Traffic prediction based resource configuration in space-based systems

In this paper, we considers the resource allocation problems for video transmission in space based information networks. The queueing system analyzed in this work is composed of multiple users and a single server. To minimize both of the time average cost and delay of the system, and subject to the constraint that the queues in the system must be stable, we introduce a predictive backpressure algorithm into the consideration of resource allocation to make decision on which packets to be served first. Meanwhile, a multi-resolution wavelet decomposition based backpropagation neural network for the prediction of video traffic is designed in this paper. Performances of the proposed video traffic prediction system and resource allocation scheme are analyzed in the simulations. Results indicate that the prediction accuracy for the video traffic is improved according to the proposed prediction system, and the delay of the queueing system can be reduced through this prediction based resource allocation.