WLM: Predict the Future Using SMF, Spark and R

Project and Program: MVS, MVS Core Technologies

Tags: Proceedings, 2018, SHARE St. Louis 2018

During this session, the speaker will present a machine learning approach using the distributed data processing framework Apache Spark and the programming language R to uncover the hidden treasure that is stored in your performance SMF data. We will demonstrate to predict the time series of the Appl Percentage (ApplPerc) from the workload manager of the z/OS mainframe system using different machine learning and deep learning models such as random forest regression, recurrent neural network, and k-nearest neighbor regression.-Andreas Henicke-IBM R&D Germany

Back to Proceedings File Library