Analysis of methods of predicting reactive loads of industrial enterprises
DOI:
https://doi.org/10.31498/2225-6733.30.2015.52735Keywords:
reactive load, modeling, neural networks, statistical methods, the mean value of the load, predicting errorAbstract
The algorithm of the simulation graph of industrial enterprises reactive load at different values of the correlation functions parameters have been developed. The simulated graph has 172 values: 162 are used for training of each of the prediction methods, and the remaining 10 for comparison with the predicted values and for calculation of errors. A two-layer network with back-propagation of a mistake, with seven neurons in the hidden layer, one input and one output were used in predicting with neural networks in Matlab package. The activation function of the first layer is Hyperbolic tangent sigmoid transfer function, and the second one is a linear function. The Lewenberg-Markvart function was selected for training of the model. Predicting by using statistical methods was made by extrapolation. In this paper, predicting based on extrapolation is implemented in the Mathcad program. The problem reduces to determining the value of a parameter outside the region in which the value of this parameter is known. This function is implemented in Mathcad by the command "predict". The last of the studied methods widely used today in industrial enterprises is predicting of the mean value. Its essence lies in finding the arithmetic mean value of the reactive load for the previous day and tuning the compensating devices to the power. The conclusions of the feasibility of each of the methods of the reactive loads predicting for different values of the attenuation coefficient of the correlation function are based on the comparison of the errors of predicting methodsReferences
Ноздренков В.С. Прогнозирование электрических нагрузок промышленных пред-приятий / В.С. Ноздренков, А.Ю. Хатунцев, И.В. Мошенский // Вестник СумДУ. Серия : Технические науки. – Сумы, 2009. – № 2. – С. 135-139.
Сидоров С.Г. Анализ временных рядов как метод построения прогноза потребления электроэнергии / С.Г. Сидоров, А.В. Никологорская // Вестник ИГЭУ. – Иваново, 2010. – Вып. 3. – C. 43-46.
Манусов В.З. Краткосрочное прогнозирование электрической нагрузки на основе нечёткой нейронной сети и её сравнение с другими методами / В.З. Манусов, Е.В. Бирюков // Известия Томского политехнического университета. – Томск, 2006. – № 6, Т. 309. – С. 153-158.
Жежеленко И.В. Методы вероятностного моделирования в расчётах характеристик электрических нагрузок потребителей / И.В. Жежеленко, Ю.Л. Саенко, В.П. Степанов. – М.: Энергоатомиздат, 1990. – 128 с.
Сергиенко А.Б. Цифровая обработка сигналов : учебное пособие / А.Б. Сергиенко. – СПб.: БХВ-Петербург, 2011. – 768 с.
Солонина А.И. Цифровая обработка сигналов. Моделирование в MATLAB / А.И. Солонина, С.М. Арбузов. – СПб.: БХВ-Петербург, 2008. – 816 с.
Хайкин С. Нейронные сети: полный курс / С. Хайкин. – М.: Издательский дом «Вильямс», 2006. – 1104 с.
Медведев В.С. Нейронные сети. MATLAB 6 / В.С. Медведев, В.Г. Потемкин. – М.: ДИАЛОГ-МИФИ, 2001. – 630 с.
Четыркин Е.М. Статистические методы прогнозирования / Е.М. Четыркин. –М.: Статистика, 1977 – 200 с.
Гмурман В.Е. Теория вероятностей и математическая статистика: учебное пособие для ВУЗов / В.Е. Гмурман. – М.: Высшая школа, 2003. – 479 с.
Макаров Е. Инженерные расчёты в Mathcad 15 : учебный курс / Е. Макаров. – СПб.: Питер, 2011. – 400 с.
Downloads
How to Cite
Issue
Section
License
Journal "Reporter of the Priazovskyi State Technical University. Section: Technical sciences" is published under license CC-BY (License "Attribution").This license allows you to distribute, edit, correct and take work as a basis for derivatives, even on a commercial basis with an indication of authorship. It is the most convenient of all the proposed license. Recommended for maximum dissemination and use of licensed materials.
Authors who publish in this journal agree to the following terms:
1. The authors reserve the right to authorship of his work and pass the journal right of first publication of the work under the terms of Creative Commons Attribution License, which allows others to freely distribute the work published with the obligatory reference to the authors of the original work and the first publication of the work in this journal.
2. The authors have the right to enter into separate supplemental agreements relating to the non-exclusive dissemination of works in the form in which it was published in the journal (for example, to place the work in the institution, or to publish a monograph as part of an electronic store), while maintaining links to the first publication of the work in this magazine.