سال انتشار: ۱۳۹۰

محل انتشار: پنجمین کنفرانس بین المللی پیشرفتهای علوم و تکنولوژی

تعداد صفحات: ۹

نویسنده(ها):

Seyed Rasool Moosavi-Nejad – Islamic Azad University, Arak
S.S Mortazavi – Shahid Chamran University
Bijan Vosoughi Vahdat – Sharif University of Technology

چکیده:

The load model of the distributed systems tends to change dynamically. Hence, fast. Precise Load balancing is an essential factor in increasing distributed system operation efficiency. Lack of shared memory among independent systems, and the delays in interface channels, leads to ambiguous information of the condition of system. This ambiguity brings about uncertainty in decision for load balancing. To solve this problem; this paper proposes an intelligent algorithm based on fuzzy logic in the centralized distributed system. In comparative study, the length of sent packets and the service rate in each node are considered variable. The fuzzy decision is done based on the current load and waiting time in this paper. Throughput, average of response time, and drop rate of the packets are considered as measures in a comparative study with other static and dynamic algorithms