ID	原文	译文
3623	将 DS 证据理论应用到协作频谱感知算法中，针对经典 DS 证据理论中存在的证据悖论问题，提出了一种新的加权距离测度。	The Dempster-Shafer(DS) evidence theory was applied to cooperative spectrum sensing and address the para-dox of evidence in classical DS evidence theory, a new weighted distance measure based algorithm was proposed.
3624	首先，对每个感知用户进行证据提取。	Firstly,the evidences were extracted for each sensing user.
3625	然后，根据提取到的基本概率分配数据，利用加权距离测度计算出各个感知用户的证据间相似性。	Then, the weighted distance measure of extracted basic probabilityassignment data was adopted as the similarity between evidences of sensing users.
3626	最后，将证据间相似性转化成可信度，并利用可信度来加权平均感知用户的基本概率分配。	Finally, the similarity of evidences wastransformed into credibility, which was utilized as the weight to obtain the weighted average of basic probability assign-ment.
3627	针对协作开销大的问题，在证据提取后采用投影近似法调整基本概率分配来减少上传到融合中心的数据量。	In order to reduce the amount of data reported to the fusion center, the projection approximation method was em-ployed to adjust the basic probability assignment.
3628	理论分析和仿真结果显示，与传统方法相比，所提方法能提高证据悖论问题存在时的检测性能，并且减少协作开销。	Both theoretical analysis and simulation results show that the proposedmethod can improve the detection performance of spectrum sensing while the paradox of evidence exists. Compared withtraditional methods the cooperation overhead is reduced.
3629	为了提升移动边缘网络中系统的能量使用效率，面向多任务、多终端设备、多边缘网关、多边缘服务器共存网络架构的下行通信过程，提出了一种基于双深度 Q 学习（DDQL）的通信、计算、存储融合资源分配方法。	To improve the system energy efficiency in mobile edge networks, a resource allocation method based ondouble deep Q-learning(DDQL) for integration of communication, computing, storage resources was proposed for thedownlink communication process under the network architecture of multiple tasks, end devices, edge gateways and edgeservers.
3630	以任务平均能耗最小化为优化目标，设置任务时延和通信、计算、存储资源限制等约束条件，构建了对应的资源分配模型。	A resource allocation model was constructed, which took the minimization of average energy consumption oftasks as the optimization goal and set the constraints of task delay limits and communication, computing, and storage re-source limits.
3631	依据模型特征，基于 DDQL 框架，提出了适用于通信和计算资源智能决策、存储资源按需分配的资源分配模型和算法。	According to the model characteristics, a suitable resource allocation model and method based on DDQLframework was proposed to make intelligent allocation decisions for communication and computing resources and allo-cate storage resources on demand.
3632	仿真结果表明，所提出的基于 DDQL 资源分配方法可以有效地解决多任务资源分配问题，具有较好的收敛性和较低的时间复杂度，在保障业务服务质量的同时，相对于基于随机算法、贪心算法、粒子群优化算法、深度 Q 学习等方法，降低了至少 5%的任务平均能耗。	Simulation results show that the proposed DDQL-based solution can effectively solvethe multi-task resource allocation problem with good converge and low time complexity, and it reduces the average ener-gy consumption of tasks by at least 5% compared with the solving methods based on random algorithm, greedy algorithm,particle swarm optimization algorithm and deep Q-learning while ensuring the quality of service.