Short Term Load Forecasting using Artificial Neural Network
Amera Ismail Melhum1, Lamya abd allateef Omar2, Sozan Abdulla Mahmood3
1Amera Ismail Melhum, Computer Science Department, Duhok University/ College of Science/ Ministry of High Education, Duhok, Iraq,
2Lamya abd allateef Omar, Computer Science Department, Duhok University / College of Science/ Ministry of High Education, Duhok, Iraq,
3Sozan Abdulla mahmood, Computer Science Department, Sulaimani/ College of Science/ Ministry of High Education Sulaimani University, Sulaimani, Iraq.
Manuscript received on February 04, 2013. | Revised Manuscript received on February 27, 2013. | Manuscript published on March 05, 2013. | PP: 56-58 | Volume-3 Issue-1, March 2013. | Retrieval Number: A1296033113/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Load forecasting helps an electric utility to make important decisions including decisions on purchasing and generating electric power, load switching, and infrastructure development. Load forecasts are extremely important for developing country like Iraq, financial institutions, and other participants in electric energy generation, transmission, distribution must be studied and took a good attention. This work analyzes and discusses a comprehensive approach for Short Term Load Forecasting (STLF) using artificial neural network. Proposed architectures were trained and tested using previous two years actual load data obtained from Duhok ELC. Control in Iraq. In this study, four ANN models are implemented and validated with reasonable accuracy on real electric load generation output data. The first and second model are to predict values of one ahead day and seven days, while the third and fourth models are also to predict values of next and seven days, concerning the amount of period of disconnected time. A forecasting performance measure such as the absolute mean error AME has been presented for each model.
Keywords: Load forecasting, artificial neural network, back propagation.