Near-Perfect Coverage Manifold Estimation in Cellular Networks via Conditional GAN

Washim Uddin Mondal; Veni Goyal; Satish V. Ukkusuri; Goutam Das; Di Wang; Mohamed Slim Alouini; Vaneet Aggarwal

doi:10.1109/LNET.2024.3365717

Near-Perfect Coverage Manifold Estimation in Cellular Networks via Conditional GAN

Washim Uddin Mondal^*, Veni Goyal, Satish V. Ukkusuri, Goutam Das, Di Wang, Mohamed Slim Alouini, Vaneet Aggarwal

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

This letter presents a conditional generative adversarial network (cGAN) that translates base station location (BSL) information of any Region-of-Interest (RoI) to location-dependent coverage probability values within a subset of that region, called the region-of-evaluation (RoE). We train our network utilizing the BSL data of India, the USA, Germany, and Brazil. In comparison to the state-of-the-art convolutional neural networks (CNNs), our model improves the prediction error (L1 difference between the coverage manifold generated by the network under consideration and that generated via simulation) by two orders of magnitude. Moreover, the cGAN-generated coverage manifolds appear to be almost visually indistinguishable from the ground truth.

Original language	English (US)
Pages (from-to)	97-100
Number of pages	4
Journal	IEEE Networking Letters
Volume	6
Issue number	2
DOIs	https://doi.org/10.1109/LNET.2024.3365717
State	Published - Jun 1 2024

Keywords

conditional GAN
Coverage
network performance
stochastic geometry

ASJC Scopus subject areas

Electrical and Electronic Engineering
Information Systems
Communication
Hardware and Architecture

Access to Document

10.1109/LNET.2024.3365717

Cite this

@article{581e6b61148b49cfb4ca8b1a49bbccbd,

title = "Near-Perfect Coverage Manifold Estimation in Cellular Networks via Conditional GAN",

abstract = "This letter presents a conditional generative adversarial network (cGAN) that translates base station location (BSL) information of any Region-of-Interest (RoI) to location-dependent coverage probability values within a subset of that region, called the region-of-evaluation (RoE). We train our network utilizing the BSL data of India, the USA, Germany, and Brazil. In comparison to the state-of-the-art convolutional neural networks (CNNs), our model improves the prediction error (L1 difference between the coverage manifold generated by the network under consideration and that generated via simulation) by two orders of magnitude. Moreover, the cGAN-generated coverage manifolds appear to be almost visually indistinguishable from the ground truth.",

keywords = "conditional GAN, Coverage, network performance, stochastic geometry",

author = "Mondal, {Washim Uddin} and Veni Goyal and Ukkusuri, {Satish V.} and Goutam Das and Di Wang and Alouini, {Mohamed Slim} and Vaneet Aggarwal",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.",

year = "2024",

month = jun,

day = "1",

doi = "10.1109/LNET.2024.3365717",

language = "English (US)",

volume = "6",

pages = "97--100",

journal = "IEEE Networking Letters",

issn = "2576-3156",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - Near-Perfect Coverage Manifold Estimation in Cellular Networks via Conditional GAN

AU - Mondal, Washim Uddin

AU - Goyal, Veni

AU - Ukkusuri, Satish V.

AU - Das, Goutam

AU - Wang, Di

AU - Alouini, Mohamed Slim

AU - Aggarwal, Vaneet

PY - 2024/6/1

Y1 - 2024/6/1

N2 - This letter presents a conditional generative adversarial network (cGAN) that translates base station location (BSL) information of any Region-of-Interest (RoI) to location-dependent coverage probability values within a subset of that region, called the region-of-evaluation (RoE). We train our network utilizing the BSL data of India, the USA, Germany, and Brazil. In comparison to the state-of-the-art convolutional neural networks (CNNs), our model improves the prediction error (L1 difference between the coverage manifold generated by the network under consideration and that generated via simulation) by two orders of magnitude. Moreover, the cGAN-generated coverage manifolds appear to be almost visually indistinguishable from the ground truth.

AB - This letter presents a conditional generative adversarial network (cGAN) that translates base station location (BSL) information of any Region-of-Interest (RoI) to location-dependent coverage probability values within a subset of that region, called the region-of-evaluation (RoE). We train our network utilizing the BSL data of India, the USA, Germany, and Brazil. In comparison to the state-of-the-art convolutional neural networks (CNNs), our model improves the prediction error (L1 difference between the coverage manifold generated by the network under consideration and that generated via simulation) by two orders of magnitude. Moreover, the cGAN-generated coverage manifolds appear to be almost visually indistinguishable from the ground truth.

KW - conditional GAN

KW - Coverage

KW - network performance

KW - stochastic geometry

UR - http://www.scopus.com/inward/record.url?scp=85209464746&partnerID=8YFLogxK

U2 - 10.1109/LNET.2024.3365717

DO - 10.1109/LNET.2024.3365717

M3 - Article

AN - SCOPUS:85209464746

SN - 2576-3156

VL - 6

SP - 97

EP - 100

JO - IEEE Networking Letters

JF - IEEE Networking Letters

IS - 2

ER -

Near-Perfect Coverage Manifold Estimation in Cellular Networks via Conditional GAN

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this