Improve Machine Learning carbon footprint using Parquet dataset format and Mixed Precision training for regression models -- Part II

TL;DR

This study compares power consumption of regression machine learning models using CSV and Parquet data formats with mixed precision training, finding that hyper-parameter tuning and data format choices have limited impact on overall power savings.

Contribution

It provides empirical evidence on how mixed precision and data formats affect power consumption in regression models, highlighting the importance of hyper-parameter optimization.

Findings

Mixed precision training reduces power consumption by 7-11 Watts.

Hyper-parameters like batch size and neurons influence power use negatively.

No statistically significant difference in power consumption was found between data formats.

Abstract

This is the 2nd part of the dissertation for my master degree and compared the power consumption using the Comma-Separated-Values (CSV) and parquet dataset format with the default floating point (32bit) and Nvidia mixed precision (16bit and 32bit) while training a regression ML model. The same custom PC as per the 1st part, which was dedicated to the classification testing and analysis, was built to perform the experiments, and different ML hyper-parameters, such as batch size, neurons, and epochs, were chosen to build Deep Neural Networks (DNN). A benchmarking test with default hyper-parameter values for the DNN was used as a reference, while the experiments used a combination of different settings. The results were recorded in Excel, and descriptive statistics were chosen to calculate the mean between the groups and compare them using graphs and tables. The outcome was positive when using mixed precision combined with specific hyper-parameters. Compared to the benchmarking, optimising the regression models reduced the power consumption between 7 and 11 Watts. The regression results show that while mixed precision can help improve power consumption, we must carefully consider the hyper-parameters. A high number of batch sizes and neurons will negatively affect power consumption. However, this research required inferential statistics, specifically ANOVA and T-test, to compare the relationship between the means. The results reported no statistical significance between the means in the regression tests and accepted H0. Therefore, choosing different ML techniques and the Parquet dataset format will not improve the computational power consumption and the overall ML carbon footprint. However, a more extensive implementation with a cluster of GPUs can increase the sample size significantly, as it is an essential factor and can change the outcome of the statistical analysis.