Comparative Analysis of Machine Learning and Deep Learning Models for Solar Energy Forecasting: A Meteorological Data-Driven Approach

View Full Paper

Ask AI

Bookmark

LSTM networks achieve high performance for hourly solar energy forecasting with R^2 = 0.9622, capturing complex temporal dependencies.
Ridge regression performs exceptionally well in daily forecasting, boasting an R^2 = 0.9997 and RMSE = 8.53 kWh, demonstrating strong generalization.
XGBoost provides competitive hourly performance with R^2 = 0.9541, while classical models like ARIMA face limitations in complex meteorological contexts.
Meteorological data significantly improves forecasting accuracy over models that rely solely on historical energy production values.

Discussion

No takes yet. Share an insight, caveat, or question.

This analysis compares LSTM, XGBoost, and classical methods for solar forecasting, indicating how meteorological data enhances prediction accuracy.

Yavuz et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

This analysis compares LSTM, XGBoost, and classical methods for solar forecasting, indicating how meteorological data enhances prediction accuracy.