Pub Date : 2023-03-01DOI: 10.1109/MCOMSTD.0003.2100100
Dengzhi Liu, Fan Sun, Weizheng Wang, K. Dev
Vehicular networking is a communication platform that integrates the computing power of vehicles, roadside units, and infrastructures, which is capable of offering services to terminals characterized by low latency, high bandwidth, and reliability. Artificial intelligence (AI) has been developed rapidly over the past few years, and numerous AI applications requiring high computing power in vehicular networking have emerged (e.g., automatic driving, collision avoidance, and trajectory prediction). However, the computation of the AI model requires high computing power, and the vehicles on the road have low computation capability, which significantly hinder the development of intelligent transportation based on AI in vehicular networking. In this article, a distributed computatin offloading scheme is developed, which can be used to outsource the tasks of the AI model computation to nearby vehicles and roadside units in vehicular networking. To reduce the computational burden and decrease the latency of the computation on the vehicle side, the optimized genetic algorithm is adopted to divide the computation of the sigmoid function into multiple sub-tasks. Moreover, secure multi-party computation and homomorphic encryption are applied in the sub-task computation to enhance the security of the AI model computation in vehicular networking. As indicated by the security analysis, the proposed scheme can be proved to support privacy preservation in the multi-party computation of the AI model. As revealed by the simulation results, the proposed scheme can be performed with low computational time with different lengths of keys and transmitted parameters in practice.
{"title":"Distributed Computation Offloading with Low Latency for Artificial Intelligence in Vehicular Networking","authors":"Dengzhi Liu, Fan Sun, Weizheng Wang, K. Dev","doi":"10.1109/MCOMSTD.0003.2100100","DOIUrl":"https://doi.org/10.1109/MCOMSTD.0003.2100100","url":null,"abstract":"Vehicular networking is a communication platform that integrates the computing power of vehicles, roadside units, and infrastructures, which is capable of offering services to terminals characterized by low latency, high bandwidth, and reliability. Artificial intelligence (AI) has been developed rapidly over the past few years, and numerous AI applications requiring high computing power in vehicular networking have emerged (e.g., automatic driving, collision avoidance, and trajectory prediction). However, the computation of the AI model requires high computing power, and the vehicles on the road have low computation capability, which significantly hinder the development of intelligent transportation based on AI in vehicular networking. In this article, a distributed computatin offloading scheme is developed, which can be used to outsource the tasks of the AI model computation to nearby vehicles and roadside units in vehicular networking. To reduce the computational burden and decrease the latency of the computation on the vehicle side, the optimized genetic algorithm is adopted to divide the computation of the sigmoid function into multiple sub-tasks. Moreover, secure multi-party computation and homomorphic encryption are applied in the sub-task computation to enhance the security of the AI model computation in vehicular networking. As indicated by the security analysis, the proposed scheme can be proved to support privacy preservation in the multi-party computation of the AI model. As revealed by the simulation results, the proposed scheme can be performed with low computational time with different lengths of keys and transmitted parameters in practice.","PeriodicalId":36719,"journal":{"name":"IEEE Communications Standards Magazine","volume":"7 1","pages":"74-80"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42822473","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 : 2023-03-01DOI: 10.1109/MCOMSTD.0003.2200050
Rudraksh Shrivastava, Sudeep Hegde, O. Blume
Sidelink communication technology has gained prominence in the recent years, with support for advanced V2X and machine-type communications by providing a direct interface between user devices. Recent 3GPP releases (up to Rel. 17) have introduced many additional features to sidelink, such as relaying and discontinuous reception to improve Quality of Service (QoS) and reduce power consumption. Further enhancements to sidelink, such as carrier aggregation, are currently being discussed in 3GPP working groups to be specified in Rel. 18 and beyond. In this work, challenges related to sidelink group communications are identified as recommendations to be addressed in future releases. With simulation analysis, the identified challenges, such as sidelink group resource management and inter-cell interference are shown to affect the QoS of group of devices communicating using the sidelink interface.
{"title":"Sidelink Evolution Toward 5G-A/6G Future Considerations for Standardization of Group Communications","authors":"Rudraksh Shrivastava, Sudeep Hegde, O. Blume","doi":"10.1109/MCOMSTD.0003.2200050","DOIUrl":"https://doi.org/10.1109/MCOMSTD.0003.2200050","url":null,"abstract":"Sidelink communication technology has gained prominence in the recent years, with support for advanced V2X and machine-type communications by providing a direct interface between user devices. Recent 3GPP releases (up to Rel. 17) have introduced many additional features to sidelink, such as relaying and discontinuous reception to improve Quality of Service (QoS) and reduce power consumption. Further enhancements to sidelink, such as carrier aggregation, are currently being discussed in 3GPP working groups to be specified in Rel. 18 and beyond. In this work, challenges related to sidelink group communications are identified as recommendations to be addressed in future releases. With simulation analysis, the identified challenges, such as sidelink group resource management and inter-cell interference are shown to affect the QoS of group of devices communicating using the sidelink interface.","PeriodicalId":36719,"journal":{"name":"IEEE Communications Standards Magazine","volume":"7 1","pages":"24-30"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41822867","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 : 2023-03-01DOI: 10.1109/MCOMSTD.0006.2200056
A. Salkintzis, M. Kühlewind, S. Rommer, Rainer Liebhart
The proliferation of modern mobile devices equipped with several wireless interfaces (multi-homed), along with the increasing demand for high-throughput and ultra-reliable connectivity, motivated 3GPP to specify a solution that enables multi-access communication, called access traffic steering, switching, and splitting (ATSSS). Based on this solution, a mobile device can exchange data traffic with the 5G core network by simultaneously using different access networks (e.g., WiFi and 5G-NR). Consequently, data flows can enjoy aggregated bandwidth and also reduced delay and increased reliability. In this article, we briefly present the key concepts and functionality of ATSSS, and we focus on the ATSSS enhancements considered for 5G Advanced (i.e., in 3GPP Rel-18). In particular, we present a new steering functionality that is based on the QUIC protocol and its multipath extensions. We discuss the motivation for this steering functionality, its features and user-plane operation, and we explain how it can be applied to proxy UDP traffic over HTTP.
{"title":"Multipath QUIC for Access Traffic Steering Switching and Splitting in 5G Advanced","authors":"A. Salkintzis, M. Kühlewind, S. Rommer, Rainer Liebhart","doi":"10.1109/MCOMSTD.0006.2200056","DOIUrl":"https://doi.org/10.1109/MCOMSTD.0006.2200056","url":null,"abstract":"The proliferation of modern mobile devices equipped with several wireless interfaces (multi-homed), along with the increasing demand for high-throughput and ultra-reliable connectivity, motivated 3GPP to specify a solution that enables multi-access communication, called access traffic steering, switching, and splitting (ATSSS). Based on this solution, a mobile device can exchange data traffic with the 5G core network by simultaneously using different access networks (e.g., WiFi and 5G-NR). Consequently, data flows can enjoy aggregated bandwidth and also reduced delay and increased reliability. In this article, we briefly present the key concepts and functionality of ATSSS, and we focus on the ATSSS enhancements considered for 5G Advanced (i.e., in 3GPP Rel-18). In particular, we present a new steering functionality that is based on the QUIC protocol and its multipath extensions. We discuss the motivation for this steering functionality, its features and user-plane operation, and we explain how it can be applied to proxy UDP traffic over HTTP.","PeriodicalId":36719,"journal":{"name":"IEEE Communications Standards Magazine","volume":"7 1","pages":"48-56"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44218899","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}
The ultimate goal of Internet of Things (IoT) technology is to evolve into the Internet of Everything. Two key elements of IoT are artificial intelligence (AI) for smart devices and the Internet for communication. Privacy protection has posed as a critical challenge for the next intelligent IoT technology revolution as the rapid development of communication technology and big data. Federated learning (FL) combines the privacy protection with machine data analytic and it balances the needs of huge volume data for AI and privacy protection, which also makes it as a leading position in the field of machine learning. However, the way of communication that adopted in federated learning resulted in several critical challenges, such as limited bandwidth, data security, and inconsistent internet speed. In this article, we introduce a super-wireless-over-the-air federated learning framework based on 6G technology to address these issues. By training private data in wireless communication with interference-resistant solid radio waves, future security, and ultra-high-performance AI technology can be realized, which could drive the development of IoT to be smarter, wider, and faster.
物联网(IoT)技术的最终目标是向万物互联(Internet of Everything)发展。物联网的两个关键要素是智能设备的人工智能(AI)和通信的互联网。随着通信技术和大数据的快速发展，隐私保护已成为下一次智能物联网技术革命的关键挑战。联邦学习(FL)将隐私保护与机器数据分析相结合，平衡了海量数据对人工智能和隐私保护的需求，这也使其在机器学习领域处于领先地位。然而，在联邦学习中采用的通信方式导致了几个关键的挑战，例如有限的带宽、数据安全性和不一致的互联网速度。在本文中，我们将介绍一种基于6G技术的超级无线空中联合学习框架来解决这些问题。通过抗干扰固体无线电波训练无线通信中的私有数据，可以实现未来的安全性和超高性能的AI技术，从而推动物联网向更智能、更广泛、更快的方向发展。
{"title":"Federated Learning Encounters 6G Wireless Communication in the Scenario of Internet of Things","authors":"Jiaming Pei, Shike Li, Zhi-fu Yu, Laishan Ho, Wenxuan Liu, Lukun Wang","doi":"10.1109/MCOMSTD.0005.2200044","DOIUrl":"https://doi.org/10.1109/MCOMSTD.0005.2200044","url":null,"abstract":"The ultimate goal of Internet of Things (IoT) technology is to evolve into the Internet of Everything. Two key elements of IoT are artificial intelligence (AI) for smart devices and the Internet for communication. Privacy protection has posed as a critical challenge for the next intelligent IoT technology revolution as the rapid development of communication technology and big data. Federated learning (FL) combines the privacy protection with machine data analytic and it balances the needs of huge volume data for AI and privacy protection, which also makes it as a leading position in the field of machine learning. However, the way of communication that adopted in federated learning resulted in several critical challenges, such as limited bandwidth, data security, and inconsistent internet speed. In this article, we introduce a super-wireless-over-the-air federated learning framework based on 6G technology to address these issues. By training private data in wireless communication with interference-resistant solid radio waves, future security, and ultra-high-performance AI technology can be realized, which could drive the development of IoT to be smarter, wider, and faster.","PeriodicalId":36719,"journal":{"name":"IEEE Communications Standards Magazine","volume":"7 1","pages":"94-100"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48550717","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 : 2023-03-01DOI: 10.1109/MCOMSTD.0001.2100077
Zhaona Wu, K. Umebayashi, Janne J. Lehtomäki, N. Zorba
One of the key parameters that plays a major role in enabling the data rate requirements is spectrum or bandwidth, which is scarce and expensive. Therefore, spectrum management policies are required to optimize its usage to meet all the requirements and the promised data rate growth. Another strategy to deal with spectrum scarcity is to move toward higher frequency bands (terahertz bands), which are expected in the next 6G communication standard. It is therefore important to develop not only new techniques that enable efficient dynamic spectrum access and sharing at such bands, but also suitable channel models for the terahertz bands. Meanwhile, offloading mechanisms are very promising for cellular networks where a plethora of options have been proposed in the research arena in terms of device-to-device, licensed assisted access, or WiFi offloading, among others; but their behavior, when operated at high frequencies (terahertz band) remains unclear. Therefore, this article will tackle two technologies that will shape future networks: terahertz channel modeling/communications and offloading mechanisms.
{"title":"Device-to-device Communications at the Terahertz Band: Open Challenges for Realistic Implementation","authors":"Zhaona Wu, K. Umebayashi, Janne J. Lehtomäki, N. Zorba","doi":"10.1109/MCOMSTD.0001.2100077","DOIUrl":"https://doi.org/10.1109/MCOMSTD.0001.2100077","url":null,"abstract":"One of the key parameters that plays a major role in enabling the data rate requirements is spectrum or bandwidth, which is scarce and expensive. Therefore, spectrum management policies are required to optimize its usage to meet all the requirements and the promised data rate growth. Another strategy to deal with spectrum scarcity is to move toward higher frequency bands (terahertz bands), which are expected in the next 6G communication standard. It is therefore important to develop not only new techniques that enable efficient dynamic spectrum access and sharing at such bands, but also suitable channel models for the terahertz bands. Meanwhile, offloading mechanisms are very promising for cellular networks where a plethora of options have been proposed in the research arena in terms of device-to-device, licensed assisted access, or WiFi offloading, among others; but their behavior, when operated at high frequencies (terahertz band) remains unclear. Therefore, this article will tackle two technologies that will shape future networks: terahertz channel modeling/communications and offloading mechanisms.","PeriodicalId":36719,"journal":{"name":"IEEE Communications Standards Magazine","volume":"7 1","pages":"82-87"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48023329","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 : 2023-03-01DOI: 10.1109/mcomstd.2023.10078091
Muhammad Ikram Ashraf, M. Guizani, Varun G. Menon, S. Mumtaz
{"title":"Series Editorial: Ultra-Low-Latency and Reliable Communications for Future Wireless Networks","authors":"Muhammad Ikram Ashraf, M. Guizani, Varun G. Menon, S. Mumtaz","doi":"10.1109/mcomstd.2023.10078091","DOIUrl":"https://doi.org/10.1109/mcomstd.2023.10078091","url":null,"abstract":"","PeriodicalId":36719,"journal":{"name":"IEEE Communications Standards Magazine","volume":"48 1","pages":"64-65"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79926214","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：