Estimation of the Daily Production Levels of a Run-of-River Hydropower Plant Using the Artificial Neural Network

Abstract

Renewable energy sources, as well as the studies being conducted regarding these energy sources, are becoming increasingly important for our world. In this manuscript, the daily energy production level of a small (15 MW) run-of-river hydropower plant (RRHPP) was estimated using the artificial neural network (ANN) model. In this context, the model utilized both meteorological data and HPP-related data. The input parameters of the artificial neural network included the daily total precipitation, daily mean temperature, daily mean water vapour pressure, daily mean relative humidity, and the daily mean river water elevation at the hydropower plant, while the only output parameter consisted of the total daily energy production. For the ANN, data from the four years between 2017 and 2020 were used for training purposes, while data from the first eight months of 2021 were used for testing purposes. Ten different ANN networks were tested. A comparison of the ANN data with the real data indicated that the model provided satisfying results. The minimum error rate was 0.13%, the maximum error rate was 9.13%, and the mean error rate was 3.13%. Furthermore, six different algorithms were compared with each other. It was observed that the best results were obtained from the Levenberg-Marquardt algorithm.This study demonstrated that the ANN can estimate the daily energy production of a run-of-river HPP with high accuracy and that this model can potentially contribute to studies investigating the potential of renewable energies.

Artificial Neural Networks-Based Route Selection Model for Multimodal Freight Transport Network During Global Pandemic

“…ANNs are practically employed in solving learning, generalization, specification, identification, classification, association, and optimization problems. With this method, information obtained from the samples is recorded in networks, essentially networks are trained with the data, over time the networks become better at making decisions, recognizing patterns, and producing reliable results in similar situations [32] and also during the COVID-19 pandemic [33]. The reason for using this integrated methodology is its applicability to redirecting alternative multimodal transportation routes in response to changes or fluctuations in fare rates, contracts and weather conditions in freight cases.…”