Pub Date : 2020-12-01DOI: 10.1109/GLOBECOM42002.2020.9322397
Ashutosh Balakrishnan, S. De, Li-Chun Wang
Solar-powered and power grid connected green cellular networks are becoming attractive due to low carbon footprint and cost-effectiveness in providing uninterrupted service. In this paper, we analyze the performance of such dualpowered multi-cell network in presence of skewed traffic load across the different base stations (BSs). Cell coverage is decided at the network design stage based on long-term average traffic intensity across the various regions of a multi-cell coverage area. In presence of dynamically-changing skewness of traffic loads across different cells, we propose to adjust the cell coverage to accommodate the traffic and energy availability imbalance in the cells, while the demand for residual energy deficiency for serving the customers is fulfilled through the power grid connectivity. Network service provider’s cost with the proposed coverage adjustment based strategy is compared with that of the conventional approach where the individual BSs do not undergo any cell coverage adjustment and seek to provide the maximum network performance. Our analysis and simulation-based performance results demonstrate, that the network performance as well as monetary gains of the service provider are significantly higher with our proposed strategy. For example, at a moderate (30%) traffic skewness, the proposed strategy offers about 4% gain in operator’s annual profit, while serving about 8% more users on average at the peak hour. At a very high (80%) skewness, these numbers are respectively about 50% and 39%.
{"title":"Traffic Skewness-aware Performance Analysis of Dual-powered Green Cellular Networks","authors":"Ashutosh Balakrishnan, S. De, Li-Chun Wang","doi":"10.1109/GLOBECOM42002.2020.9322397","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322397","url":null,"abstract":"Solar-powered and power grid connected green cellular networks are becoming attractive due to low carbon footprint and cost-effectiveness in providing uninterrupted service. In this paper, we analyze the performance of such dualpowered multi-cell network in presence of skewed traffic load across the different base stations (BSs). Cell coverage is decided at the network design stage based on long-term average traffic intensity across the various regions of a multi-cell coverage area. In presence of dynamically-changing skewness of traffic loads across different cells, we propose to adjust the cell coverage to accommodate the traffic and energy availability imbalance in the cells, while the demand for residual energy deficiency for serving the customers is fulfilled through the power grid connectivity. Network service provider’s cost with the proposed coverage adjustment based strategy is compared with that of the conventional approach where the individual BSs do not undergo any cell coverage adjustment and seek to provide the maximum network performance. Our analysis and simulation-based performance results demonstrate, that the network performance as well as monetary gains of the service provider are significantly higher with our proposed strategy. For example, at a moderate (30%) traffic skewness, the proposed strategy offers about 4% gain in operator’s annual profit, while serving about 8% more users on average at the peak hour. At a very high (80%) skewness, these numbers are respectively about 50% and 39%.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"30 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":"74895676","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/GLOBECOM42002.2020.9322587
Kailing Yao, Jin Chen, Yuli Zhang, Li Cui, Yang Yang, Yuhua Xu
Device-to-device (D2D)-enabled mobile edge computing (MEC) is an emerging technology which has been widely investigated in terrestrial networks. Different from most existing relevant work, where the network is base station-assisted and offloadings are made on homogeneous channels, this paper focuses on an unmanned aerial vehicle (UAV) swarm, where both the decentralized character and the heterogeneous data computation demands are considered. To fully utilize the limited time, spectrum and computation resources, the joint computation offloading and variable-width channel access problem is investigated. The problem is solved by a game-theoretic based solution. Specifically, the problem is first formulated into a game model which is proved to be an exact constrained potential game (ECPG). The game has at least one pure strategy generalized Nash equilibrium (GNE) and the best GNE is the global optimum of the problem. After that, to enable the UAV swarm reach the GNE autonomously, a distributed collective best response (COBR) algorithm is then proposed. The algorithm can converge to a GNE of the game, which is the local or global optimum of the proposed problem. Simulation results show that the proposed method can save about 10% energy than offloading on homogeneous channels.
{"title":"Joint Computation Offloading and Variable-width Channel Access Optimization in UAV Swarms","authors":"Kailing Yao, Jin Chen, Yuli Zhang, Li Cui, Yang Yang, Yuhua Xu","doi":"10.1109/GLOBECOM42002.2020.9322587","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322587","url":null,"abstract":"Device-to-device (D2D)-enabled mobile edge computing (MEC) is an emerging technology which has been widely investigated in terrestrial networks. Different from most existing relevant work, where the network is base station-assisted and offloadings are made on homogeneous channels, this paper focuses on an unmanned aerial vehicle (UAV) swarm, where both the decentralized character and the heterogeneous data computation demands are considered. To fully utilize the limited time, spectrum and computation resources, the joint computation offloading and variable-width channel access problem is investigated. The problem is solved by a game-theoretic based solution. Specifically, the problem is first formulated into a game model which is proved to be an exact constrained potential game (ECPG). The game has at least one pure strategy generalized Nash equilibrium (GNE) and the best GNE is the global optimum of the problem. After that, to enable the UAV swarm reach the GNE autonomously, a distributed collective best response (COBR) algorithm is then proposed. The algorithm can converge to a GNE of the game, which is the local or global optimum of the proposed problem. Simulation results show that the proposed method can save about 10% energy than offloading on homogeneous channels.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"14 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":"75269803","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/GLOBECOM42002.2020.9348039
G. Yue, Xiao-Feng Qi
In this paper, we first define a high dimensional (HiDi) channel characteristics, i.e., space-frequency covariance, for wideband MIMO-OFDM systems. We then design the conversion of the HiDi covariance in frequency domain from one carrier frequency to another, e.g., for FDD systems. Specifically, we apply the projection method in a Hilbert space to estimate the power angle delay spectrum and form the frequency domain conversion of the space-frequency covariance. We also obtain the asymptotic solutions when considering the infinite delay spread, which significantly reduces the complexity. Moreover, we generalize the conversions of space-frequency covariance in both spatial and frequency domains with two exemplary multi-panel scenarios. We then apply the general solutions to a specific antenna array configuration, i.e., uniform linear array (ULA), and obtain the explicit expressions of conversions. Numerical simulations demonstrate the efficiency of the designed conversions.
{"title":"Multi-Domain Conversions of High Dimensional Channel Characteristics for Massive MIMO-OFDM","authors":"G. Yue, Xiao-Feng Qi","doi":"10.1109/GLOBECOM42002.2020.9348039","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9348039","url":null,"abstract":"In this paper, we first define a high dimensional (HiDi) channel characteristics, i.e., space-frequency covariance, for wideband MIMO-OFDM systems. We then design the conversion of the HiDi covariance in frequency domain from one carrier frequency to another, e.g., for FDD systems. Specifically, we apply the projection method in a Hilbert space to estimate the power angle delay spectrum and form the frequency domain conversion of the space-frequency covariance. We also obtain the asymptotic solutions when considering the infinite delay spread, which significantly reduces the complexity. Moreover, we generalize the conversions of space-frequency covariance in both spatial and frequency domains with two exemplary multi-panel scenarios. We then apply the general solutions to a specific antenna array configuration, i.e., uniform linear array (ULA), and obtain the explicit expressions of conversions. Numerical simulations demonstrate the efficiency of the designed conversions.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"1 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":"75681049","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/GLOBECOM42002.2020.9322214
J. Yang, Yufei Jiang, Xu Zhu, Da Sun, Tong Wang, F. Zheng
In this paper, we propose a blind direct current bias (DCB) based timing synchronization and a blind null subcarrier (NS) based timing synchronization methods for direct current biased optical-orthogonal frequency division multiplexing (DCO-OFDM) visible light communications (VLC) systems. This is the first work to investigate blind timing synchronization for DCO-OFDM VLC systems, achieving high bandwidth efficiency, unlike the previous works which require a number of pilots. The two blind approaches are robust against the limited bandwidth of light emitting diode (LED), as the timing synchronization is conducted in frequency domain to mitigate the effect of inter-symbol-interference (ISI) caused by LED limited bandwidth, rather than being performed in time domain as the previous works that are vulnerable to the ISI. The DC bias is utilized by the proposed DCB based approach to perform blind timing synchronization, and the null subcarrier is used by the proposed NS based approach. Simulation results show that the proposed blind DCB and NS timing synchronization approaches significantly outperform the state-of-the-art methods in terms of the probability of false detection and bit error rate (BER), and yield BER performance close to ideal case with perfect synchronization, zero forcing (ZF) equalization and perfect channel state information (CSI).
{"title":"Blind Timing Synchronization for DCO-OFDM VLC Systems","authors":"J. Yang, Yufei Jiang, Xu Zhu, Da Sun, Tong Wang, F. Zheng","doi":"10.1109/GLOBECOM42002.2020.9322214","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322214","url":null,"abstract":"In this paper, we propose a blind direct current bias (DCB) based timing synchronization and a blind null subcarrier (NS) based timing synchronization methods for direct current biased optical-orthogonal frequency division multiplexing (DCO-OFDM) visible light communications (VLC) systems. This is the first work to investigate blind timing synchronization for DCO-OFDM VLC systems, achieving high bandwidth efficiency, unlike the previous works which require a number of pilots. The two blind approaches are robust against the limited bandwidth of light emitting diode (LED), as the timing synchronization is conducted in frequency domain to mitigate the effect of inter-symbol-interference (ISI) caused by LED limited bandwidth, rather than being performed in time domain as the previous works that are vulnerable to the ISI. The DC bias is utilized by the proposed DCB based approach to perform blind timing synchronization, and the null subcarrier is used by the proposed NS based approach. Simulation results show that the proposed blind DCB and NS timing synchronization approaches significantly outperform the state-of-the-art methods in terms of the probability of false detection and bit error rate (BER), and yield BER performance close to ideal case with perfect synchronization, zero forcing (ZF) equalization and perfect channel state information (CSI).","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"22 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75748387","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/GLOBECOM42002.2020.9322506
A. Albalawi, Hamed Yousefi, C. Westphal, K. Makhijani, J. Garcia-Luna-Aceves
A new transport protocol is introduced to increase the responsiveness of the network to congestion. The new transport protocol, QUCO, reacts to congestion by selectively dropping off parts of a payload packet (combined with mitigation mechanisms to handle the loss of part of the payload). This packet trimming scheme greatly reduces the variations in the number of the packets going through the network. This allows to set tighter targets on the number of packets in flight and on the depth of the switch buffers. QUCO has less delay and much less delay variations than TCP. The resulting reduction in jitter is extremely useful, especially for media distribution.
{"title":"Enhancing End-to-End Transport with Packet Trimming","authors":"A. Albalawi, Hamed Yousefi, C. Westphal, K. Makhijani, J. Garcia-Luna-Aceves","doi":"10.1109/GLOBECOM42002.2020.9322506","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322506","url":null,"abstract":"A new transport protocol is introduced to increase the responsiveness of the network to congestion. The new transport protocol, QUCO, reacts to congestion by selectively dropping off parts of a payload packet (combined with mitigation mechanisms to handle the loss of part of the payload). This packet trimming scheme greatly reduces the variations in the number of the packets going through the network. This allows to set tighter targets on the number of packets in flight and on the depth of the switch buffers. QUCO has less delay and much less delay variations than TCP. The resulting reduction in jitter is extremely useful, especially for media distribution.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"23 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":"74549769","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/GLOBECOM42002.2020.9322562
Wenjing Xiao, Rui Wang, Jeungeun Song, Di Wu, Long Hu, Min Chen
With the advent of the Internet era, the trend of highly informed society has been becoming more and more obvious, and the requirement of society on communication is also increasing. flexible satellite communication mode has many advantages such as large communication load and no geographic restriction, which cannot be replaced by other communication modes. In the satellite communication system, the most important is the satellite earth station (SES). When receiving signals from the target satellite, the SES terminal must accurately point to the satellite and track it to obtain the maximum receiving signal and reduce the interference with other signals simultaneously. However, the motion of either satellite or terminal can cause a change in signal intensity, so it is necessary to adjust the pointing of the SES antenna in time to maintain optimal signal receiving conditions. In order to satisfy different satellite communication scenarios, in this paper, Artificial intelligent (AI) technology is applied to the satellite communication process, mainly to optimize the optimal antenna angle and time consumption reduction. Firstly, the process of antenna pointing is introduced, and the traditional antenna search algorithm Auto-Acqire algorithm (AA algorithm) is analyzed in detail. Considering that the satellite system needs to adapt to the communication requirements of different terminals, based on AI antenna pointing algorithms are proposed. In order to verify this research, we build an experimental platform and compare the traditional AA algorithm as a benchmark algorithm with FI-GRU and II-DRL algorithms. According to the experimental results, the two algorithms proposed in this paper can improve the efficiency of satellite pointing and tracking tasks.
{"title":"AI-based Satellite Ground Communication System with Intelligent Antenna Pointing","authors":"Wenjing Xiao, Rui Wang, Jeungeun Song, Di Wu, Long Hu, Min Chen","doi":"10.1109/GLOBECOM42002.2020.9322562","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322562","url":null,"abstract":"With the advent of the Internet era, the trend of highly informed society has been becoming more and more obvious, and the requirement of society on communication is also increasing. flexible satellite communication mode has many advantages such as large communication load and no geographic restriction, which cannot be replaced by other communication modes. In the satellite communication system, the most important is the satellite earth station (SES). When receiving signals from the target satellite, the SES terminal must accurately point to the satellite and track it to obtain the maximum receiving signal and reduce the interference with other signals simultaneously. However, the motion of either satellite or terminal can cause a change in signal intensity, so it is necessary to adjust the pointing of the SES antenna in time to maintain optimal signal receiving conditions. In order to satisfy different satellite communication scenarios, in this paper, Artificial intelligent (AI) technology is applied to the satellite communication process, mainly to optimize the optimal antenna angle and time consumption reduction. Firstly, the process of antenna pointing is introduced, and the traditional antenna search algorithm Auto-Acqire algorithm (AA algorithm) is analyzed in detail. Considering that the satellite system needs to adapt to the communication requirements of different terminals, based on AI antenna pointing algorithms are proposed. In order to verify this research, we build an experimental platform and compare the traditional AA algorithm as a benchmark algorithm with FI-GRU and II-DRL algorithms. According to the experimental results, the two algorithms proposed in this paper can improve the efficiency of satellite pointing and tracking tasks.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"59 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":"74696645","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/GLOBECOM42002.2020.9322196
Yimin He, Hongzhi Zhao, Wenbo Guo, Youxi Tang
In full-duplex (FD) systems, time alignment error between the received self-interference (SI) and the reconstructed one results in performance degradation of the SI cancellation. As a crucial part of SI cancellation, nonlinear interference (NI) cancellation is usually invested in the ideal situation, and the impact of the time alignment error on NI cancellation performance is rarely considered. In this paper, a robust NI cancellation algorithm is proposed to tackle the time alignment error in FD systems. At first, the impact of the time alignment error on NI cancellation is analyzed. The approximate expression of the residual NI power with time alignment error is derived to predict the NI cancellation performance. Then, an improved memory polynomial (IMP) model is derived to describe both time alignment error and nonlinearity. Finally, based on the IMP model, a novel NI cancellation algorithm with robustness to the time alignment error is proposed. Simulations present the impact of the time alignment error on NI cancellation capability, in which the theoretical value is coincident with the actual value. Besides, the proposed algorithm significantly enhances the NI cancellation performance. Specifically, when the time alignment error is 10% of the sampling interval and the interference to noise ratio is 60 dB, the proposed algorithm outperforms the conventional algorithm by 33 dB.
{"title":"Robust Nonlinear Interference Cancellation with Time Alignment Error in Full-Duplex Systems","authors":"Yimin He, Hongzhi Zhao, Wenbo Guo, Youxi Tang","doi":"10.1109/GLOBECOM42002.2020.9322196","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322196","url":null,"abstract":"In full-duplex (FD) systems, time alignment error between the received self-interference (SI) and the reconstructed one results in performance degradation of the SI cancellation. As a crucial part of SI cancellation, nonlinear interference (NI) cancellation is usually invested in the ideal situation, and the impact of the time alignment error on NI cancellation performance is rarely considered. In this paper, a robust NI cancellation algorithm is proposed to tackle the time alignment error in FD systems. At first, the impact of the time alignment error on NI cancellation is analyzed. The approximate expression of the residual NI power with time alignment error is derived to predict the NI cancellation performance. Then, an improved memory polynomial (IMP) model is derived to describe both time alignment error and nonlinearity. Finally, based on the IMP model, a novel NI cancellation algorithm with robustness to the time alignment error is proposed. Simulations present the impact of the time alignment error on NI cancellation capability, in which the theoretical value is coincident with the actual value. Besides, the proposed algorithm significantly enhances the NI cancellation performance. Specifically, when the time alignment error is 10% of the sampling interval and the interference to noise ratio is 60 dB, the proposed algorithm outperforms the conventional algorithm by 33 dB.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"69 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":"74772409","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/GLOBECOM42002.2020.9322344
Davide Callegaro, Yoshitomo Matsubara, M. Levorato
Many modern applications rely on complex machine learning algorithms, such as Deep Neural Networks (DNNs), to analyze images. However, both mobile and edge computing strategies may fail to provide satisfactory performance in some parameter regions. To mitigate this issue, the research community recently proposed methods to split the execution of DNNs to optimize the balance between computing load allocation and channel usage. Building on this set of results, this paper presents an optimization framework that enables the dynamic control of how images are processed in mobile device-edge server systems. The system is modeled as a Markov process, and a Linear Fractional Program is defined to identify the optimal stationary state-action distribution minimizing the overall average inference time under a constraint on the number of discarded images. Results indicate the advantage of using a dynamic control strategy with respect to available fixed strategies.
{"title":"Optimal Task Allocation for Time-Varying Edge Computing Systems with Split DNNs","authors":"Davide Callegaro, Yoshitomo Matsubara, M. Levorato","doi":"10.1109/GLOBECOM42002.2020.9322344","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322344","url":null,"abstract":"Many modern applications rely on complex machine learning algorithms, such as Deep Neural Networks (DNNs), to analyze images. However, both mobile and edge computing strategies may fail to provide satisfactory performance in some parameter regions. To mitigate this issue, the research community recently proposed methods to split the execution of DNNs to optimize the balance between computing load allocation and channel usage. Building on this set of results, this paper presents an optimization framework that enables the dynamic control of how images are processed in mobile device-edge server systems. The system is modeled as a Markov process, and a Linear Fractional Program is defined to identify the optimal stationary state-action distribution minimizing the overall average inference time under a constraint on the number of discarded images. Results indicate the advantage of using a dynamic control strategy with respect to available fixed strategies.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"83 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":"74798357","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/GLOBECOM42002.2020.9348250
Shilin Xu, Caili Guo, R. Hu, Y. Qian
With the explosive growth of the computation intensive vehicular applications, the demand for computational resource in vehicular networks has increased dramatically. However some vehicular networks may be deployed in an environment that lack resource-rich facilities to support computationally expensive vehicular applications. In this work we propose a new scheme that enables computational resource sharing among vehicles in vehicular cloud network (VCN), which can be formulated as a complex multi-knapsack problem. In order to solve it, a deep reinforcement learning (DRL) algorithm is developed. Considering the non-stationary behavior brought in by the parallel learning and exploring processes among vehicles, computational resource sharing in such a vehicular network is a typical multiagent problem, therefore we model the problem with a Markov game problem. In addition, to tackle the heterogeneity property of the computational resources, a multi-hot encoding scheme is designed to standardize the action space in DRL. Furthermore, we propose a centralized training and decentralized execution framework that can be solved by a multi-agent deep deterministic policy gradient (MADDPG) algorithm. The numerical simulation results demonstrate the effectiveness of the proposed scheme.
{"title":"Computational Resource Sharing in a Vehicular Cloud Network via Deep Reinforcement Learning","authors":"Shilin Xu, Caili Guo, R. Hu, Y. Qian","doi":"10.1109/GLOBECOM42002.2020.9348250","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9348250","url":null,"abstract":"With the explosive growth of the computation intensive vehicular applications, the demand for computational resource in vehicular networks has increased dramatically. However some vehicular networks may be deployed in an environment that lack resource-rich facilities to support computationally expensive vehicular applications. In this work we propose a new scheme that enables computational resource sharing among vehicles in vehicular cloud network (VCN), which can be formulated as a complex multi-knapsack problem. In order to solve it, a deep reinforcement learning (DRL) algorithm is developed. Considering the non-stationary behavior brought in by the parallel learning and exploring processes among vehicles, computational resource sharing in such a vehicular network is a typical multiagent problem, therefore we model the problem with a Markov game problem. In addition, to tackle the heterogeneity property of the computational resources, a multi-hot encoding scheme is designed to standardize the action space in DRL. Furthermore, we propose a centralized training and decentralized execution framework that can be solved by a multi-agent deep deterministic policy gradient (MADDPG) algorithm. The numerical simulation results demonstrate the effectiveness of the proposed scheme.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"59 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":"73277457","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/GLOBECOM42002.2020.9348059
Kefei Liu, Jiao Zhang, D. Wei, Kai Zhang, Tao Huang
In order to accommodate ever-increasing new tenants and applications, datacenter networks (DCNs) require an efficient load balancing scheme to fully utilize their bisection bandwidth. Equal-cost MultiPath routing (ECMP) is a widely used load-balancing mechanism in the DCN. However, ECMP blindly hashes traffic to parallel paths and results in imbalance and collisions. Motivated by ECMP's shortcomings, some recent schemes provide more visibility into networks via active probing. They could be broadly classified as probing all the paths or a fixed number of paths (e.g., 3 paths) each probe interval. However, they all suffer from some limitations. Probing all paths introduces high probing overhead while probing a fixed number of paths is suboptimal when the network topology and traffic load change. To our best knowledge, none of the existing schemes adapt the number of paths being probed to the network conditions. Enlightened by the defects of previous work, we introduce PLB, an adaptive partial congestion-aware load-balancing mechanism. At its heart, PLB randomly probes partial paths each probe interval and the number of them changes according to the network topology and the traffic load. Besides, PLB splits flow into flowlets and makes careful routing/rerouting decisions for them. Through analysis, we formulate the correlations between the number of paths being probed and the network conditions. Furthermore, simulations with realistic workloads validate our conclusions and show that PLB reduces overall flow completion times compared to the state-of-the-art load balancing schemes both in symmetric and asymmetric topologies.
{"title":"PLB: Adaptive Partial Congestion-aware Load Balancing for Datacenter Networks","authors":"Kefei Liu, Jiao Zhang, D. Wei, Kai Zhang, Tao Huang","doi":"10.1109/GLOBECOM42002.2020.9348059","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9348059","url":null,"abstract":"In order to accommodate ever-increasing new tenants and applications, datacenter networks (DCNs) require an efficient load balancing scheme to fully utilize their bisection bandwidth. Equal-cost MultiPath routing (ECMP) is a widely used load-balancing mechanism in the DCN. However, ECMP blindly hashes traffic to parallel paths and results in imbalance and collisions. Motivated by ECMP's shortcomings, some recent schemes provide more visibility into networks via active probing. They could be broadly classified as probing all the paths or a fixed number of paths (e.g., 3 paths) each probe interval. However, they all suffer from some limitations. Probing all paths introduces high probing overhead while probing a fixed number of paths is suboptimal when the network topology and traffic load change. To our best knowledge, none of the existing schemes adapt the number of paths being probed to the network conditions. Enlightened by the defects of previous work, we introduce PLB, an adaptive partial congestion-aware load-balancing mechanism. At its heart, PLB randomly probes partial paths each probe interval and the number of them changes according to the network topology and the traffic load. Besides, PLB splits flow into flowlets and makes careful routing/rerouting decisions for them. Through analysis, we formulate the correlations between the number of paths being probed and the network conditions. Furthermore, simulations with realistic workloads validate our conclusions and show that PLB reduces overall flow completion times compared to the state-of-the-art load balancing schemes both in symmetric and asymmetric topologies.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"20 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":"74442620","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：