How to apply modeling and optimization to select the appropriate cloud platform

Abstract

In this paper we will review results of the workload characterization for On Prem Data Warehouse environment. Secondly, we collect measurement data for standard TPC-DS benchmark tests performed in AWS Vantage, Redshift and Snowflake Cloud platforms for different sizes of the data sets and different number of concurrent users. During third step we use the results of the workload characterization and measurement data collected during the benchmark to modify BEZNext On Prem closed queueing network model to model individual Clouds. And finally, during the fourth step we use the model to consider differences in concurrency, priorities and resource allocation to different workloads. BEZNext Capacity Planning optimization algorithms incorporate gradient search mechanism to find the AWS instance type and minimum number of instances which will be required to meet SLGs for each of the workloads.