The Design of Cloud Computing Platform for Massive Data Processing of Distributed Photovoltaic Power

摘要

Because of distributed photovoltaic power generating a large amount of data in every second and in every node, to collect and handle the massive of data in the photovoltaic power system within the prescribed time, it puts the storage and processing of massive data forward higher request, and brings serious challenges. In order to process those massive data, this paper sets up the open source cloud computing platform based on OpenStack, utilizing OpenStack' ability that it can quickly deploy virtual machines and OpenStack' plug-in Savanna, deploying the elastic Hadoop cluster on the virtual machines in cloud platform, then utilizing its powerful distributed data processing capacity, processing the data in the system and environmental parameters efficiently and quickly. Experimental results show that the system can effectively complete data correlation processing, mining the useful information from huge amounts of the data, providing the support for the research and application of distributed photovoltaic data processing.