Artificial neural networks approaches for predicting the potential for hydropower generation: a case study for Amazon region

Lopes, Marcio N.G.; Rocha, Brígida Ramati Pereira da; Vieira, Alen Costa; Sá, José Alberto Silva de; Rolim, Pedro Alberto Moura; Silva, Arilson Galdino da

doi:10.3233/jifs-181604

Cited by 27 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Using Adam optimizer to train the models at different calibrations, error rates from RNN and LSTM were higher (i.e., RMSE ranged from 14 to 20), compared with GMDH-type ANN (RMSE of 0.09). In line with our observations, many studies [ 24 , 25 , 34 , 35 ] have also demonstrated the superiority of GMDH-type ANN over both RNN and LSTM. In addition, we observed that RNN and LSTM algorithms might be less suitable because of the few data points available for this study, coupled with the problems of gradient vanishing and gradient explosion (i.e., accumulation of large error gradients leading to unstable models).…”

Section: Discussionsupporting

confidence: 91%

“…GMDH-type ANN was purposefully selected from the class of deep learning algorithms because of its robustness against incorrect, noisy, and small dataset [ 33 ]. Also, recent studies in other disciplines have demonstrated its superiority over RNN and LSTM [ 24 , 25 , 34 , 35 ]. P -value < 0.05 and 95% confidence intervals (CI) were used to assess statistical significance.…”

Section: Methodsmentioning

confidence: 99%

“…Their study showed more accurate results with GMDH-type ANN. Also, other studies (outside of medicine and population health) have demonstrated the superiority of GMDH-type ANN compared with adaptive neuro fuzzy inference system (ANFIS) and long short-term memory (LSTM) [ 24 , 25 ]. On this basis, our study focuses on generating accurate estimates and observing the patterns of U5MR for Nigeria during the SDG-implementation era.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Time series prediction of under-five mortality rates for Nigeria: comparative analysis of artificial neural networks, Holt-Winters exponential smoothing and autoregressive integrated moving average models

Adeyinka

Muhajarine

2020

BMC Med Res Methodol

View full text Add to dashboard Cite

Background Accurate forecasting model for under-five mortality rate (U5MR) is essential for policy actions and planning. While studies have used traditional time series modeling techniques (e.g., autoregressive integrated moving average (ARIMA) and Holt-Winters smoothing exponential methods), their appropriateness to predict noisy and non-linear data (such as childhood mortality) has been debated. The objective of this study was to model long-term U5MR with group method of data handling (GMDH)-type artificial neural network (ANN), and compare the forecasts with the commonly used conventional statistical methods—ARIMA regression and Holt-Winters exponential smoothing models. Methods The historical dataset of annual U5MR in Nigeria from 1964 to 2017 was obtained from the official website of World Bank. The optimal models for each forecasting methods were used for forecasting mortality rates to 2030 (ending of Sustainable Development Goal era). The predictive performances of the three methods were evaluated, based on root mean squared errors (RMSE), root mean absolute error (RMAE) and modified Nash-Sutcliffe efficiency (NSE) coefficient. Statistically significant differences in loss function between forecasts of GMDH-type ANN model compared to each of the ARIMA and Holt-Winters models were assessed with Diebold-Mariano (DM) test and Deming regression. Results The modified NSE coefficient was slightly lower for Holt-Winters methods (96.7%), compared to GMDH-type ANN (99.8%) and ARIMA (99.6%). The RMSE of GMDH-type ANN (0.09) was lower than ARIMA (0.23) and Holt-Winters (2.87). Similarly, RMAE was lowest for GMDH-type ANN (0.25), compared with ARIMA (0.41) and Holt-Winters (1.20). From the DM test, the mean absolute error (MAE) was significantly lower for GMDH-type ANN, compared with ARIMA (difference = 0.11, p-value = 0.0003), and Holt-Winters model (difference = 0.62, p-value< 0.001). Based on the intercepts from Deming regression, the predictions from GMDH-type ANN were more accurate (β0 = 0.004 ± standard error: 0.06; 95% confidence interval: − 0.113 to 0.122). Conclusions GMDH-type neural network performed better in predicting and forecasting of under-five mortality rates for Nigeria, compared to the ARIMA and Holt-Winters models. Therefore, GMDH-type ANN might be more suitable for data with non-linear or unknown distribution, such as childhood mortality. GMDH-type ANN increases forecasting accuracy of childhood mortalities in order to inform policy actions in Nigeria.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Time series prediction of under-five mortality rates for Nigeria: comparative analysis of artificial neural networks, Holt-Winters exponential smoothing and autoregressive integrated moving average models

Adeyinka

Muhajarine

2020

BMC Med Res Methodol

View full text Add to dashboard Cite

show abstract

“…Following the success of neural networks in many areas [9,10], the departing hypothesis of this paper is that ANN models can better capture the dynamics of hydroelectric production and, therefore, provide better results in our use case-even though the number of observations is not very large. In the literature, there are a few contributions studying hydroelectric production in countries such as China, Serbia, and Brazil [5,11,12]. Still, there are no similar studies in the literature applying recurrent neural networks and focused on a medium-size region during a large period in which the installed capacity has evolved, as is the case in Ecuador.…”

Section: Introductionmentioning

confidence: 99%

Hydropower production prediction using artificial neural networks: an Ecuadorian application case

Barzola-Monteses

Gómez‐Romero

Espinoza‐Andaluz

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

Hydropower is among the most efficient technologies to produce renewable electrical energy. Hydropower systems present multiple advantages since they provide sustainable and controllable energy. However, hydropower plants’ effectiveness is affected by multiple factors such as river/reservoir inflows, temperature, electricity price, among others. The mentioned factors make the prediction and recommendation of a station’s operational output a difficult challenge. Therefore, reliable and accurate energy production forecasts are vital and of great importance for capacity planning, scheduling, and power systems operation. This research aims to develop and apply artificial neural network (ANN) models to predict hydroelectric production in Ecuador’s short and medium term, considering historical data such as hydropower production and precipitations. For this purpose, two scenarios based on the prediction horizon have been considered, i.e., one-step and multi-step forecasted problems. Sixteen ANN structures based on multilayer perceptron (MLP), long short-term memory (LSTM), and sequence-to-sequence (seq2seq) LSTM were designed. More than 3000 models were configured, trained, and validated using a grid search algorithm based on hyperparameters. The results show that the MLP univariate and differentiated model of one-step scenario outperforms the other architectures analyzed in both scenarios. The obtained model can be an important tool for energy planning and decision-making for sustainable hydropower production.

show abstract

“…Based on the correlation values between the observed and predicted energies, Abdulkadir et al [7] justified the use of neural network approaches in modelling the hydropower generation as a function of reservoir variables at two reservoirs along the River Niger in Nigeria. Developing predictive models of the hydropower generation in the Amazon, Lopes et al [8] presented a comparative analysis between polynomial and ANNs using rainfall as the only input. Using three algorithms, group method of data handling (GMDH), ANN with Levenberg-Marquardt (ANN-LM), and ANN with Bayesian regulation (ANN-BR), it was shown that GMDH is the most appropriate algorithm to optimize the model result because of its adroitness in selecting the variables at the model entry layer and that ANN-LM algorithm failed to live up to expectations due to largely dispersed data and less accuracy.…”

Section: Introductionmentioning

confidence: 99%

Regression-Based Prediction of Power Generation at Samanalawewa Hydropower Plant in Sri Lanka Using Machine Learning

Ekanayake

Wickramasinghe

Jayasinghe

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper presents the development of models for the prediction of power generation at the Samanalawewa hydropower plant, which is one of the major power stations in Sri Lanka. Four regression-based machine learning and statistical techniques were applied to develop the prediction models. Rainfall data at six locations in the catchment area of the Samanalawewa reservoir from 1993 to 2019 were used as the main input variables. The minimum and maximum temperature and evaporation at the reservoir site were also incorporated. The collinearities between the variables were investigated in terms of Pearson’s and Spearman’s correlation coefficients. It was found that rainfall at one location is less impactful on power generation, while that at other locations are highly correlated with each other. Prediction models based on monthly and quarterly data were developed, and their performance was evaluated in terms of the correlation coefficient (R), mean absolute percentage error (MAPE), ratio of the root mean square error (RMSE) to the standard deviation of measured data (RSR), BIAS, and the Nash number. Of the Gaussian process regression (GPR), support vector regression (SVR), multiple linear regression (MLR), and power regression (PR), the machine learning techniques (GPR and SVR) produced the comparably accurate prediction models. Being the most accurate prediction model, the GPR produced the best correlation coefficient closer to 1 with a very less error. This model could be used in predicting the hydropower generation at the Samanalawewa power station using the rainfall forecast.

show abstract

Artificial neural networks approaches for predicting the potential for hydropower generation: a case study for Amazon region

Cited by 27 publications

References 35 publications

Time series prediction of under-five mortality rates for Nigeria: comparative analysis of artificial neural networks, Holt-Winters exponential smoothing and autoregressive integrated moving average models

Time series prediction of under-five mortality rates for Nigeria: comparative analysis of artificial neural networks, Holt-Winters exponential smoothing and autoregressive integrated moving average models

Hydropower production prediction using artificial neural networks: an Ecuadorian application case

Regression-Based Prediction of Power Generation at Samanalawewa Hydropower Plant in Sri Lanka Using Machine Learning

Contact Info

Product

Resources

About