Novel machine learning approach for solar photovoltaic energy output forecast using extra-terrestrial solar irradiance

Frederiksen, Cornelia A. Fjelkestam; Cai, Zuansi

doi:10.1016/j.apenergy.2021.118152

Cited by 20 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two research gaps are recognized in this section. The first is the lack of comparative studies on DL-based GHI forecasting models' performance with and without exogenous inputs, as what has been carried out in the literature with statistical models [12][13][14][15] and traditional ML models [16][17][18][19][20]. The second is the dearth of research on the effect of aerosol measurements, as one of the exogenous inputs, on ML-based GHI forecasting models' performance, as what has been done with physical and statistical GHI forecasting models [25][26][27][28][29][30].…”

Section: Research Gapmentioning

confidence: 99%

The Effect of Using Aerosol Variables on the Performance of Deep Learning-based GHI Forecasting Models

Alkhayat,

Hamid Hasan,

Mehmood

2024

Preprint

View full text Add to dashboard Cite

Solar energy adoption worldwide has expanded exponentially due to a surge in international interest in producing clean energy and the declining cost of solar power plants and their technology. It is anticipated that by 2050, solar will have surpassed fossil fuels to become the primary source of energy. However, one of the main challenges associated with solar energy production is the instability of photovoltaic (PV) power generation because of weather changes. Short-term forecasting of the power output of photovoltaic systems is essential for efficient management of the power grid and energy markets. This paper aims to evaluate the ability of deep learning (DL) models to provide accurate forecasting of hourly global horizontal irradiance (GHI) using different sets of features, including weather and aerosol variables along with solar radiation components. The results show that the best forecast skills are achieved by the long short-term memory autoencoder (LSTM-AE) model.

show abstract

Section: Research Gapmentioning

confidence: 99%

The Effect of Using Aerosol Variables on the Performance of Deep Learning-based GHI Forecasting Models

Alkhayat,

Hamid Hasan,

Mehmood

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Thus, to balance the supply and demand of the electricity system, power grid systems need to take more action to curtail renewable solar energy generation. Correspondingly, despite many countries struggling to meet renewable solar energy generation and carbon emission targets, electricity generated from renewables is still being wasted (Cornelia et al, 2022). The best mitigation strategy would be the use of forecasting techniques to anticipate the variations in the solar energy inputs (Caldas et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…Various models have been used for solar photovoltaic energy output forecasting (Cornelia et al, 2022). The models are commonly divided into empirical methods, physical models, and statistical approaches (Ahmed et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Artificial neural network modeling of solar photovoltaic panel energy output

Zeng

2024

10.5267/j.jfs

View full text Add to dashboard Cite

Solar panel energy output is an essential parameter for the design and operation of renewable energy systems. Previously, little was known about the precise relationship between the energy outputs of solar panels with various meteorological, radiometric, and weather conditions in the southern California region. Without precise modeling or prediction systems, solar energy can potentially be wasted due to grid energy fluctuation. Thus, it is intended to use an artificial neural network (ANN) to develop solar panel energy output prediction model with a high degree of accuracy. A self-developed feedforward ANN model utilizing the Rectified linear unit (ReLu) activation function was used in the present study. Meteorological, weather, and sun irradiation data collected throughout the last year from a residential location have been used to train the models. The model’s performance was identified based on the minimum mean absolute error (MAE) and root mean square error (RMSE) and maximum linear correlation coefficient (R2). Further, the present self-developed ANN model was consistent with other solar energy experimental results and theoretical analysis. The developed ANN model using the Python programming language achieved a high R2 of more than 85% which ascertains the accuracy and suitability of the model to predict the daily solar energy output in local southern California area. This ANN modeling approach can be extended to many other applications such as SCORE, commercial, and residential building design.

show abstract

A comparative study of LSTM-ED architectures in forecasting day-ahead solar photovoltaic energy using Weather Data

Ekinci

2024

Computing

View full text Add to dashboard Cite

Solar photovoltaic (PV) energy, with its clean, local, and renewable features, is an effective complement to traditional energy sources today. However, the photovoltaic power system is highly weather-dependent and therefore has unstable and intermittent characteristics. Despite the negative impact of these features on solar sources, the increase in worldwide installed PV capacity has made solar energy prediction an important research topic. This study compares three encoder-decoder (ED) networks for day-ahead solar PV energy prediction: Long Short-Term Memory ED (LSTM-ED), Convolutional LSTM ED (Conv-LSTM-ED), and Convolutional Neural Network and LSTM ED (CNN-LSTM-ED). The models are tested using 1741-day-long datasets from 26 PV panels in Istanbul, Turkey, considering both power and energy output of the panels and meteorological features. The results show that the Conv-LSTM-ED with 50 iterations is the most successful model, achieving an average prediction score of up to 0.88 over R-square (R2). Evaluation of the iteration counts’ effect reveals that the Conv-LSTM-ED with 50 iterations also yields the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values, confirming its success. In addition, the fitness and effectiveness of the models are evaluated, with the Conv-LSTM-ED achieving the lowest Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) values for each iteration. The findings of this work can help researchers build the best data-driven methods for forecasting PV solar energy based on PV features and meteorological features.

show abstract

Novel machine learning approach for solar photovoltaic energy output forecast using extra-terrestrial solar irradiance

Cited by 20 publications

References 14 publications

The Effect of Using Aerosol Variables on the Performance of Deep Learning-based GHI Forecasting Models

The Effect of Using Aerosol Variables on the Performance of Deep Learning-based GHI Forecasting Models

Artificial neural network modeling of solar photovoltaic panel energy output

A comparative study of LSTM-ED architectures in forecasting day-ahead solar photovoltaic energy using Weather Data

Contact Info

Product

Resources

About