In this paper, we consider the physical layer security for a mobile edge computing (MEC) network where multiple single-antenna users aim to securely offload partial computation tasks simultaneously to an access point (AP) integrated with an MEC server by leveraging an intelligent reflecting surface (IRS) in the presence of a multi-antenna eavesdropper. A friendly jammer is further introduced to improve transmission secrecy. We formulate a problem of minimizing the sum energy consumption by jointly designing the allocation of computation bits for local computing and offloading, the transmit power of both users and jammer, the multi-user detection matrix at the AP, and the phase shift matrix at the IRS. The formulated problem is a non-convex problem that is hard to tackle directly, so we decompose it into tractable subproblems and develop an alternating optimization approach by combing semidefinite relaxation algorithm. Numerical results are provided to demonstrate the effectiveness of the proposed scheme and the benefit of deploying an IRS for achieving a secure and energy-efficient MEC network.
{"title":"Energy-efficient Resource Allocation for Intelligent Reflecting Surface Aided MEC Networks","authors":"Yating Wen, Tongxing Zheng, Yongxia Tong, Xin Chen, Menghan Lin, Wenjie Wang","doi":"10.1109/ICCWorkshops53468.2022.9882166","DOIUrl":"https://doi.org/10.1109/ICCWorkshops53468.2022.9882166","url":null,"abstract":"In this paper, we consider the physical layer security for a mobile edge computing (MEC) network where multiple single-antenna users aim to securely offload partial computation tasks simultaneously to an access point (AP) integrated with an MEC server by leveraging an intelligent reflecting surface (IRS) in the presence of a multi-antenna eavesdropper. A friendly jammer is further introduced to improve transmission secrecy. We formulate a problem of minimizing the sum energy consumption by jointly designing the allocation of computation bits for local computing and offloading, the transmit power of both users and jammer, the multi-user detection matrix at the AP, and the phase shift matrix at the IRS. The formulated problem is a non-convex problem that is hard to tackle directly, so we decompose it into tractable subproblems and develop an alternating optimization approach by combing semidefinite relaxation algorithm. Numerical results are provided to demonstrate the effectiveness of the proposed scheme and the benefit of deploying an IRS for achieving a secure and energy-efficient MEC network.","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115721438","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 : 2022-05-16DOI: 10.1109/iccworkshops53468.2022.9814661
Yingchao Yang, Zhiquan Bai, Hongwu Liu, K. Pang, Xinhong Hao, K. Kim
In order to enhance the effectiveness and the reliability of high mobility communication, we propose a spatial-index modulation (SIM) based orthogonal time frequency space (OTFS) system, named SIM-OTFS, which is a three dimensional index modulation (IM) adopting the transmit antenna, delay, and Doppler indexes in the space and delay-Doppler domains, respectively, to achieve higher transmission rate. The system model and the detailed signal processing of the SIM-OTFS system are provided. Then, we also analyze the average bit error rate (ABER) performance of the proposed SIM-OTFS system based on the union bound theory. Numerical results verify the correctness of the theoretical ABER analysis and demonstrate the ABER superiority of the SIM-OTFS system over the traditional multiple-input multiple-output OTFS (MIMO-OTFS) and spatial modulation (SM) and IM based orthogonal frequency division multiplexing (SM-OFDM-IM) systems under high mobility. Furthermore, the influence of the multipath channel on the ABER performance of the SIM-OTFS system is also illustrated.
{"title":"Design and Performance Analysis of Spatial-Index Modulation Based Orthogonal Time Frequency Space System","authors":"Yingchao Yang, Zhiquan Bai, Hongwu Liu, K. Pang, Xinhong Hao, K. Kim","doi":"10.1109/iccworkshops53468.2022.9814661","DOIUrl":"https://doi.org/10.1109/iccworkshops53468.2022.9814661","url":null,"abstract":"In order to enhance the effectiveness and the reliability of high mobility communication, we propose a spatial-index modulation (SIM) based orthogonal time frequency space (OTFS) system, named SIM-OTFS, which is a three dimensional index modulation (IM) adopting the transmit antenna, delay, and Doppler indexes in the space and delay-Doppler domains, respectively, to achieve higher transmission rate. The system model and the detailed signal processing of the SIM-OTFS system are provided. Then, we also analyze the average bit error rate (ABER) performance of the proposed SIM-OTFS system based on the union bound theory. Numerical results verify the correctness of the theoretical ABER analysis and demonstrate the ABER superiority of the SIM-OTFS system over the traditional multiple-input multiple-output OTFS (MIMO-OTFS) and spatial modulation (SM) and IM based orthogonal frequency division multiplexing (SM-OFDM-IM) systems under high mobility. Furthermore, the influence of the multipath channel on the ABER performance of the SIM-OTFS system is also illustrated.","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114829196","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 : 2022-05-16DOI: 10.1109/iccworkshops53468.2022.9814565
Pankaj Singh, B. Kim, Sung-Yoon Jung
Display field communication (DFC) is an imper-ceptible display-to-camera (D2C) communication paradigm in which data is conveyed by taking advantage of the spectral domain properties of individual video frames. The data are embedded in the frequency domain of an image frame and the data-embedded image is then displayed on an electronic screen. The display screen is subsequently been captured by a camera receiver and the data are decoded. Although DFC successfully transmits and decodes data from the frequency domain of images, it uses reference frames to reliably decode the data, which significantly degrades the achievable data rate of the system. In this paper, we propose a technique termed pilot-assisted iterative spectral image reconstruction, which eliminates the use of reference frames. In particular, a $256times 256$ pixel grayscale image is used for embedding the data that consists of information bits and pilots. The pilot symbols were used for the reconstruction of the reference frames at the receiver. More importantly, the proposed method reconstructs the spectral image frames iteratively using the reliable information symbol estimates fed back by the camera decoder that are being used as fresh pilots in subsequent iterations. After successful reference image reconstruction, the data are decoded using an advanced minimum mean-square error (MMSE) receiver. From numerical simulations, we show that the proposed method significantly boosts the data transmission capacity of the DFC system over the conventional DFC that uses reference frames.
{"title":"Iterative Spectral Image Reconstruction-Based Display Field Communication Using Advanced Receiver","authors":"Pankaj Singh, B. Kim, Sung-Yoon Jung","doi":"10.1109/iccworkshops53468.2022.9814565","DOIUrl":"https://doi.org/10.1109/iccworkshops53468.2022.9814565","url":null,"abstract":"Display field communication (DFC) is an imper-ceptible display-to-camera (D2C) communication paradigm in which data is conveyed by taking advantage of the spectral domain properties of individual video frames. The data are embedded in the frequency domain of an image frame and the data-embedded image is then displayed on an electronic screen. The display screen is subsequently been captured by a camera receiver and the data are decoded. Although DFC successfully transmits and decodes data from the frequency domain of images, it uses reference frames to reliably decode the data, which significantly degrades the achievable data rate of the system. In this paper, we propose a technique termed pilot-assisted iterative spectral image reconstruction, which eliminates the use of reference frames. In particular, a $256times 256$ pixel grayscale image is used for embedding the data that consists of information bits and pilots. The pilot symbols were used for the reconstruction of the reference frames at the receiver. More importantly, the proposed method reconstructs the spectral image frames iteratively using the reliable information symbol estimates fed back by the camera decoder that are being used as fresh pilots in subsequent iterations. After successful reference image reconstruction, the data are decoded using an advanced minimum mean-square error (MMSE) receiver. From numerical simulations, we show that the proposed method significantly boosts the data transmission capacity of the DFC system over the conventional DFC that uses reference frames.","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"13 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116434685","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}
Recent investigations show that, both reconfigurable intelligent surface (RIS) and unmanned aerial vehicle (UAV) could be utilized in enhancing the wireless coverage and improving the positioning accuracy. Since the position information and communication connections are unavailable in urban blind areas, we propose a novel UAV-mounted RIS (URIS)-aided communication and localization integration system for ground vehicles (GVs). We first introduce the metrics of position error bound (PEB) and spectral efficiency (SE) to evaluate the localization and communication performances of the GV. A unified joint UAV trajectory planning and RIS phase-shifts configuration problem is formulated to strike a balance between localization and commu-nication. This non-convex problem can be decomposed into two subproblems: RIS phase-shifts configuration and UAV trajectory planning problems, respectively. A Block Coordinate Descent (BCD) based phase-shifts optimizer and a deep reinforcement learning (DRL) based real-time trajectory generator are designed to tackle the decomposed problems. Finally, numerical results are provided and can verify the effectiveness of our proposed framework.
{"title":"A UAV mounted RIS aided communication and localization integration system for ground vehicles","authors":"Jiping Luo, Tianhao Liang, Chunsheng Chen, Tingting Zhang","doi":"10.1109/iccworkshops53468.2022.9814581","DOIUrl":"https://doi.org/10.1109/iccworkshops53468.2022.9814581","url":null,"abstract":"Recent investigations show that, both reconfigurable intelligent surface (RIS) and unmanned aerial vehicle (UAV) could be utilized in enhancing the wireless coverage and improving the positioning accuracy. Since the position information and communication connections are unavailable in urban blind areas, we propose a novel UAV-mounted RIS (URIS)-aided communication and localization integration system for ground vehicles (GVs). We first introduce the metrics of position error bound (PEB) and spectral efficiency (SE) to evaluate the localization and communication performances of the GV. A unified joint UAV trajectory planning and RIS phase-shifts configuration problem is formulated to strike a balance between localization and commu-nication. This non-convex problem can be decomposed into two subproblems: RIS phase-shifts configuration and UAV trajectory planning problems, respectively. A Block Coordinate Descent (BCD) based phase-shifts optimizer and a deep reinforcement learning (DRL) based real-time trajectory generator are designed to tackle the decomposed problems. Finally, numerical results are provided and can verify the effectiveness of our proposed framework.","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"27 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120859191","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 : 2022-05-16DOI: 10.1109/ICCWorkshops53468.2022.9882162
Eun-Se Lee, Hyungbin Park, C. Kim, Suk-Shin Lee
With the rise in computation-intensive and delay-sensitive applications, the limited resource of the user device has become a significant challenge. Mobile Edge Computing(MEC) has emerged as a paradigm to compensate for the resource shortage. When offloading application’s tasks to the Mobile Edge Network(MEN) of the MEC with consideration of task dependency and resource usage, the offloading process also requires consideration of user device’s mobility. However, most existing research that consider user mobility or task dependency among several factors assume that the offloaded tasks in the MEC are parallelizable or that the user device is immobile. Nev-ertheless, real-world applications have sequential dependencies and user devices are frequently mobile. In this situation, the previous methods no longer apply. In this paper, we propose a novel algorithm that jointly considers task dependency and user mobility to minimize application completion time in MEN. We show the improved performance of our proposed algorithm over the existing research.
{"title":"Offloading Dependent Tasks with Mobility in Mobile Edge Computing","authors":"Eun-Se Lee, Hyungbin Park, C. Kim, Suk-Shin Lee","doi":"10.1109/ICCWorkshops53468.2022.9882162","DOIUrl":"https://doi.org/10.1109/ICCWorkshops53468.2022.9882162","url":null,"abstract":"With the rise in computation-intensive and delay-sensitive applications, the limited resource of the user device has become a significant challenge. Mobile Edge Computing(MEC) has emerged as a paradigm to compensate for the resource shortage. When offloading application’s tasks to the Mobile Edge Network(MEN) of the MEC with consideration of task dependency and resource usage, the offloading process also requires consideration of user device’s mobility. However, most existing research that consider user mobility or task dependency among several factors assume that the offloaded tasks in the MEC are parallelizable or that the user device is immobile. Nev-ertheless, real-world applications have sequential dependencies and user devices are frequently mobile. In this situation, the previous methods no longer apply. In this paper, we propose a novel algorithm that jointly considers task dependency and user mobility to minimize application completion time in MEN. We show the improved performance of our proposed algorithm over the existing research.","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123936285","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 : 2022-05-16DOI: 10.1109/iccworkshops53468.2022.9814464
Jia Guo, Chenyang Yang
When knowing the goal of transmission, resources can be used more efficiently in semantic communication systems, where only the information necessary for accomplishing the goal needs to be transmitted. Existing works for semantic commu-nications do not investigate resource allocation. In this paper, we consider a multi-antenna-multi-subcarrier system for trans-mitting images to multiple users, by taking a goal of classifying the images as an example. We propose a semantic information-aware precoding policy to mitigate multi-user interference based on deep learning, where the modulated symbols of the users are input into a graph neural network together with estimated channel matrix for learning the policy. To emphasize the impact of harnessing semantic information on precoding, we apply two convolutional neural networks to learn the mapping from the image of each user to modulated symbols and the mapping from the received symbols of each user to a representation of the image, respectively. A fully-connected neural network is followed for image classification. After training these neural networks jointly, the learned precoding policy operates in a water-filling manner, which allocates more power for transmitting stronger symbols, where the important information for classification is carried. Simulation results show that the learned precoding policy is superior to existing precoding policies in reducing the bandwidth for transmission required to achieve an expected classification accuracy when the signal-to-noise ratio is low, channel estimation error is high, and the number of users is large,
{"title":"Learning Precoding for Semantic Communications","authors":"Jia Guo, Chenyang Yang","doi":"10.1109/iccworkshops53468.2022.9814464","DOIUrl":"https://doi.org/10.1109/iccworkshops53468.2022.9814464","url":null,"abstract":"When knowing the goal of transmission, resources can be used more efficiently in semantic communication systems, where only the information necessary for accomplishing the goal needs to be transmitted. Existing works for semantic commu-nications do not investigate resource allocation. In this paper, we consider a multi-antenna-multi-subcarrier system for trans-mitting images to multiple users, by taking a goal of classifying the images as an example. We propose a semantic information-aware precoding policy to mitigate multi-user interference based on deep learning, where the modulated symbols of the users are input into a graph neural network together with estimated channel matrix for learning the policy. To emphasize the impact of harnessing semantic information on precoding, we apply two convolutional neural networks to learn the mapping from the image of each user to modulated symbols and the mapping from the received symbols of each user to a representation of the image, respectively. A fully-connected neural network is followed for image classification. After training these neural networks jointly, the learned precoding policy operates in a water-filling manner, which allocates more power for transmitting stronger symbols, where the important information for classification is carried. Simulation results show that the learned precoding policy is superior to existing precoding policies in reducing the bandwidth for transmission required to achieve an expected classification accuracy when the signal-to-noise ratio is low, channel estimation error is high, and the number of users is large,","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"82 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125922808","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 : 2022-05-16DOI: 10.1109/iccworkshops53468.2022.9814638
Qi Li, Jinhong Yuan, Hai-Hsing Lin
In this article, a successive interference cancellation (SIC) based minimum mean squared error (MMSE) signal detection is investigated for orthogonal time frequency space (OTFS) modulation. In this proposed detection technique, the transmit symbols will be detected on the basis of layers, and different multipath components of the same layer signal together with its interference will be coherently combined and suppressed through MMSE filtering. The performance will be further improved from an iterative operation on SIC-MMSE detection. The complexity of calculating MMSE filter coefficients can be reduced when detection is performed in the time domain due to its simpler channel structures. Simulation shows that our proposed SIC-MMSE detection can outperform maximum-ratio-combing (MRC) thanks to its inherent balances on matched filter and zero-forcing detector.
{"title":"Iterative MMSE Detection for Orthogonal Time Frequency Space Modulation","authors":"Qi Li, Jinhong Yuan, Hai-Hsing Lin","doi":"10.1109/iccworkshops53468.2022.9814638","DOIUrl":"https://doi.org/10.1109/iccworkshops53468.2022.9814638","url":null,"abstract":"In this article, a successive interference cancellation (SIC) based minimum mean squared error (MMSE) signal detection is investigated for orthogonal time frequency space (OTFS) modulation. In this proposed detection technique, the transmit symbols will be detected on the basis of layers, and different multipath components of the same layer signal together with its interference will be coherently combined and suppressed through MMSE filtering. The performance will be further improved from an iterative operation on SIC-MMSE detection. The complexity of calculating MMSE filter coefficients can be reduced when detection is performed in the time domain due to its simpler channel structures. Simulation shows that our proposed SIC-MMSE detection can outperform maximum-ratio-combing (MRC) thanks to its inherent balances on matched filter and zero-forcing detector.","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124828077","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 : 2022-05-16DOI: 10.1109/iccworkshops53468.2022.9814491
Yimeng Zhang, Wenjun Xu, Hui Gao, Fengyu Wang
In this paper, a multi-user semantic communication system is studied to execute object-identification tasks, where correlated source data among different users is transmitted via a shared channel, and the introduced inter-user data-stream interference (IDI) deteriorates the identification performance severely. Traditional solutions adopt powerful channel codes for individual data protection, e.g., very low coding rate, to guarantee the identification performance, at the cost of sacrificing the real-time requirements. We propose to exploit the data correlation among users to perform cooperative identification. Specifically, by designing a convolutional neural network (CNN) based framework and constructing a combination of loss functions, a deep learning (DL) based multi-user semantic communication system for cooperative object identification, named DeepSC-COl, is proposed to fuse individual semantic features into a global feature through dynamically-tailored weights. In this way, multiple semantic features are jointly leveraged for identification without an extra increase of latency. Evaluation results show that the proposed DeepSC-COI outperforms the non-cooperative scheme with the performance gain of 86.9% at -3 dB, in terms of mean Average Precision (mAP).
{"title":"Multi-User Semantic Communications for Cooperative Object Identification","authors":"Yimeng Zhang, Wenjun Xu, Hui Gao, Fengyu Wang","doi":"10.1109/iccworkshops53468.2022.9814491","DOIUrl":"https://doi.org/10.1109/iccworkshops53468.2022.9814491","url":null,"abstract":"In this paper, a multi-user semantic communication system is studied to execute object-identification tasks, where correlated source data among different users is transmitted via a shared channel, and the introduced inter-user data-stream interference (IDI) deteriorates the identification performance severely. Traditional solutions adopt powerful channel codes for individual data protection, e.g., very low coding rate, to guarantee the identification performance, at the cost of sacrificing the real-time requirements. We propose to exploit the data correlation among users to perform cooperative identification. Specifically, by designing a convolutional neural network (CNN) based framework and constructing a combination of loss functions, a deep learning (DL) based multi-user semantic communication system for cooperative object identification, named DeepSC-COl, is proposed to fuse individual semantic features into a global feature through dynamically-tailored weights. In this way, multiple semantic features are jointly leveraged for identification without an extra increase of latency. Evaluation results show that the proposed DeepSC-COI outperforms the non-cooperative scheme with the performance gain of 86.9% at -3 dB, in terms of mean Average Precision (mAP).","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128518241","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 : 2022-05-16DOI: 10.1109/iccworkshops53468.2022.9814643
Qiaohong Yu, Huandong Wang, Tong Li, Depeng Jin, Xing Wang, Lin Zhu, Junlan Feng, Chao Deng
With the rapid explosion of network traffic volume, the prediction of traffic overload in the cellular network, which is defined as whether the traffic of a base station exceeds a predefined threshold, has become a crucial research problem regarding energy utilization and resource allocation. Most existing methods primarily model the dynamic patterns of traffic time series and compare the results with the predefined thresholds to predict traffic overload, taking into account a large amount of small-scale redundant data. To focus on the changes near the thresholds, i.e., the traffic burst circumstances, this paper adopts the soft-attention mechanism to fuse the threshold-based discrete and continuous time series characteristics to predict traffic overload. In addition, to capture the spatial correlations of the most related neighbors, we employ a Dual-KNN mechanism to select neighboring base stations and leverage the Graph Attention Network (GAT) to capture the spatial dependencies. Furthermore, we deploy a gated Temporal Convolutional Network (TCN) to model the temporal dependencies of the network traffic. Extensive experiments demonstrate that our proposed method effectively forecasts the traffic overload and outperforms the state-of-the-art algorithms by 4.07%.
{"title":"Network Traffic Overload Prediction with Temporal Graph Attention Convolutional Networks","authors":"Qiaohong Yu, Huandong Wang, Tong Li, Depeng Jin, Xing Wang, Lin Zhu, Junlan Feng, Chao Deng","doi":"10.1109/iccworkshops53468.2022.9814643","DOIUrl":"https://doi.org/10.1109/iccworkshops53468.2022.9814643","url":null,"abstract":"With the rapid explosion of network traffic volume, the prediction of traffic overload in the cellular network, which is defined as whether the traffic of a base station exceeds a predefined threshold, has become a crucial research problem regarding energy utilization and resource allocation. Most existing methods primarily model the dynamic patterns of traffic time series and compare the results with the predefined thresholds to predict traffic overload, taking into account a large amount of small-scale redundant data. To focus on the changes near the thresholds, i.e., the traffic burst circumstances, this paper adopts the soft-attention mechanism to fuse the threshold-based discrete and continuous time series characteristics to predict traffic overload. In addition, to capture the spatial correlations of the most related neighbors, we employ a Dual-KNN mechanism to select neighboring base stations and leverage the Graph Attention Network (GAT) to capture the spatial dependencies. Furthermore, we deploy a gated Temporal Convolutional Network (TCN) to model the temporal dependencies of the network traffic. Extensive experiments demonstrate that our proposed method effectively forecasts the traffic overload and outperforms the state-of-the-art algorithms by 4.07%.","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129968482","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 : 2022-05-16DOI: 10.1109/iccworkshops53468.2022.9814666
A. Bora, K. Phan, Y. Hong
Low earth orbit (LEO) satellite communication (satcom) systems are expected to provide reliable high-speed communications under high-mobility environments. Recent research has demonstrated that the orthogonal time frequency space (OTFS) modulation technique has the potential to meet the demands for LEO satcom. In addition, multiple-input multiple-output (MIMO) communication technology has been deployed in LEO satcom systems. This paper investigates the performance of MIMO-OTFS based LEO satcom systems, considering spatial correlation at both the transmit and receive ends. As the error performance degrades due to the correlation effect, this work proposes whitening transformations at the transmitter (Tx) and the receiver (Rx) to combat the Tx/Rx spatial correlations. Simulation results with practical LEO satcom channel models and configurations demonstrate a significant improvement in the error performance with the proposed decorrelation operations.
{"title":"Spatially Correlated MIMO-OTFS for LEO Satellite Communication Systems","authors":"A. Bora, K. Phan, Y. Hong","doi":"10.1109/iccworkshops53468.2022.9814666","DOIUrl":"https://doi.org/10.1109/iccworkshops53468.2022.9814666","url":null,"abstract":"Low earth orbit (LEO) satellite communication (satcom) systems are expected to provide reliable high-speed communications under high-mobility environments. Recent research has demonstrated that the orthogonal time frequency space (OTFS) modulation technique has the potential to meet the demands for LEO satcom. In addition, multiple-input multiple-output (MIMO) communication technology has been deployed in LEO satcom systems. This paper investigates the performance of MIMO-OTFS based LEO satcom systems, considering spatial correlation at both the transmit and receive ends. As the error performance degrades due to the correlation effect, this work proposes whitening transformations at the transmitter (Tx) and the receiver (Rx) to combat the Tx/Rx spatial correlations. Simulation results with practical LEO satcom channel models and configurations demonstrate a significant improvement in the error performance with the proposed decorrelation operations.","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130051258","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：