ID 原文 译文
57698 同时，在网络规模很大、业务数量很多的情况下，深度强化学习算法可有效提高计算效率. At the same time，for scenarios with a large network size and a large number of services，the deep reinforcement learning algorithm can effec- tively improve the computational efficiency.
57699 为了更好地实现数据中心网络的节能，基于交换机链路速率级的能耗特点，基于软件定义网络技术，提出一种 Floyd-Warshall 动态规划和局部重路由的节能服务质量路由优化算法. Based on link speed-scaling energy consumption strategy，Floyd-Warshall dynamic planning ＆rerouting parts of flows strategy based routing optimization algorithm was proposed.
57700 控制器在保障流的时延性能前提下，采用流在空间和时间上均衡传输的策略，依次为每个流计算传输路径和传输速率; Considering the condition of flow deadline-aware and balanced transmission of flows strategy in space and time，controller insoftware defined data center network sorts the online incoming flows and chooses the route and calculatesthe transmission rate for every flow. In case of routing failure，the algorithm improves the acceptance rateof network traffic with less overhead.
57701 在选路失败的情况下，尽量用较少的开销提高网络的接受率.仿真结果表明，该算法有效地降低了能耗，同时提高了网络流的接受率. Simulations show that the algorithm effectively reduces energy consumption and improves the acceptance rate of network traffic.
57702 为了解决全双工能量受限中继网络的无线物理层安全问题，提出了一种基于能量和信息联合传输的安全波束成形方法. In order to solve the problem of optimizing the security rate of full duplex relay eavesdroppingchannel with energy harvesting capability，a secure beamforming design was proposed under simultaneouswireless information and power transfer ( SWIPT) method.
57703 在满足中继节点和能量收集节点收集能量的约束条件下，通过联合优化能量信号协方差矩阵、波束成形矩阵和功率分配因子，实现了系统安全速率最大化. An optimization problem was considered aiming to maximize the secrecy rate of the system by jointly optimizing the beamforming matrix，energy signal covariance matrix and the power splitting ration under the constraint of the energy harvesting of the relay and energy-harvesting node.
57704 目标问题是非凸的，采用分步优化方法将原始问题转化为 2个子问题. Since this problem is a non-convex secrecy rate maximization ( SＲM)problem，We use a step-by-step optimization approach to turn the objective problem into two sub-problems was decoupled.
57705 将第 1 个子问题转化为双层优化问题，外层优化问题采用一维搜索求解，内层优化问题采用半定松弛技术解决;然后通过一维搜索得到第 2 个子问题的最优解. The first subproblem can be recast as a two-level optimization problem. Amongthem，the outer optimization problem was solved by one-dimensional search，and the inner optimizationproblem was solved by semidefinite relaxation ( SDＲ) technique.
57706 仿真结果表明，提出的方法显著提高了系统的安全速率 The second subproblem can be solvedby one-dimensional search. Simulation results show that the proposed method increases the security rateof the system.
57707 针对密集物联网环境下的信号碰撞问题，提出了一种分组及时应答多个节点、降低碰撞率的广播协议. Aiming at the problem of signal collision in the dense Internet of Things environment，an anticollision broadcasting scheme was proposed which can group respond to multiple nodes in time and reducethe collision rate.