Short Term Load Forecasting Using ANN Considering Weather Information and Price
Needhu Varghese1, Reji P2
1Needhu Varghese, EEE, IES College of Engineering, Chittilappilly affiliated to Calicut University, India.
2Dr. Reji P, EEE, Government Engineering College Thrissur, Thrissur affiliated to Calicut University, India.
Manuscript received on August 11, 2013. | Revised Manuscript received on August 15, 2013. | Manuscript published on August 25, 2013. | PP: 5-9 | Volume-1, Issue-10, August 2013. | Retrieval Number: J04060811013/2013©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Short-term load forecast is an essential part of electric power system planning and operation. Forecasted values of system load affect the decisions made for unit commitment and security assessment, which have a direct impact on operational costs and system security. Conventional regression methods are used by most power companies for load forecasting. However, due to the nonlinear relationship between load and factors affecting it, conventional methods are not sufficient enough to provide accurate load forecast or to consider the seasonal variations of load. In recent years multilayered feed forward (MLFF) networks with back propagation learning algorithm have been extensively applied to short term load forecasting (STLF) in electric power systems with very good results. This paper presents an artificial neural network based approach for short-term load forecasting that uses temperature, humidity, wind speed and price as inputs. The results are compared by calculating mean Absolute percentage error (MAPE). The suitability of the proposed approach is illustrated through an application to the actual load data of the Kerala System for regulated system and Lanco Kondapilli for deregulated system.
Keywords: Artificial neural network, back propagation algorithm, deregulated system and short term load forecasting.