ID 原文 译文
17285 最后采用变步长的稀疏自适应子空间追踪(SASP)算法对源信号进行重构恢复。 Finally, the source signal is reconstructed and restored by a variable step size SparsityAdaptive Subspace Pursuit(SASP) algorithm.
17286 仿真实验表明，该算法在低信噪比(SNR)条件下，跳频信号波达方向估计和恢复精度较高，能够有效完成同步跳频信号的盲分离。 The simulation experiments show that the proposed algorithmhas higher recovery accuracy of the frequency hopping signal under the condition of low Signal to Noise Ratio(SNR), and can effectively complete the blind separation of the synchronous frequency hopping signal.
17287 针对NFV/SDN架构下，服务功能链(SFC)的资源需求动态变化引起的虚拟网络功能(VNF)迁移优化问题，该文提出一种基于深度强化学习的VNF迁移优化算法。 To solve the problem of Virtual Network Function (VNF) migration optimization, which is caused by the dynamic change of resource requirements of Service Function Chain (SFC) under Network FunctionVirtualization/ Software Defined Network (NFV/SDN) architecture, a VNF migration optimization algorithm is proposed based on deep reinforcement learning.
17288 首先，在底层CPU、带宽资源和SFC端到端时延约束下，建立基于马尔可夫决策过程(MDP)的随机优化模型，该模型通过迁移VNF来联合优化网络能耗和SFC端到端时延。 Firstly, based on the underlying CPU, bandwidth resourcesand SFC end-to-end delay constraints, a Markov Decision Process (MDP) based stochastic optimization modelis established. This model is used to optimize jointly network energy consumption and SFC end-to-end delay bymigrating VNF.
17289 其次，由于状态空间和动作空间是连续值集合，提出一种基于深度确定性策略梯度(DDPG)的VNF智能迁移算法，从而得到近似最优的VNF迁移策略。 Secondly, since the state space and action space of this paper are continuous value sets, a VNFintelligent migration algorithm based on Deep Deterministic Policy Gradient (DDPG) is proposed to obtain anapproximate optimal VNF migration strategy. This model is used to optimize jointly network energy consumption and SFC end-to-end delay bymigrating VNF.
17290 仿真结果表明，该算法可以实现网络能耗和SFC端到端时延的折中，并提高物理网络的资源利用率。 The simulation results show that the algorithm can achieve thecompromise between network energy consumption and SFC end-to-end delay, and improve the resourceutilization of the physical network.
17291 传输时延和数据包丢失率是电力通信业务可靠传输重点关注的问题，该文提出一种面向软件定义电力通信网络的最小路径选择度路由控制策略。 Transmission delay and packet loss rate are critical issues in reliable transmission of powercommunication services. A minimum path selection routing control strategy for software-defined powercommunication networks is proposed.
17292 结合电力通信网络软件定义网络(SDN)集中控制架构的特点，利用图卷积神经网络构建的链路带宽占用率预测模型(LBOP-GCN)分析下一时刻路径带宽占用率。 Combining the characteristics of the centralized control structure of thesoftware-defined power communication network, a Link Bandwidth Occupancy Predictive model based onGraph Convolutional Network (LBOP-GCN) is built to analyze the route paths bandwidth occupancy in thenext period.
17293 通过三角模算子(TMO)融合路径的传输时延、当前时刻的路径带宽占用率和下一时刻的路径带宽占用率，计算出从源节点到目的节点间不同传输路径的选择度(Q)，然后将Q值最小的路径作为SDN控制器下发的流表项。 The selectivity (Q) of different transmission paths from the source node is calculated to thedestination node is calculated by using Triangle Modular Operator (TMO) to fuse the transmission delay of thepath, the path bandwidth occupancy at the current moment and the path bandwidth occupancy at the nextmoment. Then the path with the lowest Q value is used as the flow table of the OpenFlow switch delivered bythe Software Defined Network (SDN) controller.
17294 实验结果表明，该文所提出的路由控制策略能有效减小业务传输时延和数据包丢失率。 Experiments show that the proposed routing control strategycan effectively reduce service transmission delay and packet loss rate.