在5G边缘网络飞速发展的过程中,边缘用户对高带宽、低时延的网络服务的质量要求也显著提高.从移动边缘网络的角度来看,网络内的整体服务质量与边缘用户的分配息息相关,用户移动的复杂性为边缘用户分配带来困难,边缘用户分配过程中还存...在5G边缘网络飞速发展的过程中,边缘用户对高带宽、低时延的网络服务的质量要求也显著提高.从移动边缘网络的角度来看,网络内的整体服务质量与边缘用户的分配息息相关,用户移动的复杂性为边缘用户分配带来困难,边缘用户分配过程中还存在隐私泄露问题.本文提出一种移动边缘环境下基于联邦学习的动态QoS(Quality of Service)优化方法MECFLD_QoS,基于联邦学习的思想,优化边缘区域的服务缓存,在动态移动场景下根据用户位置分配边缘服务器,有效保护用户隐私,实现区域服务质量优化,对动态用户移动场景有更好的适应性.MECFLD_QoS主要做了以下几个方面的优化工作:(1)优化了传统QoS数据集,将数据集映射到边缘网络环境中,充分考虑边缘计算的移动、分布式、实时性、复杂场景等特点,形成边缘QoS特征数据集;(2)优化了边缘服务器缓存,在用户终端训练用户偏好模型,与区域公有模型交互时只传输参数,将用户的隐私数据封装在用户终端中,避免数据的传输,可以有效地保护用户特征隐私;(3)优化了用户移动场景,在动态移动场景中收集用户移动信息,利用用户接入基站的地理位置拟合用户的移动轨迹进行预测,有效地模糊了用户的真实位置,在轨迹预测的同时有效地保护了用户的位置隐私;(4)优化了用户分配方法,提出改进的基于二维解的人工蜂群算法对边缘网络中的用户分配问题进行优化,事实证明改进的人工蜂群算法针对其多变量多峰值的特点有效地优化了用户分配,达到了较优的分配效果.通过边缘QoS特征数据集实验表明,本方法在多变量多峰值的用户分配问题中能产生全局最优的分配.展开更多
Human mobility prediction is important for many applications.However,training an accurate mobility prediction model requires a large scale of human trajectories,where privacy issues become an important problem.The ris...Human mobility prediction is important for many applications.However,training an accurate mobility prediction model requires a large scale of human trajectories,where privacy issues become an important problem.The rising federated learning provides us with a promising solution to this problem,which enables mobile devices to collaboratively learn a shared prediction model while keeping all the training data on the device,decoupling the ability to do machine learning from the need to store the data in the cloud.However,existing federated learningbased methods either do not provide privacy guarantees or have vulnerability in terms of privacy leakage.In this paper,we combine the techniques of data perturbation and model perturbation mechanisms and propose a privacy-preserving mobility prediction algorithm,where we add noise to the transmitted model and the raw data collaboratively to protect user privacy and keep the mobility prediction performance.Extensive experimental results show that our proposed method significantly outperforms the existing stateof-the-art mobility prediction method in terms of defensive performance against practical attacks while having comparable mobility prediction performance,demonstrating its effectiveness.展开更多
针对异构网络中的多样业务需求,并且为了能够适应网络环境的动态变化,为每一个会话选择一个最合适的网络为其服务同时实现网络负载的均衡,以HSDPA和W iM ax构成的异构网络为背景,基于Q学习算法,提出了一种异构网络环境下无线接入网络选...针对异构网络中的多样业务需求,并且为了能够适应网络环境的动态变化,为每一个会话选择一个最合适的网络为其服务同时实现网络负载的均衡,以HSDPA和W iM ax构成的异构网络为背景,基于Q学习算法,提出了一种异构网络环境下无线接入网络选择的新算法。该算法在进行网络选择时不仅考虑到网络的负载情况,还充分考虑了发起会话的业务属性、终端的移动性以及终端在网络中所处位置的不同。仿真结果表明该算法降低了系统阻塞率,提高了频谱效用,实现了网络选择的自主性。展开更多
Federated learning(FL)is a distributed machine learning(ML)framework where several clients cooperatively train an ML model by exchanging the model parameters without directly sharing their local data.In FL,the limited...Federated learning(FL)is a distributed machine learning(ML)framework where several clients cooperatively train an ML model by exchanging the model parameters without directly sharing their local data.In FL,the limited number of participants for model aggregation and communication latency are two major bottlenecks.Hierarchical federated learning(HFL),with a cloud-edge-client hierarchy,can leverage the large coverage of cloud servers and the low transmission latency of edge servers.There are growing research interests in implementing FL in vehicular networks due to the requirements of timely ML training for intelligent vehicles.However,the limited number of participants in vehicular networks and vehicle mobility degrade the performance of FL training.In this context,HFL,which stands out for lower latency,wider coverage and more participants,is promising in vehicular networks.In this paper,we begin with the background and motivation of HFL and the feasibility of implementing HFL in vehicular networks.Then,the architecture of HFL is illustrated.Next,we clarify new issues in HFL and review several existing solutions.Furthermore,we introduce some typical use cases in vehicular networks as well as our initial efforts on implementing HFL in vehicular networks.Finally,we conclude with future research directions.展开更多
In recent years,online ride-hailing services have emerged as an important component of urban transportation system,which not only provide significant ease for residents’travel activities,but also shape new travel beh...In recent years,online ride-hailing services have emerged as an important component of urban transportation system,which not only provide significant ease for residents’travel activities,but also shape new travel behavior and diversify urban mobility patterns.This study provides a thorough review of machine-learning-based methodologies for on-demand ride-hailing services.The importance of on-demand ride-hailing services in the spatiotemporal dynamics of urban traffic is first highlighted,with machine-learning-based macro-level ride-hailing research demonstrating its value in guiding the design,planning,operation,and control of urban intelligent transportation systems.Then,the research on travel behavior from the perspective of individual mobility patterns,including carpooling behavior and modal choice behavior,is summarized.In addition,existing studies on order matching and vehicle dispatching strategies,which are among the most important components of on-line ridehailing systems,are collected and summarized.Finally,some of the critical challenges and opportunities in ridehailing services are discussed.展开更多
Ion mobility analysis is a well-known analytical technique for identifying gas-phase compounds in fastresponse gas-monitoring systems.However,the conventional plasma discharge system is bulky,operates at a high temper...Ion mobility analysis is a well-known analytical technique for identifying gas-phase compounds in fastresponse gas-monitoring systems.However,the conventional plasma discharge system is bulky,operates at a high temperature,and inappropriate for volatile organic compounds(VOCs)concentration detection.Therefore,we report a machine learning(ML)-enhanced ion mobility analyzer with a triboelectric-based ionizer,which offers good ion mobility selectivity and VOC recognition ability with a small-sized device and non-strict operating environment.Based on the charge accumulation mechanism,a multi-switched manipulation triboelectric nanogenerator(SM-TENG)can provide a direct current(DC)bias at the order of a few hundred,which can be further leveraged as the power source to obtain a unique and repeatable discharge characteristic of different VOCs,and their mixtures,with a special tip-plate electrode configuration.Aiming to tackle the grand challenge in the detection of multiple VOCs,the ML-enhanced ion mobility analysis method was successfully demonstrated by extracting specific features automatically from ion mobility spectrometry data with ML algorithms,which significantly enhance the detection ability of the SM-TENG based VOC analyzer,showing a portable real-time VOC monitoring solution with rapid response and low power consumption for future internet of things based environmental monitoring applications.展开更多
文摘在5G边缘网络飞速发展的过程中,边缘用户对高带宽、低时延的网络服务的质量要求也显著提高.从移动边缘网络的角度来看,网络内的整体服务质量与边缘用户的分配息息相关,用户移动的复杂性为边缘用户分配带来困难,边缘用户分配过程中还存在隐私泄露问题.本文提出一种移动边缘环境下基于联邦学习的动态QoS(Quality of Service)优化方法MECFLD_QoS,基于联邦学习的思想,优化边缘区域的服务缓存,在动态移动场景下根据用户位置分配边缘服务器,有效保护用户隐私,实现区域服务质量优化,对动态用户移动场景有更好的适应性.MECFLD_QoS主要做了以下几个方面的优化工作:(1)优化了传统QoS数据集,将数据集映射到边缘网络环境中,充分考虑边缘计算的移动、分布式、实时性、复杂场景等特点,形成边缘QoS特征数据集;(2)优化了边缘服务器缓存,在用户终端训练用户偏好模型,与区域公有模型交互时只传输参数,将用户的隐私数据封装在用户终端中,避免数据的传输,可以有效地保护用户特征隐私;(3)优化了用户移动场景,在动态移动场景中收集用户移动信息,利用用户接入基站的地理位置拟合用户的移动轨迹进行预测,有效地模糊了用户的真实位置,在轨迹预测的同时有效地保护了用户的位置隐私;(4)优化了用户分配方法,提出改进的基于二维解的人工蜂群算法对边缘网络中的用户分配问题进行优化,事实证明改进的人工蜂群算法针对其多变量多峰值的特点有效地优化了用户分配,达到了较优的分配效果.通过边缘QoS特征数据集实验表明,本方法在多变量多峰值的用户分配问题中能产生全局最优的分配.
基金supported in part by the National Key Research and Development Program of China under 2020AAA0106000the National Natural Science Foundation of China under U20B2060 and U21B2036supported by a grant from the Guoqiang Institute, Tsinghua University under 2021GQG1005
文摘Human mobility prediction is important for many applications.However,training an accurate mobility prediction model requires a large scale of human trajectories,where privacy issues become an important problem.The rising federated learning provides us with a promising solution to this problem,which enables mobile devices to collaboratively learn a shared prediction model while keeping all the training data on the device,decoupling the ability to do machine learning from the need to store the data in the cloud.However,existing federated learningbased methods either do not provide privacy guarantees or have vulnerability in terms of privacy leakage.In this paper,we combine the techniques of data perturbation and model perturbation mechanisms and propose a privacy-preserving mobility prediction algorithm,where we add noise to the transmitted model and the raw data collaboratively to protect user privacy and keep the mobility prediction performance.Extensive experimental results show that our proposed method significantly outperforms the existing stateof-the-art mobility prediction method in terms of defensive performance against practical attacks while having comparable mobility prediction performance,demonstrating its effectiveness.
文摘针对异构网络中的多样业务需求,并且为了能够适应网络环境的动态变化,为每一个会话选择一个最合适的网络为其服务同时实现网络负载的均衡,以HSDPA和W iM ax构成的异构网络为背景,基于Q学习算法,提出了一种异构网络环境下无线接入网络选择的新算法。该算法在进行网络选择时不仅考虑到网络的负载情况,还充分考虑了发起会话的业务属性、终端的移动性以及终端在网络中所处位置的不同。仿真结果表明该算法降低了系统阻塞率,提高了频谱效用,实现了网络选择的自主性。
基金sponsored in part by the National Key R&D Program of China under Grant No. 2020YFB1806605the National Natural Science Foundation of China under Grant Nos. 62022049, 62111530197, and 61871254+1 种基金OPPOsupported by the Fundamental Research Funds for the Central Universities under Grant No. 2022JBXT001
文摘Federated learning(FL)is a distributed machine learning(ML)framework where several clients cooperatively train an ML model by exchanging the model parameters without directly sharing their local data.In FL,the limited number of participants for model aggregation and communication latency are two major bottlenecks.Hierarchical federated learning(HFL),with a cloud-edge-client hierarchy,can leverage the large coverage of cloud servers and the low transmission latency of edge servers.There are growing research interests in implementing FL in vehicular networks due to the requirements of timely ML training for intelligent vehicles.However,the limited number of participants in vehicular networks and vehicle mobility degrade the performance of FL training.In this context,HFL,which stands out for lower latency,wider coverage and more participants,is promising in vehicular networks.In this paper,we begin with the background and motivation of HFL and the feasibility of implementing HFL in vehicular networks.Then,the architecture of HFL is illustrated.Next,we clarify new issues in HFL and review several existing solutions.Furthermore,we introduce some typical use cases in vehicular networks as well as our initial efforts on implementing HFL in vehicular networks.Finally,we conclude with future research directions.
基金the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No.101025896.
文摘In recent years,online ride-hailing services have emerged as an important component of urban transportation system,which not only provide significant ease for residents’travel activities,but also shape new travel behavior and diversify urban mobility patterns.This study provides a thorough review of machine-learning-based methodologies for on-demand ride-hailing services.The importance of on-demand ride-hailing services in the spatiotemporal dynamics of urban traffic is first highlighted,with machine-learning-based macro-level ride-hailing research demonstrating its value in guiding the design,planning,operation,and control of urban intelligent transportation systems.Then,the research on travel behavior from the perspective of individual mobility patterns,including carpooling behavior and modal choice behavior,is summarized.In addition,existing studies on order matching and vehicle dispatching strategies,which are among the most important components of on-line ridehailing systems,are collected and summarized.Finally,some of the critical challenges and opportunities in ridehailing services are discussed.
基金supported by the research grant of‘‘Chip-Scale MEMS Micro-Spectrometer for Monitoring Harsh Industrial Gases”(R-263-000-C91-305)at the National University of Singapore(NUS),Singaporethe research grant of RIE Advanced Manufacturing and Engineering(AME)programmatic grant A18A4b0055‘‘Nanosystems at the Edge”at NUS,Singapore。
文摘Ion mobility analysis is a well-known analytical technique for identifying gas-phase compounds in fastresponse gas-monitoring systems.However,the conventional plasma discharge system is bulky,operates at a high temperature,and inappropriate for volatile organic compounds(VOCs)concentration detection.Therefore,we report a machine learning(ML)-enhanced ion mobility analyzer with a triboelectric-based ionizer,which offers good ion mobility selectivity and VOC recognition ability with a small-sized device and non-strict operating environment.Based on the charge accumulation mechanism,a multi-switched manipulation triboelectric nanogenerator(SM-TENG)can provide a direct current(DC)bias at the order of a few hundred,which can be further leveraged as the power source to obtain a unique and repeatable discharge characteristic of different VOCs,and their mixtures,with a special tip-plate electrode configuration.Aiming to tackle the grand challenge in the detection of multiple VOCs,the ML-enhanced ion mobility analysis method was successfully demonstrated by extracting specific features automatically from ion mobility spectrometry data with ML algorithms,which significantly enhance the detection ability of the SM-TENG based VOC analyzer,showing a portable real-time VOC monitoring solution with rapid response and low power consumption for future internet of things based environmental monitoring applications.
