Evolutionary Tuning for Distributed Database Performance

Modern companies dynamically change their departmental structure, type of activities and staff. Database management systems of such companies require adequate design and administration solutions. In such a system the initial estimations and predictions for performance characteristics are mandatory but not sufficient. The performance problems of data reallocation and query optimization in distributed database systems done by means of mobile agents and evolutionary algorithms are considered. These problems still present a challenge because of the dynamic changes in data amount, number of components and architectural complexity of nowadays system topologies. The distributed system is modeled as a graph structure on which is defined a dynamic cost vector. The cost vector remains consistent, relevant, by use of mobile agents performing cost statistics and vector updates. An evolutionary algorithm is proposed to solve this NP-complete problem. Experimental results prove the efficiency of the proposed technique