English

Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs

Machine Learning 2021-12-21 v1

Abstract

In this paper we evaluate the use of system identification methods to build a thermal prediction model of heterogeneous SoC platforms that can be used to quickly predict the temperature of different configurations without the need of hardware. Specifically, we focus on modeling approaches that can predict the temperature based on the clock frequency and the utilization percentage of each core. We investigate three methods with respect to their prediction accuracy: a linear state-space identification approach using polynomial regressors, a NARX neural network approach and a recurrent neural network approach configured in an FIR model structure. We evaluate the methods on an Odroid-XU4 board featuring an Exynos 5422 SoC. The results show that the model based on polynomial regressors significantly outperformed the other two models when trained with 1 hour and 6 hours of data.

Keywords

Cite

@article{arxiv.2112.10121,
  title  = {Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs},
  author = {Joel Öhrling and Sébastien Lafond and Dragos Truscan},
  journal= {arXiv preprint arXiv:2112.10121},
  year   = {2021}
}

Comments

arXiv admin note: substantial text overlap with arXiv:2104.10387

R2 v1 2026-06-24T08:23:32.367Z