Network-Level System Performance Prediction Using Deep Neural Networks with Cross-Layer Information

How to predict the wireless network level performance such as the network capacity, the average user data rate, and the 5%-tile user data rate is a million-dollar question. In the literature, some pioneering works have been proposed by exploiting either the information theoretic techniques on the physical layer (PHY) information or the Markov chain techniques on the multiple access control (MAC) layer information. However, since these mathematical model-driven approaches usually focus on a small part of the network structure, they cannot characterize the whole network performance. In this paper, we propose to utilize a data-driven machine learning approach to tackle this problem. More specifically, both PHY and MAC information is fed into a deep neural network (DNN) specifically designed for network-level performance prediction. Simulation results show that the network level performance can be accurately predicted at the cost of higher computational complexity.