Short-Term Solar Insolation Forecasting in Isolated Hybrid Power Systems Using Neural Networks
Электронный научный архив УРФУ
Информация об архиве | Просмотр оригинала| Поле | Значение | |
| Заглавие |
Short-Term Solar Insolation Forecasting in Isolated Hybrid Power Systems Using Neural Networks
|
|
| Автор |
Matrenin, P.
Manusov, V. Nazarov, M. Safaraliev, M. Kokin, S. Zicmane, I. Beryozkina, S. |
|
| Тематика |
FORECASTING
ISOLATED HYBRID POWER SYSTEM NEURAL NETWORKS RENEWABLE ENERGY SOURCES SOLAR INSOLATION |
|
| Описание |
Solar energy is an unlimited and sustainable energy source that holds great importance during the global shift towards environmentally friendly energy production. However, integrating solar power into electrical grids is challenging due to significant fluctuations in its generation. This research aims to develop a model for predicting solar radiation levels using a hybrid power system in the Gorno-Badakhshan Autonomous Oblast of Tajikistan. This study determined the optimal hyperparameters of a multilayer perceptron neural network to enhance the accuracy of solar radiation forecasting. These hyperparameters included the number of neurons, learning algorithm, learning rate, and activation functions. Since there are numerous combinations of hyperparameters, the neural network training process needed to be repeated multiple times. Therefore, a control algorithm of the learning process was proposed to identify stagnation or the emergence of erroneous correlations during model training. The results reveal that different seasons require different hyperparameter values, emphasizing the need for the meticulous tuning of machine learning models and the creation of multiple models for varying conditions. The absolute percentage error of the achieved mean for one-hour-ahead forecasting ranges from 0.6% to 1.7%, indicating a high accuracy compared to the current state-of-the-art practices in this field. The error for one-day-ahead forecasting is between 2.6% and 7.2%. © 2023 by the authors.
Ministry of Education and Science of the Russian Federation, Minobrnauka The research funding from the Ministry of Science and Higher Education of the Russian Federation (Ural Federal University Program of Development within the Priority-2030 Program) is gratefully acknowledged. |
|
| Дата |
2024-04-05T16:34:56Z
2024-04-05T16:34:56Z 2023 |
|
| Тип |
Article
Journal article (info:eu-repo/semantics/article) |info:eu-repo/semantics/publishedVersion |
|
| Идентификатор |
Matrenin, P, Manusov, V, Nazarov, M, Safaraliev, M, Kokin, S, Zicmane, I & Beryozkina, S 2023, 'Short-Term Solar Insolation Forecasting in Isolated Hybrid Power Systems Using Neural Networks', Inventions, Том. 8, № 5, 106. https://doi.org/10.3390/inventions8050106
Matrenin, P., Manusov, V., Nazarov, M., Safaraliev, M., Kokin, S., Zicmane, I., & Beryozkina, S. (2023). Short-Term Solar Insolation Forecasting in Isolated Hybrid Power Systems Using Neural Networks. Inventions, 8(5), [106]. https://doi.org/10.3390/inventions8050106 2411-5134 Final All Open Access, Gold https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175001950&doi=10.3390%2finventions8050106&partnerID=40&md5=d5c8178f9fc20e1fc15ab41d4f6e3ba5 https://www.mdpi.com/2411-5134/8/5/106/pdf?version=1692849209 http://elar.urfu.ru/handle/10995/130884 10.3390/inventions8050106 85175001950 001095423200001 |
|
| Язык |
en
|
|
| Права |
Open access (info:eu-repo/semantics/openAccess)
cc-by https://creativecommons.org/licenses/by/4.0/ |
|
| Формат |
application/pdf
|
|
| Издатель |
Multidisciplinary Digital Publishing Institute (MDPI)
|
|
| Источник |
Inventions
Inventions |
|