Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs
This work addresses thermal management for SoC designers, but it is incremental as it compares existing methods on a specific platform.
The paper tackled the problem of predicting thermal dissipation in heterogeneous SoCs without hardware by evaluating system identification methods, finding that a linear state-space approach with polynomial regressors outperformed neural network methods, achieving better accuracy with 1 and 6 hours of training data.
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.