IEEE Transactions on Green Communications and Networking最新文献_第6页

HA-A2C: Hard Attention and Advantage Actor-Critic for Addressing Latency Optimization in Edge Computing

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-06-04 DOI: 10.1109/TGCN.2024.3409390

Jing Yang;Jialin Lu;Xu Zhou;Shaobo Li;Chuanyue Xiong;Jianjun Hu

{"title":"HA-A2C: Hard Attention and Advantage Actor-Critic for Addressing Latency Optimization in Edge Computing","authors":"Jing Yang;Jialin Lu;Xu Zhou;Shaobo Li;Chuanyue Xiong;Jianjun Hu","doi":"10.1109/TGCN.2024.3409390","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3409390","url":null,"abstract":"Due to the rapid development of the IoT and data-driven applications, low-latency task scheduling methods that quickly respond to user tasks has become a significant challenge for edge servers. However, the existing task scheduling strategies do not overcome the impact of factors such as task characteristics, resource availability, and network conditions on delays. Meanwhile, the cross-regional maldistribution of edge servers is obvious, and the edge servers are either idle or overloaded. To address these issues, we propose a low-latency edge scheduling strategy based on the Hard Attention Mechanism and Advantage Actor-Critic (HA-A2C). The core element of this method is the adoption of a hard attention mechanism, which reduces computing complexity and increases efficiency. Effective attention allocation during the resource allocation process further reduces job completion time. Additionally, the deep reinforcement learning method is employed to enhance task dynamic scheduling capabilities, thereby reducing scheduling delays. The HA-A2C approach reduces task latency by approximately 40% compared to the DQN method. Consequently, the intelligent allocation of task resources achieved by integrating the hard attention technique significantly reduces task scheduling time in edge environments.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"207-217"},"PeriodicalIF":5.3,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430393","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

Static Deep Q-Learning for Green Downlink C-RAN

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-06-04 DOI: 10.1109/TGCN.2024.3408828

Yuchao Chang;Hongli Wang;Wen Chen;Yonghui Li;Naofal Al-Dhahir

{"title":"Static Deep Q-Learning for Green Downlink C-RAN","authors":"Yuchao Chang;Hongli Wang;Wen Chen;Yonghui Li;Naofal Al-Dhahir","doi":"10.1109/TGCN.2024.3408828","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3408828","url":null,"abstract":"Power saving is a main pillar in the operation of wireless communication systems. In this paper, we investigate cloud radio access network (C-RAN) capability to reduce power consumption based on the user equipment (UE) requirement. Aiming to save the long-term C-RAN energy consumption, an optimization problem is formulated to manage the downlink power without degrading the UE requirement by designing the power offset parameter. Considering stochastic traffic arrivals at UEs, we first formulate the problem as a Markov decision process (MDP) and then set up a dual objective optimization problem in terms of the downlink throughput and power. To solve this optimization problem, we develop a novel static deep Q-learning (SDQL) algorithm to maximize the downlink throughput and minimize the downlink power. In our proposed algorithm, we design multi-Q-tables to simultaneously optimize power reductions of activated RRHs by assigning one Q-table for each UE. To maximize the accumulative reward in terms of the downlink throughput loss and power reduction, our proposed algorithm performs power reductions of activated RRHs through continuous environmental interactions. Simulation resultsCode can be accessed on website: <uri>https://github.com/yuchaoch/project/tree/main</uri> show that our proposed algorithm enjoys a superior average power reduction compared to the activation and sleep schemes, and enjoys a low computational complexity.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"291-303"},"PeriodicalIF":5.3,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430392","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

SM and NOMA Joint Assisted Indoor Multi-User VLC Downlink

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-06-03 DOI: 10.1109/TGCN.2024.3409080

Fasong Wang;Ting Zuo;Jiankang Zhang;Shijie Shi;Yitong Li

{"title":"SM and NOMA Joint Assisted Indoor Multi-User VLC Downlink","authors":"Fasong Wang;Ting Zuo;Jiankang Zhang;Shijie Shi;Yitong Li","doi":"10.1109/TGCN.2024.3409080","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3409080","url":null,"abstract":"In this paper, a novel spatial modulation (SM) assisted successive interference cancelation (SIC) free non-orthogonal multiple access (NOMA) scheme is proposed for indoor multi-user visible light communications (VLC) downlink. In the proposed scheme, all users are grouped according to channel gains. The data information of users in each group is then mapped to the spatial domain and constellation symbol domain according to their bit error rate requirements. In addition, due to the inherent sparsity of SM modulated signals, the compressed sensing (CS) sparse reconstruction algorithm is revoked for demodulating signals at the receiver. In this process, the information carried by the activated light emitting diode index is demodulated using the CS aided sparsity reconstruction algorithm, while the constellation symbol information is demodulated using the maximum likelihood (ML) algorithm. Additionally, by combining the greedy algorithm with the ML algorithm, a new method for sparse signal reconstruction detection is proposed. Compared with traditional NOMA technology, at the receiver side, both the error propagation caused by SIC and intra-group interference can be eliminated. Furthermore, the computational complexity of demodulation is reduced by utilizing the proposed joint signal detection procedure. The effectiveness of the proposed indoor multi-user SM NOMA VLC architecture is validated through Monte Carlo simulations.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"15-28"},"PeriodicalIF":5.3,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430454","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 Energy Efficiency in Satellite-to-Ground Communications With Multiple Reflecting Intelligent Surfaces 利用多重反射智能表面提高卫星对地通信的能效

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-06-03 DOI: 10.1109/TGCN.2024.3408295

Muhammad I. Khalil;Jiao Lin;Ke Wang

引用次数: 0

Pareto Optimal Energy Efficiency Power Allocation: Coping With Highly Constraints in NOMA Uplink Dense Access VLC Network 帕累托最优能效功率分配：应对 NOMA 上行链路密集接入 VLC 网络中的高度约束

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-06-03 DOI: 10.1109/TGCN.2024.3408160

Yuchao Dang;Xuefen Chi;Linlin Zhao

{"title":"Pareto Optimal Energy Efficiency Power Allocation: Coping With Highly Constraints in NOMA Uplink Dense Access VLC Network","authors":"Yuchao Dang;Xuefen Chi;Linlin Zhao","doi":"10.1109/TGCN.2024.3408160","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3408160","url":null,"abstract":"Aiming at the heavy requirement of bandwidth and delay for immersive communication, we propose the optical heterogeneous network and focus on enhance network capacity and dense access capacity as well as energy efficiency (EE). An optical MIMO network based on NOMA is developed, and we design the power allocation optimization problem (OP) with the saturation throughput as the optimization objective. However, since the severity of the successive interference cancellation (SIC) inequality constraint are positively correlated with the number of users, the solution of OP exhibits inefficient convergence of the pareto front, and the solution of the OP often triggers a chain violation effect in the power allocation. We propose a power allocation scheme based on the Fuzzy Constraint Window Gradient Descent Differential Evolution (FCWGD-DE) algorithm. We design a FCWGD strategy to expand the population search area, together with the information sharing reproduction, the suitable factor sequence, and the proportional selection, to protect the distribution and diversity of the population, and drive the population to converge to the pareto optimal frontier while avoiding local convergence. The simulation results demonstrate that the proposed scheme achieves high EE, significantly improves system throughput, and provides stable quality of service guarantee for users.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1781-1795"},"PeriodicalIF":5.3,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713814","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

Performance of Statistical Power Control With Simplified User Selection and Mode Switching in Hybrid NOMA/OMA Networks

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-06-03 DOI: 10.1109/TGCN.2024.3408334

Anand Jee;Shankar Prakriya

{"title":"Performance of Statistical Power Control With Simplified User Selection and Mode Switching in Hybrid NOMA/OMA Networks","authors":"Anand Jee;Shankar Prakriya","doi":"10.1109/TGCN.2024.3408334","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3408334","url":null,"abstract":"The paucity of orthogonal resource blocks has led to focused research on non-orthogonal multiple access (NOMA) signaling. This paper considers a multi-user downlink hybrid non-orthogonal multiple access (NOMA) framework with direct links to near-users (NUs) as well as far-users (FUs). It is shown that intelligent power allocation, together with mode switching and user selection, is the key to high spectral efficiency (SE) and energy efficiency (EE). To enhance the system throughput, intelligent NU and FU selection, and switching among NOMA Mode (NM), cooperative NOMA mode (CNM), and OMA mode (OM) have been considered. Switching to OM when both NM and CNM fail ensures performance equivalent to OM. The closed-form expressions for the outage probability, mode probability, throughput, and EE are derived with mode switching and user selection. It is demonstrated that choosing the optimal target rate and NOMA power allocation coefficient is essential to maximize the EE. Only statistical channel knowledge is used for this purpose. Furthermore, we demonstrate that the proposed framework outperforms known schemes in terms of throughput and EE. In particular, the energy savings with the proposed scheme can be very significant. Monte Carlo simulations validate the derived expressions.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"2-14"},"PeriodicalIF":5.3,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430400","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

Energy Efficient Query Processing Mechanism for IoT-Enabled WSNs 物联网 WSN 的高能效查询处理机制

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-04-29 DOI: 10.1109/TGCN.2024.3394908

Vaibhav Agarwal;Shashikala Tapaswi;Prasenjit Chanak

{"title":"Energy Efficient Query Processing Mechanism for IoT-Enabled WSNs","authors":"Vaibhav Agarwal;Shashikala Tapaswi;Prasenjit Chanak","doi":"10.1109/TGCN.2024.3394908","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3394908","url":null,"abstract":"Wireless Sensor Networks (WSNs) act as an integral part of any Internet of Things (IoT) based system. In IoT-based applications such as disaster management, industry automation, and healthcare, the end user demands real-time data for decision-making. In these applications, query-driven WSNs play a vital role in real-time decision-making. Existing state-of-the-art query-driven approaches suffer from a huge query processing delay, end-to-end delay, and poor network lifetime. Therefore, this paper presents an energy-efficient query processing mechanism for IoT-enabled WSNs where mobile sinks-based query processing is performed to reduce end-to-end delay and improve overall network performance. The proposed scheme uses a minimal set cover algorithm to identify the optimal number of rendezvous points. Furthermore, it selects the optimal number of mobile sinks using an improved shark smell optimization algorithm. Extensive simulations and mathematical analysis have shown that the proposed scheme outperformed as compared to the existing state-of-the-art algorithms such as LEDC, QDWSN, QWRP, and QDVGDD. The proposed scheme depicts 41.26%, 39.84%, 40.77%, 39.74%, and 40.15% improvement in terms of average energy consumption, query processing delay, end-to-end delay, network lifetime, and data delivery ratio, respectively.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1632-1644"},"PeriodicalIF":5.3,"publicationDate":"2024-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713810","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

AFC-TH Hybrid Precoding With High Energy Efficiency for Millimeter Wave Communication Systems 为毫米波通信系统提供高能效的 AFC-TH 混合预编码

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-04-29 DOI: 10.1109/TGCN.2024.3394834

Ruiyan Du;Long Li;Zhiqing Guan;Baozhu Shi;Zhuoyao Duan;Fulai Liu

{"title":"AFC-TH Hybrid Precoding With High Energy Efficiency for Millimeter Wave Communication Systems","authors":"Ruiyan Du;Long Li;Zhiqing Guan;Baozhu Shi;Zhuoyao Duan;Fulai Liu","doi":"10.1109/TGCN.2024.3394834","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3394834","url":null,"abstract":"As a structure with lower power consumption and hardware cost, the adaptive fully-connected (AFC) structure can improve energy efficiency significantly for hybrid precoding. Based on this, this paper proposes an energy-efficient AFC Tomlinson-Harashima (AFC-TH) hybrid precoding algorithm. Specifically, to alleviate inter-user interference and enhance system performance, a TH algorithm based on the mean square error minimization of signals (S-MMSE-TH) is proposed to obtain the optimal digital precoding matrix. Furthermore, to reduce the computational complexity of optimization the switch precoding matrix, a branch-and-bound based on subspace projection method is developed. Different from the traditional branch-and-bound method by the convex relaxation, the subspace projection method is used to obtain a closed-form lower bound of the objective function. It can reduce the computational cost effectively. Moreover, according to the norm and the nonlinear programming theories, a phase shifters precoding matrix optimization method is proposed. In this method, the phase-shifter precoding matrix optimization problem is transformed into a positive semidefinite quadratic form satisfying the KKT condition. Especially, a diagonal loading factor is introduced to satisfy the KKT condition to reduce the computational cost. Simulation results and complexity analysis show that the proposed method provides high energy efficiency while enjoying satisfactory spectral efficiency with a low computational complexity.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1622-1631"},"PeriodicalIF":5.3,"publicationDate":"2024-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713795","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

SNNOT: Spiking Neural Network With On-Chip Training for MIMO-OFDM Symbol Detection SNNOT：用于 MIMO-OFDM 符号检测的片上训练尖峰神经网络

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-04-25 DOI: 10.1109/TGCN.2024.3393854

Honghao Zheng;Jiarui Xu;Lingjia Liu;Yang Yi

{"title":"SNNOT: Spiking Neural Network With On-Chip Training for MIMO-OFDM Symbol Detection","authors":"Honghao Zheng;Jiarui Xu;Lingjia Liu;Yang Yi","doi":"10.1109/TGCN.2024.3393854","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3393854","url":null,"abstract":"Advancing 5G and beyond communications require innovative solutions for symbol detection in MIMO-OFDM. Our research leverages Spiking Neural Networks (SNNs), surpassing the efficiency of traditional Deep Neural Networks (DNNs) and Artificial Neural Networks (ANNs) in dynamic wireless contexts. The SNNOT architecture features a novel triplet Spike-Timing-Dependent Plasticity (STDP) learning circuit, utilizing 22FDX technology from GlobalFoundries, which overcomes STDP’s supervised learning limitations and enhances dynamic learning by converting spikes into voltages. This innovation leads to substantial efficiency gains, with a minimal energy requirement of \u0000<inline-formula> <tex-math>$20.92 mu W$ </tex-math></inline-formula>\u0000 and a small silicon footprint of \u0000<inline-formula> <tex-math>$37 times 62 mu m^{2}$ </tex-math></inline-formula>\u0000. Performance evaluations show the triplet STDP rule in SNNOT considerably improves image classification and symbol detection, with over 3% error rate reduction in MNIST and CIFAR-10. Additionally, it achieves a 0.07 symbol error rate (SER) at 5 dB \u0000<inline-formula> <tex-math>$E_{b}/N_{o}$ </tex-math></inline-formula>\u0000 in 4 pulse amplitude modulation (4-PAM) Gaussian channel symbol detection, outperforming other methods. With 8-PAM, it surpasses other methods by at least 0.03 SER and maintains lower or comparable SERs in scenarios using the WINNER II channel model and 16 quadrature amplitude modulation (16-QAM). Importantly, our method offers up to 32% faster processing, providing a potent, efficient solution for receiver processing in cutting-edge wireless systems.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1809-1823"},"PeriodicalIF":5.3,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713812","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

Cooperative Beamforming for Double-RIS Assisted CoMP Systems 双 RIS 辅助 CoMP 系统的合作波束成形

IF 5.3 2区计算机科学

IEEE Transactions on Green Communications and Networking Pub Date : 2024-04-25 DOI: 10.1109/TGCN.2024.3393554

Jian Chen;Yuchen Sun;Jie Jia;Baoxin Yin;Xingwei Wang

{"title":"Cooperative Beamforming for Double-RIS Assisted CoMP Systems","authors":"Jian Chen;Yuchen Sun;Jie Jia;Baoxin Yin;Xingwei Wang","doi":"10.1109/TGCN.2024.3393554","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3393554","url":null,"abstract":"Energy efficiency (EE) has become a key performance indicator in designing future wireless networks. In this regard, we propose a novel two reconfigurable intelligent surfaces (RISs) assisted coordinated multipoint (CoMP) network, where two RISs cooperate to reduce energy consumption by constructing an intelligent radio environment. Aiming to maximize this system’s energy efficiency (EE), the joint optimization problem on the cooperative beamforming among base stations (BSs) and passive beamforming among RISs, subject to each user’s data rate requirement, is formulated. An alternative optimization algorithm is proposed by decoupling it into a cooperative beamforming subproblem among BSs and a cooperative reflective coefficients design subproblem among RISs. Dinkelbach’s transform and complex fractional programming algorithms are also invoked to transform these two subproblems into convex optimization problems and obtain the optimal solution for each sub-problem. Numerical results validate the proposed algorithm’s feasibility, fast convergence, and flexibility. It also shows that the proposed scheme with cooperative beamforming design for both BSs and RISs outperforms that without RIS and that with randomly initialized RISs.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1917-1929"},"PeriodicalIF":5.3,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679325","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