首页|Estimates of hydroelectric energy generation in BRICS-T countries using a new hybrid model
Estimates of hydroelectric energy generation in BRICS-T countries using a new hybrid model
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Taylor & Francis
Realistic energy production and consumption projections are needed bynational governments that are developing policies to reduce greenhousegas emissions and ensure energy supply security. In this study, four types ofartificial neural network (ANN) models – including a back propagation (BP)model, ANN-BP, and three Rao algorithm models, namely ANN-Rao_1,ANN_Rao2 and ANN-Rao_3 were developed to determine hydroelectricpower (HEP) generation projections for Brazil, Russia, India, China, SouthAfrica, and Turkey (BRICS-T) countries. Gross domestic product (GDP), population,import, and export data were inputted as independent variables intothe models. Data from the period of 1990‒2014 were used for ANN modeldevelopment. Data from the period of 2015‒2020 were used as referencedata to test the models’ predictive power. According to the error valuescalculated for the training and test sets, the ANN-Rao_3 model predicted HEPgeneration values for BRICS-T countries more accurately than the othermodels. The results obtained from this study predict that the HEP generationvalue of the BRICS-T countries will increase by 28.1% by 2040. According tothe RMSE values obtained for the test datasets, compared to the BP algorithm,the Rao_3 algorithm increased ANN performance by 34.1% for Brazil,24.1% for Russia, 3% for India, 13% for South Africa, and 12.1% for Turkey. Thetotal HEP generation value of the BRICS-T countries in 2040 was projected tobe 2815.69 TWh. Current BRICS-T countries’ HEP investments are not sufficientto achieve their renewable energy targets. In light of this research,relevant policy implications may be derived.
NETL
NSTL
Taylor & Francis
