Abstract

This paper presents techniques to reduce energy with minimal degradation in system performance for multimedia signal processing algorithms. It first provides a survey of energy-saving techniques such as those based on voltage scaling, reducing number of computations and reducing dynamic range. While these techniques reduce energy, they also introduce errors that affect the performance quality. To compensate for these errors, techniques that exploit algorithm characteristics are presented. Next, several hybrid energy-saving techniques that further reduce the energy consumption with low performance degradation are presented. For instance, a combination of voltage scaling and dynamic range reduction is shown to achieve 85% energy saving in a low pass FIR filter for a fairly low noise level. A combination of computation reduction and dynamic reduction for Discrete Cosine Transform shows, on average, 33% to 46% reduction in energy consumption while incurring 0.5 dB to 1.5 dB loss in PSNR. Both of these techniques have very little overhead and achieve significant energy reduction with little quality degradation.

Original languageEnglish (US)
Article number6525371
Pages (from-to)1579-1593
Number of pages15
JournalIEEE Transactions on Multimedia
Volume15
Issue number7
DOIs
StatePublished - 2013

Fingerprint

Multimedia signal processing
Energy conservation
Degradation
Energy utilization
Discrete cosine transforms
FIR filters
Low pass filters

Keywords

  • Error compensation
  • low-power
  • multimedia algorithms
  • variable precision
  • voltage scaling

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Media Technology
  • Computer Science Applications

Cite this

Energy and quality-aware multimedia signal processing. / Emre, Yunus; Chakrabarti, Chaitali.

In: IEEE Transactions on Multimedia, Vol. 15, No. 7, 6525371, 2013, p. 1579-1593.

Research output: Contribution to journalArticle

@article{2f62170a2c2447a1b4bd41370200581b,
title = "Energy and quality-aware multimedia signal processing",
abstract = "This paper presents techniques to reduce energy with minimal degradation in system performance for multimedia signal processing algorithms. It first provides a survey of energy-saving techniques such as those based on voltage scaling, reducing number of computations and reducing dynamic range. While these techniques reduce energy, they also introduce errors that affect the performance quality. To compensate for these errors, techniques that exploit algorithm characteristics are presented. Next, several hybrid energy-saving techniques that further reduce the energy consumption with low performance degradation are presented. For instance, a combination of voltage scaling and dynamic range reduction is shown to achieve 85{\%} energy saving in a low pass FIR filter for a fairly low noise level. A combination of computation reduction and dynamic reduction for Discrete Cosine Transform shows, on average, 33{\%} to 46{\%} reduction in energy consumption while incurring 0.5 dB to 1.5 dB loss in PSNR. Both of these techniques have very little overhead and achieve significant energy reduction with little quality degradation.",
keywords = "Error compensation, low-power, multimedia algorithms, variable precision, voltage scaling",
author = "Yunus Emre and Chaitali Chakrabarti",
year = "2013",
doi = "10.1109/TMM.2013.2266094",
language = "English (US)",
volume = "15",
pages = "1579--1593",
journal = "IEEE Transactions on Multimedia",
issn = "1520-9210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "7",

}

TY - JOUR

T1 - Energy and quality-aware multimedia signal processing

AU - Emre, Yunus

AU - Chakrabarti, Chaitali

PY - 2013

Y1 - 2013

N2 - This paper presents techniques to reduce energy with minimal degradation in system performance for multimedia signal processing algorithms. It first provides a survey of energy-saving techniques such as those based on voltage scaling, reducing number of computations and reducing dynamic range. While these techniques reduce energy, they also introduce errors that affect the performance quality. To compensate for these errors, techniques that exploit algorithm characteristics are presented. Next, several hybrid energy-saving techniques that further reduce the energy consumption with low performance degradation are presented. For instance, a combination of voltage scaling and dynamic range reduction is shown to achieve 85% energy saving in a low pass FIR filter for a fairly low noise level. A combination of computation reduction and dynamic reduction for Discrete Cosine Transform shows, on average, 33% to 46% reduction in energy consumption while incurring 0.5 dB to 1.5 dB loss in PSNR. Both of these techniques have very little overhead and achieve significant energy reduction with little quality degradation.

AB - This paper presents techniques to reduce energy with minimal degradation in system performance for multimedia signal processing algorithms. It first provides a survey of energy-saving techniques such as those based on voltage scaling, reducing number of computations and reducing dynamic range. While these techniques reduce energy, they also introduce errors that affect the performance quality. To compensate for these errors, techniques that exploit algorithm characteristics are presented. Next, several hybrid energy-saving techniques that further reduce the energy consumption with low performance degradation are presented. For instance, a combination of voltage scaling and dynamic range reduction is shown to achieve 85% energy saving in a low pass FIR filter for a fairly low noise level. A combination of computation reduction and dynamic reduction for Discrete Cosine Transform shows, on average, 33% to 46% reduction in energy consumption while incurring 0.5 dB to 1.5 dB loss in PSNR. Both of these techniques have very little overhead and achieve significant energy reduction with little quality degradation.

KW - Error compensation

KW - low-power

KW - multimedia algorithms

KW - variable precision

KW - voltage scaling

UR - http://www.scopus.com/inward/record.url?scp=84886488503&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886488503&partnerID=8YFLogxK

U2 - 10.1109/TMM.2013.2266094

DO - 10.1109/TMM.2013.2266094

M3 - Article

AN - SCOPUS:84886488503

VL - 15

SP - 1579

EP - 1593

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

SN - 1520-9210

IS - 7

M1 - 6525371

ER -