信道预测是支撑变电站等电力物联网通信系统自适应传输的重要技术。为了解决过期信道状态信息降低通信系统自适应传输性能的问题,提出了一种基于自适应跳跃学习网络的信道状态信息预测方法。该方法主要包括递归微调算法和混合惩戒网络...信道预测是支撑变电站等电力物联网通信系统自适应传输的重要技术。为了解决过期信道状态信息降低通信系统自适应传输性能的问题,提出了一种基于自适应跳跃学习网络的信道状态信息预测方法。该方法主要包括递归微调算法和混合惩戒网络两部分。其中,前者主要用于微调学习网络的随机输入权重矩阵,后者主要通过两层惩戒网络来解决输出权重矩阵的病态解问题。由于具有oracle属性,自适应跳跃学习网络不仅具有良好的泛化能力,还可以生成稀疏性输出权重矩阵。仿真结果表明,自适应跳跃学习网络在IEEE802.11ah协议的正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)通信系统中具有良好的单步预测性能和多步预测性能。展开更多
Spectrum prediction plays an important role for the secondary user(SU)to utilize the shared spectrum resources.However,currently utilized prediction methods are not well applied to spectrum with high burstiness,as par...Spectrum prediction plays an important role for the secondary user(SU)to utilize the shared spectrum resources.However,currently utilized prediction methods are not well applied to spectrum with high burstiness,as parameters of prediction models cannot be adjusted properly.This paper studies the prediction problem of bursty bands.Specifically,we first collect real Wi Fi transmission data in 2.4GHz Industrial,Scientific,Medical(ISM)band which is considered to have bursty characteristics.Feature analysis of the data indicates that the spectrum occupancy law of the data is time-variant,which suggests that the performance of commonly used single prediction model could be restricted.Considering that the match between diverse spectrum states and multiple prediction models may essentially improve the prediction performance,we then propose a deep-reinforcement learning based multilayer perceptron(DRL-MLP)method to address this matching problem.The state space of the method is composed of feature vectors,and each of the vectors contains multi-dimensional feature values.Meanwhile,the action space consists of several multilayer perceptrons(MLPs)that are trained on the basis of multiple classified data sets.We finally conduct experiments with the collected real data and simulations with generated data to verify the performance of the proposed method.The results demonstrate that the proposed method significantly outperforms the stateof-the-art methods in terms of the prediction accuracy.展开更多
IEEE 802.11ah is a new Wi-Fi standard for sub-1Ghz communications,aiming to address the challenges of the Internet of Things(IoT).Significant changes in the legacy 802.11 standards have been proposed to improve the ne...IEEE 802.11ah is a new Wi-Fi standard for sub-1Ghz communications,aiming to address the challenges of the Internet of Things(IoT).Significant changes in the legacy 802.11 standards have been proposed to improve the network performance in high contention scenarios,the most important of which is the Restricted Access Window(RAW)mechanism.This mechanism promises to increase the throughput and energy efficiency by dividing stations into different groups.Under this scheme,only the stations belonging to the same group may access the channel,which reduces the collision probability in dense scenarios.However,the standard does not define the RAW grouping strategy.In this paper,we develop a new mathematical model based on the renewal theory,which allows for tracking the number of transmissions within the limited RAW slot contention period defined by the standard.We then analyze and evaluate the performance of RAW mechanism.We also introduce a grouping scheme to organize the stations and channel access time into different groups within the RAW.Furthermore,we propose an algorithm to derive the RAW configuration parameters of a throughput maximizing grouping scheme.We additionally explore the impact of channel errors on the contention within the time-limited RAW slot and the overall RAW optimal configuration.The presented analytical framework can be applied to many other Wi-Fi standards that integrate periodic channel reservations.Extensive simulations using the MATLAB software validate the analytical model and prove the effectiveness of the proposed RAW configuration scheme.展开更多
Mobility support to change the connection from one access point(AP)to the next(i.e.,handover)becomes one of the important issues in IEEE 802.11 wireless local area networks(WLANs).During handover,the channel scanning ...Mobility support to change the connection from one access point(AP)to the next(i.e.,handover)becomes one of the important issues in IEEE 802.11 wireless local area networks(WLANs).During handover,the channel scanning procedure,which aims to collect neighbor AP(NAP)information on all available channels,accounts for most of the delay time.To reduce the channel scanning procedure,a neighbor beacon frame transmission scheme(N-BTS)was proposed for a seamless handover.N-BTS can provide a seamless handover by removing the channel scanning procedure.However,N-BTS always requires operating overhead even if there are few mobile stations(MSs)for the handover.Therefore,this paper proposes a reinforcement learning-based handover scheme with neighbor beacon frame transmission(MAN-BTS)to properly consider the use of N-BTS.The optimization equation is defined to maximize the expected reward tofind the optimal policy and is solved using Q-learning.Simulation results show that the proposed scheme outperforms the comparison schemes in terms of the expected reward.展开更多
文摘信道预测是支撑变电站等电力物联网通信系统自适应传输的重要技术。为了解决过期信道状态信息降低通信系统自适应传输性能的问题,提出了一种基于自适应跳跃学习网络的信道状态信息预测方法。该方法主要包括递归微调算法和混合惩戒网络两部分。其中,前者主要用于微调学习网络的随机输入权重矩阵,后者主要通过两层惩戒网络来解决输出权重矩阵的病态解问题。由于具有oracle属性,自适应跳跃学习网络不仅具有良好的泛化能力,还可以生成稀疏性输出权重矩阵。仿真结果表明,自适应跳跃学习网络在IEEE802.11ah协议的正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)通信系统中具有良好的单步预测性能和多步预测性能。
基金supported in part by the China National Key R&D Program(no.2020YF-B1808000)Beijing Natural Science Foundation(No.L192002)+2 种基金in part by the Fundamental Research Funds for the Central Universities(No.328202206)the National Natural Science Foundation of China(No.61971058)in part by"Advanced and sophisticated"discipline construction project of universities in Beijing(No.20210013Z0401)。
文摘Spectrum prediction plays an important role for the secondary user(SU)to utilize the shared spectrum resources.However,currently utilized prediction methods are not well applied to spectrum with high burstiness,as parameters of prediction models cannot be adjusted properly.This paper studies the prediction problem of bursty bands.Specifically,we first collect real Wi Fi transmission data in 2.4GHz Industrial,Scientific,Medical(ISM)band which is considered to have bursty characteristics.Feature analysis of the data indicates that the spectrum occupancy law of the data is time-variant,which suggests that the performance of commonly used single prediction model could be restricted.Considering that the match between diverse spectrum states and multiple prediction models may essentially improve the prediction performance,we then propose a deep-reinforcement learning based multilayer perceptron(DRL-MLP)method to address this matching problem.The state space of the method is composed of feature vectors,and each of the vectors contains multi-dimensional feature values.Meanwhile,the action space consists of several multilayer perceptrons(MLPs)that are trained on the basis of multiple classified data sets.We finally conduct experiments with the collected real data and simulations with generated data to verify the performance of the proposed method.The results demonstrate that the proposed method significantly outperforms the stateof-the-art methods in terms of the prediction accuracy.
基金supported by the Spanish Ministry of Science,Education and Universities,the European Regional Development Fund and the State Research Agency,Grant No.RTI2018-098156-B-C52.
文摘IEEE 802.11ah is a new Wi-Fi standard for sub-1Ghz communications,aiming to address the challenges of the Internet of Things(IoT).Significant changes in the legacy 802.11 standards have been proposed to improve the network performance in high contention scenarios,the most important of which is the Restricted Access Window(RAW)mechanism.This mechanism promises to increase the throughput and energy efficiency by dividing stations into different groups.Under this scheme,only the stations belonging to the same group may access the channel,which reduces the collision probability in dense scenarios.However,the standard does not define the RAW grouping strategy.In this paper,we develop a new mathematical model based on the renewal theory,which allows for tracking the number of transmissions within the limited RAW slot contention period defined by the standard.We then analyze and evaluate the performance of RAW mechanism.We also introduce a grouping scheme to organize the stations and channel access time into different groups within the RAW.Furthermore,we propose an algorithm to derive the RAW configuration parameters of a throughput maximizing grouping scheme.We additionally explore the impact of channel errors on the contention within the time-limited RAW slot and the overall RAW optimal configuration.The presented analytical framework can be applied to many other Wi-Fi standards that integrate periodic channel reservations.Extensive simulations using the MATLAB software validate the analytical model and prove the effectiveness of the proposed RAW configuration scheme.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea Government(MSIT)(No.2020R1G1A1100493).
文摘Mobility support to change the connection from one access point(AP)to the next(i.e.,handover)becomes one of the important issues in IEEE 802.11 wireless local area networks(WLANs).During handover,the channel scanning procedure,which aims to collect neighbor AP(NAP)information on all available channels,accounts for most of the delay time.To reduce the channel scanning procedure,a neighbor beacon frame transmission scheme(N-BTS)was proposed for a seamless handover.N-BTS can provide a seamless handover by removing the channel scanning procedure.However,N-BTS always requires operating overhead even if there are few mobile stations(MSs)for the handover.Therefore,this paper proposes a reinforcement learning-based handover scheme with neighbor beacon frame transmission(MAN-BTS)to properly consider the use of N-BTS.The optimization equation is defined to maximize the expected reward tofind the optimal policy and is solved using Q-learning.Simulation results show that the proposed scheme outperforms the comparison schemes in terms of the expected reward.
文摘随着人工智能、大数据、物联网等技术的高速发展,4K/8K视频、在线大型游戏、虚拟现实(Virtual Reality,VR)和远程办公等应用程序也应运而生。然而,现有的Wi-Fi 6标准难以满足其高吞吐量和低时延的网络需求。因此,IEEE将发布下一代无线局域网(Wireless Local Area Network,WLAN)标准IEEE 802.11be,也称为Wi-Fi 7。文章重点介绍和分析了Wi-Fi 7的技术特点和应用场景,最后总结和展望了Wi-Fi 7的研究方向和潜在发展。
