A deep learning based energy efficient downlink power control mechanism for cellular networks

Subrata Biswas; Aurongo Mohammod Nasir; Md Farhad Hossain

doi:10.1109/ICECE51571.2020.9393086

A deep learning based energy efficient downlink power control mechanism for cellular networks

Subrata Biswas
, Aurongo Mohammod Nasir
, Md Farhad Hossain

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Management of radio resources in wireless communication has always been a challenging task. The complexity of this resource management is high, because wireless channels always contribute to different interference levels which ultimately results in degradation of the quality of service (QoS). To combat these challenges, many power control algorithms are developed. In this paper, we propose a deep learning (DL) based mechanism for power controlling. A convolutional time-series prediction model is developed which predicts future signal-to-noise-to-interference-ratio (SINR) and allocates power to maintain minimum required SINR level subject to overall amount of power consumed remaining minimum. The results generated by this method are benchmarked with greedy iterative SINR target setting power control technique and the result shows significant improvement in total power consumption and energy efficiency (EE).

Original language	English
Title of host publication	Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	343-346
Number of pages	4
ISBN (Electronic)	9781665422543
DOIs	https://doi.org/10.1109/ICECE51571.2020.9393086
Publication status	Published - 17 Dec 2020
Externally published	Yes
Event	11th International Conference on Electrical and Computer Engineering, ICECE 2020 - Virtual, Dhaka, Bangladesh Duration: 17 Dec 2020 → 19 Dec 2020

Publication series

Name	Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020

Conference

Conference	11th International Conference on Electrical and Computer Engineering, ICECE 2020
Country/Territory	Bangladesh
City	Virtual, Dhaka
Period	17/12/20 → 19/12/20

UN SDGs

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

SDG 7 Affordable and Clean Energy

Access to Document

10.1109/ICECE51571.2020.9393086

Cite this

Biswas, S., Nasir, A. M., & Hossain, M. F. (2020). A deep learning based energy efficient downlink power control mechanism for cellular networks. In Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020 (pp. 343-346). Article 9393086 (Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICECE51571.2020.9393086

Biswas, Subrata ; Nasir, Aurongo Mohammod ; Hossain, Md Farhad. / A deep learning based energy efficient downlink power control mechanism for cellular networks. Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020. IEEE, Institute of Electrical and Electronics Engineers, 2020. pp. 343-346 (Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020).

@inproceedings{0c692c2c5cf248e5ac3d1a283186fe88,

title = "A deep learning based energy efficient downlink power control mechanism for cellular networks",

abstract = "Management of radio resources in wireless communication has always been a challenging task. The complexity of this resource management is high, because wireless channels always contribute to different interference levels which ultimately results in degradation of the quality of service (QoS). To combat these challenges, many power control algorithms are developed. In this paper, we propose a deep learning (DL) based mechanism for power controlling. A convolutional time-series prediction model is developed which predicts future signal-to-noise-to-interference-ratio (SINR) and allocates power to maintain minimum required SINR level subject to overall amount of power consumed remaining minimum. The results generated by this method are benchmarked with greedy iterative SINR target setting power control technique and the result shows significant improvement in total power consumption and energy efficiency (EE).",

keywords = "AUC, CNN, Energy Efficiency, Power control, SINR, Time-series",

author = "Subrata Biswas and Nasir, \{Aurongo Mohammod\} and Hossain, \{Md Farhad\}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 11th International Conference on Electrical and Computer Engineering, ICECE 2020 ; Conference date: 17-12-2020 Through 19-12-2020",

year = "2020",

month = dec,

day = "17",

doi = "10.1109/ICECE51571.2020.9393086",

language = "English",

series = "Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "343--346",

booktitle = "Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020",

address = "United States",

}

Biswas, S, Nasir, AM & Hossain, MF 2020, A deep learning based energy efficient downlink power control mechanism for cellular networks. in Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020., 9393086, Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020, IEEE, Institute of Electrical and Electronics Engineers, pp. 343-346, 11th International Conference on Electrical and Computer Engineering, ICECE 2020, Virtual, Dhaka, Bangladesh, 17/12/20. https://doi.org/10.1109/ICECE51571.2020.9393086

A deep learning based energy efficient downlink power control mechanism for cellular networks. / Biswas, Subrata; Nasir, Aurongo Mohammod; Hossain, Md Farhad.
Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020. IEEE, Institute of Electrical and Electronics Engineers, 2020. p. 343-346 9393086 (Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020).

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - A deep learning based energy efficient downlink power control mechanism for cellular networks

AU - Biswas, Subrata

AU - Nasir, Aurongo Mohammod

AU - Hossain, Md Farhad

PY - 2020/12/17

Y1 - 2020/12/17

N2 - Management of radio resources in wireless communication has always been a challenging task. The complexity of this resource management is high, because wireless channels always contribute to different interference levels which ultimately results in degradation of the quality of service (QoS). To combat these challenges, many power control algorithms are developed. In this paper, we propose a deep learning (DL) based mechanism for power controlling. A convolutional time-series prediction model is developed which predicts future signal-to-noise-to-interference-ratio (SINR) and allocates power to maintain minimum required SINR level subject to overall amount of power consumed remaining minimum. The results generated by this method are benchmarked with greedy iterative SINR target setting power control technique and the result shows significant improvement in total power consumption and energy efficiency (EE).

AB - Management of radio resources in wireless communication has always been a challenging task. The complexity of this resource management is high, because wireless channels always contribute to different interference levels which ultimately results in degradation of the quality of service (QoS). To combat these challenges, many power control algorithms are developed. In this paper, we propose a deep learning (DL) based mechanism for power controlling. A convolutional time-series prediction model is developed which predicts future signal-to-noise-to-interference-ratio (SINR) and allocates power to maintain minimum required SINR level subject to overall amount of power consumed remaining minimum. The results generated by this method are benchmarked with greedy iterative SINR target setting power control technique and the result shows significant improvement in total power consumption and energy efficiency (EE).

KW - AUC

KW - CNN

KW - Energy Efficiency

KW - Power control

KW - SINR

KW - Time-series

UR - https://www.scopus.com/pages/publications/85104656271

UR - https://ieeexplore.ieee.org/xpl/conhome/9393009/proceeding

U2 - 10.1109/ICECE51571.2020.9393086

DO - 10.1109/ICECE51571.2020.9393086

M3 - Conference contribution

AN - SCOPUS:85104656271

T3 - Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020

SP - 343

EP - 346

BT - Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - 11th International Conference on Electrical and Computer Engineering, ICECE 2020

Y2 - 17 December 2020 through 19 December 2020

ER -

Biswas S, Nasir AM, Hossain MF. A deep learning based energy efficient downlink power control mechanism for cellular networks. In Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020. IEEE, Institute of Electrical and Electronics Engineers. 2020. p. 343-346. 9393086. (Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020). doi: 10.1109/ICECE51571.2020.9393086

A deep learning based energy efficient downlink power control mechanism for cellular networks

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this