The invention discloses a method for predicting the
outage probability performance of a mobile cooperative communication
system. Based on the multi-transmit and multi-receive and
hybrid decoding, amplification and forwarding cooperative communication technologies, a mobile cooperative communication
system model is established, an optimal
mobile relay node is selected, and a mobile information source is selected. When the
signal-to-
noise ratio of the link to the optimal
mobile relay node is greater than the
signal-to-
noise ratio threshold, the decoding and forwarding strategy is used to forward the mobile source
signal to the destination, and when it is smaller than the signal-to-
noise ratio, the amplification and forwarding strategy is used to forward the signal to the destination. A transmission antenna selection scheme, respectively deduces the closed expressions of the
outage probability of its mobile cooperative communication
system, and uses neural networks to intelligently predict the
outage probability performance of the
physical layer of mobile communication, which is consistent with the existing
extreme learning machine, local weighted linear The methods of regression,
support vector machine, generalized regression neural network and
radial basis function neural network are compared, and better
performance prediction effect of outage probability is achieved.