Adaptive Evolutionary Programming with Neural Network for Transient Stability Constrained Optimal Power Flow

Abstract

An adaptive evolutionary programming (AEP) with a neural network is presented to solve transient stability con- strained optimal power flow (TSCOPF). The AEP adjusts its population size automatically during an optimization process to obtain the TSCOPF solution. The artificial neural network is embedded into AEP to reduce the computational load caused by transient stability constraints. The fuel cost minimization is se- lected as the objective function of TSCOPF. The proposed me- thod is tested on the IEEE 30-bus system with two types of the fuel cost functions, i.e. the conventional quadratic function and the quadratic function superimposed by sine component to model the cost curve without and with valve-point loading effects re- spectively. The numerical examples show that AEP is more effec- tive than conventional EP in searching the global solution, and when the neural network is incorporated into AEP, it can signifi- cantly enhance the computational speed. A study of the architec- ture of the neural network is also conducted and discussed.