Data-Driven Geometric Programming for System-Level Performance Optimization

Soihem Gonmei; Junhwan Lee; Taesoo Kwon

doi:10.1109/ICTC58733.2023.10393275

Data-Driven Geometric Programming for System-Level Performance Optimization

Soihem Gonmei
, Junhwan Lee
, Taesoo Kwon

Dept. of Computer Science and Engineering

Seoul National University of Science and Technology (SNUST)
Electronics and Telecommunications Research Institute

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

More than often, the output of a comprehensive network-wide performance modeling is a non-linear and non-convex function of the input data. To estimate the non-linear relationship of such a procedure, this paper employs a data-driven methodology. By formulating the non-linear objective as a geometric program, we leverage Levenberg-Marquardt algorithm to fit a convex log-sum-exponential function to data obtained through system-level simulation. Focusing on the downlink energy efficiency in mmWave cellular networks, we formulate a convex optimization problem and numerically obtain the optimal BS density and transmit power.

Original language	English
Title of host publication	ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence
Subtitle of host publication	Exploring the Frontiers of ICT Innovation
Publisher	IEEE Computer Society
Pages	338-340
Number of pages	3
ISBN (Electronic)	9798350313277
DOIs	https://doi.org/10.1109/ICTC58733.2023.10393275
State	Published - 2023
Event	14th International Conference on Information and Communication Technology Convergence, ICTC 2023 - Jeju Island, Korea, Republic of Duration: 11 Oct 2023 → 13 Oct 2023

Publication series

Name	International Conference on ICT Convergence
ISSN (Print)	2162-1233
ISSN (Electronic)	2162-1241

Conference

Conference	14th International Conference on Information and Communication Technology Convergence, ICTC 2023
Country/Territory	Korea, Republic of
City	Jeju Island
Period	11/10/23 → 13/10/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Energy Efficiency
Geometric Programming
Levenberg-Marquardt algorithm (LMA)
mmWave
Regression

Access to Document

10.1109/ICTC58733.2023.10393275

Cite this

Gonmei, S., Lee, J., & Kwon, T. (2023). Data-Driven Geometric Programming for System-Level Performance Optimization. In ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation (pp. 338-340). (International Conference on ICT Convergence). IEEE Computer Society. https://doi.org/10.1109/ICTC58733.2023.10393275

@inproceedings{ae7685017f394483a1aefccb4ec45536,

title = "Data-Driven Geometric Programming for System-Level Performance Optimization",

abstract = "More than often, the output of a comprehensive network-wide performance modeling is a non-linear and non-convex function of the input data. To estimate the non-linear relationship of such a procedure, this paper employs a data-driven methodology. By formulating the non-linear objective as a geometric program, we leverage Levenberg-Marquardt algorithm to fit a convex log-sum-exponential function to data obtained through system-level simulation. Focusing on the downlink energy efficiency in mmWave cellular networks, we formulate a convex optimization problem and numerically obtain the optimal BS density and transmit power.",

keywords = "Energy Efficiency, Geometric Programming, Levenberg-Marquardt algorithm (LMA), mmWave, Regression",

author = "Soihem Gonmei and Junhwan Lee and Taesoo Kwon",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 14th International Conference on Information and Communication Technology Convergence, ICTC 2023 ; Conference date: 11-10-2023 Through 13-10-2023",

year = "2023",

doi = "10.1109/ICTC58733.2023.10393275",

language = "English",

series = "International Conference on ICT Convergence",

publisher = "IEEE Computer Society",

pages = "338--340",

booktitle = "ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence",

}

Gonmei, S, Lee, J & Kwon, T 2023, Data-Driven Geometric Programming for System-Level Performance Optimization. in ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation. International Conference on ICT Convergence, IEEE Computer Society, pp. 338-340, 14th International Conference on Information and Communication Technology Convergence, ICTC 2023, Jeju Island, Korea, Republic of, 11/10/23. https://doi.org/10.1109/ICTC58733.2023.10393275

Data-Driven Geometric Programming for System-Level Performance Optimization. / Gonmei, Soihem; Lee, Junhwan; Kwon, Taesoo.
ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation. IEEE Computer Society, 2023. p. 338-340 (International Conference on ICT Convergence).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Data-Driven Geometric Programming for System-Level Performance Optimization

AU - Gonmei, Soihem

AU - Lee, Junhwan

AU - Kwon, Taesoo

PY - 2023

Y1 - 2023

N2 - More than often, the output of a comprehensive network-wide performance modeling is a non-linear and non-convex function of the input data. To estimate the non-linear relationship of such a procedure, this paper employs a data-driven methodology. By formulating the non-linear objective as a geometric program, we leverage Levenberg-Marquardt algorithm to fit a convex log-sum-exponential function to data obtained through system-level simulation. Focusing on the downlink energy efficiency in mmWave cellular networks, we formulate a convex optimization problem and numerically obtain the optimal BS density and transmit power.

AB - More than often, the output of a comprehensive network-wide performance modeling is a non-linear and non-convex function of the input data. To estimate the non-linear relationship of such a procedure, this paper employs a data-driven methodology. By formulating the non-linear objective as a geometric program, we leverage Levenberg-Marquardt algorithm to fit a convex log-sum-exponential function to data obtained through system-level simulation. Focusing on the downlink energy efficiency in mmWave cellular networks, we formulate a convex optimization problem and numerically obtain the optimal BS density and transmit power.

KW - Energy Efficiency

KW - Geometric Programming

KW - Levenberg-Marquardt algorithm (LMA)

KW - mmWave

KW - Regression

UR - https://www.scopus.com/pages/publications/85184597664

U2 - 10.1109/ICTC58733.2023.10393275

DO - 10.1109/ICTC58733.2023.10393275

M3 - Conference contribution

AN - SCOPUS:85184597664

T3 - International Conference on ICT Convergence

SP - 338

EP - 340

BT - ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence

PB - IEEE Computer Society

T2 - 14th International Conference on Information and Communication Technology Convergence, ICTC 2023

Y2 - 11 October 2023 through 13 October 2023

ER -

Gonmei S, Lee J, Kwon T. Data-Driven Geometric Programming for System-Level Performance Optimization. In ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation. IEEE Computer Society. 2023. p. 338-340. (International Conference on ICT Convergence). doi: 10.1109/ICTC58733.2023.10393275

Data-Driven Geometric Programming for System-Level Performance Optimization

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this