基于云环境的集中式处理作业模式研究

Research on centralized processing work pattern based on cloud environment

本文通过对传统DSM、DEM、DOM影像数据处理生产作业模式进行难点分析,并经过大量的前期测试和研究,利用基于超融合基础架构、GPU云计算、云桌面的方式完成了底层系统架构,构建了多租户模式的生产资源池,解决了传统生产作业模式的弊端。通过试验数据对比,基于云环境下的集中式处理方式在资源利用率与管理方式方面具有较大幅度的提升,且能够充分发挥底层硬件的能力,进一步提高了生产效率。同时也能够有效解决重复采购、重复部署造成的资源浪费问题。本文的研究成果可在项目实际生产中得到进一步的推广和应用。

This article analyzes the pain points of the traditional DSM, DEM, DOM image data processing production mode, after a lot of preliminary testing and research, the method based on HCI, GPU cloud computing and cloud desktop is used as the underlying system architecture of this research, builds a production resource pool for the multi-tenant model, in order to solve the shortcomings of the traditional mode. Through the test data comparison, the centralized processing method based on the cloud environment has a significant improvement in resource utilization and management methods, which can give full play to the capabilities of underlying hardware, further improve production efficiency. At the same time, it can effectively solve the problem of resource waste caused by repeated procurement and repeated deployment. The research results of this article will also be further promoted and applied in the actual project.