Three-dimensional spectrum coverage gap map construction in cellular networks: A non-linear estimation approach

Funding Number

1-21)–2020-Oct-01-14-33-33

Funding Sponsor

American University in Cairo

Author's Department

Electronics & Communications Engineering Department

Second Author's Department

Electronics & Communications Engineering Department

Third Author's Department

Electronics & Communications Engineering Department

Find in your Library

https://doi.org/10.1016/j.pmcj.2024.101998

All Authors

Ahmed Fahim Mostafa, Mohamed Abdel-Kader, Yasser Gadallah

Document Type

Research Article

Publication Title

Pervasive and Mobile Computing

Publication Date

1-1-2025

doi

10.1016/j.pmcj.2024.101998

Abstract

Data collection techniques can be used to determine the coverage conditions of a cellular communication network within a given area. In such tasks, the data acquisition process faces significant challenges for larger or inaccessible locations. Such challenges can be alleviated through the use of unmanned aerial vehicles (UAVs). This way, data acquisition obstacles can be overcome to acquire and process the necessary data points with relative ease to estimate a full area coverage map for the concerned network. In this study, we formulate the problem of deploying a UAV to acquire the minimum possible measurement data points in a geographical region for the purpose of constructing a full communication coverage gap map for this region. We then devise an estimation model that utilizes the measured data samples and determines the noise/loss levels of the communication links at the other unvisited spots of the region accordingly. The proposed estimation model is based on a cascade-forward neural network to allow for both nonlinear and direct linear relationships between the input data and the output estimations. We further investigate the conventional method of using linear regression estimators to decide on the received power levels at the different locations of the examined area. Our simulation evaluations show that the proposed nonlinear estimator outperforms the conventional linear regression technique in terms of the communication coverage error level while using the minimum possible collected data points. These minimum data points are then used in constructing a complete coverage gap map visualization that demonstrates the overall network service conditions within the surveyed region.

Comments

Article. Record derived from SCOPUS.

Link to Full Text
Find this item online

Share

COinS