Enhancing Regression Models for Complex Systems Using Evolutionary Techniques for Feature Engineering

TL;DR

This paper introduces an automatic feature engineering and symbolic regression method using evolutionary techniques to improve power consumption modeling in complex systems like cloud data centers, achieving high accuracy without expert intervention.

Contribution

It presents a novel combination of Grammatical Evolution and classical regression for automatic feature selection and model inference in complex system modeling.

Findings

Achieved an average power prediction error of 3.98% in cloud data centers.

Demonstrated effectiveness of the method on real cloud applications.

Enhanced potential for energy-efficient policies in cloud infrastructure.

Abstract

This work proposes an automatic methodology for modeling complex systems. Our methodology is based on the combination of Grammatical Evolution and classical regression to obtain an optimal set of features that take part of a linear and convex model. This technique provides both Feature Engineering and Symbolic Regression in order to infer accurate models with no effort or designer's expertise requirements. As advanced Cloud services are becoming mainstream, the contribution of data centers in the overall power consumption of modern cities is growing dramatically. These facilities consume from 10 to 100 times more power per square foot than typical office buildings. Modeling the power consumption for these infrastructures is crucial to anticipate the effects of aggressive optimization policies, but accurate and fast power modeling is a complex challenge for high-end servers not yet satisfied by analytical approaches. For this case study, our methodology minimizes error in power prediction. This work has been tested using real Cloud applications resulting on an average error in power estimation of 3.98%. Our work improves the possibilities of deriving Cloud energy efficient policies in Cloud data centers being applicable to other computing environments with similar characteristics.