The use of artificial neural networks to predict the electrical demand
Łukasz Szabłowski , Jarosław Milewski , Jerzy Kuta
Proposed artificial neural network model is used to predict the demand for electric power. Appropriate architecture has been developed that network in terms of number of layers and number of neurons in each layer. Inputs to the model included: daily charge in 1 hour and day of the week, which is related to the load. However, the network received the outputs of the expected demand for electric power for the next day. The network was taught to load the data from the Institute of Thermal Technology and Warsaw University of Central Canteens of the time period from 08.10.2011 to 15.10.2011 and tested on data from a range of 10/16/2011 to 10/23/2011.
|Journal series||Rynek Energii, ISSN 1425-5960|
|Score|| = 9.0, 21-09-2020, ArticleFromJournal|
= 11.0, 21-09-2020, ArticleFromJournal
|Publication indicators||= 5; = 2.0; : 2013 = 0.569; : 2010 = 0 (2)|
|Citation count*||2 (2015-02-26)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.