Translated Abstract
With the development of network technologies such as SDN and 5G, the data and standardization of network cloud computing has become the direction of future information processing development. As a virtualized enterprise information service platform, cloud computing mainly includes grid computing, distributed computing, and parallel computing. The cloud computing platform can manage the virtual hardware resources through the virtualized server network system, thus providing enterprises with the required information services. This is the task scheduling algorithm in cloud computing. However, with the continuous increase in the size of enterprise data and the number of users, how to ensure the efficient use of data resources and meet the diverse service quality requirements of users have become the main issues that need to be resolved in cloud computing task scheduling. The ant colony algorithm as a method to solve the combinatorial optimization problem can solve the task scheduling problem of cloud computing. Therefore, the integration of cloud computing and improved ant colony algorithm and its application to task scheduling in cloud computing environment can effectively solve the data processing and resource allocation problems faced by enterprises.
This paper mainly studies cloud computing task scheduling strategy based on improved ant colony algorithm. The current ant colony algorithm mainly focuses on reducing the task execution time. Therefore, during the execution of task scheduling, it is prone to load imbalance and local optimal solution. For these problems, this paper proposes an improved ant colony algorithm. In order to solve the problem of unbalanced load and low optimization accuracy in cloud computing task scheduling, the internal load balance of the system is achieved through pheromone updating. Based on the improved ant colony algorithm for cloud computing task scheduling, the pheromone factor of the ant colony algorithm is mainly used for heuristic search, so as to reduce the search scope and reduce the complexity of the problem. After that, the pheromone adjustment factor PAF of the virtual machine is used to complete the task allocation in the iterative process of the ant colony algorithm so as to achieve the load balance within the system.
After improving the research of ant colony algorithm and cloud computing task scheduling, this paper uses CloudSim cloud computing simulation simulation platform to analyze the feasibility of improving ant colony algorithm in cloud computing task scheduling, and compares the ant colony algorithm and the improved ant colony algorithm. Cloud computing task scheduling performance. First, in the cloud computing hardware platform, create virtual machines, network resources, and user tasks. After that, we analyzed CloudSim cloud computing task scheduling process. Then through the Cloudsim cloud computing simulation platform, the computational performance of the ant colony algorithm (ACO) and the load balancing adaptive-ant colony algorithm (LBA-ACO) are compared. Experimental results show that the improved ant colony algorithm cloud task scheduling has significant advantages in task queue response time and task execution time. The improved ant colony algorithm can effectively complete the resource allocation in the virtual machine task scheduling and satisfy the load balancing of the entire cloud computing system resource under the condition of satisfying the different users＇ service quality requirements.
Translated Keyword
[Cloudsim simulation, Improve ant colony algorithm, load balancing, Task scheduling in cloud computing]
Corresponding authors email
