Comparative optimization of global solar radiation forecasting using machine learning and time series models

Belmahdi, Brahim; Louzazni, Mohamed; Bouardi, Abdelmajid El

doi:10.1007/s11356-021-16760-8

Cited by 26 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results agree with Kuhe, Achirgbenda, and Agada [16,25], as the MAPE of their FFNN model was 5.67%, and our models' MAPEs, for most of the cities, range from 3.37% to 8.08%, except for Peshawar and Lahore. The results of Brahim Belmahdi, Mohamed Louzazni, and Abdelmajid El Bouardi [17] were more accurate than ours, as their model's MAPE was 1.80%. ANN results are dependent on data correlation.…”

Section: Resultscontrasting

confidence: 39%

Evaluation of Artificial Neural Networks with Satellite Data Inputs for Daily, Monthly, and Yearly Solar Irradiation Prediction for Pakistan

et al. 2022

View full text Add to dashboard Cite

Solar irradiation is the most critical parameter to consider when designing solar energy systems. The high cost and difficulty of measuring solar irradiation makes it impractical in every location. This study’s primary objective was to develop an artificial neural network (ANN) model for global horizontal irradiation (GHI) prediction using satellite data inputs. Three types of ANN, namely, the feed forward neural network (FFNN), cascaded forward neural network (CFNN), and Elman neural network (EMNN), were tested. The findings revealed that altitude, relative humidity, and satellite GHI are the most effective parameters, as they are present in all the best-performing models. The best model for daily GHI prediction was FFNN, which decreased daily MAPE, RMSE, and MBE by 25.4 %, 0.11 kWh/m2/d, and 0.01 kWh/m2/d. The FFNN daily MAPE, RMSE, and MBE values were 7.83%, 0.49 kWh/m2/d, and 0.01 kWh/m2/d. The EMNN performed best for monthly and annual prediction, reducing monthly MAPE, RMSE, and MBE by 50.62%, 0.13 kWh/m2/d, and 0.13 kWh/m2/d, while the reduction for yearly was 91.6%, 0.11 kWh/m2/d, 0.2 kWh/m2/d. The EMNN monthly MAPE, RMSE, and MBE values were 3.36%, 0.16 kWh/m2/d, and 0.16 kWh/m2/d, while the yearly values were 0.47%, 0.18 kWh/m2/d, and 0.004 kWh/m2/d.

show abstract

Section: Resultscontrasting

confidence: 39%

Evaluation of Artificial Neural Networks with Satellite Data Inputs for Daily, Monthly, and Yearly Solar Irradiation Prediction for Pakistan

et al. 2022

View full text Add to dashboard Cite

show abstract

“… [ 122 ] Tetouan in Morocco ARIMA, FFNN, and k-NN Top of atmosphere radiation, clearness index, maximum, average, delta, and ratio temperature Daily global solar radiation January 1, 2013, to December 31, 2015 MAPE, RMSE, MBE, NRMSE, Ts and σ FFNN (6 × 10 × 1) gave better results than those of time series, and k-NN model with very low error magnitudes. [ 123 ] …”

Section: Literature Reviewmentioning

confidence: 99%

A state of art review on estimation of solar radiation with various models

Gürel¹,

Ağbulut²,

Bakır³

et al. 2023

Heliyon

View full text Add to dashboard Cite

“…Also, accurate forecasts support the safe operation of the grid and allow maximum access to solar energy. To date, solar radiation forecasting based on various methods such as physical model (Caldas and Alonso-Suárez 2019 ; Kakimoto et al 2019 ; Marzouq et al 2020 ), statistical approach (Scolari et al 2018 ; Van Der Meer et al 2018 ; Louzazni et al 2020 ), data mining-based solutions such as artificial neural network (ANN) (Khan et al 2020 ; Wang et al 2020a, b ; Zambrano and Giraldo 2020 ), machine learning (Prasad et al 2019 ; Deo et al 2019 ; Yagli et al 2019 ; Feng et al 2019 ; Belmahdi et al 2022 ), and deep learning (Wang et al 2019b ; Khodayar et al 2020 ; Wen et al 2021 ; Abdel-Nasser et al 2021 ; Liu et al 2022 ) techniques has been investigated in various studies.…”

Section: Introductionmentioning

confidence: 99%

“…The developed algorithm performs the forecasting process in three steps including feature extraction, determining the best features, and finally forecasting the monthly solar radiation. Belmahdi et al ( 2022 ) provide a complete assessment of the machine learning and time series methods used for solar radiation forecasting. In Yagli et al ( 2019 ), the hourly solar radiation forecasting for 7 locations and 5 climatic zones in the continental United States has been done using 68 machine learning algorithms in a comparative approach.…”

Section: Introductionmentioning

confidence: 99%

Generalized global solar radiation forecasting model via cyber-secure deep federated learning

Moradzadeh,

Moayyed,

Mohammadi-Ivatloo

et al. 2023

Environ Sci Pollut Res

View full text Add to dashboard Cite

Recently, the increasing prevalence of solar energy in power and energy systems around the world has dramatically increased the importance of accurately predicting solar irradiance. However, the lack of access to data in many regions and the privacy concerns that can arise when collecting and transmitting data from distributed points to a central server pose challenges to current predictive techniques. This study proposes a global solar radiation forecasting approach based on federated learning (FL) and convolutional neural network (CNN). In addition to maintaining input data privacy, the proposed procedure can also be used as a global supermodel. In this paper, data related to eight regions of Iran with different climatic features are considered as CNN input for network training in each client. To test the effectiveness of the global supermodel, data related to three new regions of Iran named Abadeh, Jarqavieh, and Arak are used. It can be seen that the global forecasting supermodel was able to forecast solar radiation for Abadeh, Jarqavieh, and Arak regions with 95%, 92%, and 90% accuracy coefficients, respectively. Finally, in a comparative scenario, various conventional machine learning and deep learning models are employed to forecast solar radiation in each of the study regions. The results of the above approaches are compared and evaluated with the results of the proposed FL-based method. The results show that, since no training data were available from regions of Abadeh, Jarqavieh, and Arak, the conventional methods were not able to forecast solar radiation in these regions. This evaluation confirms the high ability of the presented FL approach to make acceptable predictions while preserving privacy and eliminating model reliance on training data.

show abstract

Comparative optimization of global solar radiation forecasting using machine learning and time series models

Cited by 26 publications

References 43 publications

Evaluation of Artificial Neural Networks with Satellite Data Inputs for Daily, Monthly, and Yearly Solar Irradiation Prediction for Pakistan

Evaluation of Artificial Neural Networks with Satellite Data Inputs for Daily, Monthly, and Yearly Solar Irradiation Prediction for Pakistan

A state of art review on estimation of solar radiation with various models

Generalized global solar radiation forecasting model via cyber-secure deep federated learning

Contact Info

Product

Resources

About