ew 16(10): e4

Research Article

Univariate Interpolation-based Modeling of Power and Performance

Download283 downloads
  • @ARTICLE{10.4108/eai.14-12-2015.2262579,
        author={J\^{o}akim von Kistowski and Samuel Kounev},
        title={Univariate Interpolation-based Modeling of Power and Performance},
        journal={EAI Endorsed Transactions on Energy Web},
        volume={3},
        number={10},
        publisher={ACM},
        journal_a={EW},
        year={2016},
        month={1},
        keywords={interpolation, energy efficiency, power, performance, utilization, sert},
        doi={10.4108/eai.14-12-2015.2262579}
    }
    
  • Jóakim von Kistowski
    Samuel Kounev
    Year: 2016
    Univariate Interpolation-based Modeling of Power and Performance
    EW
    EAI
    DOI: 10.4108/eai.14-12-2015.2262579
Jóakim von Kistowski1,*, Samuel Kounev1
  • 1: University of Würzburg
*Contact email: joakim.kistowski@uni-wuerzburg.de

Abstract

Performance and power scale non-linearly with device utilization, making characterization and prediction of energy efficiency at a given load level a challenging issue. A common approach to address this problem is the creation of power or performance state tables for a pre-measured subset of all possible system states. Approaches to determine performance and power for a state not included in the measured subset use simple interpolation, such as nearest neighbor interpolation, or define state switching rules. This leads to a loss in accuracy, as unmeasured system states are not considered. In this paper, we compare different interpolation functions and automatically configure and select functions for a given domain or measurement set. We evaluate our approach by comparing interpolation of measurement data subsets against power and performance measurements on a commodity server. We show that for non-extrapolating models interpolation is significantly more accurate than regression, with our automatically configured interpolation function improving modeling accuracy up to 43.6%.