OVERLOAD AND TRAFFIC MANAGEMENT OF MESSAGE SOURCES WITH DIFFERENT PRIORITY OF SERVICE

Abstract

The scheme of dynamic management of traffic and activity of message sources with different priority of service is considered. The schemeis built on the basis of the neuroprognostic analysis model and the gradient descent method. For prediction and early detection of overload, the apparatus of the general theory of sensitivity with indirect feedback and control of activity of message sourcesis used. The control algorithm is startedat the bottleneck of the network node. It uses a recursive prediction approach where the neural network outputis referred to as many steps as definedby a given prediction horizon. Traffic with a higher priority is served without delay using the entire available bandwidth. Low-priority traffic willuse the remaining bandwidth not used by higher-priority traffic. An algorithm for estimating the maximum available bandwidth of a communication node for traffic with a low service priority has been developed. This approach makes it possible to improve the efficiency of channel use without affectingthe quality of servicefor high-priority traffic.