Congestion control in TCP/IP differentiated services network using neural network

The use of internet services for time sensitive applications like voice and video, requires the forecasting quality of service. The TCP/IP differentiated services structure is given to achieve this target. However, network congestion control is limited and comes from the high priority. Some studies are still seeking a replacement techniques such as random early detection (RED) and its modification to manage congestion. In this paper we present neural network control research results to implement RED, called NRED. We found that with neural network we can perform better for discrimination acts to cancel the packets for gathering traffic flow, and also provide better quality services to all types different traffic while ensuring high utilization.