|
advertisement |
|
|
|
|
|
|
Industrial Automatic Control Systems and Controllers Annotation << Back
On the Assessment of the Accuracy of Forecasting of Dynamical Systems Method of Constructing Approximating Functions |
A.Yu. Ermakova
The paper continues the study of the method of predicting the state of dynamical system based on the construction of approximating functions, started earlier. In addition to the previously proposed algorithm for the selection of basic functions, we consider the condition under which the value of the predicted values does not exceed the specifi ed limit. Under these conditions, and within the framework of the initial dynamical system model, as some random process, theoretical estimates of the probability of the variation distance between the predicted values of the original system and its actual values are obtained. Theoretical estimates of the General form are specifi ed for the cases when the initial dynamical system can be approximate with sufficient accuracy by the normal distribution and Poisson distribution. As an example of the approximation of the state of the dynamic system by normal distribution, the data on the rate of purchase by Savings bank of US dollars in the period from 01.01.2017 to 31.03.2017 are considered. To test the hypothesis of correspondence to the normal distribution, Pearson’s criterion is constructed.
Keywords: dynamical system; forecast model; approximating function; variation distance stochastic.
Contacts: E-mail: a.alla1105@mail.ru
Pp. 36-42. |
|
|
|
Last news:
Выставки по автоматизации и электронике «ПТА-Урал 2018» и «Электроника-Урал 2018» состоятся в Екатеринбурге Открыта электронная регистрация на выставку Дефектоскопия / NDT St. Petersburg Открыта регистрация на 9-ю Международную научно-практическую конференцию «Строительство и ремонт скважин — 2018» ExpoElectronica и ElectronTechExpo 2018: рост площади экспозиции на 19% и новые формы контент-программы Тематика и состав экспозиции РЭП на выставке "ChipEXPO - 2018" |