The Selection and Placement Method of Materialized Views on Big Data Platform of Equipment Condition Assessment

2017 2nd Asia Conference on Power and Electrical Engineering

能源学;电工学

Ma, Yan^1 ; Yao, Jinxia^1 ; Gu, Chao^1 ; Chen, Yufeng^1 ; Yang, Yi^1 ; Zou, Lida^2

State Grid Shandong Electric Power Research Institute, No. 2000 WangYue Road, Shandong Province, Jinan

250002, China^1

Shandong University of Finance and Economics, No. 7366 Bicyclic East Road, Shandong Province, Jinan

250014, China^2

关键词: Big data platforms;    Equipment conditions;    Materialized view;    Network transmission;    Optimization ability;    Placement methods;    Relevance weights;    Selection methods;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/199/1/012105/pdf
DOI  :  10.1088/1757-899X/199/1/012105

来源: IOP

【 摘 要 】

With the formation of electric big data environment, more and more big data analyses emerge. In the complicated data analysis on equipment condition assessment, there exist many join operations, which are time-consuming. In order to save time, the approach of materialized view is usually used. It places part of common and critical join results on external storage and avoids the frequent join operation. In the paper we propose the methods of selecting and placing materialized views to reduce the query time of electric transmission and transformation equipment, and make the profits of service providers maximal. In selection method we design a computation way for the value of non-leaf node based on MVPP structure chart. In placement method we use relevance weights to place the selected materialized views, which help reduce the network transmission time. Our experiments show that the proposed selection and placement methods have a high throughput and good optimization ability of query time for electric transmission and transformation equipment.