Machine Learning Application in Reservoir Water Level Forecasting for Sustainable Hydropower Generation Strategy

Abstract

The aim of this study is to accurately forecast the changes in water level of a reservoir located in Malaysia with two different scenarios; Scenario 1 (SC1) includes rainfall and water level as input and Scenario 2 (SC2) includes rainfall, water level, and sent out. Different time horizons (one day ahead to seven days) will be investigated to check the accuracy of the proposed models. In this study, four supervised machine learning algorithms for both scenarios were proposed such as Boosted Decision Tree Regression (BDTR), Decision Forest Regression (DFR), Bayesian Linear Regression (BLR) and Neural Network Regression (NNR). Eighty percent of the total data were used for training the datasets while 20% for the dataset used for testing. The models’ performance is evaluated using five statistical indexes; the Correlation Coefficient (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Relative Absolute Error (RAE), and Relative Squared Error (RSE). The findings showed that among the four proposed models, the BLR model outperformed other models with R2 0.998952 (1-day ahead) for SC1 and BDTR for SC2 with R2 0.99992 (1-day ahead). With regards to the uncertainty analysis, 95PPU and d-factors were adopted to measure the uncertainties of the best models (BLR and BDTR). The results showed the value of 95PPU for both models in both scenarios (SC1 and SC2) fall into the range between 80% to 100%. As for the d-factor, all values in SC1 and SC2 fall below one.

Machine learning algorithm as a sustainable tool for dissolved oxygen prediction: a case study of Feitsui Reservoir, Taiwan

“…To test the proposed model's reliability and to determine the model's validity, Taylor’s diagram is recommended by many researchers and is commonly used 19 , 49 . It can be seen from Fig.…”

“…Artificial Neural Network (ANN) methods were used in conjunction with numerical simulation models to boost the simulation results 12 . Recently, ML techniques have been used intensively in modeling complex parameters related to water resources, such as predicting sea-level rise 13 – 15 , rainfall prediction 16 , 17 , reservoir water level prediction 18 , 19 , and streamflow forecasting 11 , 20 , 21 . Inspired by the robust performance of ML in capturing the nonlinearity patterns in most of the engineering systems, different algorithms of ML have been adopted to predict the water quality parameters.…”

AB-Net: A Novel Deep Learning Assisted Framework for Renewable Energy Generation Forecasting

“…Different types of prediction approaches have been presented for the better planning and management of hydropower plants [49]. For instance, Sapitang et al [50] predicted the water level at a hydropower generation plant using the supervised ML approaches of Bayesian linear regression (LR), boosted DT regression, neural network regression, and decision forest regression. Similarly, Dehghani et al [51] presented a promising approach using gray wolf optimization and an adaptive neuro-fuzzy inference system for hydropower generation prediction.…”

Developing machine learning algorithms for meteorological temperature and humidity forecasting at Terengganu state in Malaysia

“…Models based on differential equations are employed in the data-driven approach to detect the optimal inputs-outputs mapping deprived of a comprehensive examination of the fundamental configuration of phenomena process. In many areas, data-driven models have been shown to offer accurate predictions 9 – 11 . However, because most of these models do not attempt to reflect the nonlinear dynamics that are inherent in meteorological phenomena, they may not always perform well and achieve an acceptable level of forecasting accuracy as expected.…”