Pub Date : 2024-09-26DOI: 10.1109/LCOMM.2024.3468872
Mahmoud Saad Abouamer;Patrick Mitran
We consider configuring discrete reconfigurable intelligent surfaces (RIS) with phase-dependent amplitude responses. The problem is formulated as a constrained virtual-channel selection problem. When considered over subsets with maximum phase-variation ${theta _{max }}lt pi $ , the solution is shown to be bounded between two matroid-constrained problems. We illustrate configuration problems whose optimal solution lies within such subsets and show that a greedy framework guarantees a worst-case $|2log _{2}cos (theta _{max }/2)|$ optimality gap uniformly over all system parameters. Subsequently, a low-complexity framework is proposed for general discrete configuration problems. Numerical experiments show that the framework performs within 4% of the optimal binary-RIS configuration and achieves at least 90% of the continuous phase-shift performance using a 3-bit configuration.
{"title":"Practical Configuration of a Discrete RIS With Phase-Dependent Amplitude Response","authors":"Mahmoud Saad Abouamer;Patrick Mitran","doi":"10.1109/LCOMM.2024.3468872","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3468872","url":null,"abstract":"We consider configuring discrete reconfigurable intelligent surfaces (RIS) with phase-dependent amplitude responses. The problem is formulated as a constrained virtual-channel selection problem. When considered over subsets with maximum phase-variation \u0000<inline-formula> <tex-math>${theta _{max }}lt pi $ </tex-math></inline-formula>\u0000, the solution is shown to be bounded between two matroid-constrained problems. We illustrate configuration problems whose optimal solution lies within such subsets and show that a greedy framework guarantees a worst-case \u0000<inline-formula> <tex-math>$|2log _{2}cos (theta _{max }/2)|$ </tex-math></inline-formula>\u0000 optimality gap uniformly over all system parameters. Subsequently, a low-complexity framework is proposed for general discrete configuration problems. Numerical experiments show that the framework performs within 4% of the optimal binary-RIS configuration and achieves at least 90% of the continuous phase-shift performance using a 3-bit configuration.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2678-2682"},"PeriodicalIF":3.7,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-09-26DOI: 10.1109/LCOMM.2024.3468299
Guanghai Xu;Yonghua Wang;Bingfeng Zheng;Jiawen Li
Deep learning (DL) has been introduced to spectrum sensing to improve spectrum utilization effectively. However, some DL-based methods struggle to sense spectrum occupancy at low-signal-to-noise ratio (SNR) and require significant quantities of labeled samples for training in new environments. Therefore, this letter proposes a novel spectrum sensing method based on deep semi-supervised learning (DSSL). Specifically, adopting the DSSL during offline training can effectively mitigate the issue of insufficient labeled samples, while introducing an improved Generative Adversarial Network (GAN) makes the convolutional neural network (CNN) model robust to incorrect pseudo-labels through adversarial learning, thereby enhancing the adaptability and performance of the CNN model. Simulation results show that the proposed approach is more effective and robust than existing methods, particularly under low SNR levels.
{"title":"Deep Semi-Supervised Learning-Based Spectrum Sensing at Low SNR","authors":"Guanghai Xu;Yonghua Wang;Bingfeng Zheng;Jiawen Li","doi":"10.1109/LCOMM.2024.3468299","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3468299","url":null,"abstract":"Deep learning (DL) has been introduced to spectrum sensing to improve spectrum utilization effectively. However, some DL-based methods struggle to sense spectrum occupancy at low-signal-to-noise ratio (SNR) and require significant quantities of labeled samples for training in new environments. Therefore, this letter proposes a novel spectrum sensing method based on deep semi-supervised learning (DSSL). Specifically, adopting the DSSL during offline training can effectively mitigate the issue of insufficient labeled samples, while introducing an improved Generative Adversarial Network (GAN) makes the convolutional neural network (CNN) model robust to incorrect pseudo-labels through adversarial learning, thereby enhancing the adaptability and performance of the CNN model. Simulation results show that the proposed approach is more effective and robust than existing methods, particularly under low SNR levels.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2558-2562"},"PeriodicalIF":3.7,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-09-25DOI: 10.1109/LCOMM.2024.3468158
Shengcai Zhou;Luping Xiang;Kun Yang
In this letter, an integrated sensing and communication (ISAC) system is investigated. Initially, we introduce a design criterion wherein sensing data acquired from the preceding time slot is employed for instantaneous optimal beamforming in the succeeding time slot, aiming to enhance the communication rate. Subsequently, the development of optimal beamforming is addressed, and a high-caliber suboptimal resolution is derived utilizing successive convex approximation (SCA) techniques combined with the iterative rank minimization (IRM) methodology. Our evaluations, grounded on numerical analyses, reveal that the communication rate of the introduced beamforming strategy surpasses that of conventional omnidirectional sensing and pilot based approaches.
{"title":"Temporal-Assisted Dynamic Beampattern Optimization in Integrated Sensing and Communication Systems","authors":"Shengcai Zhou;Luping Xiang;Kun Yang","doi":"10.1109/LCOMM.2024.3468158","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3468158","url":null,"abstract":"In this letter, an integrated sensing and communication (ISAC) system is investigated. Initially, we introduce a design criterion wherein sensing data acquired from the preceding time slot is employed for instantaneous optimal beamforming in the succeeding time slot, aiming to enhance the communication rate. Subsequently, the development of optimal beamforming is addressed, and a high-caliber suboptimal resolution is derived utilizing successive convex approximation (SCA) techniques combined with the iterative rank minimization (IRM) methodology. Our evaluations, grounded on numerical analyses, reveal that the communication rate of the introduced beamforming strategy surpasses that of conventional omnidirectional sensing and pilot based approaches.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2548-2552"},"PeriodicalIF":3.7,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-09-25DOI: 10.1109/LCOMM.2024.3465393
Xue Xiyue;He Meilin;Guo Rui
Polar codes can achieve near-capacity performance under low-complexity successive cancellation (SC) decoding. However, short to medium-length block codes exhibit insufficient error-correction performance with the SC algorithm, which limits their practical applications. Although the successive cancellation flip (SCF) decoder improves SC performance, its variable execution time poses challenges in certain scenarios. The simplified restart mechanism (SRM) reduces the execution time of SCF decoders through conditional restart of the additional trials from the second half of the codeword. However, regardless of the position of the flipped bit on the RHS, additional decoding trials can only start from a fixed restart position, which limits efficiency improvements. This letter proposes a flexible restart mechanism (FRM), introducing multiple optional restart positions to further optimize the simplified restart mechanism, reducing both execution time and its variability. In simulations, we used P(1024, 128) and P(2048, 256) polar codes to compare the performance of SCF decoders embedding with FRM and SRM. The results indicate that, compared to the SCF decoder, the SCF decoder with FRM reduces average execution time, average additional execution time, execution time variance, and median additional execution time by 14.95%, 63.42%, 86.55%, and 58.20%, respectively. Compared to the SCF decoder embedding with SRM, FRM achieves improvements in these metrics by 5.15%, 23.14%, 20.24%, and 29.71%, respectively.
{"title":"Flexible Restart Mechanism for Successive Cancellation Flip Decoding of Polar Codes","authors":"Xue Xiyue;He Meilin;Guo Rui","doi":"10.1109/LCOMM.2024.3465393","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3465393","url":null,"abstract":"Polar codes can achieve near-capacity performance under low-complexity successive cancellation (SC) decoding. However, short to medium-length block codes exhibit insufficient error-correction performance with the SC algorithm, which limits their practical applications. Although the successive cancellation flip (SCF) decoder improves SC performance, its variable execution time poses challenges in certain scenarios. The simplified restart mechanism (SRM) reduces the execution time of SCF decoders through conditional restart of the additional trials from the second half of the codeword. However, regardless of the position of the flipped bit on the RHS, additional decoding trials can only start from a fixed restart position, which limits efficiency improvements. This letter proposes a flexible restart mechanism (FRM), introducing multiple optional restart positions to further optimize the simplified restart mechanism, reducing both execution time and its variability. In simulations, we used P(1024, 128) and P(2048, 256) polar codes to compare the performance of SCF decoders embedding with FRM and SRM. The results indicate that, compared to the SCF decoder, the SCF decoder with FRM reduces average execution time, average additional execution time, execution time variance, and median additional execution time by 14.95%, 63.42%, 86.55%, and 58.20%, respectively. Compared to the SCF decoder embedding with SRM, FRM achieves improvements in these metrics by 5.15%, 23.14%, 20.24%, and 29.71%, respectively.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2459-2463"},"PeriodicalIF":3.7,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this letter, we propose a subcarrier interleaved index modulation assisted orthogonal frequency division multiplexing (SIIM-OFDM) scheme for backscatter system. Specifically, the tag data vector, modulated with subcarrier index modulation (IM), is reconstructed leveraging the combined permutation and Hadamard matrix to mitigate the sensitivity of the inter-carrier interference. Then we derive the average bit error probability (ABEP) for the SIIM-OFDM backscattered signal and analyze the asymptotic detection performance bound of the proposed system. Furthermore, a hardware verification prototype is built to validate the proposed scheme. Experimental results and simulations validate that the proposed SIIM-OFDM backscatter achieves significant performance gains compared to the existing schemes.
{"title":"Subcarrier Interleaved Index Modulation Assisted OFDM Backscatter Communication","authors":"Dongdong Mou;Lixia Xiao;Miaoran Peng;Jiaxi Zhou;Guanghua Liu;Tao Jiang","doi":"10.1109/LCOMM.2024.3467669","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3467669","url":null,"abstract":"In this letter, we propose a subcarrier interleaved index modulation assisted orthogonal frequency division multiplexing (SIIM-OFDM) scheme for backscatter system. Specifically, the tag data vector, modulated with subcarrier index modulation (IM), is reconstructed leveraging the combined permutation and Hadamard matrix to mitigate the sensitivity of the inter-carrier interference. Then we derive the average bit error probability (ABEP) for the SIIM-OFDM backscattered signal and analyze the asymptotic detection performance bound of the proposed system. Furthermore, a hardware verification prototype is built to validate the proposed scheme. Experimental results and simulations validate that the proposed SIIM-OFDM backscatter achieves significant performance gains compared to the existing schemes.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2533-2537"},"PeriodicalIF":3.7,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-09-24DOI: 10.1109/LCOMM.2024.3466995
Shuai Lyu;Yao Sun;Linke Guo;Xiaoyong Yuan;Fang Fang;Lan Zhang;Xianbin Wang
Task-oriented semantic communications (TSC) enhance radio resource efficiency by transmitting task-relevant semantic information. However, current research often overlooks the inherent semantic distinctions among encoded features. Due to unavoidable channel variations from time and frequency-selective fading, semantically sensitive feature units could be more susceptible to erroneous inference if corrupted by dynamic channels. Therefore, this letter introduces a unified channel-resilient TSC framework via information bottleneck. This framework complements existing TSC approaches by controlling information flow to capture fine-grained feature-level semantic robustness. Experiments on a case study for real-time subchannel allocation validate the framework’s effectiveness.
{"title":"Improving Channel Resilience for Task-Oriented Semantic Communications: A Unified Information Bottleneck Approach","authors":"Shuai Lyu;Yao Sun;Linke Guo;Xiaoyong Yuan;Fang Fang;Lan Zhang;Xianbin Wang","doi":"10.1109/LCOMM.2024.3466995","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3466995","url":null,"abstract":"Task-oriented semantic communications (TSC) enhance radio resource efficiency by transmitting task-relevant semantic information. However, current research often overlooks the inherent semantic distinctions among encoded features. Due to unavoidable channel variations from time and frequency-selective fading, semantically sensitive feature units could be more susceptible to erroneous inference if corrupted by dynamic channels. Therefore, this letter introduces a unified channel-resilient TSC framework via information bottleneck. This framework complements existing TSC approaches by controlling information flow to capture fine-grained feature-level semantic robustness. Experiments on a case study for real-time subchannel allocation validate the framework’s effectiveness.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2623-2627"},"PeriodicalIF":3.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This letter proposes a multi-features space domain fusion network (MFSDF-Net) to address impulsive noise suppression issues in power line communication (PLC) systems. As an end-to-end model, the proposed deep learning algorithm eliminates the need for designing null subcarriers in the original signals and fitting the data distribution at the receiver side. By utilizing parallel convolutional kernels to extract and fuse details from different domains of the signals, MFSDF-Net effectively captures dynamic changes. This enables it to more accurately and effectively identify and suppress impulsive noise, thus addressing the shortcomings of existing algorithms that inadequately identify impulsive noise and exhibit the bit error ratio (BER) floor effect. Simulation results show that with perfect channel estimation, the signal-to-noise ratio (SNR) at a BER of 1e-5 is 18 dB for this model, compared to 26 dB or higher for others, indicating an 8 dB improvement. With imperfect channel estimation, this model achieves an SNR of 30 dB at a BER of 1e-5, while other algorithms exhibit a BER floor effect.
{"title":"Impulsive Noise Suppression Network for Power Line Communication","authors":"Shuiqing Ouyang;Guojin Liu;Tiancong Huang;Yuanbo Liu;Weiyang Xu;Yucheng Wu","doi":"10.1109/LCOMM.2024.3466893","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3466893","url":null,"abstract":"This letter proposes a multi-features space domain fusion network (MFSDF-Net) to address impulsive noise suppression issues in power line communication (PLC) systems. As an end-to-end model, the proposed deep learning algorithm eliminates the need for designing null subcarriers in the original signals and fitting the data distribution at the receiver side. By utilizing parallel convolutional kernels to extract and fuse details from different domains of the signals, MFSDF-Net effectively captures dynamic changes. This enables it to more accurately and effectively identify and suppress impulsive noise, thus addressing the shortcomings of existing algorithms that inadequately identify impulsive noise and exhibit the bit error ratio (BER) floor effect. Simulation results show that with perfect channel estimation, the signal-to-noise ratio (SNR) at a BER of 1e-5 is 18 dB for this model, compared to 26 dB or higher for others, indicating an 8 dB improvement. With imperfect channel estimation, this model achieves an SNR of 30 dB at a BER of 1e-5, while other algorithms exhibit a BER floor effect.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2628-2632"},"PeriodicalIF":3.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-09-24DOI: 10.1109/LCOMM.2024.3467169
Gangfei Hu;Yukun Yang;Pingping Shang;Yuyang Peng;Poongundran Selvaprabhu;Han Hai
Adaptive spatial modulation (ASM) is a novel technology in multiple-input-multiple-output (MIMO) systems, which dynamically adjusts the modulation order of the transmit antenna based on the constantly changing channel state information (CSI). The combination of ASM and Huffman coding, using the Huffman method, allows for flexible spatial symbols to provide different activation probabilities for the transmit antenna. However, the exhaustive search conducted by Huffman-ASM requires a large number of candidate combinations to identify the optimal modulation combination. This results in high computational complexity and a heavy feedback burden. To address the challenge, this letter proposes a low-complexity algorithm based on the Huffman-ASM scheme. This scheme does not include all candidate combinations in the calculation but directly selects several optimal candidate combinations based on channel gain sorting; therefore, it reduces system complexity and alleviates the burden on the feedback path. The simulation results indicate that, compared to the conventional scheme, the proposed scheme exhibits only a slight decrease in performance while significantly reducing computational complexity.
{"title":"Low-Complexity Huffman Coding-Based Adaptive Spatial Modulation","authors":"Gangfei Hu;Yukun Yang;Pingping Shang;Yuyang Peng;Poongundran Selvaprabhu;Han Hai","doi":"10.1109/LCOMM.2024.3467169","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3467169","url":null,"abstract":"Adaptive spatial modulation (ASM) is a novel technology in multiple-input-multiple-output (MIMO) systems, which dynamically adjusts the modulation order of the transmit antenna based on the constantly changing channel state information (CSI). The combination of ASM and Huffman coding, using the Huffman method, allows for flexible spatial symbols to provide different activation probabilities for the transmit antenna. However, the exhaustive search conducted by Huffman-ASM requires a large number of candidate combinations to identify the optimal modulation combination. This results in high computational complexity and a heavy feedback burden. To address the challenge, this letter proposes a low-complexity algorithm based on the Huffman-ASM scheme. This scheme does not include all candidate combinations in the calculation but directly selects several optimal candidate combinations based on channel gain sorting; therefore, it reduces system complexity and alleviates the burden on the feedback path. The simulation results indicate that, compared to the conventional scheme, the proposed scheme exhibits only a slight decrease in performance while significantly reducing computational complexity.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2468-2472"},"PeriodicalIF":3.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-09-24DOI: 10.1109/LCOMM.2024.3466954
Jianghao Wu;Haoyu Wu;Yun Chen
Ultra-wideband (UWB) technology has been widely used for low-cost accurate ranging and positioning. To ensure communication security, a secret key must be derived before every ranging session. However, this process introduces significant latency and requires additional hardware. Therefore, this letter proposes a low-cost physical layer key generation algorithm that leverages the characteristics of multi-path channels for authentication and encryption. By effectively utilizing channel impulse response (CIR) and channel features, the proposed approach significantly reduces the key disagreement rate (KDR). Moreover, a scrambled timestamp sequence (STS) assisted error correction method is also proposed to further reduce the KDR. Simulation results demonstrate that, for a 128-bit physical key, the proposed scheme achieves a 0.5% KDR and over 83% STS matching rate at a 10 dB Signal to Noise Ratio (SNR). By utilizing several generation processes, the proposed algorithm can efficiently generate the physical layer key during the ranging session.
{"title":"A Robust Physical Layer Key Generation Algorithm for Ultra-Wideband Ranging Process","authors":"Jianghao Wu;Haoyu Wu;Yun Chen","doi":"10.1109/LCOMM.2024.3466954","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3466954","url":null,"abstract":"Ultra-wideband (UWB) technology has been widely used for low-cost accurate ranging and positioning. To ensure communication security, a secret key must be derived before every ranging session. However, this process introduces significant latency and requires additional hardware. Therefore, this letter proposes a low-cost physical layer key generation algorithm that leverages the characteristics of multi-path channels for authentication and encryption. By effectively utilizing channel impulse response (CIR) and channel features, the proposed approach significantly reduces the key disagreement rate (KDR). Moreover, a scrambled timestamp sequence (STS) assisted error correction method is also proposed to further reduce the KDR. Simulation results demonstrate that, for a 128-bit physical key, the proposed scheme achieves a 0.5% KDR and over 83% STS matching rate at a 10 dB Signal to Noise Ratio (SNR). By utilizing several generation processes, the proposed algorithm can efficiently generate the physical layer key during the ranging session.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2478-2482"},"PeriodicalIF":3.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-09-24DOI: 10.1109/LCOMM.2024.3467100
Ziyan Lin;Jiamin Li;Pengcheng Zhu;Dongming Wang
In this study, we consider a downlink millimeter wave (mmWave) transmission model with the objective of efficiently reducing beam training overhead and maximizing long-term average spectral efficiency. We propose a fast adaptive intelligent beam training algorithm based on a model-agnostic meta-reinforcement learning framework to interactively extract statistical information from mmWave environments and promptly detect beam failure by leveraging the spatial sparsity of mmWave channels. Simulation results demonstrate that the proposed algorithm exhibits rapid adaptability to dynamic communication environments and significantly enhances the spectral efficiency compared to existing algorithms.
{"title":"Fast Adaptive Intelligent Beam Training Method for mmWave Networks","authors":"Ziyan Lin;Jiamin Li;Pengcheng Zhu;Dongming Wang","doi":"10.1109/LCOMM.2024.3467100","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3467100","url":null,"abstract":"In this study, we consider a downlink millimeter wave (mmWave) transmission model with the objective of efficiently reducing beam training overhead and maximizing long-term average spectral efficiency. We propose a fast adaptive intelligent beam training algorithm based on a model-agnostic meta-reinforcement learning framework to interactively extract statistical information from mmWave environments and promptly detect beam failure by leveraging the spatial sparsity of mmWave channels. Simulation results demonstrate that the proposed algorithm exhibits rapid adaptability to dynamic communication environments and significantly enhances the spectral efficiency compared to existing algorithms.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2618-2622"},"PeriodicalIF":3.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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：