Cost Optimization Strategy for Long-Term Storage of Scientific Workflow  

作　　者：Zaibing Lv Cheng Zhang Futian Wang 

机构地区：[1]School of Computer Science and Technology, Anhui University, Hefei, China

出　　处：《国际计算机前沿大会会议论文集》2019年第1期156-157,共2页International Conference of Pioneering Computer Scientists, Engineers and Educators（ICPCSEE）

基　　金：Anhui Natural Science Foundation 1908085MF206 and National Natural Science Foundation of China (NO. 61402007, 61573022);the Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry.

摘　　要：With the rapid development of cloud environment, the capabilities of systems have been promoted with powerful computing and storage. But for the characteristic of “pay-as-you-go” of cloud resources, it is necessary to consider the different data storage cost. Especially for processing of “old data” in longterm storage, an appropriate strategy is needed to reduce users’ cost. Considering the characteristics of price stratification in the current commercial cloud environment, a three-level price stratified storage strategy is proposed based on the CTT-SP algorithm, which stores part of the “old data” on relatively inexpensive secondary and tertiary storage, and ensures that the time delay caused by three-level storage does not exceed the deadline. Compared with other storage methods, the experimental result shows the strategy proposed can guarantee the time delay while reducing the cost of users significantly in longterm storage.

关 键 词：CTT-SP algorithm PRICE STRATIFICATION LONG-TERM STORAGE 

分 类 号：C[社会学]