Short, Medium and Long Term Load Forecasting Model and Virtual Load

Only available on StudyMode
  • Download(s) : 315
  • Published : October 15, 2012
Open Document
Text Preview
Electrical Power and Energy Systems 32 (2010) 743–750

Contents lists available at ScienceDirect

Electrical Power and Energy Systems
journal homepage: www.elsevier.com/locate/ijepes

Short, medium and long term load forecasting model and virtual load forecaster based on radial basis function neural networks Changhao Xia a,b,*, Jian Wang b,*, Karen McMenemy c
a

College of Electrical Engineering and Information Technology, China Three Gorges University, Yichang Hubei 443002, China School of Mechanical and Aerospace Engineering, Queen’s University, Belfast, Northern Ireland BT9 5AH, UK c School of Electronics, Electrical Engineering and Computer Science, Queen’s University, Belfast, Northern Ireland BT9 5AH, UK b

a r t i c l e

i n f o

a b s t r a c t
Artificial neural networks (ANNs) can be easily applied to short-term load forecasting (STLF) models for electric power distribution applications. However, they are not typically used in medium and long term load forecasting (MLTLF) electric power models because of the difficulties associated with collecting and processing the necessary data. Virtual instrument (VI) techniques can be applied to electric power load forecasting but this is rarely reported in the literature. In this paper, we investigate the modelling and design of a VI for short, medium and long term load forecasting using ANNs. Three ANN models were built for STLF of electric power. These networks were trained using historical load data and also considering weather data which is known to have a significant affect of the use of electric power (such as wind speed, precipitation, atmospheric pressure, temperature and humidity). In order to do this a V-shape temperature processing model is proposed. With regards MLTLF, a model was developed using radial basis function neural networks (RBFNN). Results indicate that the forecasting model based on the RBFNN has a high accuracy and stability. Finally, a virtual load forecaster which integrates the VI and the RBFNN is presented. Ó 2010 Elsevier Ltd. All rights reserved.

Article history: Received 26 March 2008 Received in revised form 30 September 2009 Accepted 28 January 2010

Keywords: Electric load forecasting Radial basis function Neural network Virtual instrument

1. Introduction Short-term, medium and long-term forecasting of load demand is necessary for the correct operation of electric utilities. Forecasts are required for proper scheduling activities, such as generation scheduling, fuel purchasing scheduling, maintenance scheduling, investment scheduling, and for security analysis [1]. Generally the forecasting methods found in the literature are typically based on the following forms of mathematical analysis: regressive analysis, exponential smoothing, time series, grey box systems, Kalman filtering, expert systems, wavelet analysis, fuzzy system modelling, neural network modelling, etc. Many models for STLF [2–16,21–24] and MLTLF [1,17–20] have been proposed in the literature. In some cases researchers have combined several methods to develop their own hybrid method. For example in [2] a fuzzy linear regression method is used for load forecasting weekend power usage whereas weekday loads are forecast using a general exponential smoothing method. The latest developments in general load forecasting cited in the literature use artificial intelli-

* Corresponding authors. Address: School of Mechanical and Aerospace Engineering, Queen’s University, Belfast, Northern Ireland BT9 5AH, UK. Tel.: +44 0 28 90974181; fax: +44 0 28 90975576. E-mail addresses: c.xia@qub.ac.uk (C. Xia), j.wang@qub.ac.uk (J. Wang), k.mcmenemy@ee.qub.ac.uk (K. McMenemy). 0142-0615/$ - see front matter Ó 2010 Elsevier Ltd. All rights reserved. doi:10.1016/j.ijepes.2010.01.009

gent-based forecasting (AIBF) techniques, such as ANN [1– 4,6,8,13,14,16–19], fuzzy logic [2,12,14,15], and genetic algorithms [9], all of which show promising results for STLF. Less literature...
tracking img