ID	原文	译文
4623	实验结果表明，在上述 2 种问题场景中，所提位置隐私保护机制与基于差分隐私的位置隐私保护方法相比具有更低的隐私泄露，且当真实位置数据具有显著不同的受欢迎程度时，优势更明显。	Experimental results show the superiority of the proposed LPPM over anexisting LPPM in terms of location privacyutility tradeoff in both scenarios, which is more conspicuous when there arehighly popular locations.
4624	为解决软件定义网络场景中，当前主流的基于启发式算法的 QoS 优化方案常因参数与网络场景不匹配出现性能下降的问题，提出了基于深度强化学习的软件定义网络 QoS 优化算法。	To solve the problem that the QoS optimization schemes which based on heuristic algorithm degraded oftendue to the mismatch between parameters and network characteristics in software-defined networking scenarios, a soft-ware-defined networking QoS optimization algorithm based on deep reinforcement learning was proposed.
4625	首先将网络资源和状态信息统一到网络模型中，然后通过长短期记忆网络提升算法的流量感知能力，最后基于深度强化学习生成满足 QoS 目标的动态流量调度策略。	Firstly, thenetwork resources and state information were integrated into the network model, and then the flow perception capabilitywas improved by the long short-term memory, and finally the dynamic flow scheduling strategy, which satisfied the spe-cific QoS objectives, were generated in combination with deep reinforcement learning.
4626	实验结果表明，相对于现有算法，所提算法不但保证了端到端传输时延和分组丢失率，而且提高了 22.7%的网络负载均衡程度，增加了 8.2%的网络吞吐率。	The experimental results show that, compared with the existing algorithms, the proposed algorithm not only ensures the end-to-end delay and packet lossrate, but also improves the network load balancing by 22.7% and increases the throughput by 8.2%.
4627	针对 Storm 存在低效率、高能耗的问题，通过分析 Storm 平台的基本框架与拓扑结构，设计了资源约束模型、最优线程数据重组原则和节点降压原则，并在此基础上提出了基于 Storm 平台的数据迁移合并节能策略（DMM-Storm），包括资源约束算法、数据迁移合并算法和节点降压算法。	Storm is suffering the problems of high energy consumption but low efficiency. Aiming at this problem, the re-source constraint model, the optimal principle of data reorganization in executors and node voltage reduction principle were proposed based on the analysis of the architecture and topology of Storm, and further the energy-efficient strategy for datamigration and merging was put forward in Storm(DMM-Storm), which was composed of resource constraint algorithm, data migration and merging algorithm as well as node voltage reduction algorithm.
4628	其中资源约束算法根据资源约束模型，判断工作节点是否允许数据的迁移；	The resource constraint algorithm estimateswhether work nodes are appropriate for data migration according to the resource constraint model.
4629	数据迁移合并算法根据最优线程数据重组原则，设计了最优的线程数据迁移方法；	The data migration andmerging algorithm designs an optimal method to migrate data according to the the optimal principle of data reorganization inexecutors.
4630	节点降压算法根据节点降压限制条件，降低了工作节点的电压。	The node voltage reduction algorithm reduces voltage of work nodes according to node voltage reduction prin-ciple.
4631	实验结果表明，与现有的节能策略相比，执行 DMM-Storm 在不影响集群性能的前提下，有效降低了能耗。	The experimental results show that the DMM-Storm can reduce energy consumption efficiently without affecting theperformance of cluster compared with the existing researches.
4632	针对回程干扰门限与链路容量限制下的超密集网络（UDN）场景，提出了一种基于整数线性规划和拉格朗日对偶分解的能量效率与频谱效率联合优化算法。	Aiming at the scenarios which consider the constraint of backhaul capacity restriction and interference thre-shold in ultra-dense networks (UDN), an integer linear programming (ILP) and Lagrangian dual decomposition (LDD)based joint optimization algorithm of energy efficiency and spectrum efficiency was proposed.