Optimized artificial neural network using differential evolution for prediction of RF power in VHF/UHF TV and GSM 900 bands for cognitive radio networks

Abstract

Abstract-Cognitive radio (CR) technology has emerged as a promising solution to many wireless communication problems including spectrum scarcity and underutilization. The knowledge of Radio Frequency (RF) power (primary signals and/ or interfering signals plus noise) in the channels to be exploited by CR is of paramount importance, not just the existence or absence of primary users. If a channel is known to be noisy, even in the absence of primary users, using such channels will demand large quantities of radio resources (transmission power, bandwidth, etc) in order to deliver an acceptable quality of service to users. Computational Intelligence (CI) techniques can be applied to these scenarios to predict the required RF power in the available channels to achieve optimum Quality of Service (QoS). While most of the prediction schemes are based on the determination of spectrum holes, those designed for power prediction use known radio parameters such as signal to noise ratio (SNR), bandwidth, and bit error rate. Some of these parameters may not be available or known to cognitive users. In this paper, we developed a time domain based optimized Artificial Neural Network (ANN) model for the prediction of real world RF power within the GSM 900, Very High Frequency (VHF) and Ultra High Frequency (UHF) TV bands. The application of the models produced was found to increase the robustness of CR applications, specifically where the CR had no prior knowledge of the RF power related parameters. The models used implemented a novel and innovative initial weight optimization of the ANN's through the use of differential evolutionary algorithms. This was found to enhance the accuracy and generalization of the approach

Pronóstico de Oportunidades de Espectro Radioeléctrico en una Red Móvil con base en el Modelo de Propagación Interino de la Universidad de Stanford

“…Para sistemas cognitivos en (Bai et al, 2014) se hace uso de una red neuronal de propagación hacia atrás para predecir el estado del espectro, y en (Kunwei et al, 2014;Bai et al, 2015) se optimiza la red neuronal con un algoritmo genético. También, en (Iliya et al, 2014) una red neuronal pronostica la potencia en las bandas de televisión y GSM900. Los ejemplos anteriores y lo descrito en (Pedraza et al, 2016b) demuestran el carácter promisorio de las redes neuronales en el pronóstico de la potencia recibida en canales inalámbricos, sobre modelos como Markov y de descomposición de modo empírico-vector de soporte para regresión.…”

RF-Spectrum Opportunities for Cognitive Radio Networks Operating Over GSM Channels

“…Reference [14] demonstrates the integration of cognitive radio capabilities, on the fly, such as the spectrum sensing of GSM bands being used by secondary users and its interaction with GSM basestations. SDR devices were also adopted in [15] to sense GSM bands in order to feed artificial neural networks able to predict real world RF power within the GSM 900 band. The main purpose of the work described in [15] is to predictively select channels with the least noise among those that were unused, improving traditional channel selection schemes proposed to GSM channels.…”

A Model to Determine the Propagation Losses Based on the Integration of Hata-Okumura and Wavelet Neural Models

“…For cognitive systems in [27] a backpropagation neural network is used to predict the state of the spectrum; also in [28,29] a genetic algorithm was used to optimize the neural network. In [30] a neural network was utilized to forecast the power of television and GSM-900 bands. In [31], the spectrum is modeled and forecasted using the Daubechies wavelets.…”