Forecasting of Photovoltaic Generation Based on Solar Radiation Prediction Models DOI

Jorge Lechón,

Eliana Ormeño-Mejía

2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON), Journal Year: 2023, Volume and Issue: unknown, P. 1 - 6

Published: Dec. 5, 2023

Amidst the pursuit of sustainable energy, photo-voltaic generation plays a crucial role in global energy landscape. The effectiveness harnessing photovoltaic resources significantly relies on accurate measurement horizontal solar irradiation (GHI). However, certain locations, availability suitable sensors for installation is limited. Nevertheless, other meteorological variables, such as temperature, are more easily accessible. These variables can be used prediction models to estimate resource. Thus, this work presents training and validation based method predict GHI, applying 14 models: Thirteen empirical maximum minimum temperatures, along with one machine learning model relative humidity, wind speed, direction. Also, obtained resource forecast daily electrical system. Data from station 40 kW system located Quito, Ecuador, employed. A statistical evaluation was carried out validate forecasted energy. results show that relying solely temperatures did not exhibit strong fits, contrast incorporated parameters during its training. Goodin performs better places where only temperature data available. Likewise, when accessible, Random Forest demonstrates remarkable proficiency predicting available Regarding estimated notable findings were identified, highlighting fundamental within intricate process.

Language: Английский

Neural Networks Forecast Models Comparison for the Solar Energy Generation in Amazon Basin DOI Creative Commons
andre luis ferreira marques, Márcio José Teixeira, Felipe V. de Almeida

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 17915 - 17925

Published: Jan. 1, 2024

Deep learning has grown among the prediction tools used within renewable energy options. Solar belongs to options with lowest atmosphere impact after considering their limitations. In last five years, Brazil seen expansion of wind and solar almost all over country, preserve Amazon rainforest, use helped large small cities towards a greener future. The novelty this research covers Learning data from twelve in state Amazonas forecast irradiation (W.h/m 2 ) 30 days. input came ground stations, as much possible, NASA satellite models, daily time aggregation. types neural networks considered are Long Short-Term Memory (LSTM), Multi-Layer Perceptron (MLP), an LSTM Gated Recurrent Unit (GRU). Among metrics check algorithm's performance, Mean Absolute Percentage Error (MAPE) indicates that values coherent other scenarios energy; boundary conditions were not same, however. MAPE was observed city Labrea GRU.

Language: Английский

Citations

3
Artificial intelligence applications in solar energy DOI Creative Commons
Thanh Tuan Le, Thi Thai Le, Huu Cuong Le

et al.

JOIV International Journal on Informatics Visualization, Journal Year: 2024, Volume and Issue: 8(2), P. 826 - 826

Published: May 31, 2024

Renewable energy research has become significant in the modern period owing to escalating prices of fossil fuels and pressing need reduce greenhouse gas emissions. Solar stands out among these sources due its abundance global accessibility. However, weather-dependent cyclical nature add inherent risks, making effective planning management difficult. Soft computing technologies provide attractive solutions for modeling such systems, while machine learning optimization techniques are gaining popularity solar industry. The current literature highlights growing use soft technologies, emphasizing their potential address difficult challenges systems. To effectively reap benefits, strategies must be seamlessly connected with emerging like Internet Things (IoT), big data analytics, cloud computing. This integration provides a unique opportunity improve scalability, flexibility, efficiency Researchers can synergies create intelligent, linked ecosystems capable real-time production, delivery, consumption. These have transform renewable environment, allowing more resilient sustainable infrastructures. Furthermore, as improve, there is demand trained experts associated cybersecurity problems, assuring integrity security sophisticated may pave road energy-efficient future by working collaboratively using interdisciplinary methodologies.

Language: Английский

Citations

3
Hourly global solar radiation prediction based on seasonal and stochastic feature DOI Creative Commons
You Li, Yafei Wang, Hui Qian

et al.

Heliyon, Journal Year: 2023, Volume and Issue: 9(9), P. e19823 - e19823

Published: Sept. 1, 2023

Accurate and detailed solar radiation data play a crucial role in the simulation of building thermal photovoltaic systems. However, developing highly precise dependable model using cost-effective has proven challenging. This work proposes new attenuation formed by conducting comprehensive analysis existing models gaining insights into radiation's seasonal stochastic properties. Meanwhile, is constructed easily obtainable surface meteorological parameters. The results demonstrate that proposed exhibits good performance terms prediction accuracy. Moreover, majority hourly have been primarily developed for clear-sky conditions. there growing demand estimations can uphold high level accuracy reliability even different weather state. Conversely, validated more than twenty year's encompassing various conditions Japan. It effectively captures nature utilizing turbidity parameters, on cloudy rainy days. Additionally, inclusion interaction variables significantly enhances its interpretability.

Language: Английский

Citations

7
A Hybrid Machine Learning - Numerical Weather Prediction Approach for Day Ahead Solar Irradiance Prediction DOI

A. P. Patil,

Kedar Kulkarni

Published: July 31, 2024

Language: Английский

Citations

0
A Review on the Intersection of Artificial Intelligence on Building Resilient Infrastructure, Promoting Inclusive and Sustainable Industrialization and Fostering Innovation DOI Creative Commons

Mokanmiyo Adedeji Olawale,

Ayomide Abdulbaqi Ayeh,

Faruk Obasanjo Adekola

et al.

INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY, Journal Year: 2023, Volume and Issue: 9(3), P. 44 - 74

Published: Dec. 2, 2023

Artificial Intelligence (AI) has made significant global impacts across various domains. However, it is evident that certain areas have yet to harness the full spectrum of opportunities AI can provide. This review aims investigate transformative effects on diverse sustainable goals, including development resilient infrastructure, promotion inclusivity, and cultivation innovation. By shedding light previously unnoticed challenges within realms industrialization this study unveils a novel perspective potential for an AI-driven industrial innovative world while preserving enhancing efficiency

Language: Английский

Citations

1
Forecasting of Photovoltaic Generation Based on Solar Radiation Prediction Models DOI

Jorge Lechón,

Eliana Ormeño-Mejía

2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON), Journal Year: 2023, Volume and Issue: unknown, P. 1 - 6

Published: Dec. 5, 2023

Amidst the pursuit of sustainable energy, photo-voltaic generation plays a crucial role in global energy landscape. The effectiveness harnessing photovoltaic resources significantly relies on accurate measurement horizontal solar irradiation (GHI). However, certain locations, availability suitable sensors for installation is limited. Nevertheless, other meteorological variables, such as temperature, are more easily accessible. These variables can be used prediction models to estimate resource. Thus, this work presents training and validation based method predict GHI, applying 14 models: Thirteen empirical maximum minimum temperatures, along with one machine learning model relative humidity, wind speed, direction. Also, obtained resource forecast daily electrical system. Data from station 40 kW system located Quito, Ecuador, employed. A statistical evaluation was carried out validate forecasted energy. results show that relying solely temperatures did not exhibit strong fits, contrast incorporated parameters during its training. Goodin performs better places where only temperature data available. Likewise, when accessible, Random Forest demonstrates remarkable proficiency predicting available Regarding estimated notable findings were identified, highlighting fundamental within intricate process.

Language: Английский

Citations

0