Autonomic configuration is one of the most important components of an autonomic system.rnDatabase Management Systems (DBMSs) are one of the areas where autonomic configurationrnis highly required. In order for a DBMS to configure itself on changing external workloads, itrnshould be able to detect and classify the workloads into their dominant categories, mainly intornDSS (Decision Support Systems) and OLTP (Online Transaction Processing). Previousrnresearch works in this area have proposed a methodology for classification of workloads. Butrnthe tests are performed using limited algorithms and on only one commercial DBMS.rnIn this thesis a model where an autonomic DBMS can identify and characterize the type ofrnworkload acting up on it is developed and the most important database status variables whichrnare highly affected by changing workloads are identified. This is important for a selfrnconfiguring autonomic DBMS because it needs to reconfigure itself based on identifiedrnchanging workloads. Two algorithms are selected for database workload classification:rnhierarchical clustering and classification & regression tree for classifying database workloadsrnafter running database workloads from TPC benchmark queries and transactions. The costs ofrnthese workloads are measured in terms of status variables of the selected DBMS (MySQL).rnThese costs are used to show whether a workload is DSS or OLTP using the selectedrnclassification algorithms.rnAfter a set of extensive experiments and analyses, we have found out that all the DBMS statusrnvariables are not equally important in classifying the collected workloads. In fact, some of thernworkloads do not have a significant relevance apart from increasing the classificationrncomplexity. We have identified these variables and listed them in this thesis. Even though bothrnthe selected classification algorithms are good at classifying the collected workloads,rnhierarchical clustering algorithm has an additional advantage of showing the degree ofrncorrelation among clusters. This can be important in the area of database workload shiftrndetection.