The method and programme complicated implementation for power consumption restoration scheme search in networks based on network count algorithm processing and artificial neural networks (ANN) are proposed and justified. Both algorithms work in a competitive mode, smoothing out the flaws of each method separately. Theoretical proofs are made for difficult ideas, such as the use of the generalised error vector for ANN self-training and solution stability. The 'advisor of the distributive network dispatcher' software complex was tested on a distribution network of 201 buses, 7 sources, and 227 lines and produced positive results.
Author(S) Details
M. Uspensky
ISE& EPN Komi SC UrO RAN, Corp. VYMPELCOM, Syktyvkar, Russia
I. Kyzrodev
ISE& EPN Komi SC UrO RAN, Corp. VYMPELCOM, Syktyvkar, Russia.
View Book:- https://stm.bookpi.org/IST-V2/article/view/5426
No comments:
Post a Comment