Kernel-Based Adaptive Online Reconstruction of Coverage Maps With Side Information

Martin Kasparick, Renato L G Cavalcante, Stefan Valentin, Sławomir Stańczak, Masahiro Yukawa

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

In this paper, we address the problem of reconstructing coverage maps from path-loss measurements in cellular networks. We propose and evaluate two kernel-based adaptive online algorithms as an alternative to typical offline methods. The proposed algorithms are application-tailored extensions of powerful iterative methods such as the adaptive projected subgradient method (APSM) and a state-of-the-art adaptive multikernel method. Assuming that the moving trajectories of users are available, it is shown how side information can be incorporated in the algorithms to improve their convergence performance and the quality of the estimation. The complexity is significantly reduced by imposing sparsity awareness in the sense that the algorithms exploit the compressibility of the measurement data to reduce the amount of data that is saved and processed. Finally, we present extensive simulations based on realistic data to show that our algorithms provide fast and robust estimates of coverage maps in real-world scenarios. Envisioned applications include path-loss prediction along trajectories of mobile users as a building block for anticipatory buffering or traffic offloading.

Original languageEnglish
Article number7152980
Pages (from-to)5461-5473
Number of pages13
JournalIEEE Transactions on Vehicular Technology
Volume65
Issue number7
DOIs
Publication statusPublished - 2016 Jul 1

Fingerprint

Side Information
Path Loss
Coverage
kernel
Trajectory
Subgradient Method
Robust Estimate
Online Algorithms
Compressibility
Adaptive Method
Cellular Networks
Adaptive Algorithm
Sparsity
Building Blocks
Fast Algorithm
Trajectories
Traffic
Iteration
Scenarios
Iterative methods

Keywords

  • Adaptive filters
  • coverage estimation
  • Kernel-based filtering machine learning
  • mobile communications

ASJC Scopus subject areas

  • Automotive Engineering
  • Aerospace Engineering
  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

Kernel-Based Adaptive Online Reconstruction of Coverage Maps With Side Information. / Kasparick, Martin; Cavalcante, Renato L G; Valentin, Stefan; Stańczak, Sławomir; Yukawa, Masahiro.

In: IEEE Transactions on Vehicular Technology, Vol. 65, No. 7, 7152980, 01.07.2016, p. 5461-5473.

Research output: Contribution to journalArticle

Kasparick, Martin ; Cavalcante, Renato L G ; Valentin, Stefan ; Stańczak, Sławomir ; Yukawa, Masahiro. / Kernel-Based Adaptive Online Reconstruction of Coverage Maps With Side Information. In: IEEE Transactions on Vehicular Technology. 2016 ; Vol. 65, No. 7. pp. 5461-5473.
@article{b13f266633cb4e348f5fe1ae878ae8f7,
title = "Kernel-Based Adaptive Online Reconstruction of Coverage Maps With Side Information",
abstract = "In this paper, we address the problem of reconstructing coverage maps from path-loss measurements in cellular networks. We propose and evaluate two kernel-based adaptive online algorithms as an alternative to typical offline methods. The proposed algorithms are application-tailored extensions of powerful iterative methods such as the adaptive projected subgradient method (APSM) and a state-of-the-art adaptive multikernel method. Assuming that the moving trajectories of users are available, it is shown how side information can be incorporated in the algorithms to improve their convergence performance and the quality of the estimation. The complexity is significantly reduced by imposing sparsity awareness in the sense that the algorithms exploit the compressibility of the measurement data to reduce the amount of data that is saved and processed. Finally, we present extensive simulations based on realistic data to show that our algorithms provide fast and robust estimates of coverage maps in real-world scenarios. Envisioned applications include path-loss prediction along trajectories of mobile users as a building block for anticipatory buffering or traffic offloading.",
keywords = "Adaptive filters, coverage estimation, Kernel-based filtering machine learning, mobile communications",
author = "Martin Kasparick and Cavalcante, {Renato L G} and Stefan Valentin and Sławomir Stańczak and Masahiro Yukawa",
year = "2016",
month = "7",
day = "1",
doi = "10.1109/TVT.2015.2453391",
language = "English",
volume = "65",
pages = "5461--5473",
journal = "IEEE Transactions on Vehicular Technology",
issn = "0018-9545",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "7",

}

TY - JOUR

T1 - Kernel-Based Adaptive Online Reconstruction of Coverage Maps With Side Information

AU - Kasparick, Martin

AU - Cavalcante, Renato L G

AU - Valentin, Stefan

AU - Stańczak, Sławomir

AU - Yukawa, Masahiro

PY - 2016/7/1

Y1 - 2016/7/1

N2 - In this paper, we address the problem of reconstructing coverage maps from path-loss measurements in cellular networks. We propose and evaluate two kernel-based adaptive online algorithms as an alternative to typical offline methods. The proposed algorithms are application-tailored extensions of powerful iterative methods such as the adaptive projected subgradient method (APSM) and a state-of-the-art adaptive multikernel method. Assuming that the moving trajectories of users are available, it is shown how side information can be incorporated in the algorithms to improve their convergence performance and the quality of the estimation. The complexity is significantly reduced by imposing sparsity awareness in the sense that the algorithms exploit the compressibility of the measurement data to reduce the amount of data that is saved and processed. Finally, we present extensive simulations based on realistic data to show that our algorithms provide fast and robust estimates of coverage maps in real-world scenarios. Envisioned applications include path-loss prediction along trajectories of mobile users as a building block for anticipatory buffering or traffic offloading.

AB - In this paper, we address the problem of reconstructing coverage maps from path-loss measurements in cellular networks. We propose and evaluate two kernel-based adaptive online algorithms as an alternative to typical offline methods. The proposed algorithms are application-tailored extensions of powerful iterative methods such as the adaptive projected subgradient method (APSM) and a state-of-the-art adaptive multikernel method. Assuming that the moving trajectories of users are available, it is shown how side information can be incorporated in the algorithms to improve their convergence performance and the quality of the estimation. The complexity is significantly reduced by imposing sparsity awareness in the sense that the algorithms exploit the compressibility of the measurement data to reduce the amount of data that is saved and processed. Finally, we present extensive simulations based on realistic data to show that our algorithms provide fast and robust estimates of coverage maps in real-world scenarios. Envisioned applications include path-loss prediction along trajectories of mobile users as a building block for anticipatory buffering or traffic offloading.

KW - Adaptive filters

KW - coverage estimation

KW - Kernel-based filtering machine learning

KW - mobile communications

UR - http://www.scopus.com/inward/record.url?scp=84979294060&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979294060&partnerID=8YFLogxK

U2 - 10.1109/TVT.2015.2453391

DO - 10.1109/TVT.2015.2453391

M3 - Article

AN - SCOPUS:84979294060

VL - 65

SP - 5461

EP - 5473

JO - IEEE Transactions on Vehicular Technology

JF - IEEE Transactions on Vehicular Technology

SN - 0018-9545

IS - 7

M1 - 7152980

ER -