Reinforcement learning-based neural network congestion controller for ATM networks

This paper presents a new approach to the problem of congestion control arising at the user-to-network interface (UNI) of the ATM-based broadband integrated services digital networks (BISDN). Our approach employs an adaptive rate-based feedback control algorithm using reinforcement learning neural networks (NNs). The reinforcement learning NN controller provides an adaptive optimal control solution. This is achieved via the formulation of a performance measure function (cost function) that is used to, adaptively, tune the weights of the NN. The cost function is defined in terms of two main objectives: (1) to minimize the cell loss rate (CLR), i.e., control congestion and (2) to preserve the quality of the voice/video traffic via maintaining the original coding rate of the multimedia sources. The results show that the NN control system is adaptive in the sense that it is applicable to any type of multimedia traffic. Also, the control signal is optimal in the sense that it maximizes the performance of the system which is defined in terms of its performance measure function. Hence, our novel approach is very effective in controlling congestion of the multimedia traffic in ATM networks.