سال انتشار: ۱۳۸۴
محل انتشار: یازدهمین کنفرانس سالانه انجمن کامپیوتر ایران
تعداد صفحات: ۴
Kamyar Izadi – Department of Computer Engineering Iran University of Science and Technology Tehran, Iran
Mostafa S. Haghjoo –
In order to minimize the number of network locations to be accessed in query processing an appropriate data distribution is required. Additionally data distribution should allow equitable distribution of system load to all network locations. This process is NP-Hard and requires the optimization of conflicting objectives. In this study an improved and practical genetic algorithm was designed and verified based on multi-niche crowding GA to achieve load balancing. The power of this method stems from its ability to find multiple optima over multimodal landscape.