"Evaluating the Role of Feature Selection Techniques in Supervised Machine Learning Models for Renewable Energy Prediction"

EasyChair Preprint 14450

Abstract

The increasing demand for renewable energy and the need for accurate energy predictions have made supervised machine learning (ML) models essential in forecasting renewable energy generation. However, the performance of these models is highly dependent on the quality and relevance of the input features. This research focuses on evaluating the role of feature selection techniques in enhancing the performance, interpretability, and computational efficiency of supervised ML models for renewable energy prediction.

Feature selection plays a critical role in reducing the dimensionality of the dataset, eliminating redundant or irrelevant features, and improving the model’s generalization capabilities. This study provides a comprehensive analysis of various feature selection methods, including filter, wrapper, and embedded approaches, and their impact on different ML algorithms, such as linear regression, decision trees, support vector machines, and neural networks.

The findings of this research reveal significant variations in the impact of feature selection techniques across different ML models and renewable energy datasets. The study concludes with recommendations for selecting appropriate feature selection methods based on the specific characteristics of the renewable energy data and the intended application. The insights gained from this research are expected to contribute to the development of more efficient and accurate predictive models in the renewable energy sector, ultimately supporting the transition to sustainable energy systems.

Keyphrases: Model Interpretability, Renewable Energy Prediction, Solar energy forecasting, Supervised Machine Learning, Wind Energy Prediction, computational efficiency, cross-validation, data preprocessing, dimensionality reduction, feature selection, hydroelectric power, model performance, predictive accuracy

@booklet{EasyChair:14450,
  author    = {John Owen},
  title     = {"Evaluating the Role of Feature Selection Techniques in Supervised Machine Learning Models for Renewable Energy Prediction"},
  howpublished = {EasyChair Preprint 14450},
  year      = {EasyChair, 2024}}