A novel prediction technique to improve quality of service (QoS) for heterogeneous data traffic

The present and future high-speed networks are expected to support wide variety real-time applications. However, the current Internet architecture offers mainly best-effort service. It means that the network will do its best to deliver the data at the destination without any guarantee. But the future integrated services networks will require guarantee for transferring heterogeneous data. There are many parameters involved in improving the Quality of Service (QoS). QoS is a set of service requirements to be met by the network while transporting a flow. In this paper, we consider four primary parameters are such as reliability, delay, jitter, bandwidth which together determine the QoS. The requirements of the above parameters will vary from one application to another application. Applications like file transfer, remote login, etc., will require high reliability. But, applications like audio, video, etc., will require low reliability, because they can tolerate errors. The objectives of this paper are to propose a novel technique to predict reason(s) for deterioration in the QoS and to identify the algorithm(s)/mechanism(s) responsible for the deterioration. We are sure that this paper will give better results to improve the QoS and to improve the performance of the network.