基于moosefs工业采集数据云存储系统分析.docx

Abstract
With the development of , the rise of of Things and puting, building up the work e the inevitable trend of the development of industrial the difficult of mass data’s management,highly cost of data storage, low scalability,difficult to guarantee safety and reliability,wise enterprise will build up his own industrial private cloud storage system .They adopt distributed collection ,management system and use those characteristics of cloud storage: high universality, high scalability, high reliability and Mass traditional industrial data acquisition bined with structure of Cloud storage would accelerate the construction of the working.
Industrial data acquisition cloud storage system was architected based on the MooseFS(MFS) which detailed code was analyzed,design philosophy of storage nodes pute nodes is proposed on this paper. Special distributed storage algorithm is designed for the problem of mass industrial acquisition data is difficult to storage, the dedicated interface industry is provided to data lot of time and resources should be spended for quering large-scale industrial data in cloud storage system, parallel-distributed query algorithm for the timing data can greatly shorten the query time and improve the resources utilization ratio. Query efficiency es a key problem for query large-scale random data, distributed index algorithm and random data parallel-distributed algorithm is designed to improve the query efficiency.
The main contributions of this thesis are listed as following:
Solutions that industrial acquisition data storage to cloud storage is proposed,cloud storage resources pool is also industrial puting resources pool, compute node which is also storage plete tasks such as create distributed index and puting;
Data Mining can be executed on industrial data cloud system:random data index is created in order to quickly inquires the random industrial data, at the same time the timing data would