Probabilistic day-ahead prediction of PV generation. A comparative analysis of forecasting methodologies and of the factors influencing accuracy

Solar Energy, Journal Year: 2024, Volume and Issue: 271, P. 112422 - 112422

Published: March 1, 2024

Language: Английский

---

Prediction of Anti-Corrosion performance of new triazole derivatives via Machine learning

Computational and Theoretical Chemistry, Journal Year: 2024, Volume and Issue: 1236, P. 114599 - 114599

Published: April 8, 2024

Language: Английский

---

Data-driven investigation to model the corrosion inhibition efficiency of Pyrimidine-Pyrazole hybrid corrosion inhibitors

Computational and Theoretical Chemistry, Journal Year: 2023, Volume and Issue: 1229, P. 114307 - 114307

Published: Sept. 3, 2023

Language: Английский

---

Short-term PV power forecast methodology based on multi-scale fluctuation characteristics extraction

Renewable Energy, Journal Year: 2023, Volume and Issue: 208, P. 141 - 151

Published: March 15, 2023

Language: Английский

---

Improving Solar PV Prediction Performance with RF-CatBoost Ensemble: A Robust and Complementary Approach

Renewable energy focus, Journal Year: 2023, Volume and Issue: 46, P. 207 - 221

Published: June 28, 2023

Language: Английский

---

Effect of particle size on second law of thermodynamics analysis of Al2O3 nanofluid: Application of XGBoost and gradient boosting regression for prognostic analysis

International Journal of Thermal Sciences, Journal Year: 2023, Volume and Issue: 197, P. 108825 - 108825

Published: Dec. 12, 2023

Language: Английский

---

A complementary fused method using GRU and XGBoost models for long-term solar energy hourly forecasting

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 254, P. 124286 - 124286

Published: June 5, 2024

Language: Английский

---

A predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regions

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101734 - 101734

Published: Jan. 8, 2024

Growth and expansion in construction has increased recently especially coastal areas. In Alexandria, Egypt, mega projects such as El-Max Port Project (Middle Port), of ABU QIR (EG AKI), hotels, restaurants were spread along the lines, thus, it will need a high electrical energy. Although, great economic benefits projects, have some negative impacts, overloading on present grid. According to recommendations COP 27, Egypt is one countries targeting increase dependency green energy minimize production greenhouse gases. This study interested wave renewable source Using machine learning model that predicts height period through year 2030 three separate places (Alamein, Mersa-Matruh), this try estimate future amount Egypt's coast. Hourly measurements significant mean for 1979–2023 been utilized this. An extractor can also be built Overtopping Breakwater Energy Conversion (OBREC) order use fill hole electric The was developed using hourly data from buoys, result, results root square error (RMSE) 0.52. taken, power, system efficiency at each place then fully determined mathematical locations. area coast Alamein had highest extraction rates, followed by Alexandria Mersa-Matruh order. indicate yearly power generation Alamein, 25287 MWhr, 14713 4865 respectively.

Language: Английский

---

Harnessing AI for solar energy: Emergence of transformer models

Applied Energy, Journal Year: 2024, Volume and Issue: 369, P. 123541 - 123541

Published: June 1, 2024

Language: Английский

---

Design and Development of a Short-Term Photovoltaic Power Output Forecasting Method Based on Random Forest, Deep Neural Network and LSTM Using Readily Available Weather Features

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 41578 - 41595

Published: Jan. 1, 2023

Renewable energy sources (RES) are an essential part of building a more sustainable future, with higher diversity clean energy, reduced emissions and less dependence on finite fossil fuels such as coal, oil natural gas. The advancements in the renewable domain bring hardware efficiency lower costs, which improves likelihood wider RES adoption. However, integrating renewables photovoltaic (PV) systems current grid is still major challenge. main reason volatile, intermittent nature RES, increases complexity management maintenance. Having access to accurate PV power output forecasting could reduce number supply disruptions, improve planning available reserve capacities decrease operational costs. In this context, paper explores evaluates three Artificial Intelligence (AI) methods - random forest (RF), deep neural network (DNN) long short-term memory (LSTM), applied for task forecasting. Following statistical approach, selected models trained weather data collected Berlin, Germany. assembled set contains predominantly broadly accessible features, makes proposed approach cost efficient easily applicable even geographic locations without specialized or hard-to-obtain input features. performance achieved by two algorithms indicates that RF DNN able generate solar forecasts also handle sudden changes shifts output.

Language: Английский

---