NFISiS: New Perspectives on Fuzzy Inference Systems for Renewable Energy Forecasting

TL;DR

This paper introduces enhanced fuzzy inference systems for renewable energy forecasting, combining genetic algorithms and ensemble techniques to improve accuracy, robustness, and interpretability over traditional models and deep learning approaches.

Contribution

It extends fuzzy models to Mamdani-based regressors with feature selection and ensemble methods, demonstrating superior performance on photovoltaic energy datasets.

Findings

Genetic and ensemble fuzzy models outperform traditional machine learning.

Models achieve high accuracy with interpretable rule structures.

Proposed models are validated on real photovoltaic energy data.

Abstract

Deep learning models, despite their popularity, face challenges such as long training times and a lack of interpretability. In contrast, fuzzy inference systems offer a balance of accuracy and transparency. This paper addresses the limitations of traditional Takagi-Sugeno-Kang fuzzy models by extending the recently proposed New Takagi-Sugeno-Kang model to a new Mamdani-based regressor. These models are data-driven, allowing users to define the number of rules to balance accuracy and interpretability. To handle the complexity of large datasets, this research integrates wrapper and ensemble techniques. A Genetic Algorithm is used as a wrapper for feature selection, creating genetic versions of the models. Furthermore, ensemble models, including the Random New Mamdani Regressor, Random New Takagi-Sugeno-Kang, and Random Forest New Takagi-Sugeno-Kang, are introduced to improve robustness. The proposed models are validated on photovoltaic energy forecasting datasets, a critical application due to the intermittent nature of solar power. Results demonstrate that the genetic and ensemble fuzzy models, particularly the Genetic New Takagi-Sugeno-Kang and Random Forest New Takagi-Sugeno-Kang, achieve superior performance. They often outperform both traditional machine learning and deep learning models while providing a simpler and more interpretable rule-based structure. The models are available online in a library called nfisis (https://pypi.org/project/nfisis/).