DocumentCode
3298811
Title
An Algorithm for Unit Commitment Based on Hopfield Neural Network
Author
Gao, Weixin ; Tang, Nan ; Mu, Xiangyang
Author_Institution
Shaanxi Key Lab. of Oil-Drilling Rigs Controlling Tech., Xi´´an Shiyou Univ., Xi´´an
Volume
2
fYear
2008
fDate
18-20 Oct. 2008
Firstpage
286
Lastpage
290
Abstract
This paper presents an algorithm, which is based on a Hopfield neural network, for determining unit commitment. By constructing an appropriate energy function, a single layer Hopfield neural network can solve the problem of assigning output power of generators at any given time. Based on this single layer Hopfield neural network, a multi-layer Hopfield neural network is presented. The multi-layer Hopfield neural network can solve the problem of power system unit commitment. The energy functions of single layer and multi-layer Hopfield neural network and the corresponding algorithm are given in the paper. The restricted conditions of the balance between power supply and demand, maximum and minimum outputs of power plants are considered in the energy function. So is the speed of propulsion and decreasing power of generators. An example shows that the result obtained by Hopfield neural network is somewhat similar to that obtained by genetic algorithm, but the calculation time is much shorter.
Keywords
Hopfield neural nets; genetic algorithms; power distribution economics; power engineering computing; genetic algorithm; multilayer Hopfield neural network; power demand; power supply; power system unit commitment; unit commitment algorithm; Computer networks; Genetic algorithms; Hopfield neural networks; Laboratories; Mathematical model; Optimization methods; Particle swarm optimization; Power generation; Power system planning; Power systems; Hopfield neural network; optimization; planning; power system; unit commitment;
fLanguage
English
Publisher
ieee
Conference_Titel
Natural Computation, 2008. ICNC '08. Fourth International Conference on
Conference_Location
Jinan
Print_ISBN
978-0-7695-3304-9
Type
conf
DOI
10.1109/ICNC.2008.148
Filename
4667002
Link To Document