CASPIAN JOURNAL
MANAGEMENT AND HIGH TECHNOLOGIES
Neuro-fuzzy model short-term forecasting of energy consumption
 |
Read | Al-Gunaid Mokhammed Neuro-fuzzy model short-term forecasting of energy consumption // Caspian journal : management and high technologies. — 2013. — №2. — pp. 47-56. |
Al-Gunaid Mokhammed - post-graduate student, Volgograd State Technical University, 28 Lenin av., Volgograd, 400131, Russian Federation, mohammadalgunaid@gmail.com
This research aims to develop a mathematical model of fuzzy neural network (FNN). FNN structure presented and justified and it allows accurate prediction of electricity consumption in the face of uncertainty. This article presents the solution of the problem of short-term forecasting of energy consumption, taking into account a number of seasonal patterns in the data, the calendar works, high-frequency data collection, low expert support in the construction of models and the need for the interpretability of results. It shows the implementation of the method, including the consistent application of algorithms of fuzzy variables based on time series, knowledge synthesis the synthesis of a fuzzy neural network based on fuzzy knowledge bases, training FNN. We see the solution is in the fuzzy neural network learning algorithm. The high efficiency of the proposed solutions during experimental results was confirmed.
Key words: short-term forecasting,energy consumption,seasonal time series,fuzzy neural network,knowledge bases synthesis,energy saving,identification,mathematical model,association rules,learning fuzzy neural network