现有研究在多QoS(quality of service)调度问题中,由于仅依赖即时奖励反馈机制,在资源受限的场景下处理时延敏感数据和具有连续传输需求的媒体数据时,存在可扩展性差和资源浪费的问题。为此,提出了一种基于奖励回溯的DQN(reward backtra...现有研究在多QoS(quality of service)调度问题中,由于仅依赖即时奖励反馈机制,在资源受限的场景下处理时延敏感数据和具有连续传输需求的媒体数据时,存在可扩展性差和资源浪费的问题。为此,提出了一种基于奖励回溯的DQN(reward backtracking based deep Q-network,RB-DQN)算法。该算法通过未来时刻的交互来回溯调整当前状态的策略评估,以更加有效地识别并解决因不合理调度策略导致的丢包。同时,设计了一种时延-吞吐均衡度量(latency throughput trade-off,LTT)指标,该指标综合考虑了时延敏感数据和媒体类型数据的业务需求,并可通过权重调整来突出不同的侧重点。大量仿真结果表明,与其他调度策略相比,所提算法能够有效降低时延敏感数据的延迟和抖动,同时确保媒体类型数据的流畅性与稳定性。展开更多
Wireless sensor network(WSN)technologies have advanced significantly in recent years.With in WSNs,machine learning algorithms are crucial in selecting cluster heads(CHs)based on various quality of service(QoS)metrics....Wireless sensor network(WSN)technologies have advanced significantly in recent years.With in WSNs,machine learning algorithms are crucial in selecting cluster heads(CHs)based on various quality of service(QoS)metrics.This paper proposes a new clustering routing protocol employing the Traveling Salesman Problem(TSP)to locate the optimal path traversed by the Mobile Data Collector(MDC),in terms of energy and QoS efficiency.To bemore specific,to minimize energy consumption in the CH election stage,we have developed the M-T protocol using the K-Means and the grid clustering algorithms.In addition,to improve the transmission phase of the Low Energy Adaptive Clustering-Grid-KMeans(LEACH-G-K)protocol,the MDC is employed as an intermediary between the CH and the sink to improve the wireless sensor network(WSN)QoS.The results of the experiment demonstrate that the M-T protocol enhances various Low Energy Adaptive Clustering protocol(LEACH)improvements such as the LEACH-G-K,LEACH-C,Threshold sensitive Energy Efficient Sensor Networks(TEEN),MDC maximum residual energy leach protocol.展开更多
Low Earth orbit(LEO)satellite networks exhibit distinct characteristics,e.g.,limited resources of individual satellite nodes and dynamic network topology,which have brought many challenges for routing algorithms.To sa...Low Earth orbit(LEO)satellite networks exhibit distinct characteristics,e.g.,limited resources of individual satellite nodes and dynamic network topology,which have brought many challenges for routing algorithms.To satisfy quality of service(QoS)requirements of various users,it is critical to research efficient routing strategies to fully utilize satellite resources.This paper proposes a multi-QoS information optimized routing algorithm based on reinforcement learning for LEO satellite networks,which guarantees high level assurance demand services to be prioritized under limited satellite resources while considering the load balancing performance of the satellite networks for low level assurance demand services to ensure the full and effective utilization of satellite resources.An auxiliary path search algorithm is proposed to accelerate the convergence of satellite routing algorithm.Simulation results show that the generated routing strategy can timely process and fully meet the QoS demands of high assurance services while effectively improving the load balancing performance of the link.展开更多
为了解决现有路由算法无法学习历史路由决策经验导致的网络负载不均衡问题,将强化学习技术引入软件定义网络(Software Defined Network,SDN)的服务质量(Quality of Service,QoS)路由问题,提出一种基于强化学习的多业务智能QoS路由方法MD...为了解决现有路由算法无法学习历史路由决策经验导致的网络负载不均衡问题,将强化学习技术引入软件定义网络(Software Defined Network,SDN)的服务质量(Quality of Service,QoS)路由问题,提出一种基于强化学习的多业务智能QoS路由方法MDQN(Multi-service QoS routing method based on DeepQ Network)。该方法部署在SDN控制器中,能学习历史决策经验,并在网络状态发生变化时及时调整路径。通过在SDN中部署该方法,有效平衡了网络负载,增加了网络的吞吐量,为SDN中的QoS路由问题提供了一种有效的解决方案。展开更多
Wireless Body Area Network(WBAN)is essential for continuous health monitoring.However,they face energy efficiency challenges due to the low power consumption of sensor nodes.Current WBAN routing protocols face limitat...Wireless Body Area Network(WBAN)is essential for continuous health monitoring.However,they face energy efficiency challenges due to the low power consumption of sensor nodes.Current WBAN routing protocols face limitations in strategically minimizing energy consumption during the retrieval of vital health parameters.Efficient network traffic management remains a challenge,with existing approaches often resulting in increased delay and reduced throughput.Additionally,insufficient attention has been paid to enhancing channel capacity to maintain signal strength and mitigate fading effects under dynamic and robust operating scenarios.Several routing strategies and procedures have been developed to effectively reduce communication-related energy consumption based on the selection of relay nodes.The relay node selection is essential for data transmission in WBAN.This paper introduces an Adaptive Relay-Assisted Protocol(ARAP)for WBAN,a hybrid routing protocol designed to optimize energy use and Quality of Service(QoS)metrics such as network longevity,latency,throughput,and residual energy.ARAP employs neutrosophic relay node selection techniques,including the Analytic Hierarchy Process(AHP)and Technique for Order Preference by Similarity to Ideal Solution(TOPSIS)to optimally resolve data and decision-making uncertainties.The protocol was compared with existing protocols such as Low-Energy Adaptive Clustering Hierarchy(LEACH),Modified-Adaptive Threshold Testing and Evaluation Methodology for Performance Testing(M-ATTEMPT),Wireless Adaptive Sampling Protocol(WASP),and Tree-Based Multicast Quality of Service(TMQoS).The comparative results show that the ARAP significantly outperformed these protocols in terms of network longevity and energy efficiency.ARAP has lower communication cost,better throughput,reduced delay,increased network lifetime,and enhanced residual energy.The simulation results indicate that the proposed approach performed better than the conventional methods,with 68%,62%,25%,and 50%improvements in network longevity,residual energy,throughput,and latency,respectively.This significantly improves the functional lifespan of WBAN and makes them promising candidates for sophisticated health monitoring systems.展开更多
随着网络技术的不断发展,通信网络中的业务流量和终端数量急剧增加,导致网络传输的复杂性和负载压力显著上升。业务流量卸载通过将部分业务从主网络卸载至辅助网络或边缘计算节点,以缓解主网络的压力,提高整体网络的服务质量。本文研究...随着网络技术的不断发展,通信网络中的业务流量和终端数量急剧增加,导致网络传输的复杂性和负载压力显著上升。业务流量卸载通过将部分业务从主网络卸载至辅助网络或边缘计算节点,以缓解主网络的压力,提高整体网络的服务质量。本文研究了在时延QoS要求约束下,业务流量的卸载算法。结合有效容量和有效带宽理论,确保在高负载条件下满足业务的统计型时延QoS要求。通过排队论、有效容量和有效带宽理论构建时延分析模型,设计了流量卸载算法。基于不同网络的服务速率,求解相应的时延违反概率,在此基础上,计算不同网络的可支持的最大到达率,对业务流量进行权重分配,从而实现了对业务流量的动态卸载,确保了各网络资源的优化利用和系统性能的提升。仿真结果表明,在时延QoS约束条件下,算法能够有效降低网络时延,提高网络稳定性和服务质量。With the continuous development of network technology, traffic and the number of terminals in the communication network has increased sharply, resulting in a significant increase in the complexity and load pressure of network transmission. Unload some services from the primary network to the secondary network or edge computing nodes to relieve the pressure on the primary network and improve the overall network service quality. This paper studies the traffic offloading algorithm under the constraint of delay QoS requirements. Combining the theory of effective capacity and effective bandwidth, the QoS requirements of statistical delay can be satisfied under high load conditions. Based on queuing theory, effective capacity theory and effective bandwidth theory, the delay analysis model is constructed, and the traffic offloading algorithm is designed. Based on the service rate of different networks, the corresponding delay violation probability is solved. On this basis, the maximum arrival rate supported by different networks is calculated, and the weight of service traffic is assigned. In this way, the dynamic unloading of service traffic is realized, and the optimal utilization of network resources and the improvement of system performance are ensured. Simulation results show that the algorithm can effectively reduce network delay and improve network stability and service quality under the delay QoS constraint.展开更多
随着无线网络设备数量的激增和应用类型的多样化,传统路由器的静态分流策略已无法满足差异化的服务质量需求。针对网络拥塞、延迟波动和带宽分配不均等问题,设计了一种融合服务质量(quality of service,QoS)机制的智能分流算法。该算法...随着无线网络设备数量的激增和应用类型的多样化,传统路由器的静态分流策略已无法满足差异化的服务质量需求。针对网络拥塞、延迟波动和带宽分配不均等问题,设计了一种融合服务质量(quality of service,QoS)机制的智能分流算法。该算法采用分层架构设计,集成数据采集层、分析处理层和决策执行层3个核心层级。基于高通(Qualcomm)IPQ8074处理器与博通(Broadcom)BCM53134交换芯片构建硬件平台,并利用数据平面开发套件(data plane development kit,DPDK)技术实现高速数据包处理功能。通过构建星型网络拓扑结构开展多场景对比测试,实验结果表明,相较于传统先进先出(first in first out,FIFO)算法,智能分流算法在重负载场景下平均延迟降低了34%,吞吐量提升了17%,且能将关键业务丢包率控制在0.35%以下,为构建高效智能的无线网络环境提供了有力的技术支撑。展开更多
文摘现有研究在多QoS(quality of service)调度问题中,由于仅依赖即时奖励反馈机制,在资源受限的场景下处理时延敏感数据和具有连续传输需求的媒体数据时,存在可扩展性差和资源浪费的问题。为此,提出了一种基于奖励回溯的DQN(reward backtracking based deep Q-network,RB-DQN)算法。该算法通过未来时刻的交互来回溯调整当前状态的策略评估,以更加有效地识别并解决因不合理调度策略导致的丢包。同时,设计了一种时延-吞吐均衡度量(latency throughput trade-off,LTT)指标,该指标综合考虑了时延敏感数据和媒体类型数据的业务需求,并可通过权重调整来突出不同的侧重点。大量仿真结果表明,与其他调度策略相比,所提算法能够有效降低时延敏感数据的延迟和抖动,同时确保媒体类型数据的流畅性与稳定性。
基金supported by the Ministry of Education of the Republic of Korea and the National Research Foundation of Korea(NRF-2023S1A5C2A07096111).
文摘Wireless sensor network(WSN)technologies have advanced significantly in recent years.With in WSNs,machine learning algorithms are crucial in selecting cluster heads(CHs)based on various quality of service(QoS)metrics.This paper proposes a new clustering routing protocol employing the Traveling Salesman Problem(TSP)to locate the optimal path traversed by the Mobile Data Collector(MDC),in terms of energy and QoS efficiency.To bemore specific,to minimize energy consumption in the CH election stage,we have developed the M-T protocol using the K-Means and the grid clustering algorithms.In addition,to improve the transmission phase of the Low Energy Adaptive Clustering-Grid-KMeans(LEACH-G-K)protocol,the MDC is employed as an intermediary between the CH and the sink to improve the wireless sensor network(WSN)QoS.The results of the experiment demonstrate that the M-T protocol enhances various Low Energy Adaptive Clustering protocol(LEACH)improvements such as the LEACH-G-K,LEACH-C,Threshold sensitive Energy Efficient Sensor Networks(TEEN),MDC maximum residual energy leach protocol.
基金National Key Research and Development Program(2021YFB2900604)。
文摘Low Earth orbit(LEO)satellite networks exhibit distinct characteristics,e.g.,limited resources of individual satellite nodes and dynamic network topology,which have brought many challenges for routing algorithms.To satisfy quality of service(QoS)requirements of various users,it is critical to research efficient routing strategies to fully utilize satellite resources.This paper proposes a multi-QoS information optimized routing algorithm based on reinforcement learning for LEO satellite networks,which guarantees high level assurance demand services to be prioritized under limited satellite resources while considering the load balancing performance of the satellite networks for low level assurance demand services to ensure the full and effective utilization of satellite resources.An auxiliary path search algorithm is proposed to accelerate the convergence of satellite routing algorithm.Simulation results show that the generated routing strategy can timely process and fully meet the QoS demands of high assurance services while effectively improving the load balancing performance of the link.
文摘为了解决现有路由算法无法学习历史路由决策经验导致的网络负载不均衡问题,将强化学习技术引入软件定义网络(Software Defined Network,SDN)的服务质量(Quality of Service,QoS)路由问题,提出一种基于强化学习的多业务智能QoS路由方法MDQN(Multi-service QoS routing method based on DeepQ Network)。该方法部署在SDN控制器中,能学习历史决策经验,并在网络状态发生变化时及时调整路径。通过在SDN中部署该方法,有效平衡了网络负载,增加了网络的吞吐量,为SDN中的QoS路由问题提供了一种有效的解决方案。
文摘Wireless Body Area Network(WBAN)is essential for continuous health monitoring.However,they face energy efficiency challenges due to the low power consumption of sensor nodes.Current WBAN routing protocols face limitations in strategically minimizing energy consumption during the retrieval of vital health parameters.Efficient network traffic management remains a challenge,with existing approaches often resulting in increased delay and reduced throughput.Additionally,insufficient attention has been paid to enhancing channel capacity to maintain signal strength and mitigate fading effects under dynamic and robust operating scenarios.Several routing strategies and procedures have been developed to effectively reduce communication-related energy consumption based on the selection of relay nodes.The relay node selection is essential for data transmission in WBAN.This paper introduces an Adaptive Relay-Assisted Protocol(ARAP)for WBAN,a hybrid routing protocol designed to optimize energy use and Quality of Service(QoS)metrics such as network longevity,latency,throughput,and residual energy.ARAP employs neutrosophic relay node selection techniques,including the Analytic Hierarchy Process(AHP)and Technique for Order Preference by Similarity to Ideal Solution(TOPSIS)to optimally resolve data and decision-making uncertainties.The protocol was compared with existing protocols such as Low-Energy Adaptive Clustering Hierarchy(LEACH),Modified-Adaptive Threshold Testing and Evaluation Methodology for Performance Testing(M-ATTEMPT),Wireless Adaptive Sampling Protocol(WASP),and Tree-Based Multicast Quality of Service(TMQoS).The comparative results show that the ARAP significantly outperformed these protocols in terms of network longevity and energy efficiency.ARAP has lower communication cost,better throughput,reduced delay,increased network lifetime,and enhanced residual energy.The simulation results indicate that the proposed approach performed better than the conventional methods,with 68%,62%,25%,and 50%improvements in network longevity,residual energy,throughput,and latency,respectively.This significantly improves the functional lifespan of WBAN and makes them promising candidates for sophisticated health monitoring systems.
文摘车载自组织网络(Vehicular Ad-hoc Networks, VANETs)环境中,节点高速移动、网络拓扑频繁变化以及链路质量不稳定等特性,使得多维服务质量(Quality of Service, QoS)保障面临严峻挑战。针对现有方法难以协同考虑时延、丢包率与带宽利用率等多重指标的不足,本研究提出一种分层SDN与SRv6协同驱动的蚁群优化路由框架。该框架通过路侧单元(Roadside Unit, RSU)与中心控制器的协同决策,实现了局部快速响应与全局流量调度的有机融合。并提出了蚁群驱动SRv6路由算法(Ant Colony-based Segment Routing over SRv6, ACSR)算法,在传统信息素模型中引入欧氏距离启发式,并以多维QoS综合代价函数引导路径搜索,加速收敛至高质量解。还提出了基于关键节点保留的路径压缩算法,有效降低了段路由扩展头的开销。实验结果表明,所提出的ACSR算法在网络吞吐量、时延、丢包率等指标上表现出色,具有广阔的实际应用前景。
文摘随着网络技术的不断发展,通信网络中的业务流量和终端数量急剧增加,导致网络传输的复杂性和负载压力显著上升。业务流量卸载通过将部分业务从主网络卸载至辅助网络或边缘计算节点,以缓解主网络的压力,提高整体网络的服务质量。本文研究了在时延QoS要求约束下,业务流量的卸载算法。结合有效容量和有效带宽理论,确保在高负载条件下满足业务的统计型时延QoS要求。通过排队论、有效容量和有效带宽理论构建时延分析模型,设计了流量卸载算法。基于不同网络的服务速率,求解相应的时延违反概率,在此基础上,计算不同网络的可支持的最大到达率,对业务流量进行权重分配,从而实现了对业务流量的动态卸载,确保了各网络资源的优化利用和系统性能的提升。仿真结果表明,在时延QoS约束条件下,算法能够有效降低网络时延,提高网络稳定性和服务质量。With the continuous development of network technology, traffic and the number of terminals in the communication network has increased sharply, resulting in a significant increase in the complexity and load pressure of network transmission. Unload some services from the primary network to the secondary network or edge computing nodes to relieve the pressure on the primary network and improve the overall network service quality. This paper studies the traffic offloading algorithm under the constraint of delay QoS requirements. Combining the theory of effective capacity and effective bandwidth, the QoS requirements of statistical delay can be satisfied under high load conditions. Based on queuing theory, effective capacity theory and effective bandwidth theory, the delay analysis model is constructed, and the traffic offloading algorithm is designed. Based on the service rate of different networks, the corresponding delay violation probability is solved. On this basis, the maximum arrival rate supported by different networks is calculated, and the weight of service traffic is assigned. In this way, the dynamic unloading of service traffic is realized, and the optimal utilization of network resources and the improvement of system performance are ensured. Simulation results show that the algorithm can effectively reduce network delay and improve network stability and service quality under the delay QoS constraint.
文摘随着无线网络设备数量的激增和应用类型的多样化,传统路由器的静态分流策略已无法满足差异化的服务质量需求。针对网络拥塞、延迟波动和带宽分配不均等问题,设计了一种融合服务质量(quality of service,QoS)机制的智能分流算法。该算法采用分层架构设计,集成数据采集层、分析处理层和决策执行层3个核心层级。基于高通(Qualcomm)IPQ8074处理器与博通(Broadcom)BCM53134交换芯片构建硬件平台,并利用数据平面开发套件(data plane development kit,DPDK)技术实现高速数据包处理功能。通过构建星型网络拓扑结构开展多场景对比测试,实验结果表明,相较于传统先进先出(first in first out,FIFO)算法,智能分流算法在重负载场景下平均延迟降低了34%,吞吐量提升了17%,且能将关键业务丢包率控制在0.35%以下,为构建高效智能的无线网络环境提供了有力的技术支撑。
