الفهرس 
summaryOnly 14 pages are availabe for public view
 |  | from | 326 |  |  |
| | | from | 326 | | |
Abstract
This thesis describes a new method for the electric load forecasting using artificial
neural networks. The work has been done for both the short term and the long term load
forecasting. A full study has been done on the various variables influencing the electric
load. A detailed study has been done on the weather variables and their effect on
individuals and the electric demand. A novel feature classification technique has been
used for the analysis of the various inputs of the network. The system uses a feedforward
multi-layer perceptron network that is trained using the backpropagation technique.
F or the short term load forecasting the system will be used following two paradigms,
one for the prediction of the weekdays and the other for the prediction of the weekends.
The system produces each hour the forecast of the following twenty-four hours and uses
the last load value for its forecast. The weather variables are fully implemented in the
system. The system is only retrained weekly with the change from weekdays to weekend.
The retraining time is well below the time limit. The adaptivity, retraining frequency and
time horizon emphasizes the applicability of the system.
For the long-term load forecasting, two models are used. One model to forecast the
maximum demand and the other to forecast the energy consumption. The system
forecasts the following ten years. The economic and demographic indices are fully
implemented in the system.
The data used in this work is real data obtained from a major electric utility. The data
covers a large period of time. It has been used without any pre-processing. The system
has been tested extensively. The tests have been done on various weather patterns in
order to make sure of its ability to perform for any characteristics. The results have been
analyzed not only depending on the accuracy but also on their sustainability and the
system requirements to produce them. These requirements, such as data availability, time
and computational requirements are realistic and simple.
The use of neural networks for the electric load forecasting is shown to be superior to
the conventional methods. The obtained accuracy is better than that of the conventional
methods. It also does not suffer from high computational requirements or numerical
instabilities. Furthermore, it combines the capability to include various variables without
affecting the non-stationarity characteristic of the electric load.
This work presents a system for the electric load forecasting. Its performance makes it
a significant step forward towards achieving a complete and accurate knowledge about
the future load. This knowledge will certainly improve the operational and planning
procedures of the power system. The proposed system can be used by any utility for its
load forecasting operation. It is suitable for on-line operation without the need of human
experts.