Question

英语翻译1

为了解决云计算执行大规模并行任务时容易出现节点负载不均，导致整个云计算系统执行效率下降的问题，提出一种提高负载均衡约束的改进蚁群算法，算法以速度快、成本低，负载均衡为目标，设计了相应的负载模型，并通过实验仿真测试，验证了算法在任务执行方面可有效保持云计算中虚拟机负载均衡，提高了云计算系统效率。
云计算是面向客户的商业模式，其计算数据量庞大，结构复杂，资源配置差异大。因为要将如何将不同用户的任务合理地分配到各个虚拟机上执行是算法的研究重点，让整个系统节点的负载更加均衡，提升云计算系统的执行效率和用户满意度
在云计算资源分配算法方面，传统的算法早已无法满足当前海量数据增加的需求，很多学者尝试人工智能算法，启发式智能优化算法运用在云计算资源调度过程中，比如粒子群算法，遗传算法都拥有很好的寻找全局最优解的能力，能够快速提供云计算任务分配的解决方案。但是这些算法直接应用到云任务分配过程中，随机性不强，不易获得全局最优解，因此需要对仿生智能算法加以改进，一些学者从不同的方面提出了改进后的仿生智能算法，比如魏赟,陈元元等提出通过将大量用户提交的任务都分解成多个子任务，子任务之间相互牵制，使得任务的执行具备并行性和整个任务的串行执行，根据任务执行次序，设置调度次序的优先级，缩短了任务的延迟时间；李建峰，彭舰等提出在云资源调度中加入遗传算法(DFGA)，减少了任务执行时间；本文在标准蚁群算法基础上，重点改进任务调度过程中的云计算虚拟资源负载不平衡的情况，创新地提出利用动态约束函数改进信息素的更新, 通过负载均衡差函数改进启发信息的改进蚁群算法实现任务调度

Answer 1

回答和翻译如下：

In order to solve the problem of cloud computing implementation of large-scale parallel tasks to node load imbalance, leading to the decline in the efficiency of cloud computing system, proposed an improved ant colony algorithm of load balancing algorithm with constraints, fast speed, low cost, load balance as the goal, design a load model, and through experimental simulation test to verify the algorithm, which can effectively keep the virtual machine in cloud computing load balancing in task execution, improve the efficiency of cloud computing system. Cloud computing is a customer-oriented business model, the huge amount of computing data, complex structure, large differences in resource allocation. Because to different user assignment to each virtual machine implementation is the focus of research on the algorithm, let the whole system node load more balanced, to enhance cloud computing system execution efficiency and user satisfaction In the cloud computing resource allocation algorithm, the traditional algorithm is already unable to meet the increasing demand of massive data, many scholars try to artificial intelligence algorithm, heuristic intelligent optimization in cloud computing resource scheduling process using algorithms such as particle swarm optimization algorithm, genetic algorithm has good ability to find the global optimum solution, the solution can be quickly cloud computing task assignment. But these algorithms are applied directly to the process of task allocation in the cloud, randomness is not strong, not easy to obtain the global optimal solution, so the need for intelligent bionic algorithm is improved, some scholars put forward the improved algorithm of bionic intelligence from different aspects, such as Wei Yun, Chen Yuanyuan proposed by a large number of users to submit the task decomposition a number of sub tasks, mutual restraint between the sub tasks, the task execution with parallel and serial execution of the task, according to the task execution order, set the scheduling order of priority, shorten the delay time of tasks; Li Jianfeng, Peng ship proposed adding genetic algorithm in cloud resource scheduling (DFGA), to reduce the task the execution time; based on the standard ant colony algorithm, focus on the improvement of task scheduling in cloud computing virtual resource load imbalance, a The new improved pheromone updating is proposed using dynamic constraint function, the improved ant colony algorithm to realize task scheduling load equalization function heuristic information.

Answer 2

Parents are the closest people to you in the world.