Real power transfer capability calculations using multi-layer feed-forward neural networks

Abstract

This paper proposes a neural network solution methodology for the problem of real power transfer capability calculations. Based on the optimal power flow formulation of the problem, the inputs for the neural network are generator status, line status and load status and the output is the transfer capability. The Quickprop algorithm is used in the paper to train the neural network. A case study of IEEE 30-bus system is presented demonstrating the feasibility of this approach. The new method will be useful for reliability assessment in the new utility environment.

Load Modelling in studies of Available Transfer Capability in Power System Networks

“…But in DC power flows calculations are based on approximations, much attention has been gained by AC power flows [2]. Security Constrained Optimal Power Flow (SCOPF) method: This method solves based on interior point approach, two-level approaches and the TTC can be calculated [3][4]. Continuation Power Flow (CPF) method: The implementation of this mathematically complicated method involves predictor, parameterization, corrector and step-size control as discussed by Chiang [5], etc.…”

Transmission Line Loadability Improvement Using Facts Device

“…There are several methods for transfer capability calculations [1,7,11]. These methods mostly used are continuation power flow (CPF) method, optimal power flow (OPF) method and repetitive power flow (RPF) method, ANN based methods etc.…”

Development of Hybrid Learning Machine with Complex Domain Neurocomputing

“…Moreover, the traditional neural network employs real back propagation (ŘBP) algorithm for learning which has foremost limitations of slow convergence and getting stuck into local minima. To surmount these limitations, some variations in basic error propagation procedure were given like addition of momentum term [10], modified error function [11] and Quick Prop [12]. But none of these variations was capable to make significant improvement in convergence rate.…”