- Conference Article
4
- 10.1109/inista.2016.7571823
Prediction of the optimal threshold value in DF relay selection schemes based on artificial neural networks
- Aug 01, 2016
- Ferdi Kara + 3 more +3
In wireless communications, the cooperative communication (CC) technology\npromises performance gains compared to traditional Single-Input Single Output\n(SISO) techniques. Therefore, the CC technique is one of the nominees for 5G\nnetworks. In the Decode-and-Forward (DF) relaying scheme which is one of the CC\ntechniques, determination of the threshold value at the relay has a key role\nfor the system performance and power usage. In this paper, we propose\nprediction of the optimal threshold values for the best relay selection scheme\nin cooperative communications, based on Artificial Neural Networks (ANNs) for\nthe first time in literature. The average link qualities and number of relays\nhave been used as inputs in the prediction of optimal threshold values using\nArtificial Neural Networks (ANNs): Multi-Layer Perceptron (MLP) and Radial\nBasis Function (RBF) networks. The MLP network has better performance from the\nRBF network on the prediction of optimal threshold value when the same number\nof neurons is used at the hidden layer for both networks. Besides, the optimal\nthreshold values obtained using ANNs are verified by the optimal threshold\nvalues obtained numerically using the closed form expression derived for the\nsystem. The results show that the optimal threshold values obtained by ANNs on\nthe best relay selection scheme provide a minimum Bit-Error-Rate (BER) because\nof the reduction of the probability that error propagation may occur. Also, for\nthe same BER performance goal, prediction of optimal threshold values provides\n2dB less power usage, which is great gain in terms of green communicationBER\nperformance goal, prediction of optimal threshold values provides 2dB less\npower usage, which is great gain in terms of green communication.\n
Read more