Pub Date : 2024-03-15DOI: 10.1109/TGCN.2024.3401486
Chandan Kumar;Salil Kashyap
We derive new upper bounds on outage probability (OP) and spectral efficiency (SE) for a simultaneous wireless information and energy transfer system under spatial correlation and optimal phase configuration at intelligent reflecting surface (IRS) when users are served based on round-robin (RR) scheduling, share common source to IRS links and adopt nonlinear energy harvesting. Diversity order for this system is characterized. We then extend our study to a multi-antenna source and analyze OP and SE under random and equal phase shift configurations at IRS. We design beamformers at the source and at IRS under different strategies, namely RR scheduling and simultaneous service with and without signal-to-interference-plus-noise ratio (SINR) constraint. Numerical results are presented to validate the accuracy of our statistical modeling and mathematical analysis and quantify the gain in performance relative to random and equal phase shifts. We illustrate that higher number of users can be served by increasing number of IRS elements while keeping OP fixed. We identify the operational regime where RR scheduling yields better performance than serving users simultaneously without SINR constraint. We show that increasing IRS elements can help maintain target harvested power even under stricter SINR constraint. Impact of estimation error on performance is illustrated.
{"title":"Intelligent Reflecting Surface Aided Simultaneous Wireless Information and Energy Transfer to IoT Users Under Spatial Correlation","authors":"Chandan Kumar;Salil Kashyap","doi":"10.1109/TGCN.2024.3401486","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3401486","url":null,"abstract":"We derive new upper bounds on outage probability (OP) and spectral efficiency (SE) for a simultaneous wireless information and energy transfer system under spatial correlation and optimal phase configuration at intelligent reflecting surface (IRS) when users are served based on round-robin (RR) scheduling, share common source to IRS links and adopt nonlinear energy harvesting. Diversity order for this system is characterized. We then extend our study to a multi-antenna source and analyze OP and SE under random and equal phase shift configurations at IRS. We design beamformers at the source and at IRS under different strategies, namely RR scheduling and simultaneous service with and without signal-to-interference-plus-noise ratio (SINR) constraint. Numerical results are presented to validate the accuracy of our statistical modeling and mathematical analysis and quantify the gain in performance relative to random and equal phase shifts. We illustrate that higher number of users can be served by increasing number of IRS elements while keeping OP fixed. We identify the operational regime where RR scheduling yields better performance than serving users simultaneously without SINR constraint. We show that increasing IRS elements can help maintain target harvested power even under stricter SINR constraint. Impact of estimation error on performance is illustrated.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1955-1969"},"PeriodicalIF":5.3,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679380","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 : 2024-03-15DOI: 10.1109/TGCN.2024.3401575
Jianghui Liu;Hongtao Zhang
In mobile millimeter wave (mm-Wave) systems, most deep learning-based beamforming models only input channel state information (CSI). However, as user speed increases, CSI inaccuracy increases, leading to severe performance degradation. Their single model structures cause a low generalization in large-scale networks. In this paper, a multi-branch unsupervised learning model, named MB-IncepNet, is established for mobile user beamforming, where inaccurate user location information (ULI) is extra considered to improve the beamforming robustness, and an Inception-Shortcut block is rationally constructed to improve the generalization of MB-IncepNet. Specifically, MB-IncepNet has two sub-networks for ULI and CSI inputs, which are processed first by the Inception-Shortcut processing and then fused to correct beamforming results by full-connection processing. Furthermore, the Inception-Shortcut block has multiple parallel convolution branches with convolution kernels of different sizes and a shortcut, which indicates MB-IncepNet can adapt to networks of different scales. Besides, the base station power constraint is incorporated into the model as a power layer, and the inverse of the sum-rate is chosen as the loss function for unsupervised training. The simulation results show that, under inaccurate ULI and CSI, MB-IncepNet can still achieve more than 90% effective sum-rate compared with the ideal iterative algorithm.
{"title":"Multi-Branch Unsupervised Learning-Based Beamforming in mm-Wave Massive MIMO Systems With Inaccurate Information","authors":"Jianghui Liu;Hongtao Zhang","doi":"10.1109/TGCN.2024.3401575","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3401575","url":null,"abstract":"In mobile millimeter wave (mm-Wave) systems, most deep learning-based beamforming models only input channel state information (CSI). However, as user speed increases, CSI inaccuracy increases, leading to severe performance degradation. Their single model structures cause a low generalization in large-scale networks. In this paper, a multi-branch unsupervised learning model, named MB-IncepNet, is established for mobile user beamforming, where inaccurate user location information (ULI) is extra considered to improve the beamforming robustness, and an Inception-Shortcut block is rationally constructed to improve the generalization of MB-IncepNet. Specifically, MB-IncepNet has two sub-networks for ULI and CSI inputs, which are processed first by the Inception-Shortcut processing and then fused to correct beamforming results by full-connection processing. Furthermore, the Inception-Shortcut block has multiple parallel convolution branches with convolution kernels of different sizes and a shortcut, which indicates MB-IncepNet can adapt to networks of different scales. Besides, the base station power constraint is incorporated into the model as a power layer, and the inverse of the sum-rate is chosen as the loss function for unsupervised training. The simulation results show that, under inaccurate ULI and CSI, MB-IncepNet can still achieve more than 90% effective sum-rate compared with the ideal iterative algorithm.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1840-1851"},"PeriodicalIF":5.3,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713815","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}
Unmanned aerial vehicles (UAVs) enable flexible data collection from Internet of Things (IoT) nodes in remote areas, but the data of IoT nodes face security threats. In the proposed data collection strategy based on a double cluster head (CH) framework, we exploit the inter-user interference (IUI) of uplink non-orthogonal multiple access (NOMA) to improve the security of IoT nodes. Specifically, inter-CH interference in NOMA is used as jamming signals to hide confidential data. Then a CH selection scheme is designed to alleviate the unbalanced energy consumption among member nodes in a cluster. Based on the CH selection scheme, we maximize the secrecy energy efficiency (SEE) via joint optimization of power, time scheduling, and trajectory. Due to the highly coupled variables and non-convex constraints, an alternating optimization method is used to decouple the original problem into subproblems and they are solved iteratively. In each iteration, Dinkelbach’s method is used to tackle the fractional objective function; the successive convex approximation technique is used to transform the non-convex subproblems into convex forms. In numerical simulations, our proposed data collection strategy shows effectiveness in improving SEE and hindering wiretapping. Furthermore, the proposed CH selection scheme efficiently extends the lifetime of energy-constrained IoT nodes.
{"title":"Secure Resource Allocation and Trajectory Design for UAV-Assisted IoT With Double Cluster Head","authors":"Xiangyun Meng;Xuanli Wu;Ziyi Xie;Tingting Zhang;Tao Xu","doi":"10.1109/TGCN.2024.3401107","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3401107","url":null,"abstract":"Unmanned aerial vehicles (UAVs) enable flexible data collection from Internet of Things (IoT) nodes in remote areas, but the data of IoT nodes face security threats. In the proposed data collection strategy based on a double cluster head (CH) framework, we exploit the inter-user interference (IUI) of uplink non-orthogonal multiple access (NOMA) to improve the security of IoT nodes. Specifically, inter-CH interference in NOMA is used as jamming signals to hide confidential data. Then a CH selection scheme is designed to alleviate the unbalanced energy consumption among member nodes in a cluster. Based on the CH selection scheme, we maximize the secrecy energy efficiency (SEE) via joint optimization of power, time scheduling, and trajectory. Due to the highly coupled variables and non-convex constraints, an alternating optimization method is used to decouple the original problem into subproblems and they are solved iteratively. In each iteration, Dinkelbach’s method is used to tackle the fractional objective function; the successive convex approximation technique is used to transform the non-convex subproblems into convex forms. In numerical simulations, our proposed data collection strategy shows effectiveness in improving SEE and hindering wiretapping. Furthermore, the proposed CH selection scheme efficiently extends the lifetime of energy-constrained IoT nodes.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1661-1675"},"PeriodicalIF":5.3,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713807","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 : 2024-03-15DOI: 10.1109/TGCN.2024.3401250
K. M. Deepika Rajpoot;P. Maheswaran
Orthogonal time frequency space (OTFS) is a novel modulation technique that improves the transmission reliability of the system in high-mobility scenarios. Spatial modulation (SM) appears as a green communication technique to enhance the spectral efficiency (SE) and energy efficiency (EE) of the system. In this paper, we propose the transmit antenna selection (TAS) based SM-OTFS system to improve the transmit diversity (TD) and reliability in mobile communication environments. TAS is performed based on the Euclidean distances (EDTAS) of the transmit antenna (TA) subset. Further, we present low-complexity TAS based on a tree search scheme (LCTAS-TSS) for a small-scale SM-OTFS system. We show norm and antenna correlation (N-AC) based TAS scheme (LCTAS-N-AC) to reduce the search complexity of LCTAS-TSS further. The complexities of EDTAS, LCTAS-TSS, and LCTAS-N-AC are analyzed. Analytical expressions of TD for EDTAS are verified using simulation results. Simulation results show that LCTAS-TSS attains the same BER performance as the EDTAS scheme offers at reduced complexity. Moreover, results show that LCTAS-N-AC provides substantial complexity reduction compared to LCTAS-TSS and performs better than the conventional OTFS and SM-OTFS for comparable configurations.
{"title":"Transmit Antenna Selection-Based SM-OTFS System for Green Communication","authors":"K. M. Deepika Rajpoot;P. Maheswaran","doi":"10.1109/TGCN.2024.3401250","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3401250","url":null,"abstract":"Orthogonal time frequency space (OTFS) is a novel modulation technique that improves the transmission reliability of the system in high-mobility scenarios. Spatial modulation (SM) appears as a green communication technique to enhance the spectral efficiency (SE) and energy efficiency (EE) of the system. In this paper, we propose the transmit antenna selection (TAS) based SM-OTFS system to improve the transmit diversity (TD) and reliability in mobile communication environments. TAS is performed based on the Euclidean distances (EDTAS) of the transmit antenna (TA) subset. Further, we present low-complexity TAS based on a tree search scheme (LCTAS-TSS) for a small-scale SM-OTFS system. We show norm and antenna correlation (N-AC) based TAS scheme (LCTAS-N-AC) to reduce the search complexity of LCTAS-TSS further. The complexities of EDTAS, LCTAS-TSS, and LCTAS-N-AC are analyzed. Analytical expressions of TD for EDTAS are verified using simulation results. Simulation results show that LCTAS-TSS attains the same BER performance as the EDTAS scheme offers at reduced complexity. Moreover, results show that LCTAS-N-AC provides substantial complexity reduction compared to LCTAS-TSS and performs better than the conventional OTFS and SM-OTFS for comparable configurations.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1492-1504"},"PeriodicalIF":5.3,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672035","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 : 2024-03-15DOI: 10.1109/TGCN.2024.3401192
Hao Feng;Yuping Zhao
Due to the substantial path loss inherent to millimeter-wave (mmWave) frequencies, the signal sent by the outdoor base station is seriously attenuated when it reaches the indoors. Recent research has introduced a glass-based metasurface to enhance mmWave signals in indoor settings. While a transparent reconfigurable intelligent surface (RIS) can focus signals in specific areas, achieving ideal coverage is hindered by constraints such as building structures. To address this limitation, we propose a novel RIS-assisted mmWave indoor enhancement scheme in which a transparent RIS is deployed on the glass, and a reflection RIS is introduced to enhance signal connectivity, ensuring mmWave coverage across indoor spaces. Three distinct assisted transmission scenarios are considered in this proposed scheme: passive RIS (PRIS), active RIS (ARIS), and hybrid RIS (HRIS). This paper aims to maximize the signal-to-noise ratio (SNR) of the received signal for the three assisted transmission scenarios. The closed-form solution is presented in the PRIS and the ARIS-assisted transmission scenarios. In addition, the performance of the proposed scheme is analyzed under three assisted transmission scenarios. The results indicate that the ARIS-assisted transmission scenario achieves the highest data rate and energy efficiency under a smaller transmit power while demanding minimal unit cells.
{"title":"Active RIS-Assisted mmWave Indoor Signal Enhancement Based on Transparent RIS","authors":"Hao Feng;Yuping Zhao","doi":"10.1109/TGCN.2024.3401192","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3401192","url":null,"abstract":"Due to the substantial path loss inherent to millimeter-wave (mmWave) frequencies, the signal sent by the outdoor base station is seriously attenuated when it reaches the indoors. Recent research has introduced a glass-based metasurface to enhance mmWave signals in indoor settings. While a transparent reconfigurable intelligent surface (RIS) can focus signals in specific areas, achieving ideal coverage is hindered by constraints such as building structures. To address this limitation, we propose a novel RIS-assisted mmWave indoor enhancement scheme in which a transparent RIS is deployed on the glass, and a reflection RIS is introduced to enhance signal connectivity, ensuring mmWave coverage across indoor spaces. Three distinct assisted transmission scenarios are considered in this proposed scheme: passive RIS (PRIS), active RIS (ARIS), and hybrid RIS (HRIS). This paper aims to maximize the signal-to-noise ratio (SNR) of the received signal for the three assisted transmission scenarios. The closed-form solution is presented in the PRIS and the ARIS-assisted transmission scenarios. In addition, the performance of the proposed scheme is analyzed under three assisted transmission scenarios. The results indicate that the ARIS-assisted transmission scenario achieves the highest data rate and energy efficiency under a smaller transmit power while demanding minimal unit cells.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1943-1954"},"PeriodicalIF":5.3,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679326","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 : 2024-03-13DOI: 10.1109/TGCN.2024.3399403
Raghu T. V.;M. Kiran
This research proposes priority-driven application-based channel assignment and power optimization frameworks called Channel State Information-based Resource Allocation (CSIRA) and Binary Search Power Control Mechanism (BSPCM) in D2D-enabled cellular communication. The CSIRA framework is cluster-based and uses a K-means clustering algorithm to group the D2D users into clusters. CSIRA allows the D2D users to share the cellular user’s resources without compromising the cellular user’s Quality of Service (QoS) in each cluster. Also, CSIRA ensures that public safety communication will get an edge over commercial communication during resource allocation. In order to ensure the QoS for cellular users is maintained while also enhancing the sum rate of D2D communication, the CSIRA employs the BSPCM framework. BSPCM framework utilizes a binary search algorithm to determine the optimal transmission power required for guaranteed D2D transmission within a cluster, thereby mitigating interference effects. A theoretical proof is provided to show that the suggested frameworks converge to a stable matching and end after a finite number of iterations. Simulation results demonstrate that the proposed frameworks effectively prioritizes public safety over commercial applications while preserving optimal system efficiency and quality with minimal complications.
{"title":"Priority-Driven Resource Allocation and Power Optimization in D2D Communication","authors":"Raghu T. V.;M. Kiran","doi":"10.1109/TGCN.2024.3399403","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3399403","url":null,"abstract":"This research proposes priority-driven application-based channel assignment and power optimization frameworks called Channel State Information-based Resource Allocation (CSIRA) and Binary Search Power Control Mechanism (BSPCM) in D2D-enabled cellular communication. The CSIRA framework is cluster-based and uses a K-means clustering algorithm to group the D2D users into clusters. CSIRA allows the D2D users to share the cellular user’s resources without compromising the cellular user’s Quality of Service (QoS) in each cluster. Also, CSIRA ensures that public safety communication will get an edge over commercial communication during resource allocation. In order to ensure the QoS for cellular users is maintained while also enhancing the sum rate of D2D communication, the CSIRA employs the BSPCM framework. BSPCM framework utilizes a binary search algorithm to determine the optimal transmission power required for guaranteed D2D transmission within a cluster, thereby mitigating interference effects. A theoretical proof is provided to show that the suggested frameworks converge to a stable matching and end after a finite number of iterations. Simulation results demonstrate that the proposed frameworks effectively prioritizes public safety over commercial applications while preserving optimal system efficiency and quality with minimal complications.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1479-1491"},"PeriodicalIF":5.3,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142671999","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}
Under the framework of Cellular-Vehicle-to-Everything (C-V2X) technology, although vehicles can avoid potential risks and improve traffic efficiency, shared vehicle data may have defects or faults due to inevitable environmental noise or potential sensor failures, which could pose dangers to drivers. Therefore, detecting anomalies in data transmitted via C-V2X is crucial, particularly for the driving control messages, i.e., Basic Safety Messages (BSM). However, anomaly detection in BSM data faces multiple challenges. First, BSM data contains rich driving details, necessitating modeling its high variability to better learn complex and nonlinear spatio-temporal relationships. Second, the rarity of anomalous events and the potential diversity of normal behaviors make defining anomalies more complex, increasing the difficulty of anomaly detection. Third, extracting meaningful information from a large amount of data and understanding the abstract patterns or regularities within it can also be challenging for effective reasoning at the data level. To address these challenges, we propose a hybrid generative model named CoGAN, which combines Variational Autoencoder (VAE) and Generative Adversarial Network (GAN) to implicitly learn the feature representation of normal data in an unsupervised manner. Specifically, the VAE is responsible for learning the distribution of normal data, and capturing the fundamental patterns and structures of the data; meanwhile, the discriminator is dedicated to enhancing the model’s ability to learn the distribution of normal data, refining the model’s understanding of data through the introduction of an adversarial process. CoGAN explores the distribution characteristics of normal vehicle behavior data by jointly learning the generation process and variational inference of BSM data, thereby achieving the purpose of anomaly detection.
{"title":"Generative Abnormal Data Detection for Enhancing Cellular Vehicle-to-Everything-Based Road Safety","authors":"Liang Zhao;Xu Fan;Ammar Hawbani;Lexi Xu;Keping Yu;Zhi Liu;Osama Alfarraj","doi":"10.1109/TGCN.2024.3400403","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3400403","url":null,"abstract":"Under the framework of Cellular-Vehicle-to-Everything (C-V2X) technology, although vehicles can avoid potential risks and improve traffic efficiency, shared vehicle data may have defects or faults due to inevitable environmental noise or potential sensor failures, which could pose dangers to drivers. Therefore, detecting anomalies in data transmitted via C-V2X is crucial, particularly for the driving control messages, i.e., Basic Safety Messages (BSM). However, anomaly detection in BSM data faces multiple challenges. First, BSM data contains rich driving details, necessitating modeling its high variability to better learn complex and nonlinear spatio-temporal relationships. Second, the rarity of anomalous events and the potential diversity of normal behaviors make defining anomalies more complex, increasing the difficulty of anomaly detection. Third, extracting meaningful information from a large amount of data and understanding the abstract patterns or regularities within it can also be challenging for effective reasoning at the data level. To address these challenges, we propose a hybrid generative model named CoGAN, which combines Variational Autoencoder (VAE) and Generative Adversarial Network (GAN) to implicitly learn the feature representation of normal data in an unsupervised manner. Specifically, the VAE is responsible for learning the distribution of normal data, and capturing the fundamental patterns and structures of the data; meanwhile, the discriminator is dedicated to enhancing the model’s ability to learn the distribution of normal data, refining the model’s understanding of data through the introduction of an adversarial process. CoGAN explores the distribution characteristics of normal vehicle behavior data by jointly learning the generation process and variational inference of BSM data, thereby achieving the purpose of anomaly detection.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1466-1478"},"PeriodicalIF":5.3,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672199","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 : 2024-03-12DOI: 10.1109/TGCN.2024.3375011
Amitkumar V. Jha;Bhargav Appasani;Mohammad S. Khan;Houbing Herbert Song
Underwater wireless sensor network (UWSN) is a pervasive technology with different characteristics and requirements, where energy conservation is a stringent requirement. Improving the network lifetime can have tremendous practical utility in these networks. The energy of the nodes in the network can be conserved by devising an efficient cluster head selection mechanism. This paper presents a novel energy-efficient clustering protocol (EECP) for the UWSN. The proposed protocol segregates the network based on horizontal clustering. In every iteration, the cluster heads are selected based on the energy level of the nodes. The performance of the proposed protocol is measured in terms of energy efficiency and network lifetime. Moreover, the performance of the EECP is further improved by adding nearest neighbor criteria for selecting the cluster head. This protocol is named as energy-efficient clustering protocol with nearest neighbor (EECP-NN). The efficacy of the proposed protocols is evaluated by comparing their performance with some of the state-of-the-art cluster-based protocols in this study.
{"title":"A Novel Clustering Protocol for Network Lifetime Maximization in Underwater Wireless Sensor Networks","authors":"Amitkumar V. Jha;Bhargav Appasani;Mohammad S. Khan;Houbing Herbert Song","doi":"10.1109/TGCN.2024.3375011","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3375011","url":null,"abstract":"Underwater wireless sensor network (UWSN) is a pervasive technology with different characteristics and requirements, where energy conservation is a stringent requirement. Improving the network lifetime can have tremendous practical utility in these networks. The energy of the nodes in the network can be conserved by devising an efficient cluster head selection mechanism. This paper presents a novel energy-efficient clustering protocol (EECP) for the UWSN. The proposed protocol segregates the network based on horizontal clustering. In every iteration, the cluster heads are selected based on the energy level of the nodes. The performance of the proposed protocol is measured in terms of energy efficiency and network lifetime. Moreover, the performance of the EECP is further improved by adding nearest neighbor criteria for selecting the cluster head. This protocol is named as energy-efficient clustering protocol with nearest neighbor (EECP-NN). The efficacy of the proposed protocols is evaluated by comparing their performance with some of the state-of-the-art cluster-based protocols in this study.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1371-1384"},"PeriodicalIF":5.3,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672000","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 : 2024-03-12DOI: 10.1109/TGCN.2024.3374700
Penghong Wang;Jiahui Li;Chen Liu;Xiaopeng Fan;Mengyao Ma;Yaowei Wang
Semantic communication has significantly improved in single-modal single-task scenarios, but its progress is limited in multimodal and multi-task transmission contexts. To address this issue, this paper investigates a distributed semantic communication system for audio-visual parsing (AVP) task. The system acquires audio-visual information from distributed terminals and conducts multi-task analysis on the far-end server, which involves event categorization and boundary recording. We propose a distributed deep joint source-channel coding scheme with auxiliary information feedback to implement this system, aiming to enhance parsing performance and reduce bandwidth consumption during communication. Specifically, the server initially receives the audio feature from the audio terminal and then sends the semantic information extracted from the audio feature back to the visual terminal. The received semantic and visual information are interactively processed by the visual terminal before being encoded and transmitted. The audio and visual semantic information received is processed and parsed on the far-end server. The experimental results demonstrate a significant reduction in transmission bandwidth consumption and notable performance improvements across various evaluation metrics for distributed AVP task compared to current state-of-the-art methods.
{"title":"Distributed Semantic Communications for Multimodal Audio-Visual Parsing Tasks","authors":"Penghong Wang;Jiahui Li;Chen Liu;Xiaopeng Fan;Mengyao Ma;Yaowei Wang","doi":"10.1109/TGCN.2024.3374700","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3374700","url":null,"abstract":"Semantic communication has significantly improved in single-modal single-task scenarios, but its progress is limited in multimodal and multi-task transmission contexts. To address this issue, this paper investigates a distributed semantic communication system for audio-visual parsing (AVP) task. The system acquires audio-visual information from distributed terminals and conducts multi-task analysis on the far-end server, which involves event categorization and boundary recording. We propose a distributed deep joint source-channel coding scheme with auxiliary information feedback to implement this system, aiming to enhance parsing performance and reduce bandwidth consumption during communication. Specifically, the server initially receives the audio feature from the audio terminal and then sends the semantic information extracted from the audio feature back to the visual terminal. The received semantic and visual information are interactively processed by the visual terminal before being encoded and transmitted. The audio and visual semantic information received is processed and parsed on the far-end server. The experimental results demonstrate a significant reduction in transmission bandwidth consumption and notable performance improvements across various evaluation metrics for distributed AVP task compared to current state-of-the-art methods.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1707-1716"},"PeriodicalIF":5.3,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713826","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 : 2024-03-12DOI: 10.1109/TGCN.2024.3376571
Fulai Liu;Zhuoyao Duan;Lijie Zhang;Baozhu Shi;Yubiao Liu;Ruiyan Du
This paper presents a dynamic partially connected (DPC) structure-based convolutional neural network (CNN) hybrid precoding with multi-user optimization algorithm. In the proposed algorithm, a multi-output CNN framework is constructed to simultaneously optimize the phase shifter and switch precoders, including custom ‘Out’ layer, deep neural network (DNN)-based analog phase shifter subnetwork, namely DNN-Fps, and DNN-based switch subnetwork, called DNN-Fs. Specifically, the DNN-Fps is designed to obtain the vectorized phase shifter precoder with constant modulus constraint. The DNN-Fs is utilized to output the vectorized switch precoder with the binary constraint. The ‘Out’ layer is defined to obtain the vectorized analog precoder with constant modulus and binary constraints. Moreover, to further improve the real-time performance of hybrid precoding, a dynamic pruning technique is applied to remove the redundant parameters for the DPC-CNN model. Finally, the DPC-CNN is trained using the loss function with the residual between the vectorized analog precoders of the fully connected (FC) and DPC structures. Theoretical analyses and simulation experiments show that compared to the FC and partially connected structures, the proposed DPC-CNN hybrid precoding algorithm can achieve a balance between spectral efficiency and energy efficiency with less execution time.
{"title":"DPC-CNN Algorithm for Multiuser Hybrid Precoding With Dynamic Structure","authors":"Fulai Liu;Zhuoyao Duan;Lijie Zhang;Baozhu Shi;Yubiao Liu;Ruiyan Du","doi":"10.1109/TGCN.2024.3376571","DOIUrl":"https://doi.org/10.1109/TGCN.2024.3376571","url":null,"abstract":"This paper presents a dynamic partially connected (DPC) structure-based convolutional neural network (CNN) hybrid precoding with multi-user optimization algorithm. In the proposed algorithm, a multi-output CNN framework is constructed to simultaneously optimize the phase shifter and switch precoders, including custom ‘Out’ layer, deep neural network (DNN)-based analog phase shifter subnetwork, namely DNN-Fps, and DNN-based switch subnetwork, called DNN-Fs. Specifically, the DNN-Fps is designed to obtain the vectorized phase shifter precoder with constant modulus constraint. The DNN-Fs is utilized to output the vectorized switch precoder with the binary constraint. The ‘Out’ layer is defined to obtain the vectorized analog precoder with constant modulus and binary constraints. Moreover, to further improve the real-time performance of hybrid precoding, a dynamic pruning technique is applied to remove the redundant parameters for the DPC-CNN model. Finally, the DPC-CNN is trained using the loss function with the residual between the vectorized analog precoders of the fully connected (FC) and DPC structures. Theoretical analyses and simulation experiments show that compared to the FC and partially connected structures, the proposed DPC-CNN hybrid precoding algorithm can achieve a balance between spectral efficiency and energy efficiency with less execution time.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"8 4","pages":"1361-1370"},"PeriodicalIF":5.3,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672043","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：