E-ISSN 2414-6013 | ISSN 2411-9636
 
2026, Vol: 15, Issue: 1

Technical Note 


Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction

Itto Ouzouhou, Abdellah Laazizi, Khalid Kandoussi, Rabie El Otmani.


Abstract
Energy and climate challenges have driven significant growth in solar power generation. However, solar power production is intermittent and unstable, which complicates its integration into power grids. Techniques of forecasting Photovoltaic (PV) energy are needed to ensure its security and cost-effectiveness. This paper deals with the use of artificial intelligence techniques to predict photovoltaic power. The proposed techniques are Weighted Linear Regression (WLR) and Long Short-Term Memory neural networks (LSTM). The investigated data in this study was obtained from a photovoltaic solar power plant located in a specific geographical area. The studied parameters are wind speed (WS), ambient temperature (T), relative humidity (RH), irradiance (GHI) and wind direction (WD). The accuracy and ability of the LSTM model to explain data variation were examined by comparing its predictions with those of the WLR model, based on three performance measures: RMSE, MAE and R2. The obtained results show that weighted linear regression produces an acceptable estimation of photovoltaic power. However, the LSTM model performs better and has the potential to improve forecast reliability and accuracy.

Key words: Photovoltaic power,, prediction,, LSTM neural networks,, Weighted Linear Regression.


 
ARTICLE TOOLS
Abstract
PDF Fulltext
How to cite this articleHow to cite this article
Citation Tools
Related Records
 Articles by Itto OUZOUHOU
Articles by Abdellah LAAZIZI
Articles by Khalid Kandoussi
Articles by Rabie El Otmani
on Google
on Google Scholar


How to Cite this Article
Pubmed Style

Ouzouhou I, Laazizi A, Kandoussi K, Otmani RE. Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction. Sol. Energy Sustain. Dev.. 2024; 15(0): 77-92.

doi:10.51646/jsesd.v15iMME.340



Web Style

Ouzouhou I, Laazizi A, Kandoussi K, Otmani RE. Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction. https://www.jsesd.org/?mno=302658156 [Access: November 10, 2026].

doi:10.51646/jsesd.v15iMME.340



AMA (American Medical Association) Style

Ouzouhou I, Laazizi A, Kandoussi K, Otmani RE. Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction. Sol. Energy Sustain. Dev.. 2024; 15(0): 77-92.


doi:10.51646/jsesd.v15iMME.340



Vancouver/ICMJE Style

Ouzouhou I, Laazizi A, Kandoussi K, Otmani RE. Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction. Sol. Energy Sustain. Dev.. (2024), [cited November 10, 2026]; 15(0): 77-92.


doi:10.51646/jsesd.v15iMME.340



Harvard Style

Ouzouhou, I., Laazizi, . A., Kandoussi, . K. & Otmani, . R. E. (2024) Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction. Sol. Energy Sustain. Dev., 15 (0), 77-92.


doi:10.51646/jsesd.v15iMME.340



Turabian Style

Ouzouhou, Itto, Abdellah Laazizi, Khalid Kandoussi, and Rabie El Otmani. 2024. Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction. Solar Energy and Sustainable Development, 15 (0), 77-92.


doi:10.51646/jsesd.v15iMME.340



Chicago Style

Ouzouhou, Itto, Abdellah Laazizi, Khalid Kandoussi, and Rabie El Otmani. "Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction." Solar Energy and Sustainable Development 15 (2024), 77-92.


doi:10.51646/jsesd.v15iMME.340



MLA (The Modern Language Association) Style

Ouzouhou, Itto, Abdellah Laazizi, Khalid Kandoussi, and Rabie El Otmani. "Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction." Solar Energy and Sustainable Development 15.0 (2024), 77-92. Print.


doi:10.51646/jsesd.v15iMME.340



APA (American Psychological Association) Style

Ouzouhou, I., Laazizi, . A., Kandoussi, . K. & Otmani, . R. E. (2024) Optimized LSTM Neural Networks Model applied for Solar PV Power Prediction. Solar Energy and Sustainable Development, 15 (0), 77-92.


doi:10.51646/jsesd.v15iMME.340