Prediction of the Optimal Threshold Value in DF Relay Selection Schemes Based on Artificial Neural Networks

摘要

In wireless communications, the cooperative communication (CC) technologypromises performance gains compared to traditional Single-Input Single Output(SISO) techniques. Therefore, the CC technique is one of the nominees for 5Gnetworks. In the Decode-and-Forward (DF) relaying scheme which is one of the CCtechniques, determination of the threshold value at the relay has a key rolefor the system performance and power usage. In this paper, we proposeprediction of the optimal threshold values for the best relay selection schemein cooperative communications, based on Artificial Neural Networks (ANNs) forthe first time in literature. The average link qualities and number of relayshave been used as inputs in the prediction of optimal threshold values usingArtificial Neural Networks (ANNs): Multi-Layer Perceptron (MLP) and RadialBasis Function (RBF) networks. The MLP network has better performance from theRBF network on the prediction of optimal threshold value when the same numberof neurons is used at the hidden layer for both networks. Besides, the optimalthreshold values obtained using ANNs are verified by the optimal thresholdvalues obtained numerically using the closed form expression derived for thesystem. The results show that the optimal threshold values obtained by ANNs onthe best relay selection scheme provide a minimum Bit-Error-Rate (BER) becauseof the reduction of the probability that error propagation may occur. Also, forthe same BER performance goal, prediction of optimal threshold values provides2dB less power usage, which is great gain in terms of green communicationBERperformance goal, prediction of optimal threshold values provides 2dB lesspower usage, which is great gain in terms of green communication.