Improving Admission Control Policies in Database Management Systems, Using Data Mining Techniques

Increasing workload on multi-user database management system (DBMS) can cause maximum system´s throughput. With further increase of workload, throughput dramatically decreases and system performance fall down; then system starts to thrash. Existence of an admission control component for managing user´s requests is necessary. Admission control component in DBMS has two main tasks. These tasks are Prevention of increasing user´s communication requests to system more than a threshold and prevention, deferment or execution of received requests after optimization step and determination of request requirements. The problem is determination of allowable number of communications to DBMS. Can we predict and determine conditions to providence time and resource before reach to optimization step? In this paper we use data mining techniques to predict and describe admission control policies. According to this purpose we recommend an Admission Logging system to log existing actions before end of query processor procedures. We describe situation, structure, and changes that we need in system. Then we describe the circumstance of knowledge extraction on Admission Log.