Performance prediction and adaptation for database management system workload using Case-Based Reasoning approach
作者：
Highlights：
• We develop autonomic framework for workload performance tuning.
• Predictions are based on workload information available in advance before execution.
• Many benchmark workloads of DSS and OLTP are executed for validation.
• CBR approach better performed in comparison with machine learning techniques.
• Performed ranking of classifiers and proposed CBR model stand out the best classifier.
摘要
•We develop autonomic framework for workload performance tuning.•Predictions are based on workload information available in advance before execution.•Many benchmark workloads of DSS and OLTP are executed for validation.•CBR approach better performed in comparison with machine learning techniques.•Performed ranking of classifiers and proposed CBR model stand out the best classifier.
论文关键词：Workload management,Autonomic Computing,Case-based Reasoning,Prediction,Adaptation,DBMS,Database Management System,AWPP,Autonomic Workload Performance Prediction,OLTP,Online Transaction Processing,KCCA,Kernel Canonical Correlation Analysis,CBR,Case-Based Reasoning,DBA,Database Administrator,AC,Autonomic Computing,KNN,K-nearest neighbor,SVM,Support Vector Machine,TPC,Transaction Processing Council,QEP,Query Execution Plan,WFV,Workload Features Vector,PMV,Performance Metrics Vector,Dbt2,Database test 2,ET,Execution Time,WL Size,Workload Size,APV,Adjusted p-value
论文评审过程：Received 9 August 2017, Revised 13 March 2018, Accepted 23 April 2018, Available online 25 April 2018, Version of Record 1 May 2018.
论文官网地址：https://doi.org/10.1016/j.is.2018.04.005
