ID 原文 译文
3083 该机制通过计算交易到达节点与下一跳节点之间的托管金额,建立交易的转发规则,对于排队阈值内无法进行资金注入的节点,设计信道均衡选路算法为其计算新的转发路径。 This mechan-ism established the forwarding rules for transactions by calculating the escrow amount between the node that transactions arrived and the next hop node, where the channel balanced routing algorithm was used to calculate the new forwarding pathfor the nodes that could not carry out capital injection within the queuing threshold.
3084 仿真结果表明,所提策略可以提高交易成功率并实现付费信道网络均衡。 The simulation results show that the proposed strategy could improve the transaction success rate and realize the equilibrium of the payment channel network.
3085 针对现有随机路由防御方法对数据流拆分粒度过粗、对合法的服务质量（QoS）保障效果不佳、对抗窃听攻击的安全性有待提升等问题,提出一种基于深度确定性策略梯度（DDPG）的随机路由防御方法。 To solve the problem of the existing routing shuffling defenses, such as too coarse data flow splitting granular-ity, poor protection effect on legitimate QoS and the security against eavesdropping attacks needed to be improved, a random routing defense method based on DDPG was proposed.
3086 通过带内网络遥测（INT）技术实时监测并获取网络状态;通过DDPG方法生成兼顾安全性和QoS需求的随机路由方案;通过P4框架下的可编程交换机执行随机路由方案,实现了数据包级粒度的随机路由防御。 INT was used to monitor and obtain the network state inreal time, DDPG algorithm was used to generate random routing scheme considering both security and QoS requirements,random routing scheme was implemented with programmable switch under P4 framework to realize real-time routingshuffling with packet level granularity.
3087 实验表明,与其他典型的随机路由方法相比,所提方法在对抗窃听攻击中的安全性和对网络整体QoS的保障效果均有提升。 Experiment results show that compared with other typical routing shuffling de-fense methods, the security and QoS protection effect of the proposed method are improved.
3088 为了解决城市场景中车联网时空数据异构以及单个基础设施范围内存在连通效率低下的问题，提出一种 车联网时空数据分析及其通达性方法。 In order to solve the problems of diversity spatio-temporal data and low connectivity efficiency in a single road side unit for Internet of vehicles (IoV) in an urban scene, a spatio-temporal data analysis and accessibility method was presented.
3089 首先，给出基于噪声去除和数据填充的时空数据分析方法，构建基于张量 因子聚合的神经网络预测车辆之间的连通强度； First, a spatio-temporal data analysis method based on de-noising and data filling was introduced, and a tensor factor aggregation-based neural network was constructed to predict connectivity intensity among vehicles.
3090 然后，基于车联网连通强度给出有基础设施车联网的通达性方法。 Then, a con- nectivity intensity prediction-based accessibility method was proposed.
3091 仿真实验结果表明，基于张量因子聚合的神经网络可以有效预测车辆之间的连通强度，所提方法可以有效减少连 通冗余和路边基础设施负载。 The simulation results demonstrate that the pro- posed connectivity intensity prediction method can accurately predict connectivity intensity among vehicles, and the proposed accessibility method can effectively reduce connectivity redundancy and loads of road side units.
3092 为了应对设备差异化计算能力及非独立同分布数据对联邦学习性能的影响，高效地调度终端设备完成模 型聚合，提出了一种基于深度强化学习的设备节点选择方法。 To cope with the impact of different device computing capabilities and non-independent uniformly distributed data on federated learning performance, and to efficiently schedule terminal devices to complete model aggregation, a method of node selection based on deep reinforcement learning was proposed.