Renewable Energy Prediction: A Comparative Study of Deep Learning Models for Complex Dataset Analysis

TL;DR

This study compares various deep learning models for renewable energy prediction, highlighting the impact of hyperparameter tuning and regularization techniques on model accuracy and overfitting across different datasets.

Contribution

It provides a comprehensive comparison of seven DL models and evaluates the effectiveness of different regularization methods in renewable energy prediction tasks.

Findings

Early stopping, dropout, and L1 regularization improve CNN and TD-MLP performance with larger datasets.

L2 regularization combined with early stopping and dropout best reduces overfitting in CNN-LSTM and AE models with smaller datasets.

Different models benefit from specific regularization techniques depending on dataset size.

Abstract

The increasing focus on predicting renewable energy production aligns with advancements in deep learning (DL). The inherent variability of renewable sources and the complexity of prediction methods require robust approaches, such as DL models, in the renewable energy sector. DL models are preferred over traditional machine learning (ML) because they capture complex, nonlinear relationships in renewable energy datasets. This study examines key factors influencing DL technique accuracy, including sampling and hyperparameter optimization, by comparing various methods and training and test ratios within a DL framework. Seven machine learning methods, LSTM, Stacked LSTM, CNN, CNN-LSTM, DNN, Time-Distributed MLP (TD-MLP), and Autoencoder (AE), are evaluated using a dataset combining weather and photovoltaic power output data from 12 locations. Regularization techniques such as early stopping, neuron dropout, L1 and L2 regularization are applied to address overfitting. The results demonstrate that the combination of early stopping, dropout, and L1 regularization provides the best performance to reduce overfitting in the CNN and TD-MLP models with larger training set, while the combination of early stopping, dropout, and L2 regularization is the most effective to reduce the overfitting in CNN-LSTM and AE models with smaller training set.