Research on data cache optimization based on time series state prediction

  • Xiangxi Meng
  • , Haoming Guo
  • , Jianghua Lv*
  • , Shilong Ma
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Data cache can reduce network congestion in a certain extent, and it can also reduce server load and user’s access delay. However, the data cache is just passable in the cache hit rate and byte hit rate. It cannot play very well to accelerate query tasks response effect. Combining time series prediction method, this paper tries to predict the state of data using Autoregressive Integrated Moving Average Model and proposes a new cache strategy with Naive Bayes Classifier. Experimental results show that the new cache strategy is superior to the ID3 decision tree and BP neural network classifier in the precision and recall index. And compared with LRU algorithm, optimized cache strategy cannot only improve the cache efficiency, but also effectively improve the request hit rate of data cache.

Original languageEnglish
Title of host publication2019 IEEE 4th International Conference on Computer and Communication Systems, ICCCS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages154-158
Number of pages5
ISBN (Electronic)9781728113227
DOIs
StatePublished - Feb 2019
Event4th IEEE International Conference on Computer and Communication Systems, ICCCS 2019 - Singapore, Singapore
Duration: 23 Feb 201925 Feb 2019

Publication series

Name2019 IEEE 4th International Conference on Computer and Communication Systems, ICCCS 2019

Conference

Conference4th IEEE International Conference on Computer and Communication Systems, ICCCS 2019
Country/TerritorySingapore
CitySingapore
Period23/02/1925/02/19

Keywords

  • ARIMA
  • Cache replacement
  • Cache strategy
  • Data cache
  • Naive bayes classifiers

Fingerprint

Dive into the research topics of 'Research on data cache optimization based on time series state prediction'. Together they form a unique fingerprint.

Cite this