Premium
Timescale Ensemble Performance Enhancement through use of Artificial Neural Network
Author(s) -
Maharana Shikha,
Bhardwajan Aakanksha Avnish,
Ganesh T Subramanya,
Ramakrishna B N
Publication year - 2019
Publication title -
incose international symposium
Language(s) - English
Resource type - Journals
ISSN - 2334-5837
DOI - 10.1002/j.2334-5837.2019.00701.x
Subject(s) - perceptron , computer science , artificial neural network , algorithm , stability (learning theory) , ensemble learning , kalman filter , realization (probability) , artificial intelligence , machine learning , mathematics , statistics
A timescale is the estimate of phase and frequency of the “perfect” clock derived from the phase and frequency of the clocks which participate in the ensemble. An ensemble of clocks is the first step towards the realization of a timescale. In the past, several methodologies have been developed to solve the timescale problem such as KAS‐2, Multi‐scale Ensemble Timescale (METS), ALGOS (BIPM), AT1 (NIST) and algorithm for UTC (CRL). An adaptive ensemble algorithm based on Artificial Neural Network (ANN) has been developed which shows improvements in terms of betterment of frequency stability of the ensemble. The Neural Network in the ensemble algorithm learns differently for different sample spaces of the input phase data that is provided. The weights of the participating clocks are derived from their respective Allan deviations. The weights formulated for the ensemble undergo a regressive iteration to obtain the training data set for parameterization of weights. A single‐layer perceptron feedback Neural Network that is proposed in this paper, dynamically adapts the weights assigned to the participating clocks based on the paper clock performance. This paper dwells on the comparison of performances between the ANN‐based algorithms with that of two other algorithms, namely Reduced Kalman filter based algorithm and METS. Results of ANN‐based algorithm for different clock combinations are also presented. The behavior of this algorithm in the event of measurement data outage has also been presented in the paper.