Deep Learning for Solar Power Forecasting by Integrating Historical and Meteorological Data

Hybrid Stacking with Targeted Residual Learning for PV Forecasting

A hybrid PV forecasting framework that combines stacking ensemble learning with a targeted residual correction strategy, and demonstrates that analyzing error distribution and forecasting robustness provides valuable insights beyond conventional aggregate metrics, contributing to the development of more reliable photovoltaic forecasting systems.

Bayesian-optimized LSTM networks for accurate day-ahead photovoltaic power prediction

Accurate day-ahead photovoltaic (PV) power forecasting is essential for effective energy management and grid balancing. This study proposes a Bayesian-optimized long short-term memory (LSTM) network for day-ahead PV power prediction. The model was evaluated using a PV-meteorological time-series dataset collected from a 500-kWp grid-connected PV installation in Mosul, Iraq, between January 1, 2021 and December 31, 2023 at an hourly sampling interval. After data-quality screening, 25,842 valid synchronized observations were retained from 26,280 timestamps. Each forecasting sample used the previous 24 hours of PV power, solar irradiance, ambient temperature, relative humidity, wind speed, and temporal indicators to predict the subsequent 24-hour PV power profile. The data were divided chronologically into training, validation, and independent test subsets. Preprocessing included duplicate removal, missing-value treatment, IQR-based outlier handling, temporal alignment, and min-max normalization fitted only on the training subset. Bayesian optimization tuned the LSTM architecture and training hyperparameters, while a hybrid MSE-MAE loss balanced large deviations and overall error. The proposed model achieved an MAE of 15.2 kW, an RMSE of 20.5 kW, a MAPE of 8.3%, and an R² of 0.93, outperforming linear regression and autoregressive integrated moving average (ARIMA) under the evaluated conditions.

Simulation-Driven Short-Term Solar Power Forecasting using LSTM Neural Networks

The large-scale integration of photovoltaic (PV) systems into modern power grids impacts operational challenges in reducing the intermittency of solar irradiance. Short-term forecasting, especially with accurate result is essential for grid stability, economic dispatch, and demand-side management. However, the development of robust deep-learning models is frequently constrained by the limited readiness of high-quality and labeled actual generation data. This paper presents a simulation-driven methodology to address this data scarcity problem. A synthetic PV generation dataset is created using a deterministic mathematical model. This method captures the diurnal solar cycle, augmented with Gaussian stochastic noise to simulate the effects of cloud cover and atmospheric turbulence. A Long Short-Term Memory (LSTM) network in two layer is trained on the synthetic dataset and subsequently validated against real hourly PV generation data for Bali, Indonesia. This data was obtained from the PVGIS-ERA5 database. The method performs 1-hour-ahead sequence-to-point forecasting using a 6-hour retrospective window. A persistence baseline model is employed for comparative benchmarking. This experiment found that the LSTM outperforms the persistence baseline on both datasets significantly. For the empirical Bali PV dataset, the LSTM attains a Mean Absolute Error (MAE) and a Root Mean Square Error (RMSE) of 29.75 W and 43.31 W, respectively, with a corresponding R2 value of 0.9474. Compared to the persistence benchmark's MAE of 69.00 W, the network successfully cuts prediction error by 56.9%. These results validate both the simulation-driven training approach and the LSTM's capability for short-term solar forecasting under tropical conditions.

Residential photovoltaic generation forecast via long short-term memory and transformer

A systematic comparison of Long Short-Term Memory and transformer-based architectures for deterministic short-term PV power forecasting using publicly accessible data from multiple climatic regions highlights the advantages of attention-based sequence modeling for PV applications and offers practical guidance on feature design, input horizon selection, and hyperparameter ranges for future data-driven PV forecasting studies.

Machine learning-based prediction of solar PV power using experimental data

PV Power Prediction Using Artificial Intelligence Models: A Case Study of Meknes, Morocco

The precise forecasting of photovoltaic (PV) energy production has emerged as a crucial challenge for the optimal management of electrical grids and the stability of energy systems. This study examines the use of AI techniques for short-term forecasting of PV power, employing meteorological data from the NASA POWER satellite database (solar irradiance, air temperature, atmospheric pressure, relative humidity, and wind speed), along with real PV production data gathered in Meknes, Morocco, over a year (February 2015 – March 2016) as part of the national Propre.Ma project. Three predictive models were developed and compared: A Deep Learning model based on an Artificial Neural Network (ANN), a Support Vector Machine (SVM), and a gradient boosting model (LightGBM), evaluated using MAE, MSE, and R 2 . The results indicate that LightGBM performs the best overall (R 2 = 93.1%, MAE = 0.073, MSE = 0.0248), followed by the ANN model (R 2 = 92.5%), while the SVM has the lowest accuracy (R 2 = 81.0%). This study demonstrates the effectiveness of gradient boosting models and neural networks for accurately forecasting solar production in Meknes, thus offering promising prospects for the deployment of solar solutions in Morocco.