International Journal of Computing and Artificial Intelligence

P-ISSN: 2707-6571, E-ISSN: 2707-658X
Printed Journal   |   Refereed Journal   |   Peer Reviewed Journal

2022, Vol. 3, Issue 1, Part A

A real time series forcasting for a signal loss in a multipath antenna system using convolutionary networks


Author(s): Adegbenjo A and Adekunle Y

Abstract: This study presents propagation measurements of the fifth generation long-term evolution (5G LTE) network using Huawei Technologies drive test equipment. Measurements were taken from five transmitting evolved node base stations (eNodeBs) located along five major routes in Osogbo, Nigeria, at an operating frequency of 1800MHz. An empirical model was developed for planning and optimizing Global System for Mobile Communication (GSM) networks which address the poor quality of services provided by GSM service providers in Osogbo town. The average path losses predicted are 80.10dB, 74.27dB, 80.89, 80.65dB and 82.30dB, while the measured are 75.70, 70.20, 78.30, 79.12 and 76.10, respectively. However, according to R. Rakesh 2012, the acceptable range between measure and predicted result lies between 1 ≤ PL≤ 20dB. Therefore, the average values obtained vary between 2 to 7dB, within the acceptable range. Therefore, it can be concluded that the modified model developed from the Log-Normal shadowing model can be useful to GSM network service providers for planning and optimization their services in Osogbo, Nigeria. The study recommends that Nigerian Communication Commission (NCC), which is the regulatory body, mandate the GSM service providers in the country to experimentally test their desired scientific model to ascertain its practicability at the planning stage before the release of the operating license.

DOI: 10.33545/27076571.2022.v3.i1a.39

Pages: 01-09 | Views: 510 | Downloads: 233

Download Full Article: Click Here
How to cite this article:
Adegbenjo A, Adekunle Y. A real time series forcasting for a signal loss in a multipath antenna system using convolutionary networks. Int J Comput Artif Intell 2022;3(1):01-09. DOI: 10.33545/27076571.2022.v3.i1a.39
International Journal of Computing and Artificial Intelligence

International Journal of Computing and Artificial Intelligence

International Journal of Computing and Artificial Intelligence
Call for book chapter