Next 24-Hours Load Forecasting Using Artificial Neural Network (ANN) for the Western Area of Saudi Arabia

Abstract

Abstract. Load forecasting has become in recent years one of the major areas of research in electrical engineering. Most traditional forecasting models and artificial intelligence neural network techniques have been tried out in this task. Artificial neural networks (ANN) have lately received much attention, and a great number of papers have reported successful experiments and practical tests. This paper presents the development of an ANN-based short-term load forecasting model with improved generalization technique for the Regional Power Control Center of Saudi Electricity Company, Western Operation Area (SEC-WOA). The proposed ANN is trained with weather-related data, special events indexes and historical electric load-related data using the data from the calendar years 2003, to 2007 for training. The models tested for one week at two different seasons, typically, summer and Ramadan seasons, the mean absolute average error for day-ahead load forecasting are found 1.57% and 1.82% respectively.

Intelligent Modelling Techniques of Power Load Forecasting for the Western Area of Saudi Arabia

“…Holy cities of Makkah and Madinah host millions of Muslims in different seasons during the year to perform religious activities. In fact, the religious tourism influences the system load profile [19] . A seasonal ANN structure is also adopted to handle the major contribution of the temperature changes with the four seasons a year, and special events.…”

Efficient encoding of customer class load profiles

“…According to [7]- [10] backpropagation is the most widely used and the most suitable training algorithm for supervised learning of neural networks for our implementation. Training a neural network using backpropagation algorithm takes very long time, which confirms implementation of parallel training methods for neural networks.…”

Optimization of district heating systems based on the demand forecast in the capital region

“…Results on the prediction of the maximal short-term load were presented based on a multilayer neural network, which could be helpful in the electricity distribution [6]. Results on 1-hour predictions were reported where various date types such as holidays, Saturday and Sunday are considered as input elements [7]. In addition to the neural network forecast, predictions based on the moving average line are presented [1,8].…”