Mehdi Haghshenas, Francesco Linsalata, Luca Barbieri, Mattia Brambilla, Monica Nicoli, Maurizio Magarini
Vehicular communications are gaining a lot of attention for the delivery of enhanced mobility services that require multi-Gbps and low latency connections. In this paper, we focus on Infrastructure-to-Vehicle (I2V) communications where a gNB has to assign spatial resources to a number of connected vehicle users. To efficiently manage the scheduling, we compare the Zero Forcing (ZF) and Maximum Ratio (MR) precoding strategies by evaluating the effect of shifting from sub-6 GHz to millimeter wave (mmWave) frequencies in urban and highway mobility scenarios. We analyze the impact of the geometry of the environment and propagation characteristics at different frequencies in terms of number of users that can be served and spectral efficiency. To model the I2V channel, we integrate realistic traffic conditions generated by SUMO into an accurate channel model based on ray tracing software by WirelessInsite. By numerical results we demonstrate the degradation at mmWave compared to sub-6 GHz on the multiplexing gain. We show the higher efficiency of ZF compared to MR as the former is not limited by inter-user interference, especially in urban scenarios where the number of distinctive eigendirections in space is limited. On the other hand, highway mobility has a more uniform distribution of vehicles that can be conveniently explored by the ZF scheduling to serve more users. Lastly, we show the benefits of adopting a higher number of transmit antennas at mmWave jointly with efficient scheduling to achieve higher spectral efficiency.
{"title":"Analysis of spatial scheduling in downlink vehicular communications: Sub-6 GHz vs mmWave","authors":"Mehdi Haghshenas, Francesco Linsalata, Luca Barbieri, Mattia Brambilla, Monica Nicoli, Maurizio Magarini","doi":"10.52953/gewx7355","DOIUrl":"https://doi.org/10.52953/gewx7355","url":null,"abstract":"Vehicular communications are gaining a lot of attention for the delivery of enhanced mobility services that require multi-Gbps and low latency connections. In this paper, we focus on Infrastructure-to-Vehicle (I2V) communications where a gNB has to assign spatial resources to a number of connected vehicle users. To efficiently manage the scheduling, we compare the Zero Forcing (ZF) and Maximum Ratio (MR) precoding strategies by evaluating the effect of shifting from sub-6 GHz to millimeter wave (mmWave) frequencies in urban and highway mobility scenarios. We analyze the impact of the geometry of the environment and propagation characteristics at different frequencies in terms of number of users that can be served and spectral efficiency. To model the I2V channel, we integrate realistic traffic conditions generated by SUMO into an accurate channel model based on ray tracing software by WirelessInsite. By numerical results we demonstrate the degradation at mmWave compared to sub-6 GHz on the multiplexing gain. We show the higher efficiency of ZF compared to MR as the former is not limited by inter-user interference, especially in urban scenarios where the number of distinctive eigendirections in space is limited. On the other hand, highway mobility has a more uniform distribution of vehicles that can be conveniently explored by the ZF scheduling to serve more users. Lastly, we show the benefits of adopting a higher number of transmit antennas at mmWave jointly with efficient scheduling to achieve higher spectral efficiency.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130918994","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}
Due to their flexible deployment and line-of-sight channel conditions, using drones as base stations is a promising technology. Recent developments in Massive MIMO transmission with millimeter-wave beamforming also enables high data rates and enables simultaneous transmission to multiple ground users. In this work we consider the problem of deployment (i.e. positioning) of drone base stations for maximizing proportional fairness, along with analog MIMO beamforming that maximizes the Signal to Interference plus Noise Ratio (SINR). Simulation results reveal that careful K-means clustering of ground users and altitude adjustment performs close to a Particle Swarm Optimization (PSO)-based solution. Discrete Fourier Transform (DFT) codebook-based low-complexity beamforming also provides a promising performance, when compared to the Semi-Definite Programming (SDP)-based solution, as the number of antennas is increased.
{"title":"Optimal beamforming and deployment of millimeter-wave drone base stations","authors":"Tolga Girici, Fatih Yurekli","doi":"10.52953/blia3506","DOIUrl":"https://doi.org/10.52953/blia3506","url":null,"abstract":"Due to their flexible deployment and line-of-sight channel conditions, using drones as base stations is a promising technology. Recent developments in Massive MIMO transmission with millimeter-wave beamforming also enables high data rates and enables simultaneous transmission to multiple ground users. In this work we consider the problem of deployment (i.e. positioning) of drone base stations for maximizing proportional fairness, along with analog MIMO beamforming that maximizes the Signal to Interference plus Noise Ratio (SINR). Simulation results reveal that careful K-means clustering of ground users and altitude adjustment performs close to a Particle Swarm Optimization (PSO)-based solution. Discrete Fourier Transform (DFT) codebook-based low-complexity beamforming also provides a promising performance, when compared to the Semi-Definite Programming (SDP)-based solution, as the number of antennas is increased.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122013316","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}
Abeer Ahmad, Xiao Sha, Akshay Athalye, Samir R. Das, Kelly Caylor, Branko Glisic, Milutin Stanacevic, Petar M. Djuric
We propose a sensing system comprising a large network of tiny, battery-less, Radio Frequency (RF)-powered sensors that use backscatter communication. The sensors use an entirely passive technique to 'sense' the parameters of the wireless channel between themselves. Since the material properties influence RF channels, this fine-grain sensing can uncover multiple material properties both at a large scale and fine spatial resolution. In this paper, we study the feasibility of the proposed passive technique for monitoring parameters of material in which the sensors are embedded. We performed a set of experiments where the sensor-to-sensor wireless channel parameters are well-defined using physics-based modeling, and we compared the theoretical and experimentally obtained values. For some material parameters of interest, like humidity or strain, the relationship with the observed wireless channel parameters have to be modeled relying on data-driven approaches. The initial experiments show an observable difference in the sensor-to-sensor channel phase with variation in the applied weights.
{"title":"Dispersed passive RF-sensing for 3D structural health monitoring","authors":"Abeer Ahmad, Xiao Sha, Akshay Athalye, Samir R. Das, Kelly Caylor, Branko Glisic, Milutin Stanacevic, Petar M. Djuric","doi":"10.52953/zqyz8264","DOIUrl":"https://doi.org/10.52953/zqyz8264","url":null,"abstract":"We propose a sensing system comprising a large network of tiny, battery-less, Radio Frequency (RF)-powered sensors that use backscatter communication. The sensors use an entirely passive technique to 'sense' the parameters of the wireless channel between themselves. Since the material properties influence RF channels, this fine-grain sensing can uncover multiple material properties both at a large scale and fine spatial resolution. In this paper, we study the feasibility of the proposed passive technique for monitoring parameters of material in which the sensors are embedded. We performed a set of experiments where the sensor-to-sensor wireless channel parameters are well-defined using physics-based modeling, and we compared the theoretical and experimentally obtained values. For some material parameters of interest, like humidity or strain, the relationship with the observed wireless channel parameters have to be modeled relying on data-driven approaches. The initial experiments show an observable difference in the sensor-to-sensor channel phase with variation in the applied weights.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126756437","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}
1. MilicaLekić, 1. GordanaGardašević, Milan Mlađen, G. Gardasevic
The architectural design of Wireless Sensor Networks (WSNs) for the Industrial Internet of Things (IIoT) applications requires the careful planning and selection of an appropriate operational strategy. Harmonization of standards is crucial to ensure easier certification and commercialization of IIoT solutions. The ongoing research activities are directed toward designing agile, reliable, and secure transmission technologies and protocols. Recently, Time Slotted Channel Hopping (TSCH) standardization bodies have started to consider support for multiple physical layers thus accommodating a wide range of applications. This paper presents the results of the extensive experimental measurement campaign to study the performance of the 6TiSCH (IPv6 over the TSCH mode of IEEE 802.15.4e) network while supporting multiple physical layers (PHYs). For measurement purposes, all experiments were performed on OpenMote-B hardware. These devices are equipped with an Atmel AT86RF215 dual radio transceiver implementing IEEE 802.15.4g. The performance evaluation is provided for the following metrics: network formation time, Packet Delivery Ratio (PDR), latency, and duty cycle. Results are encouraging, particularly in terms of high PDR for all tested PHYs. Performance evaluation indicates the importance of proper node positioning, link quality estimation and careful selection of network parameters. Moreover, collected experimental results create a dataset that provides insights into the tested PHYs' performance and their potential for indoor 6TiSCH networking.
{"title":"Experimental evaluation of multi-PHY 6TiSCH networks","authors":"1. MilicaLekić, 1. GordanaGardašević, Milan Mlađen, G. Gardasevic","doi":"10.52953/cghe6909","DOIUrl":"https://doi.org/10.52953/cghe6909","url":null,"abstract":"The architectural design of Wireless Sensor Networks (WSNs) for the Industrial Internet of Things (IIoT) applications requires the careful planning and selection of an appropriate operational strategy. Harmonization of standards is crucial to ensure easier certification and commercialization of IIoT solutions. The ongoing research activities are directed toward designing agile, reliable, and secure transmission technologies and protocols. Recently, Time Slotted Channel Hopping (TSCH) standardization bodies have started to consider support for multiple physical layers thus accommodating a wide range of applications. This paper presents the results of the extensive experimental measurement campaign to study the performance of the 6TiSCH (IPv6 over the TSCH mode of IEEE 802.15.4e) network while supporting multiple physical layers (PHYs). For measurement purposes, all experiments were performed on OpenMote-B hardware. These devices are equipped with an Atmel AT86RF215 dual radio transceiver implementing IEEE 802.15.4g. The performance evaluation is provided for the following metrics: network formation time, Packet Delivery Ratio (PDR), latency, and duty cycle. Results are encouraging, particularly in terms of high PDR for all tested PHYs. Performance evaluation indicates the importance of proper node positioning, link quality estimation and careful selection of network parameters. Moreover, collected experimental results create a dataset that provides insights into the tested PHYs' performance and their potential for indoor 6TiSCH networking.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130931536","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}
Evangelos N. Papasotiriou, Alexandros-Apostolos A. Boulogeorgos, Angeliki Alexiou
The terahertz (THz) band offers a vast amount of still unallocated bandwidth, which makes it a promising enabler for future sixth generation wireless systems. The high frequencies of the THz band lead to a significantly reduced multipath richness of the propagating THz signals. However, there are still paths that can carry a significant amount of power. As a result, the THz band small-scale fading characterization is of particular interest and the appropriate stochastic distributions that best fit the empirical channels need to be identified. This work investigates the suitability of the 'alpha-mu', Rice and Nakagami-m distributions to adequately model the small-scale fading statistics of the channel gain measurements of various Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) indoor THz wireless links. The fitting accuracy of the examined analytical distributions is validated by means of the Kolmogorov-Smirnov test, the Kullback-Leibler divergence, the logarithmic Kolmogorov-Smirnov test and the root-mean-square-error. Also, the ergodic capacity based on the channel gain measurements as well as on the 'alpha-mu', Rice and Nakagami-m distributions is presented. Based on the fitting accuracy metrics the Rice and 'alpha-mu' yield the best fit for the LoS and NLoS links, respectively. The Nakagami-m does not fit the empirical distributions for any of the presented links. Furthermore, insights are provided for the ranges of the extracted values of the analytical distributions in LoS and NLoS transmission conditions.
{"title":"A measurement data-based investigation of fading modeling for indoor THz wireless systems","authors":"Evangelos N. Papasotiriou, Alexandros-Apostolos A. Boulogeorgos, Angeliki Alexiou","doi":"10.52953/spjd5569","DOIUrl":"https://doi.org/10.52953/spjd5569","url":null,"abstract":"The terahertz (THz) band offers a vast amount of still unallocated bandwidth, which makes it a promising enabler for future sixth generation wireless systems. The high frequencies of the THz band lead to a significantly reduced multipath richness of the propagating THz signals. However, there are still paths that can carry a significant amount of power. As a result, the THz band small-scale fading characterization is of particular interest and the appropriate stochastic distributions that best fit the empirical channels need to be identified. This work investigates the suitability of the 'alpha-mu', Rice and Nakagami-m distributions to adequately model the small-scale fading statistics of the channel gain measurements of various Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) indoor THz wireless links. The fitting accuracy of the examined analytical distributions is validated by means of the Kolmogorov-Smirnov test, the Kullback-Leibler divergence, the logarithmic Kolmogorov-Smirnov test and the root-mean-square-error. Also, the ergodic capacity based on the channel gain measurements as well as on the 'alpha-mu', Rice and Nakagami-m distributions is presented. Based on the fitting accuracy metrics the Rice and 'alpha-mu' yield the best fit for the LoS and NLoS links, respectively. The Nakagami-m does not fit the empirical distributions for any of the presented links. Furthermore, insights are provided for the ranges of the extracted values of the analytical distributions in LoS and NLoS transmission conditions.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117165425","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}
Modern network environments are starting to engulf billions of different interconnected devices that support a wide range of applications. Depending on the case, these environments range from static (e.g., wireless sensors) to highly dynamic (e.g., vehicular networks) with respect to topology changes and have different constraints for throughput, time delay, energy consumption etc. Supporting such applications in a topology-varying ad hoc environment is a challenging task. Thus, TDMA-based MAC policies are revisited here and a new policy, i.e., the refined policy is proposed, which builds and improves on the topology-independent policies that appear in the literature. In particular, an individual access probability is introduced that is distributively calculated by each node to access time slots that may result to collisions, but if not then unused network resources will be utilized, thus, increasing throughput. The key idea under the refined policy is to identify and refrain from transmitting during slots that collisions are likely to appear. An analytical expression for the individual access probability is also derived here. It is also shown through simulation experiments that energy consumption is also reduced in addition to throughput incremented under the proposed policy.
{"title":"A probabilistic refined policy for topology-independent medium access control in ad hoc network environments","authors":"Vasileios Dragonas, Georgios Tsoumanis, Konstantinos Oikonomou","doi":"10.52953/wsyn6375","DOIUrl":"https://doi.org/10.52953/wsyn6375","url":null,"abstract":"Modern network environments are starting to engulf billions of different interconnected devices that support a wide range of applications. Depending on the case, these environments range from static (e.g., wireless sensors) to highly dynamic (e.g., vehicular networks) with respect to topology changes and have different constraints for throughput, time delay, energy consumption etc. Supporting such applications in a topology-varying ad hoc environment is a challenging task. Thus, TDMA-based MAC policies are revisited here and a new policy, i.e., the refined policy is proposed, which builds and improves on the topology-independent policies that appear in the literature. In particular, an individual access probability is introduced that is distributively calculated by each node to access time slots that may result to collisions, but if not then unused network resources will be utilized, thus, increasing throughput. The key idea under the refined policy is to identify and refrain from transmitting during slots that collisions are likely to appear. An analytical expression for the individual access probability is also derived here. It is also shown through simulation experiments that energy consumption is also reduced in addition to throughput incremented under the proposed policy.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129176995","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}
Yong Song, Zhiwei Yan, Yukun Qin, Yuchen Xie, Xiaozhou Ye, Ye Ouyang
Log anomaly detection is an important and challenging task in the field of Artificial Intelligence for IT Operations (AIOps). Logs that record important runtime information are widely used for troubleshooting purposes. There have been many studies that use log data to construct deep learning methods for detecting system anomalies, which are usually based on log parsing. However, they ignore the effect of keywords that are promising for system status analysis. Here, we propose KELog (Keyword Embedding Log), a novel log anomaly detection approach that utilizes keyword information. We build a keyword library by keyword information extraction and fuse them into log representations. In this way, KELog can raise the reliability of anomaly detection. The experimental results on a real-world log dataset of a communications operator show that the F1 score of our proposed KELog method achieves a maximum increase of 0.341 compared with the commonly used machine learning algorithms (PCA, SVM, Invaiant Mining) and a maximum increase of 0.039 compared with deep learning algorithms (DeepLog, LogBERT) respectively. In 2021, ITU launched the second ITU AI/ML in 5G Challenge. We used KELog to participate in the thematic track of the Artificial Intelligence Innovation and Application Competition in the China Division, and won first place with a full F1 score.
{"title":"Network anomaly detection based on keyword embedding log","authors":"Yong Song, Zhiwei Yan, Yukun Qin, Yuchen Xie, Xiaozhou Ye, Ye Ouyang","doi":"10.52953/icxq5497","DOIUrl":"https://doi.org/10.52953/icxq5497","url":null,"abstract":"Log anomaly detection is an important and challenging task in the field of Artificial Intelligence for IT Operations (AIOps). Logs that record important runtime information are widely used for troubleshooting purposes. There have been many studies that use log data to construct deep learning methods for detecting system anomalies, which are usually based on log parsing. However, they ignore the effect of keywords that are promising for system status analysis. Here, we propose KELog (Keyword Embedding Log), a novel log anomaly detection approach that utilizes keyword information. We build a keyword library by keyword information extraction and fuse them into log representations. In this way, KELog can raise the reliability of anomaly detection. The experimental results on a real-world log dataset of a communications operator show that the F1 score of our proposed KELog method achieves a maximum increase of 0.341 compared with the commonly used machine learning algorithms (PCA, SVM, Invaiant Mining) and a maximum increase of 0.039 compared with deep learning algorithms (DeepLog, LogBERT) respectively. In 2021, ITU launched the second ITU AI/ML in 5G Challenge. We used KELog to participate in the thematic track of the Artificial Intelligence Innovation and Application Competition in the China Division, and won first place with a full F1 score.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127791882","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}
Milad Kazemi Darazam, Pelin Angin, Cengiz Acarturk
The Internet of Things (IoT) has shown significant growth in the past decades. Recently, IoT networks have been subject to cybersecurity threats on multiple fronts. A lack of improvement in IoT infrastructures' cybersecurity may result in challenges with a broad impact, such as DDoS attacks that target global DNS services. This paper reviews existing solutions to mitigate attacks on and from IoT networks. As a specific mitigation approach, we propose the use of a standardized whitelisting method, namely Manufacturer Usage Description (MUD), which provides enhanced explainability over machine learning-based approaches and is complementary to them. For evaluating the use of MUD in IoT networks, we report a case study, which we conducted through traffic analysis of two IoT devices by detecting recognizable and distinctive traffic patterns, which demonstrate the feasibility of MUD-based intrusion prevention.
{"title":"Using manufacturer usage descriptions for IoT network security: An experimental investigation of smart home network devices","authors":"Milad Kazemi Darazam, Pelin Angin, Cengiz Acarturk","doi":"10.52953/nsqz3214","DOIUrl":"https://doi.org/10.52953/nsqz3214","url":null,"abstract":"The Internet of Things (IoT) has shown significant growth in the past decades. Recently, IoT networks have been subject to cybersecurity threats on multiple fronts. A lack of improvement in IoT infrastructures' cybersecurity may result in challenges with a broad impact, such as DDoS attacks that target global DNS services. This paper reviews existing solutions to mitigate attacks on and from IoT networks. As a specific mitigation approach, we propose the use of a standardized whitelisting method, namely Manufacturer Usage Description (MUD), which provides enhanced explainability over machine learning-based approaches and is complementary to them. For evaluating the use of MUD in IoT networks, we report a case study, which we conducted through traffic analysis of two IoT devices by detecting recognizable and distinctive traffic patterns, which demonstrate the feasibility of MUD-based intrusion prevention.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132736381","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}
I. Correa, A. Oliveira, Bojian Du, C. Nahum, Daisuke Kobuchi, Felipe Bastos, Hirofumi Ohzeki, João Borges, Mohit Mehta, Pedro Batista, Ryoma Kondo, Sundesh Gupta, Vimal Bhatia, A. Klautau
The fifth generation of mobile networks evolved to serve applications with distinct requirements, which results in a high management complexity due to simultaneous real-time tasks. In the physical layer, code words that allow proper data exchange between the Base Station (BS) and the served users must be chosen. While, in higher layers, the BS must choose users to be served in a given transmission opportunity. There are approaches based on Machine Learning (ML) to solve these combined tasks. However, due to the high amount of possible inputs, a challenge is the availability of data to train the models. In some cases, there may not even exist a predefined optimal answer to use as a "label" for supervised approaches. In this paper, we evaluate solutions for the combined problems of beam selection and user scheduling with Reinforcement Learning (RL), which does not need labels, as a solution for problems without a predefined answer. The algorithms were proposed for Problem Statement 6 of the challenge organized by the International Telecommunication Union (ITU) in 2021, which ranked as the finalists. We compare the approaches in relation to the cumulative reward received by the agents and show a performance comparison of different RL approaches by comparing them with baselines developed for the challenge. The paper also shows how the action taken by the trained agents affect network operation by comparing the number of packets transmitted, which is highly related to the proper selection of users and code words.
{"title":"Simultaneous beam selection and users scheduling evaluation in a virtual world with reinforcement learning","authors":"I. Correa, A. Oliveira, Bojian Du, C. Nahum, Daisuke Kobuchi, Felipe Bastos, Hirofumi Ohzeki, João Borges, Mohit Mehta, Pedro Batista, Ryoma Kondo, Sundesh Gupta, Vimal Bhatia, A. Klautau","doi":"10.52953/chuz8770","DOIUrl":"https://doi.org/10.52953/chuz8770","url":null,"abstract":"The fifth generation of mobile networks evolved to serve applications with distinct requirements, which results in a high management complexity due to simultaneous real-time tasks. In the physical layer, code words that allow proper data exchange between the Base Station (BS) and the served users must be chosen. While, in higher layers, the BS must choose users to be served in a given transmission opportunity. There are approaches based on Machine Learning (ML) to solve these combined tasks. However, due to the high amount of possible inputs, a challenge is the availability of data to train the models. In some cases, there may not even exist a predefined optimal answer to use as a \"label\" for supervised approaches. In this paper, we evaluate solutions for the combined problems of beam selection and user scheduling with Reinforcement Learning (RL), which does not need labels, as a solution for problems without a predefined answer. The algorithms were proposed for Problem Statement 6 of the challenge organized by the International Telecommunication Union (ITU) in 2021, which ranked as the finalists. We compare the approaches in relation to the cumulative reward received by the agents and show a performance comparison of different RL approaches by comparing them with baselines developed for the challenge. The paper also shows how the action taken by the trained agents affect network operation by comparing the number of packets transmitted, which is highly related to the proper selection of users and code words.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128041853","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}
Kun Chen.Hu, G. C. Alexandropoulos, Ana Garcia Armada
The Reconfigurable Intelligent Surface (RIS) constitutes one of the prominent technologies for the 6th Generation (6G) of wireless communications. It is envisioned to enhance signal coverage in cases where obstacles block direct communication from Base Stations (BSs), and when high carrier frequencies are used that are sensitive to attenuation losses. In the literature, the exploitation of RISs based on traditional coherent demodulation, relies on the availability of accurate Channel State Information (CSI). Given that CSI estimation, a multi-antenna BS or a dedicated orchestration controller jointly computes the pre-coder/combiner and the RIS configuration. The latter tasks require a significant amount of time and resources, which may not be affordable when the channel is time-varying or the CSI is not accurate enough. In this paper, we consider the uplink between a single-antenna user and a multi-antenna BS, and present a novel RIS-empowered Orthogonal Frequency Division Multiplexing (OFDM) communication system, which is based on differential phase shift keying combined with random phase configurations at the RIS, thus, avoiding the channel estimation and any complex optimization processes. This feature renders our RIS-enabled system operation proposal suitable for high noise and/or mobility scenarios. Considering both an idealistic and a realistic channel model, analytical expressions for the Signal-to-Interference and Noise Ratio (SINR) and the Symbol Error Probability (SEP) of the proposed non-coherent RIS-empowered communication system are presented. Our extensive computer simulation results verify the accuracy of the presented analysis and showcase the proposed system's performance superiority over coherent demodulation in different mobility and spatial correlation scenarios.
{"title":"Non-coherent modulation with random phase configurations in RIS-empowered cellular MIMO systems","authors":"Kun Chen.Hu, G. C. Alexandropoulos, Ana Garcia Armada","doi":"10.52953/izly2764","DOIUrl":"https://doi.org/10.52953/izly2764","url":null,"abstract":"The Reconfigurable Intelligent Surface (RIS) constitutes one of the prominent technologies for the 6th Generation (6G) of wireless communications. It is envisioned to enhance signal coverage in cases where obstacles block direct communication from Base Stations (BSs), and when high carrier frequencies are used that are sensitive to attenuation losses. In the literature, the exploitation of RISs based on traditional coherent demodulation, relies on the availability of accurate Channel State Information (CSI). Given that CSI estimation, a multi-antenna BS or a dedicated orchestration controller jointly computes the pre-coder/combiner and the RIS configuration. The latter tasks require a significant amount of time and resources, which may not be affordable when the channel is time-varying or the CSI is not accurate enough. In this paper, we consider the uplink between a single-antenna user and a multi-antenna BS, and present a novel RIS-empowered Orthogonal Frequency Division Multiplexing (OFDM) communication system, which is based on differential phase shift keying combined with random phase configurations at the RIS, thus, avoiding the channel estimation and any complex optimization processes. This feature renders our RIS-enabled system operation proposal suitable for high noise and/or mobility scenarios. Considering both an idealistic and a realistic channel model, analytical expressions for the Signal-to-Interference and Noise Ratio (SINR) and the Symbol Error Probability (SEP) of the proposed non-coherent RIS-empowered communication system are presented. Our extensive computer simulation results verify the accuracy of the presented analysis and showcase the proposed system's performance superiority over coherent demodulation in different mobility and spatial correlation scenarios.","PeriodicalId":274720,"journal":{"name":"ITU Journal on Future and Evolving Technologies","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125259760","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：