Extremely Randomized Trees Regressor Scheme for Mobile Network Coverage Prediction and REM Construction
In mobile communications network planning (and designing any radio system), coverage prediction helps network operators optimize cellular networks to improve customer experience. Accordingly, several path-loss models have been proposed that depend on many conditions, such as suitable selection of th...
Published in: | IEEE Access |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE
2023
|
Subjects: | |
Online Access: | https://doi.org/10.1109/ACCESS.2023.3287103 https://doaj.org/article/feffa07284dc49999d39281669e66854 |
id |
ftdoajarticles:oai:doaj.org/article:feffa07284dc49999d39281669e66854 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:feffa07284dc49999d39281669e66854 2023-07-30T04:07:25+02:00 Extremely Randomized Trees Regressor Scheme for Mobile Network Coverage Prediction and REM Construction Carla E. Garcia Insoo Koo 2023-01-01T00:00:00Z https://doi.org/10.1109/ACCESS.2023.3287103 https://doaj.org/article/feffa07284dc49999d39281669e66854 EN eng IEEE https://ieeexplore.ieee.org/document/10154064/ https://doaj.org/toc/2169-3536 2169-3536 doi:10.1109/ACCESS.2023.3287103 https://doaj.org/article/feffa07284dc49999d39281669e66854 IEEE Access, Vol 11, Pp 65170-65180 (2023) Coverage prediction radio environment map (REM) extremely randomized trees machine learning reference signal received power Electrical engineering. Electronics. Nuclear engineering TK1-9971 article 2023 ftdoajarticles https://doi.org/10.1109/ACCESS.2023.3287103 2023-07-09T00:35:24Z In mobile communications network planning (and designing any radio system), coverage prediction helps network operators optimize cellular networks to improve customer experience. Accordingly, several path-loss models have been proposed that depend on many conditions, such as suitable selection of the terrain for each model, the height of the receiver and transmitter above ground and the distance between them, and the presence of obstacles. This may increase the prediction error between actual and estimated values, which change according to the propagation model selected. To overcome these problems, we propose a novel approach to mobile coverage prediction based on an extremely randomized trees regressor (ERTR) algorithm. In addition, we construct a radio environment map (REM) over a Google Earth digital map to improve visualization of the results and to easily detect coverage holes and traffic hotspots. For this purpose, we utilize a dataset with real measurements collected from Victoria Island and Ikoyi in Lagos, Nigeria. For performance evaluation, we use k-fold cross-validation based on four error metrics: relative error, root mean squared error, mean absolute error, and ${R^{2}}$ score. The proposed ERTR scheme achieves the best performance in terms of accuracy and computational load in predicting the reference signal received power and the received signal strength indicator value. We prove this with extensive simulation analysis and by comparing the error metrics of the proposed ERTR approach with an existing method widely used to perform coverage prediction, called ordinary kriging. We also compared seven machine learning regression algorithms, namely, random forest, a bagging regressor, support vector regression, k-nearest neighbors, a deep neural network, Gaussian process regression, and the decision tree. Article in Journal/Newspaper Victoria Island Directory of Open Access Journals: DOAJ Articles IEEE Access 11 65170 65180 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Coverage prediction radio environment map (REM) extremely randomized trees machine learning reference signal received power Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
spellingShingle |
Coverage prediction radio environment map (REM) extremely randomized trees machine learning reference signal received power Electrical engineering. Electronics. Nuclear engineering TK1-9971 Carla E. Garcia Insoo Koo Extremely Randomized Trees Regressor Scheme for Mobile Network Coverage Prediction and REM Construction |
topic_facet |
Coverage prediction radio environment map (REM) extremely randomized trees machine learning reference signal received power Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
description |
In mobile communications network planning (and designing any radio system), coverage prediction helps network operators optimize cellular networks to improve customer experience. Accordingly, several path-loss models have been proposed that depend on many conditions, such as suitable selection of the terrain for each model, the height of the receiver and transmitter above ground and the distance between them, and the presence of obstacles. This may increase the prediction error between actual and estimated values, which change according to the propagation model selected. To overcome these problems, we propose a novel approach to mobile coverage prediction based on an extremely randomized trees regressor (ERTR) algorithm. In addition, we construct a radio environment map (REM) over a Google Earth digital map to improve visualization of the results and to easily detect coverage holes and traffic hotspots. For this purpose, we utilize a dataset with real measurements collected from Victoria Island and Ikoyi in Lagos, Nigeria. For performance evaluation, we use k-fold cross-validation based on four error metrics: relative error, root mean squared error, mean absolute error, and ${R^{2}}$ score. The proposed ERTR scheme achieves the best performance in terms of accuracy and computational load in predicting the reference signal received power and the received signal strength indicator value. We prove this with extensive simulation analysis and by comparing the error metrics of the proposed ERTR approach with an existing method widely used to perform coverage prediction, called ordinary kriging. We also compared seven machine learning regression algorithms, namely, random forest, a bagging regressor, support vector regression, k-nearest neighbors, a deep neural network, Gaussian process regression, and the decision tree. |
format |
Article in Journal/Newspaper |
author |
Carla E. Garcia Insoo Koo |
author_facet |
Carla E. Garcia Insoo Koo |
author_sort |
Carla E. Garcia |
title |
Extremely Randomized Trees Regressor Scheme for Mobile Network Coverage Prediction and REM Construction |
title_short |
Extremely Randomized Trees Regressor Scheme for Mobile Network Coverage Prediction and REM Construction |
title_full |
Extremely Randomized Trees Regressor Scheme for Mobile Network Coverage Prediction and REM Construction |
title_fullStr |
Extremely Randomized Trees Regressor Scheme for Mobile Network Coverage Prediction and REM Construction |
title_full_unstemmed |
Extremely Randomized Trees Regressor Scheme for Mobile Network Coverage Prediction and REM Construction |
title_sort |
extremely randomized trees regressor scheme for mobile network coverage prediction and rem construction |
publisher |
IEEE |
publishDate |
2023 |
url |
https://doi.org/10.1109/ACCESS.2023.3287103 https://doaj.org/article/feffa07284dc49999d39281669e66854 |
genre |
Victoria Island |
genre_facet |
Victoria Island |
op_source |
IEEE Access, Vol 11, Pp 65170-65180 (2023) |
op_relation |
https://ieeexplore.ieee.org/document/10154064/ https://doaj.org/toc/2169-3536 2169-3536 doi:10.1109/ACCESS.2023.3287103 https://doaj.org/article/feffa07284dc49999d39281669e66854 |
op_doi |
https://doi.org/10.1109/ACCESS.2023.3287103 |
container_title |
IEEE Access |
container_volume |
11 |
container_start_page |
65170 |
op_container_end_page |
65180 |
_version_ |
1772820707037675520 |