| Title |
Next day electric load forecasting using Artificial Neural Networks |
|
Authors |
Velasco, Lemuel Clark; Villezas, Christelle; Palahang, Prinz Nikko; Dagaang, Jerald Aldin |
|
Publication date |
2016 |
|
Conference |
Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), 2015 International Conference on |
| Pages |
6 |
| Publisher |
IEEE |
| Abstract |
The use of Artificial Neural Networks (ANN) by power distribution companies has gained a wide reception due to its ability to predict close to accurate forecasted electric load consumption. A local power utility company in the Philippines has existing data of its electric load consumption however there is no ANN model that can process this data to produce close to accurate forecasted load which is the requirement of their electric market in nominating electric load. To solve this problem, this study developed an electric load forecasting model using ANN. Electric load data preparation, neural network model integration using the Fast Artificial Neural Network (FANN) library and testing using Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) as error measures were conducted. Results showed that the electric load forecasting model yielded a MAPE of less than 1% and a RMSE that is close to 0. The results obtained clearly suggest that ANN model is a viable forecasting technique for a next day electric load forecasting system. |
| DOI |
10.1109/HNICEM.2015.7393166 |
| URL |
|
Mindanao State
University - Iligan Institute of Technology