Analysis of Artificial Neural Network Model Against Empirical Model (Okumara-Hata Model) For Predicting Pathloss In Gsm Networks

Abstract

Radio propagation prediction is one of the fundamentals of radio network planning. It is thereforevital that the propagation prediction models are as accurate as possible; taking into account the practical limitations that characterized the propagation environment. A drive test was conducted to obtain the field measured data with which the models were appraised. This was done to determine the most suitable model for GSM network deployment in Makurdi, Nigeria. The analysis of the results showed that Okumura – Hata Model, COST 231 – Hata Model, Standard Propagation Model and Stanford University Interim Model gave Root Mean Square Error values of 11.39 dB, 11.59 dB, 8.11 dB and 18.48 dB respectively for GSM900; and 10.75 dB, 9.78 dB, 12.39 dB and 16.99 dB respectively for GSM 1800. Therefore, it was concluded that Standard Propagation Model and COST 231 – Hata Model would be more suitable for GSM 900 and GSM 1800 network planning and deployment respectively in Umuahia City,

Authors and Affiliations

Umesi Cosmos

Keywords

Related Articles

Equilibrium Studies on a Chi Phase-Strengthened Ferritic Alloy

The phase relationships for a quaternary ferritic alloy with promising high temperature properties were investigated. The alloy of interest has the composition Fe-13 pct Cr-1.5 pct Mo-3.5 pct Ti and owes its high tempera...

Influence of heat treatment on Vitamin C Levels in Oyster Mushroom

The study was conducted to investigate the influence of heat treatment during drying process of Oyster mushroom in the tropics. Mushroom growing is carried out under carefully controlled conditions mostly in bulk in spec...

Positive and negative solutions of a boundary value problem for a fractional -difference equation

In this work, we study a boundary value problem for a fractional q, -difference equation. By using the monotone iterative technique and lower-upper solution method, we get the existence of positive or negative solutions...

Effect of Feldspar on the Properties of Swelling, Shrinkage and Bearing Capacity of Expansive Clay Soil

Expansive soil is a kind of soil to have high potential for swelling and shrinkage where it has low bearing capacity. On the pavement that laid over the expamsive soil, the uneveness of upward movement caused swelling th...

The Impact of Financial Crisis and Trade Relevance on the Market Reactions in Taiwan’s Financial Industry

Previous literature seldom investigates whether financial crisis events or events caused by trade-related countries have great impact on stock returns. However, the event characteristics and occurrence areas are critical...

Download PDF file
  • EP ID EP646593
  • DOI -
  • Views 143
  • Downloads 0

How To Cite

Umesi Cosmos (2019). Analysis of Artificial Neural Network Model Against Empirical Model (Okumara-Hata Model) For Predicting Pathloss In Gsm Networks. Invention Journal of Research Technology in Engineering & Management, 3(3), 1-8. https://europub.co.uk/articles/-A-646593