Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322334
Guangxu Zhu, Yuqing Du, Deniz Gündüz, Kaibin Huang
To mitigate the multi-access latency in federated edge learning, an efficient broadband analog transmission scheme has been recently proposed, featuring the aggregation of analog modulated gradients via the waveform-superposition property of the wireless medium. However, the assumed linear analog modulation makes it difficult to deploy this technique in modern wireless systems that exclusively use digital modulation. To address this issue, we propose in this work a novel digital version of broadband over-the-air aggregation, called one-bit broadband digital aggregation. The new scheme features one-bit gradient quantization followed by digital modulation at the edge devices and a simple threshold-based decoding at the edge server. We develop a comprehensive analysis framework for quantifying the effects of wireless channel hostilities (channel noise and fading) on the convergence rate. The analysis shows that the hostilities slow down the convergence of the learning process by introducing a scaling factor and a bias term into the gradient norm. However, all the negative effects vanish as the number of devices grows, but at a different rate for each type of channel hostility.
{"title":"One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning","authors":"Guangxu Zhu, Yuqing Du, Deniz Gündüz, Kaibin Huang","doi":"10.1109/GLOBECOM42002.2020.9322334","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322334","url":null,"abstract":"To mitigate the multi-access latency in federated edge learning, an efficient broadband analog transmission scheme has been recently proposed, featuring the aggregation of analog modulated gradients via the waveform-superposition property of the wireless medium. However, the assumed linear analog modulation makes it difficult to deploy this technique in modern wireless systems that exclusively use digital modulation. To address this issue, we propose in this work a novel digital version of broadband over-the-air aggregation, called one-bit broadband digital aggregation. The new scheme features one-bit gradient quantization followed by digital modulation at the edge devices and a simple threshold-based decoding at the edge server. We develop a comprehensive analysis framework for quantifying the effects of wireless channel hostilities (channel noise and fading) on the convergence rate. The analysis shows that the hostilities slow down the convergence of the learning process by introducing a scaling factor and a bias term into the gradient norm. However, all the negative effects vanish as the number of devices grows, but at a different rate for each type of channel hostility.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"6 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79215242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322143
Yanfang Liu, P. Olmos, David G. M. Mitchell
Generalized low-density parity-check (GLDPC) codes, where the single parity-check (SPC) nodes are replaced by generalized constraint (GC) nodes, are known to offer a reduced gap to capacity when compared with conventional LDPC codes, while also maintaining linear growth of minimum distance. However, for certain classes of practical GLDPC codes, there remains a gap to capacity even when utilizing blockwise decoding algorithm at GC nodes. In this work, we propose to optimize the design of GLDPC codes where the GC nodes are decoded with a trellis-based bit-wise Bahl-Cocke-Jelinek- Raviv (BCJR) component decoding algorithm. We analyze the asymptotic threshold behavior of GLDPC codes and determine the optimal proportion of the GC nodes in the GLDPC Tanner graph.We show significant performance improvements compared to existing designs with the same order of decoding complexity.
{"title":"On the Design of Generalized LDPC Codes with Component BCJR Decoding","authors":"Yanfang Liu, P. Olmos, David G. M. Mitchell","doi":"10.1109/GLOBECOM42002.2020.9322143","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322143","url":null,"abstract":"Generalized low-density parity-check (GLDPC) codes, where the single parity-check (SPC) nodes are replaced by generalized constraint (GC) nodes, are known to offer a reduced gap to capacity when compared with conventional LDPC codes, while also maintaining linear growth of minimum distance. However, for certain classes of practical GLDPC codes, there remains a gap to capacity even when utilizing blockwise decoding algorithm at GC nodes. In this work, we propose to optimize the design of GLDPC codes where the GC nodes are decoded with a trellis-based bit-wise Bahl-Cocke-Jelinek- Raviv (BCJR) component decoding algorithm. We analyze the asymptotic threshold behavior of GLDPC codes and determine the optimal proportion of the GC nodes in the GLDPC Tanner graph.We show significant performance improvements compared to existing designs with the same order of decoding complexity.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"16 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83331548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322364
Lei Zhou, Jiangang Shu, X. Jia
To mitigate the issues of scalability and reliability in centralized SDN, distributed SDN has emerged. However, cyber attacks in distributed SDN become increasingly serious. Since each distributed SDN controller can only obtain the network flows of its sub-network, a single controller with the biased flow information cannot detect all types of attacks in the entire network and the overall detection is a challenge. To solve the biased flow problem, we propose a collaborative anomaly detection scheme in distributed SDN, which enables multiple SDN controllers jointly train a global detection model to identify cyber attacks. We evaluate its performance based on a real-world dataset and the results show that our scheme is efficient and accurate in cyber attack detection.
{"title":"Collaborative Anomaly Detection in Distributed SDN","authors":"Lei Zhou, Jiangang Shu, X. Jia","doi":"10.1109/GLOBECOM42002.2020.9322364","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322364","url":null,"abstract":"To mitigate the issues of scalability and reliability in centralized SDN, distributed SDN has emerged. However, cyber attacks in distributed SDN become increasingly serious. Since each distributed SDN controller can only obtain the network flows of its sub-network, a single controller with the biased flow information cannot detect all types of attacks in the entire network and the overall detection is a challenge. To solve the biased flow problem, we propose a collaborative anomaly detection scheme in distributed SDN, which enables multiple SDN controllers jointly train a global detection model to identify cyber attacks. We evaluate its performance based on a real-world dataset and the results show that our scheme is efficient and accurate in cyber attack detection.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"9 2 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88517189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322515
H. Ngo, Hua Fang, Honggang Wang
Artificial intelligence (AI) is becoming a mainstream for telecommunication industry. With the utilization of millimeter-wave in 5G network, it becomes feasible to use beamforming techniques for on-body sensors in Wireless Body Area Network (WBAN) applications. Thus, there is a need for developing beamforming algorithms that can optimize WBAN network performance and a realistic dataset that can be used for training, testing, and benchmarking of the algorithms. Thus, we propose a dataset generation method for mmWave WBAN that utilizes computer vision and an adaptive deep learning-based algorithm for performance optimization of mmWave WBAN beamforming. Two major ideas are proposed: First, collecting human poses from estimation of 3D human poses in videos and generating more realistic poses using generative adversarial nets (GAN) are adopted; second, a GAN aims to predict the next beamforming directions using the previous set of directions as inputs. With available labeled human pose videos, the WBAN dataset we generate provides a sufficient amount of samples for training, testing, and benchmarking of beamforming algorithms. Additionally, the proposed adaptive beamforming algorithm does not require any intrusive data gathering methods. Our numerical studies show the advantages of our proposed approaches.
{"title":"Deep Learning-based Adaptive Beamforming for mmWave Wireless Body Area Network","authors":"H. Ngo, Hua Fang, Honggang Wang","doi":"10.1109/GLOBECOM42002.2020.9322515","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322515","url":null,"abstract":"Artificial intelligence (AI) is becoming a mainstream for telecommunication industry. With the utilization of millimeter-wave in 5G network, it becomes feasible to use beamforming techniques for on-body sensors in Wireless Body Area Network (WBAN) applications. Thus, there is a need for developing beamforming algorithms that can optimize WBAN network performance and a realistic dataset that can be used for training, testing, and benchmarking of the algorithms. Thus, we propose a dataset generation method for mmWave WBAN that utilizes computer vision and an adaptive deep learning-based algorithm for performance optimization of mmWave WBAN beamforming. Two major ideas are proposed: First, collecting human poses from estimation of 3D human poses in videos and generating more realistic poses using generative adversarial nets (GAN) are adopted; second, a GAN aims to predict the next beamforming directions using the previous set of directions as inputs. With available labeled human pose videos, the WBAN dataset we generate provides a sufficient amount of samples for training, testing, and benchmarking of beamforming algorithms. Additionally, the proposed adaptive beamforming algorithm does not require any intrusive data gathering methods. Our numerical studies show the advantages of our proposed approaches.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"3 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88716963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322194
Min Han, Jun Wu, A. Bashir, Wu Yang, Muhammad Imran, N. Nasser
Fatigue driving is one of main causes of traffic accidents. To avoid such traffic accidents, divers’ fatigue detection has been used in Intelligent Internet of Vehicles (IIoV). IIoV usually dynamically allocate computing resources according to drivers’ fatigue degree to improve the real-time of fatigue detection model. However, the traditional fatigue detection model may have bias on certain groups, which would further cause unfair resource allocation. To solve the problem, this paper proposes an improved IIoV framework, named Fair-Intelligent Internet of Vehicles (FIIoV). Compared with IIoV, we improve two layers in FIIoV, i.e., the detection layer and the normalization layer. The detection layer uses Convolutional Neural Network (CNN) to detect drivers’ fatigue degree, and then uses adversarial network to achieve fairness of detection models. The normalization layer achieves the distribution of different sensitive feature values from historical detection results generated in the detection layer, and then uses the distribution to normalize the output of the detection layer to improve the fairness and accuracy of fatigue detection models. Simulation results show that both accuracy and fairness of FIIoV is improved compared with the original IIoV.
{"title":"Adversarial Learning-based Bias Mitigation for Fatigue Driving Detection in Fair-Intelligent IoV","authors":"Min Han, Jun Wu, A. Bashir, Wu Yang, Muhammad Imran, N. Nasser","doi":"10.1109/GLOBECOM42002.2020.9322194","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322194","url":null,"abstract":"Fatigue driving is one of main causes of traffic accidents. To avoid such traffic accidents, divers’ fatigue detection has been used in Intelligent Internet of Vehicles (IIoV). IIoV usually dynamically allocate computing resources according to drivers’ fatigue degree to improve the real-time of fatigue detection model. However, the traditional fatigue detection model may have bias on certain groups, which would further cause unfair resource allocation. To solve the problem, this paper proposes an improved IIoV framework, named Fair-Intelligent Internet of Vehicles (FIIoV). Compared with IIoV, we improve two layers in FIIoV, i.e., the detection layer and the normalization layer. The detection layer uses Convolutional Neural Network (CNN) to detect drivers’ fatigue degree, and then uses adversarial network to achieve fairness of detection models. The normalization layer achieves the distribution of different sensitive feature values from historical detection results generated in the detection layer, and then uses the distribution to normalize the output of the detection layer to improve the fairness and accuracy of fatigue detection models. Simulation results show that both accuracy and fairness of FIIoV is improved compared with the original IIoV.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"146 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89269338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322093
Sheng Cao, Sixuan Dang, Xiaojiang Du, M. Guizani, Xiaosong Zhang, Xiaoming Huang
The popularity of electric vehicles depends on convenient and efficient charging services. At present, none of existing charging services allow users to reach charging stations at desirable time and charge immediately when they arrive without waiting. This paper proposes a charging reservation service approach based on the consortium blockchain and smart contract technology. Users can choose the charging station and charging time period with no charging congestion, which is based on the charging information recorded in the consortium blockchain composed of stations located in distributed regions in a city. To ensure a user arrives at the charging station on time and charge within due time as he/she has reserved, a personalized pricing scheme for reward and punishment by utilizing smart contract is proposed. We take the past charging behavior into consideration when deciding current charging price of each user, which can provide individualized prices for different users. This approach can not only greatly reduce the user’s waiting time, but also offer high cost-effective charging services for good behavior users. We carry out experimental verification under multiple sets of parameter settings, illustrate the variations in three aspects including user’s initial score, violation rate and intensity of reward and punishment, thus the feasibility of our approach is proved. Our work is a credible charging paradigm based on trust mechanism via blockchain, which has the potential to become an industry service standard for electric vehicle charging.
{"title":"An Electric Vehicle Charging Reservation Approach Based on Blockchain","authors":"Sheng Cao, Sixuan Dang, Xiaojiang Du, M. Guizani, Xiaosong Zhang, Xiaoming Huang","doi":"10.1109/GLOBECOM42002.2020.9322093","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322093","url":null,"abstract":"The popularity of electric vehicles depends on convenient and efficient charging services. At present, none of existing charging services allow users to reach charging stations at desirable time and charge immediately when they arrive without waiting. This paper proposes a charging reservation service approach based on the consortium blockchain and smart contract technology. Users can choose the charging station and charging time period with no charging congestion, which is based on the charging information recorded in the consortium blockchain composed of stations located in distributed regions in a city. To ensure a user arrives at the charging station on time and charge within due time as he/she has reserved, a personalized pricing scheme for reward and punishment by utilizing smart contract is proposed. We take the past charging behavior into consideration when deciding current charging price of each user, which can provide individualized prices for different users. This approach can not only greatly reduce the user’s waiting time, but also offer high cost-effective charging services for good behavior users. We carry out experimental verification under multiple sets of parameter settings, illustrate the variations in three aspects including user’s initial score, violation rate and intensity of reward and punishment, thus the feasibility of our approach is proved. Our work is a credible charging paradigm based on trust mechanism via blockchain, which has the potential to become an industry service standard for electric vehicle charging.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"6 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87380717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9348140
Luqiao Wang, Changle Li, Haibo Wang, Yao Zhang, Zhao Liu
As a sub-class of internet of things (IoTs), wireless sensor networks (WSNs) are becoming ubiquitous in recent years, which makes the efficient coverage of sensors challenging. Traditionally, WSNs are composed of omni-directional sensors, which, however, are still limited to unadjustable sensing angle and superfluous energy consumption. Fortunately, these limitations can be overcome by deploying directional sensors in WSNs, thus forming directional sensor networks, namely DSNs. Therefore, it is necessary to propose efficient coverage optimization methods for DSNs to solve the minimum exposure path (MEP) problem that refers to a path along which the intruder can go through WSNs with lowest detection probability. In this paper, a novel MEP-PSO algorithm-based coverage optimization mechanism is proposed to improve the coverage quality in DSNs. With our coverage optimization mechanism, the traditional MEP problem is analyzed by means of discrete geometric theories while the path searching performance is improved based on the particle swarm optimization (PSO) algorithm. Specifically, the deployment scenario is firstly discretized into multiple square grids with uniform sizes. The weighted undirected graph is thus constructed in which the path segment exposure of MEP can be analyzed by discrete geometric theory. Based on the analysis, the feasibility of PSO is evaluated and enhanced in terms of MEP searching. Using our algorithm, the coverage performance of DSNs can be improved significantly by dynamically adjusting the positions of directional sensors. Finally, we conduct extensive experiments to validate the effectiveness of our work.
{"title":"MEP-PSO Algorithm-Based Coverage Optimization in Directional Sensor Networks","authors":"Luqiao Wang, Changle Li, Haibo Wang, Yao Zhang, Zhao Liu","doi":"10.1109/GLOBECOM42002.2020.9348140","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9348140","url":null,"abstract":"As a sub-class of internet of things (IoTs), wireless sensor networks (WSNs) are becoming ubiquitous in recent years, which makes the efficient coverage of sensors challenging. Traditionally, WSNs are composed of omni-directional sensors, which, however, are still limited to unadjustable sensing angle and superfluous energy consumption. Fortunately, these limitations can be overcome by deploying directional sensors in WSNs, thus forming directional sensor networks, namely DSNs. Therefore, it is necessary to propose efficient coverage optimization methods for DSNs to solve the minimum exposure path (MEP) problem that refers to a path along which the intruder can go through WSNs with lowest detection probability. In this paper, a novel MEP-PSO algorithm-based coverage optimization mechanism is proposed to improve the coverage quality in DSNs. With our coverage optimization mechanism, the traditional MEP problem is analyzed by means of discrete geometric theories while the path searching performance is improved based on the particle swarm optimization (PSO) algorithm. Specifically, the deployment scenario is firstly discretized into multiple square grids with uniform sizes. The weighted undirected graph is thus constructed in which the path segment exposure of MEP can be analyzed by discrete geometric theory. Based on the analysis, the feasibility of PSO is evaluated and enhanced in terms of MEP searching. Using our algorithm, the coverage performance of DSNs can be improved significantly by dynamically adjusting the positions of directional sensors. Finally, we conduct extensive experiments to validate the effectiveness of our work.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"46 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84970279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322097
Xuantao Lyu, W. Feng, N. Ge
In extreme communication environments, a highly dynamic channel (HDC) often arises with quite challenging fast time-varying and nonstationary characteristics. Different from existing studies, in this work, we investigate the most intractable HDC case when the coherence time of the channel is smaller than the symbol period. We propose a deep neural network (DNN)-based symbol detector using the long short-term memory (LSTM) neural network. Particularly, the sampling sequence of the received signal per symbol is used as the input data of each LSTM unit, which can take advantage of all received information and thus achieve better performance. Furthermore, a preprocessing unit using the basis expansion model (BEM) is designed to dramatically reduce the number of parameters while training the neural network, and the BEM-DNN-based detector achieves almost the same performance as the DNNbased detector. Finally, simulation results are achieved using the highly dynamic plasma sheath channel (HDPSC) data measured from realistic shock tube experiments. The results show that the proposed DNN-based method outperforms conventional methods and requires no prior channel estimation or knowledge of channel models.
{"title":"Deep Neural Network-Based Symbol Detection for Highly Dynamic Channels","authors":"Xuantao Lyu, W. Feng, N. Ge","doi":"10.1109/GLOBECOM42002.2020.9322097","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322097","url":null,"abstract":"In extreme communication environments, a highly dynamic channel (HDC) often arises with quite challenging fast time-varying and nonstationary characteristics. Different from existing studies, in this work, we investigate the most intractable HDC case when the coherence time of the channel is smaller than the symbol period. We propose a deep neural network (DNN)-based symbol detector using the long short-term memory (LSTM) neural network. Particularly, the sampling sequence of the received signal per symbol is used as the input data of each LSTM unit, which can take advantage of all received information and thus achieve better performance. Furthermore, a preprocessing unit using the basis expansion model (BEM) is designed to dramatically reduce the number of parameters while training the neural network, and the BEM-DNN-based detector achieves almost the same performance as the DNNbased detector. Finally, simulation results are achieved using the highly dynamic plasma sheath channel (HDPSC) data measured from realistic shock tube experiments. The results show that the proposed DNN-based method outperforms conventional methods and requires no prior channel estimation or knowledge of channel models.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"44 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85353822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322416
Lijun Deng, Yixin Wang, Xiaoxi Yu, Md. Noor-A.-Rahim, Y. Guan, Zhiping Shi
Joint source channel coding (JSCC) is an effective technique in the non-asymptotic and low latency regime, while suffers from high error floor for sequences with high source probabilities and short block-lengths (HSP-SB). Aiming to address this issue, a joint source channel anytime coding (JSCAC) based on the anytime spatially coupled repeat-accumulate (ASC-RA) codes is presented. In the proposed JSCAC scheme, the adopted exponential distributed coupling (EDC) and partial joint expanding window decoding (PJEWD) can efficiently recover the early transmitted HSP-SB messages that are not fully corrected. Meanwhile, the updating mechanisms in the proposed PJEWD mitigate the complexity of expanding window decoding and the error propagation between the source and channel decoders, attributing to a better error performance. The proposed JSCAC is suitable for HSP-SB source transmission, which is a competitive candidate for communications with high reliability and low delay demands, such as streaming source and control applications, etc.
{"title":"Joint Source Channel Anytime Coding","authors":"Lijun Deng, Yixin Wang, Xiaoxi Yu, Md. Noor-A.-Rahim, Y. Guan, Zhiping Shi","doi":"10.1109/GLOBECOM42002.2020.9322416","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322416","url":null,"abstract":"Joint source channel coding (JSCC) is an effective technique in the non-asymptotic and low latency regime, while suffers from high error floor for sequences with high source probabilities and short block-lengths (HSP-SB). Aiming to address this issue, a joint source channel anytime coding (JSCAC) based on the anytime spatially coupled repeat-accumulate (ASC-RA) codes is presented. In the proposed JSCAC scheme, the adopted exponential distributed coupling (EDC) and partial joint expanding window decoding (PJEWD) can efficiently recover the early transmitted HSP-SB messages that are not fully corrected. Meanwhile, the updating mechanisms in the proposed PJEWD mitigate the complexity of expanding window decoding and the error propagation between the source and channel decoders, attributing to a better error performance. The proposed JSCAC is suitable for HSP-SB source transmission, which is a competitive candidate for communications with high reliability and low delay demands, such as streaming source and control applications, etc.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"28 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90672287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322109
Mingyang Chai, Suhua Tang, Ming Zhao, Wuyang Zhou
In multi-user millimeter wave (mmWave) communications, massive multiple-input multiple-output (MIMO) systems can achieve high gain and spectral efficiency significantly. To reduce the hardware complexity and energy consumption of massive MIMO systems, hybrid precoding as a crucial technique has attracted extensive attention. Most previous works for hybrid precoding developed algorithms based on optimization or exhaustive search approaches that either lead to sub-optimal performance or have high computational complexity. Motivated by the thought of cross-fertilization between Data-driven and Model-driven approaches, we consider applying deep learning approach and introduce the Hybrid Precoding Network(HPNet), which is a compressed deep neural network exploiting the feature extracting (thanks to convolutional kernels) and generalization ability of neural networks and the natural sparsity of mmWave channels. The HPNet takes imperfect channel state information (CSI) as the input and predicts the analog precoder and baseband precoder for multi-user massive MIMO systems. Moreover, in order to make the approach more practical in real scenarios, we further introduce a model compression algorithm, using network pruning, to greatly reduce the computational complexity and memory usage of the neural network while almost retaining the model performance and then assess the influence of pruned parameters in the network. Numerical experiments demonstrate that HPNet outperforms state-of-the-art hybrid precoding schemes with higher performance and stronger robustness. Finally, we analyze and compare the computational complexity of different schemes.
{"title":"HPNet: A Compressed Neural Network for Robust Hybrid Precoding in Multi-User Massive MIMO Systems","authors":"Mingyang Chai, Suhua Tang, Ming Zhao, Wuyang Zhou","doi":"10.1109/GLOBECOM42002.2020.9322109","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322109","url":null,"abstract":"In multi-user millimeter wave (mmWave) communications, massive multiple-input multiple-output (MIMO) systems can achieve high gain and spectral efficiency significantly. To reduce the hardware complexity and energy consumption of massive MIMO systems, hybrid precoding as a crucial technique has attracted extensive attention. Most previous works for hybrid precoding developed algorithms based on optimization or exhaustive search approaches that either lead to sub-optimal performance or have high computational complexity. Motivated by the thought of cross-fertilization between Data-driven and Model-driven approaches, we consider applying deep learning approach and introduce the Hybrid Precoding Network(HPNet), which is a compressed deep neural network exploiting the feature extracting (thanks to convolutional kernels) and generalization ability of neural networks and the natural sparsity of mmWave channels. The HPNet takes imperfect channel state information (CSI) as the input and predicts the analog precoder and baseband precoder for multi-user massive MIMO systems. Moreover, in order to make the approach more practical in real scenarios, we further introduce a model compression algorithm, using network pruning, to greatly reduce the computational complexity and memory usage of the neural network while almost retaining the model performance and then assess the influence of pruned parameters in the network. Numerical experiments demonstrate that HPNet outperforms state-of-the-art hybrid precoding schemes with higher performance and stronger robustness. Finally, we analyze and compare the computational complexity of different schemes.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"66 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90675960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：