首页|Findings from Federal University Santa Catarina Provide New Insights into Machin e Learning (Enhancing Hydroelectric Inflow Prediction In the Brazilian Power Sys tem: Comparative Analysis of Machine Learning Models and Hyperparameter Optimiza tion ...)
Findings from Federal University Santa Catarina Provide New Insights into Machin e Learning (Enhancing Hydroelectric Inflow Prediction In the Brazilian Power Sys tem: Comparative Analysis of Machine Learning Models and Hyperparameter Optimiza tion ...)
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
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Data detailed on Machine Learning have been presented. According to news reporting from Florianopolis, Brazil, by News Rx journalists, research stated, “Electricity generation in Brazil heavily depen ds on hydroelectric power, making it vulnerable to fluctuations due to its relia nce on weather patterns. Accurately forecasting water inflow into hydroelectric plants is vital for the National Electric System Operator to make decisions rega rding the monthly scheduling and operation of the power system.” The news correspondents obtained a quote from the research from Federal Universi ty Santa Catarina, “In this paper, an evaluation of predicted flows for a 14 -da y horizon are evaluated for the Tucuruihydroelectric plant, located in the Tocan tins river in the North of Brazil. The temporal fusion transformer (TFT), long s hort -term memory (LSTM), and temporal convolutional networks (TCN) are compared . The findings demonstrate that the TFT is a more suitable alternative than LSTM and TCN models for predicting inflows for the next 14 days. The TFT model is hy pertuned by Optuna to achieve an optimized structure (hTFT). The h-TFT had a mea n absolute percentage error of 13.1 and a Nash-Sutcliffe of 0.96, outperforming its initial version and even the bidirectional LSTM model in benchmarking.”
FlorianopolisBrazilSouth AmericaCy borgsEmerging TechnologiesMachine LearningFederal University Santa Catarin a
NETL
NSTL
