ID 原文 译文
20875 首先，通过经典的闭式解析算法将TDOA非线性方程转化为伪线性方程，并使用位置误差的协方差矩阵来度量定位精度。 Firstly, the localization accuracy metric is given by the error covariancematrix of classical closed-form solution, which is introduced to convert the TDOA nonlinear equations intopseudo linear equations.
20876 其次，在可用节点数量给定的条件下，在数学上将定位节点选择问题转化为最小化位置误差协方差矩阵的迹这一非凸优化问题。 Secondly, the problem of sensor selection can be mathematically transformed into the non-convex optimization problem, to minimize the trace of localization error covariance matrix under the condition that the number of active sensors is given.
20877 然后，将非凸优化问题凸松弛并化为半正定规划问题，从而快速有效地求解出最优的定位节点组合。 Then, the non-convex optimization problem is relaxed and transformed into a positive semi-definite programming problem so that the optimal subset of positioning nodes can be solved quickly and effectively.
20878 仿真结果表明，所提节点优选方法的性能非常接近穷尽搜索方法，而且克服了穷尽搜索方法运算复杂度高、时效性差的不足，从而验证了所提方法的有效性。 Simulation results validate that the performance of proposed sensorselection method is very close to the exhausted-search method, and overcomes the shortcomings of the highcomputation complexity and poor timeliness of the exhausted-search method.
20879 工作负载分配不均是制约众核密码平台资源利用率提高的重要因素，动态负载分配可提高平台资源利用率，但具有一定开销； Imbalanced workload distribution results in low resource utilization of many-core crypto-platform. Dynamic workload allocation can improve the resource utilization with some overhead.
20880 所以更高的负载均衡频率并不一定带来更高的负载均衡增益。 Therefore, a higher frequency of workload balancing is not equivalent to higher gains.
20881 因此，该文建立了关于负载均衡增益率与负载均衡频率的数学模型。 This paper establishes a mathematical modelfor gain rate and frequency of workload balancing.
20882 基于模型，提出一种面向众核密码平台的无冲突负载均衡策略和一种基于硬件作业队列的“可扩展-可移植”负载均衡引擎——“簇间微网络-簇内环阵列”。 Based on this model, a collision-free workload balancing policy is proposed for many-core crypto systems, and a hierarchical "expandable-portable" engine is put forward, which consists of "Inter-cluster micro-network and intra-cluster ring-array" adopting hardware job queue technology.
20883 实验证明：在性能、延时功耗积、资源利用率和负载均衡度方面，该文设计的负载均衡引擎与基于“作业窃取”的软件技术相比平均优化约4.06倍、7.17倍、23.01%和2.15倍； Experiment results show that the proposed workload-balancing engine is 4.06, 7.17, 23.01% and2.15 times higher than the software technology based on “job stealing” in terms of performance, delay powerconsumption, resource utilization and workload balance;
20884 与基于“作业窃取”的硬件技术相比约优化1.75倍、2.45倍、10.2%、和1.41倍； 1.75, 2.45, 10.2%, and 1.41 times better compared withthe hardware technology based on "job stealing".