CPU and Memory Allocation Optimization using Fuzzy Logic Based Clustering

The allocation of CPU time and memory resources, are well known problems in organizations with a large number of users, and a single mainframe. Usually, the amount of resources given to a single user is based on its own statistics, not on the entire statistics of the organization therefore patterns are not well identified and the allocation system is prodigal. In this work the authors suggest a fuzzy logic-based algorithm to optimize the CPU and memory distribution between the users based on the history of the users. The algorithm works separately on heavy users and light users since they have different patterns to be observed. The result is a set of rules, generated by the fuzzy logic inference engine that will allow the system to use its computing ability in an optimized manner. Test results on data taken from the Faculty of Engineering in Tel Aviv University, demonstrate the abilities of the new algorithm. This paper also examines the subject of system investigation using structured analysis (represented by Data Flow Diagrams - DFD), and the Object-Oriented Analysis and Design approaches (OOAD). The structured approach focuses on the flow and processing of data. The OOAD partitions the problem with respect to objects when analyzing the problem domain. When analyzing a large system or trying to reconstruct one using one of the two approaches mentioned above, there is apt to be a degree of inefficiency. This paper suggests a unique solution to this inefficiency. The optimization approach is based upon fuzzy logic inference engine clustering techniques. The study also presents the means for grading a system and creating a simple base for a computerized tool. By implementing the algorithm in a defined case study, we improved the modeling of the system coupling by 28 %, the system complexity by 20% and the system size criteria by 36%, for the structured analysis. This leads to system improvement process.