Title :
Optimization neural network for solving flow problems
Author_Institution :
Istituto di Elettronica, Perugia Univ., Italy
fDate :
9/1/1995 12:00:00 AM
Abstract :
This paper describes a neural network for solving flow problems, which are of interest in many areas of application as in fuel, hydro, and electric power scheduling. The neural network consist of two layers: a hidden layer and an output layer. The hidden units correspond to the nodes of the flow graph. The output units represent the branch variables. The network has a linear order of complexity, it is easily programmable, and it is suited for analog very large scale integration (VLSI) realization. The functionality of the proposed network is illustrated by a simulation example concerning the maximal flow problem
Keywords :
analogue integrated circuits; analogue processing circuits; computational complexity; flow graphs; mathematics computing; neural nets; optimisation; analog very large scale integration realization; flow graph; flow problems; hidden layer; linear order of complexity; maximal flow problem; optimization neural network; output layer; Acoustic distortion; Acoustic scattering; Acoustic testing; Artificial neural networks; Azimuth; Circuits; Interpolation; Neural networks; Sampling methods; Very large scale integration;
Journal_Title :
Neural Networks, IEEE Transactions on
