الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 166 |  |  |
| | | from | 166 | | |
Abstract
Is the main objective of this work. it is required to minimize the generation the optimal economic operation of thermal power system cost of each unit in a thermal power system over a specific period of time, taking into consideration the equality constraints.
A screening of different optimization methods which used to solve the economic load dispatch problem with and without transmission losses is considered. A sample of thermal power system is built which consists of 5-generating units. A lagrangian multiplier method is used to solve this model with and without transmission losses. The suggested modified lagranian method used to solve this model when neglecting the transmission losses.
The artificial neural network is also used for this study and two models of a neural networks are used to minimize the cost of generation of this system. The first model is the back propagation algorithm which is used with neglecting the transmission losses. The second model is the hopfield model which is used considering the transmission losses.
The results obtained by using the lagrangian method and the suggested modified lagrangian method are compared with the results obtained by using the artificial neural networks techniques.