lyapunov drift-plus-penalty approach is leveraged to transform the original dynamic resource allocation problem into a deterministic problem, which is efficiently solved by an alternating optimization. Compared with existing schemes, our proposed scheme achieves the highest average EE. Our simulations also verify the tradeoff between average EE and information freshness.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"125-139"},"PeriodicalIF":5.3,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430387","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}
Puning Zhang;Ziyun Xian;Mingjun Liao;Haiyun Huang;Junyan Yang
{"title":"Adaptive Routing Mechanism for LEO Satellite Network Based on Control Domain Partition","authors":"Puning Zhang;Ziyun Xian;Mingjun Liao;Haiyun Huang;Junyan Yang","doi":"10.1109/TGCN.2024.3425458","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3425458","url":null,"abstract":"Low Earth Orbit (LEO) satellite network has the characteristics of low delay, low propagation loss, high bandwidth, and seamless coverage, which is the cornerstone of space-air-ground integrated network. However, the complex topology and time-varying link state of LEO lead to extremely unstable data routing. Existing routing research faces the challenges of large link information update delay, high routing table storage, and query overhead, which seriously affect satellite data transmission, onboard computing, and storage efficiency. To address the above issues, an adaptive routing mechanism based on control domain partition is proposed, considering the dynamic time-varying characteristics of LEO satellite constellation topology and inter-satellite link. Specifically, a non-dominated sorting-based control domain partition architecture is designed to manage the satellite domain for reducing control delay and improving link information update efficiency. Then a distributed routing method for control domain division is proposed to sense the link status of adjacent control domains rather than the entire satellite network, so as to alleviate the problems of high storage and query complexity and slow update of link information. Furthermore, a link situation aware routing decision-making method is devised to accurately perceive the link situation and achieve optimal path decision-making. The simulation results demonstrate that the proposed mechanism respectively improves the network performance by about 12%, 22%, and 14% in terms of end-to-end average delay, packet loss rate, and throughput.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"70-82"},"PeriodicalIF":5.3,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430399","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}
Na Lin;Tianxiong Wu;Liang Zhao;Ammar Hawbani;Shaohua Wan;Mohsen Guizani
{"title":"An Energy Effective RIS-Assisted Multi-UAV Coverage Scheme for Fairness-Aware Ground Terminals","authors":"Na Lin;Tianxiong Wu;Liang Zhao;Ammar Hawbani;Shaohua Wan;Mohsen Guizani","doi":"10.1109/TGCN.2024.3424980","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3424980","url":null,"abstract":"Unmanned aerial vehicle (UAV)-assisted communications are critical in regional wireless networks. Using reconfigurable intelligent surfaces (RISs) can significantly improve UAVs’ throughput and energy efficiency. Due to limited communications resources, the data transfer rate of ground terminals (GTs) could be slower, and the throughput may be low. Using RIS-assisted UAVs can effectively address these limitations. This paper focuses on optimizing the three-dimensional (3D) trajectory of the UAV and the scheduling order of the GTs and designing the phase shift of the RIS to maximize energy efficiency while meeting the limited energy and fair service constraints in the case of fair service GTs. To address the non-convexity of this problem, we propose a triple deep q-network (TDQN) algorithm, which better avoids the overestimation problem during the optimization process. We propose an improved k-density-based spatial clustering of applications with noise (K-DBSCAN) clustering algorithm, which is characterized by the ability to output the initial movement range of the UAV and prune the deep reinforcement learning (DRL) state space by the initial movement range to speed up DRL training based on the completion of the partitioning deployment work. A fair screening mechanism is proposed to satisfy the fairness constraint. The results show that the TDQN algorithm is 2.9% more energy efficient than the baseline. The K-DBSCAN algorithm speeds up the training of the TDQN algorithm by 59.4%. The fair screening mechanism reduces the throughput variance from an average of 114099.9 to an average of 46.9.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"164-176"},"PeriodicalIF":5.3,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430455","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}
Mingda Hu;Jingjing Zhang;Xiong Wang;Shengyun Liu;Zheng Lin
{"title":"Accelerating Federated Learning With Model Segmentation for Edge Networks","authors":"Mingda Hu;Jingjing Zhang;Xiong Wang;Shengyun Liu;Zheng Lin","doi":"10.1109/TGCN.2024.3424552","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3424552","url":null,"abstract":"In the rapidly evolving landscape of distributed learning strategies, Federated Learning (FL) stands out for its features such as model training on resource-constrained edge devices and high data security. However, the growing complexity of neural network models produces two challenges such as communication bottleneck and resource under-utilization, especially in edge networks. To overcome these challenges, this paper introduces a novel framework by realizing the Parallel Communication-Computation Federated Learning Mode (P2CFed). Specifically, we design an adaptive layer-wise model segmentation strategy according to the wireless environments and computing capability of edge devices, which enables parallel training and transmission within different sub-models. In this way, parameter delivery takes place throughout the training process, thus considerably alleviating the communication overhead. Meanwhile, we also propose a joint optimization scheme with regard to the subchannel allocation, power control, and segmentation layer selection, which is then transformed into an iteration search process for obtaining optimal results. We have conducted extensive simulations to validate the effectiveness of P2CFed when compared with state-of-the-art benchmarks in terms of communication overhead and resource utilization. It also unveils that P2CFed brings a faster convergence rate and smaller training delay compared to traditional FL approaches.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"242-254"},"PeriodicalIF":5.3,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430403","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":"An AI-Enhanced Multipath TCP Scheduler for Open Radio Access Networks","authors":"Wenxuan Qiao;Yuyang Zhang;Ping Dong;Xiaojiang Du;Hongke Zhang;Mohsen Guizani","doi":"10.1109/TGCN.2024.3424202","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3424202","url":null,"abstract":"Multipath transmission technology has recently emerged as a crucial solution to address bandwidth resource constraints and uneven load distribution across access points caused by the surge in data-intensive applications. A well-designed multipath scheduler can improve the quality of service and balance the power consumption in evolving Open Radio Access Networks (O-RANs). However, wireless channel instability and RAN heterogeneity challenge the scheduler’s bandwidth aggregation capability. This paper introduces a Neural Aggregation Bandwidth Optimization (NABO) scheduler for O-RAN, combining bandwidth prediction with scheduling policy optimization. NABO employs an innovative approach by first constructing a Transformer-optimized Throughput (ToT) prediction model based on historical path characteristics. To train the model, we design a system to simulate various network conditions and collect datasets. This model is then integrated into a dual-network collaborative learning framework that combines ToT predictions with heterogeneity levels to guide the scheduler’s optimization process. The ToT model achieves a throughput prediction error of less than 2%. In numerous heterogeneous simulation scenarios and real-world wireless environments, NABO significantly outperforms state-of-the-art multipath transmission methods, with bandwidth aggregation improvements of approximately 51% and 30% over existing benchmarks, respectively. These findings demonstrate NABO’s superior efficacy and potential in enhancing the performance and energy efficiency of O-RANs.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 3","pages":"910-923"},"PeriodicalIF":5.3,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142090990","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":"A Reinforcement Learning-Based Stochastic Game for Energy-Efficient UAV Swarm-Assisted MEC With Dynamic Clustering and Scheduling","authors":"Jialiuyuan Li;Changyan Yi;Jiayuan Chen;You Shi;Tong Zhang;Xiaolong Li;Ran Wang;Kun Zhu","doi":"10.1109/TGCN.2024.3424449","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3424449","url":null,"abstract":"In this paper, we study the energy-efficient unmanned aerial vehicle (UAV) swarm assisted mobile edge computing (MEC) with dynamic clustering and scheduling. In the considered system model, UAVs are divided into multiple swarms, with each swarm consisting of a leader UAV and several follower UAVs. These UAVs serve as mobile edge servers, providing computing services to their covered ground end-users. Unlike existing works, we allow UAVs to dynamically cluster into different swarms, in other words, each follower UAV can change its leader based on the time-varying spatial positions, updated application placement, etc. in a dynamic manner. With the objective of maximizing the long-term energy efficiency of the UAV swarm assisted MEC system, a joint optimization problem of UAV swarm dynamic clustering and scheduling is formulated. Considering the inherent cooperation and competition among intelligent UAVs, we further reformulate this problem as a combination of a series of strongly interconnected multi-agent stochastic games, and theoretically prove the existence of the corresponding Nash Equilibrium (NE). Then, we propose a novel reinforcement learning based UAV swarm dynamic coordination (RLDC) algorithm for obtaining such an equilibrium. Furthermore, the convergence and complexity of the RLDC algorithm are analyzed. Simulations are performed to evaluate the performance of RLDC and illustrate its superiority compared to existing approaches.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"255-270"},"PeriodicalIF":5.3,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430356","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}