Performance Analysis of AI Based QOS Scheduler for Mobile WIMAX

Interest in broadband wireless access (BWA) has been growing due to increased user mobility and the need for data access at all times. IEEE 802.16e based WiMAX networks promise the best available quality of experience for mobile data service users. WiMAX networks incorporate several Quality of Service (QoS) mechanisms at the Media Access Control (MAC) level for guaranteed services for multimedia viz. data, voice and video. The problem of assuring QoS is how to allocate available resources among users to meet the QoS criteria such as delay, delay jitter, fairness and throughput requirements. IEEE standard does not include a standard scheduling mechanism and leaves it for various implementer differentiations. Although a lot of the real-time and non real-time packet scheduling schemes has been proposed, it needs to be modified to apply to Mobile WiMAX system that supports five kinds of service classes. In this paper, we propose a novel Priority based Scheduling scheme that uses Artificial Intelligence to support various services by considering the QoS constraints of each class. The simulation results show that slow mobility does not affect the performances and faster mobility and the increment in users beyond a particular load have their say in defining average throughput, average per user throughput, fairness index, average end to end delay and average delay jitter. Nevertheless the results are encouraging that the proposed scheme provides QoS support for each class efficiently.