Abstract: For the purpose of improving the overall efficiency of the system in the cloud computing environment, and to better simulate the actual application scenarios of cloud computing, a task scheduling strategy to improve the greedy algorithm is proposed. The algorithm takes into account the characteristics of tasks and virtual machine resources in the cloud environment, and improves the greedy selection strategy so as to better reflect the mapping relationship between tasks and resources. Through the experimental analysis on the CloudSim simulation platform, the algorithm can perform better than other commonly used scheduling algorithms in the cloud environment. At the same time, the algorithm has the ability of balanced load, and the experimental results show the balance of task assignment better than common algorithms.