A Framework for Design and Implementation of Adaptive Digital Predistortion Systems

Lin Li; Peter Deaville; Adrian Sapio; Lauri Anttila; Mikko Valkama; Marilyn Wolf; Shuvra S. Bhattacharyya

doi:10.1109/AICAS.2019.8771476

A Framework for Design and Implementation of Adaptive Digital Predistortion Systems

Lin Li, Peter Deaville, Adrian Sapio, Lauri Anttila, Mikko Valkama, Marilyn Wolf, Shuvra S. Bhattacharyya

Tutkimustuotos: Konferenssiartikkeli › Scientific › vertaisarvioitu

2 Sitaatiot (Scopus)

6 Lataukset (Pure)

Abstrakti

Digital predistortion (DPD) has important applications in wireless communication for smart systems, such as, for example, in Internet of Things (IoT) applications for smart cities. DPD is used in wireless communication transmitters to counteract distortions that arise from nonlinearities, such as those related to amplifier characteristics and local oscillator leakage. In this paper, we propose an algorithm-architecture-integrated framework for design and implementation of adaptive DPD systems. The proposed framework provides energy-efficient, real-time DPD performance, and enables efficient reconfiguration of DPD architectures so that communication can be dynamically optimized based on time-varying communication requirements. Our adaptive DPD design framework applies Markov Decision Processes (MDPs) in novel ways to generate optimized runtime control policies for DPD systems. We present a GPU-based adaptive DPD system that is derived using our design framework, and demonstrate its efficiency through extensive experiments.

Alkuperäiskieli	Englanti
Otsikko	Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019
Kustantaja	IEEE
Sivut	112-116
Sivumäärä	5
ISBN (elektroninen)	9781538678848
DOI - pysyväislinkit	https://doi.org/10.1109/AICAS.2019.8771476
Tila	Julkaistu - 1 maalisk. 2019
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	IEEE International Conference on Artificial Intelligence Circuits and Systems - Hsinchu, Taiwan Kesto: 18 maalisk. 2019 → 20 maalisk. 2019

Conference

Conference	IEEE International Conference on Artificial Intelligence Circuits and Systems
Maa/Alue	Taiwan
Kaupunki	Hsinchu
Ajanjakso	18/03/19 → 20/03/19

Julkaisufoorumi-taso

Jufo-taso 1

!!ASJC Scopus subject areas

Artificial Intelligence
Hardware and Architecture
Electrical and Electronic Engineering

YK:n kestävän kehityksen tavoitteet

Tämä tuotos edistää seuraavia kestävän kehityksen tavoitteita:

Pääsy asiakirjaan

10.1109/AICAS.2019.8771476

DPD_framework_AICAS_2019Accepted author manuscript, 840 KB

http://urn.fi/URN:NBN:fi:tuni-202012229120

Siteeraa tätä

@inproceedings{418fa5fd9e544f6b828ca53aa2b9b0d6,

title = "A Framework for Design and Implementation of Adaptive Digital Predistortion Systems",

abstract = "Digital predistortion (DPD) has important applications in wireless communication for smart systems, such as, for example, in Internet of Things (IoT) applications for smart cities. DPD is used in wireless communication transmitters to counteract distortions that arise from nonlinearities, such as those related to amplifier characteristics and local oscillator leakage. In this paper, we propose an algorithm-architecture-integrated framework for design and implementation of adaptive DPD systems. The proposed framework provides energy-efficient, real-time DPD performance, and enables efficient reconfiguration of DPD architectures so that communication can be dynamically optimized based on time-varying communication requirements. Our adaptive DPD design framework applies Markov Decision Processes (MDPs) in novel ways to generate optimized runtime control policies for DPD systems. We present a GPU-based adaptive DPD system that is derived using our design framework, and demonstrate its efficiency through extensive experiments.",

keywords = "dataflow modeling, digital predistortion, Markov decision processes, Smart systems",

author = "Lin Li and Peter Deaville and Adrian Sapio and Lauri Anttila and Mikko Valkama and Marilyn Wolf and Bhattacharyya, {Shuvra S.}",

year = "2019",

month = mar,

day = "1",

doi = "10.1109/AICAS.2019.8771476",

language = "English",

pages = "112--116",

booktitle = "Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019",

publisher = "IEEE",

note = "IEEE International Conference on Artificial Intelligence Circuits and Systems ; Conference date: 18-03-2019 Through 20-03-2019",

}

Li, L, Deaville, P, Sapio, A, Anttila, L , Valkama, M, Wolf, M & Bhattacharyya, SS 2019, A Framework for Design and Implementation of Adaptive Digital Predistortion Systems. julkaisussa Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. IEEE, Sivut 112-116, IEEE International Conference on Artificial Intelligence Circuits and Systems, Hsinchu, Taiwan, 18/03/19. https://doi.org/10.1109/AICAS.2019.8771476

TY - GEN

T1 - A Framework for Design and Implementation of Adaptive Digital Predistortion Systems

AU - Li, Lin

AU - Deaville, Peter

AU - Sapio, Adrian

AU - Anttila, Lauri

AU - Valkama, Mikko

AU - Wolf, Marilyn

AU - Bhattacharyya, Shuvra S.

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Digital predistortion (DPD) has important applications in wireless communication for smart systems, such as, for example, in Internet of Things (IoT) applications for smart cities. DPD is used in wireless communication transmitters to counteract distortions that arise from nonlinearities, such as those related to amplifier characteristics and local oscillator leakage. In this paper, we propose an algorithm-architecture-integrated framework for design and implementation of adaptive DPD systems. The proposed framework provides energy-efficient, real-time DPD performance, and enables efficient reconfiguration of DPD architectures so that communication can be dynamically optimized based on time-varying communication requirements. Our adaptive DPD design framework applies Markov Decision Processes (MDPs) in novel ways to generate optimized runtime control policies for DPD systems. We present a GPU-based adaptive DPD system that is derived using our design framework, and demonstrate its efficiency through extensive experiments.

AB - Digital predistortion (DPD) has important applications in wireless communication for smart systems, such as, for example, in Internet of Things (IoT) applications for smart cities. DPD is used in wireless communication transmitters to counteract distortions that arise from nonlinearities, such as those related to amplifier characteristics and local oscillator leakage. In this paper, we propose an algorithm-architecture-integrated framework for design and implementation of adaptive DPD systems. The proposed framework provides energy-efficient, real-time DPD performance, and enables efficient reconfiguration of DPD architectures so that communication can be dynamically optimized based on time-varying communication requirements. Our adaptive DPD design framework applies Markov Decision Processes (MDPs) in novel ways to generate optimized runtime control policies for DPD systems. We present a GPU-based adaptive DPD system that is derived using our design framework, and demonstrate its efficiency through extensive experiments.

KW - dataflow modeling

KW - digital predistortion

KW - Markov decision processes

KW - Smart systems

U2 - 10.1109/AICAS.2019.8771476

DO - 10.1109/AICAS.2019.8771476

M3 - Conference contribution

SP - 112

EP - 116

BT - Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

PB - IEEE

T2 - IEEE International Conference on Artificial Intelligence Circuits and Systems

Y2 - 18 March 2019 through 20 March 2019

ER -

A Framework for Design and Implementation of Adaptive Digital Predistortion Systems

Abstrakti

Conference

Julkaisufoorumi-taso

!!ASJC Scopus subject areas

YK:n kestävän kehityksen tavoitteet

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä