IEEE Transactions on Green Communications and Networking最新文献

{"title":"Chance-Constrained DRL for Energy-Efficient and Timely Wind-Powered WSNs Under Uncertain Underground Mine Environments","authors":"Lei Yang;Liang Niu;Zhongxu Bao;Xu Yang;Shengqiang Shen;Qiang Niu","doi":"10.1109/TGCN.2026.3718462","DOIUrl":"https://doi.org/10.1109/TGCN.2026.3718462","url":null,"abstract":"The uncertain underground mine environment is characterized by severe multipath fading, electromagnetic interference, and constrained energy, where even rare communication or power failures may trigger catastrophic safety events. These harsh conditions render conventional battery-dependent wireless sensor networks (WSNs) inadequate for persistent monitoring, yet continuous mine airflows offer a self-sustained alternative. However, wind intermittency and unobservable mechanical efficiency degradation produce outdated hazard reports, quantified by age of information (AoI), and endanger system survival, whereas conventional methods incur prohibitive global communication overhead to guarantee tail-event safety under such conditions. To address this, we propose a distributionally robust chance-constrained framework, driven by a multi-agent proximal policy optimization (MAPPO) algorithm. To provide conservative probabilistic safety margins against dual uncertainties, the unobservable hardware degradation is analytically absorbed into a robust surrogate environment. Based on this surrogate, intractable chance constraints regarding stochastic wind are conservatively transformed into deterministic safety margins, leveraging Bernstein bounds for known empirical distributions and conditional value-at-risk (CVaR)-based sufficient conditions for arbitrary distributions. Guided by this unified offline Lagrangian penalty, decentralized actors rely purely on local observations to adaptively optimize sensing and power via deterministic mapping, resolving shared bandwidth conflicts through implicit coordination without online signaling. Simulations confirm the framework substantially reduces AoI and extends node lifetime under airflow intermittency, achieving near-complete tail-event compliance for safety-critical reporting.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"3955-3970"},"PeriodicalIF":6.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11631758","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148747190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint Beamforming and Interference Management for Active RIS-Assisted RSMA-ISAC Systems","authors":"Di Zhou;Zhiquan Bai;Zhengchuan Chen;Dongfeng Yuan;DukKyung Kim;KyungSup Kwak;Tony Q. S. Quek","doi":"10.1109/TGCN.2026.3705232","DOIUrl":"https://doi.org/10.1109/TGCN.2026.3705232","url":null,"abstract":"Integrated sensing and communication (ISAC) improves spectrum utilization by enabling joint sensing and communication functionalities, but its performance in multi-user scenarios is limited by severe path loss and multi-user interference. To address these challenges, this paper proposes an active reconfigurable intelligent surface (RIS)-assisted rate-splitting multiple access (RSMA)-ISAC system, where an active RIS is employed to mitigate reflection-link attenuation and RSMA is adopted at the dual-functional base station to manage multi-user interference. We formulate a coupled non-convex optimization problem to maximize the received-echo signal-to-noise ratio (SNR) by jointly optimizing the BS precoding, active RIS beamforming, and rate-splitting variables under communication quality-of-service and active RIS power constraints. To solve this problem, an alternating optimization algorithm is developed by reformulating the original problem into tractable convex subproblems, thereby reducing redundant iterations and ensuring efficient convergence. Simulation results show that the proposed system improves radar sensing performance while maintaining the user-rate requirements, and achieves superior radar SNR, detection probability, system sum rate, and energy efficiency compared with the passive RIS-assisted, spatial division multiple access (SDMA)-assisted, and non-orthogonal multiple access (NOMA)-assisted ISAC benchmarks.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"3342-3355"},"PeriodicalIF":6.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148442510","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":"Magnetic-Transmitter to Electric-Receiver System for Underground-to-Aboveground Communication Exploiting Induction Field and Radiation Field","authors":"Guozheng Zhao;Guanghua Liu;Qiupeng Li;Yuan Hu","doi":"10.1109/TGCN.2026.3700687","DOIUrl":"10.1109/TGCN.2026.3700687","url":null,"abstract":"In recent years, the communication systems based on electric and magnetic antennas have been widely adopted as domain-optimised solutions for aboveground and underground communication, respectively. However, the optimal approach for underground-to-aboveground (UG2AG) communication remains controversial, with no established consensus. In this paper, we propose the magnetic transmitter to electric receiver (MTER) system for UG2AG communication, which uses induction and radiation fields to improve the UG2AG communication performance. Furthermore, this system is combined with the magnetic antenna transceiver system for underground-to-underground (UG2UG) communication to form a wireless underground communication system. Moreover, we establish the channel model of the proposed MTER system for UG2AG communication, which includes radiation efficiency under cross-median conditions and the radiation boundary under different underground environments. In addition, a closed-form formula is derived for the channel capacity of the proposed MTER system for UG2AG communication. Finally, we evaluate the communication performance in various underground environments and loop antenna parameters by discussing and analyzing the path loss and channel capacity. The results reveal that the MTER system for UG2AG communication can simultaneously enable nearly 10 m of underground communications and almost 800 m of aboveground communications in harsh underground environments, with a channel capacity exceeding 10 Kbps.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"3232-3245"},"PeriodicalIF":6.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433163","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":"Energy-Efficient DFRC System Using Hybrid RIS With Sub-Connected Active Partitions","authors":"Konstantinos Ntougias;Symeon Chatzinotas;Ioannis Krikidis","doi":"10.1109/TGCN.2026.3730488","DOIUrl":"https://doi.org/10.1109/TGCN.2026.3730488","url":null,"abstract":"This paper investigates hybrid reconfigurable intelligent surfaces (RIS) integrating sub-connected (SC) active partitions with fully-connected (FC) active, SC-active, or passive designs for multi-user multiple-input multiple-output dual-functional radar-communication (DFRC) systems. We formulate weighted DFRC optimization and energy efficiency maximization under DFRC constraints problems to jointly design DFRC waveforms and RIS beamforming. Efficient alternating optimization algorithms with proven convergence are developed for the proposed hybrid architectures. Numerical results demonstrate substantial performance gains: compared to conventional FC-active RIS, the hybrid SC-active/SC-active design achieves about 80% higher energy efficiency while preserving competitive sum-rate and radar-detection performance. Relative to purely passive RIS, hybrid SC-active/passive configurations provide approximately 50–70% energy-efficiency gains and 25–35% higher sum-rate over the simulated distance range. Against no-RIS DFRC baselines, even minimal SC-active partitioning, with 25% of the RIS elements assigned to the active subsurface, yields roughly 30–50% sum-rate enhancement, depending on the base station–user distance. The proposed designs exhibit superior hardware efficiency, with SC-active-based architectures requiring substantially fewer RF chains than FC-active-based alternatives while delivering competitive or superior performance. Results validate that hybrid SC-active RIS-based architectures enable scalable, power-efficient DFRC systems suitable for sustainable next-generation wireless networks.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"4220-4234"},"PeriodicalIF":6.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148925777","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":"AI-Driven Scalable Framework for Energy-Efficient SDN Configurations","authors":"José Gómez-delaHiz;Manuel Jiménez-Lázaro;Juan Luis Herrera;Mohamed Faten Zhani;Jaime Galán-Jiménez","doi":"10.1109/TGCN.2026.3724271","DOIUrl":"https://doi.org/10.1109/TGCN.2026.3724271","url":null,"abstract":"The fast-paced development of 5G and 6G technologies, together with increasing environmental concerns, highlights the urgent need for energy-efficient computer networks. A major challenge lies in reducing energy usage by dynamically adapting the number of active network devices to the actual traffic demand while still fulfilling performance requirements. Traditional approaches, based on Integer Linear Programming (ILP) and heuristic algorithms, face significant limitations in scalability and computational efficiency, particularly for large-scale networks. To address these challenges, this work proposes a Machine Learning (ML)-based algorithm that uses clustering and classification techniques to find energy-efficient configurations in Software-Defined Networks. Simulations on realistic network topologies demonstrate that our solution delivers results close to those achieved by the reference algorithms, and near-optimal performance when ILP-based solutions are used as reference, achieving up to 53% energy savings while reducing execution time by up to 8,000 times. These results highlight the potential of ML-driven approaches to enable scalable and energy-efficient network management.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"4072-4086"},"PeriodicalIF":6.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11657451","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148925862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-Link Interference Cancellation and Network Power Optimization With an FD Base Station","authors":"Changqing Song;Dian Xiao;Yan Zhao;Hongzhi Zhao;Shihai Shao;Youxi Tang","doi":"10.1109/TGCN.2026.3727148","DOIUrl":"https://doi.org/10.1109/TGCN.2026.3727148","url":null,"abstract":"Engineering breakthroughs in self-interference cancellation have advanced full-duplex (FD) networking from theoretical research to practical deployment, alleviating the spectrum supply-demand imbalance. However, the co-time co-frequency transmission for the uplink and downlink intensifies inter-user cross-link interference (CLI), yielding downlink signal-to-noise ratio degradation and network rate reduction. In this study, a CLI cancellation strategy is proposed by leveraging one FD base station to perform amplitude-phase adjustment and real-time forwarding on received uplink signals, at the cost of slightly elevating the noise power at user terminals. Besides, the CLI cancellation performance is evaluated via the network achievable rate, and the mathematical expectation and cumulative distribution function of the network achievable rate are derived by modeling the time error as an unknown constant and the channel error as a zero-mean complex Gaussian variable. With errors considered, the proposed strategy still achieves an average achievable rate enhancement of about 5.6 bps/Hz compared to the traditional FD scheme. Finally, two network power schemes are optimized for two complementary targets: 1) Maximize the network achievable rate under a network outage probability threshold. Compared to the fixed-power scheme and traditional FD scheme, the proposed scheme achieves a network sum rate enhancement of approximately 9 bps/Hz and 16 bps/Hz, respectively. 2) Minimize the network outage probability under a network achievable rate threshold. The proposed scheme reduces the outage probability by 30.3% compared to the traditional FD scheme and by 16.1% compared to the fixed-power scheme.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"4190-4204"},"PeriodicalIF":6.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148926035","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":"Energy-Efficient THz Sensing With Hybrid THz/VLC Communication Under Human Blockage Effects","authors":"Hanshita Prabhakar;Neetu. R. R;Vivek Ashok Bohara","doi":"10.1109/TGCN.2026.3719028","DOIUrl":"https://doi.org/10.1109/TGCN.2026.3719028","url":null,"abstract":"This paper presents an energy-efficient indoor system integrating terahertz (THz) with visible light communication (VLC). THz communication offers ultra-high-capacity links but is limited by severe path loss, atmospheric absorption, and susceptibility to blockages. In contrast, VLC provides robust, wide indoor coverage with illumination support, thereby enabling reliable, high-speed hybrid connectivity. To leverage their respective strengths, we propose a hybrid framework that integrates terahertz sensing-access point (<inline-formula> <tex-math>$T_{s}-AP$ </tex-math></inline-formula>) with a hybrid THz/VLC communication-access point <inline-formula> <tex-math>$(T_{c}/V_{c}-AP)$ </tex-math></inline-formula> with human blockage effects, enabling reliable coverage and enhancing the energy efficiency (EE) from an integrated sensing and communication (ISAC) perspective. We first perform optimal power allocation between the <inline-formula> <tex-math>$T_{s}-AP$ </tex-math></inline-formula> and terahertz communication-access point (<inline-formula> <tex-math>$T_{c}-AP$ </tex-math></inline-formula>) to optimize the set of users served by the <inline-formula> <tex-math>$T_{c}-AP$ </tex-math></inline-formula>, considering monostatic sensing performance metrics such as probability of detection <inline-formula> <tex-math>$(P_{d})$ </tex-math></inline-formula>, probability of false alarm (<inline-formula> <tex-math>$FA_{p}$ </tex-math></inline-formula>), and sensing coverage probability (<inline-formula> <tex-math>$SC_{p}$ </tex-math></inline-formula>) with and without human blockages. Subsequently, the overall network power consumption is minimized via a mixed-integer linear programming (MILP) optimization that selects the active visible light communication-access points (<inline-formula> <tex-math>$V_{c}-APs$ </tex-math></inline-formula>) and assigns transmit powers. Furthermore, extensive performance evaluations are conducted to analyze key metrics, including average EE, average spectral efficiency (SE), average sensing rate, and average communication rate. Simulation results demonstrate that, with <inline-formula> <tex-math>$T_{s}-AP$ </tex-math></inline-formula>, most users are connected to the <inline-formula> <tex-math>$T_{c}-AP$ </tex-math></inline-formula> for communication in the absence of blockages, whereas in the presence of blockages, the majority are served by the <inline-formula> <tex-math>$V_{c}-APs$ </tex-math></inline-formula>. Overall, the proposed system ensures reliable coverage for all users while sustaining high EE.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"3986-3998"},"PeriodicalIF":6.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148781674","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":"Covertness-Oriented Water-to-Air Optical Wireless Semantic Communications","authors":"Qingqing Hu;Bin Chen;Yi Lei;Chen Gong","doi":"10.1109/TGCN.2026.3734354","DOIUrl":"https://doi.org/10.1109/TGCN.2026.3734354","url":null,"abstract":"Optical wireless communication (OWC) enables high-rate and low-latency direct data transmission between water and air, whereas wave refraction and particle scattering give rise to the issue of information leakage. To improve the energy efficiency and security in transmission, we propose a covertness-oriented semantic communication scheme for water-to-air (W2A) OWC systems in this paper. Based on a theoretical derivation regarding the monotonic correlation between the sparsity ratio of transmission encoding vectors and covert performance metrics, we introduce a sparsity-regularized semantic transmission scheme that extracts task-relevant semantic features, which significantly reduces the transmitted data volume and thereby lowers the probability of being detected by adversarial listeners. Aimed at underwater monitoring tasks, we establish a dedicated dataset with comprehensive coverage of core underwater anomalous object categories: the underwater anomaly monitoring (UAM) dataset. Based on this dataset, we perform thorough training and optimization on the parameters of the proposed scheme and test the scheme effectiveness. Simulation results demonstrate that the proposed scheme achieves high accuracy in anomaly detection under various noise conditions, while significantly improving signal covertness via adaptive sparsification. The related code and dataset will be available at <uri>https://github.com/qingqinghu-Ricky/Covert-semantic-communication-for-W2A-OWC</uri> upon publication.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"4380-4391"},"PeriodicalIF":6.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149033779","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 Deep Learning-Based Green and Highly Reliable Underwater Bionic Communication Method","authors":"Jiaming Jiang;Jingjing Wang;Wei Shi;Wenhui Luan;Meng Wang","doi":"10.1109/TGCN.2026.3693088","DOIUrl":"https://doi.org/10.1109/TGCN.2026.3693088","url":null,"abstract":"Traditional underwater acoustic communication poses challenges to the stability of the marine ecological balance. This paper proposes a green, highly reliable underwater bionic communication method based on deep learning. By simulating marine mammal vocalizations as information carriers, it achieves environmentally sustainable and highly reliable underwater communication. First, we employ discrete wavelet multiresolution decomposition to analyze the structural features of vocalizations, extracting the fourth-level low-frequency component—which exhibits stronger fading resistance and robustness—as the communication carrier. Subsequently, a bionic generative adversarial network was designed. Comprising an encoder, decoder, and discriminator, this architecture achieves accurate information embedding and reliable decoding through collaborative modeling of multi-layer features in both time and frequency domains. During model training, the deep deterministic policy gradient algorithm was incorporated to enhance the model’s adaptability across varying channel conditions. Experimental results demonstrate that at a signal-to-noise ratio of 15 dB, the decoding error rates of all four bionic signals remain below <inline-formula> <tex-math>$2.1times 10^{-4}$ </tex-math></inline-formula> when operating at an information embedding rate of 20 bit/s. This confirms the proposed method’s capability to achieve highly reliable communication under low ecological disturbance.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"3102-3117"},"PeriodicalIF":6.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148171454","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":"Performance Analysis and Pilot Length Optimization for Multi-Dimensional Sensing in Uplink CF-ISAC Systems","authors":"Jie Wang;Zhuoyan Tian;Jiamin Li;Pengcheng Zhu;Dongming Wang;Bin Sheng;Xiaohu You","doi":"10.1109/TGCN.2026.3670395","DOIUrl":"https://doi.org/10.1109/TGCN.2026.3670395","url":null,"abstract":"The fusion of multi-dimensional communication-sensing signals can significantly raise the theoretical upper limit of integrated sensing and communication (ISAC). Distributed terminals transmit uplink communication signals that provide richer multi-perspective observation information for sensing, effectively enhancing sensing dimensionality. This paper focuses on the uplink sensing process in cell-free ISAC (CF-ISAC) architecture, aiming to integrate pilot signals and data siganls from multiple terminals to achieve efficient spectrum utilization and robust uplink sensing capability. Theoretically, under imperfect decoding conditions, we derive the Cramér-Rao lower bound (CRLB) for uplink sensing accuracy. Building on this foundation, we establish a Pareto boundary model that characterizes the trade-off between communication rate and sensing precision, highlighting the critical role of optimizing the proportion of pilot symbols to data symbols. To further enhance CF-ISAC performance, we propose a pilot optimization algorithm based on a deep Q-network (DQN), which dynamically adjusts pilot length to balance communication rate and sensing precision. Simulation results demonstrate that the proposed algorithm significantly enhances sensing accuracy by integrating pilot and data, while effectively balances the sensing performance and communication performance. Therefore, this uplink ISAC method can simultaneously support high-precision multi-dimensional sensing and reliable communication without additional resource overhead, offering an efficient and scalable solution for CF-ISAC systems.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"10 ","pages":"2477-2489"},"PeriodicalIF":6.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147557621","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}