Self-Learning Prediciton System for Optimisation of Workload Managememt in a Mainframe Operating System

Autor: Bensch, Michael, Brugger, Dominik, Rosenstiel, Wolfgang, Bogdan, Martin, Spruth, Wilhelm
Jazyk: angličtina
Rok vydání: 2007
Předmět:
Druh dokumentu: Text<br />Conference Material
Popis: We present a framework for extraction and prediction of online workload data from a workload manager of a mainframe operating system. To boost overall system performance, the prediction will be corporated into the workload manager to take preventive action before a bottleneck develops. Model and feature selection automatically create a prediction model based on given training data, thereby keeping the system flexible. We tailor data extraction, preprocessing and training to this specific task, keeping in mind the nonstationarity of business processes. Using error measures suited to our task, we show that our approach is promising. To conclude, we discuss our first results and give an outlook on future work.
Databáze: Networked Digital Library of Theses & Dissertations