Abstract
In this chapter an innovative method for one and seven-day forecast of electricity load is proposed. The new approach has been tested on three different cases from south-west Western Australia’s interconnected system. They have been tested under the most realistic conditions by considering only minimum and maximum forecasts of temperature and relative humidity as available future inputs. Two different nonlinear approaches of neural networks and decision trees have been applied to fit proper models. A modified version of mean absolute percentage error (MMAPE) of each model over the test year is presented. By applying a developed criterion to recognize the dominant component of the electricity load, user of this work will be able to choose the most efficient forecasting method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Also known as country goldfields.
- 2.
SWIS: South west interconnected system.
- 3.
The correlation between the load data decreases as the number of weeks increases. In this study the maximum number of two future weeks and two previous weeks has been used for missing data estimation.
- 4.
Quantile–Quantile or Q–Q plot is a graph that shows the probability of two distributions against each other. By using Q–Q plots similarities and differences of two different distributions can be investigated.
- 5.
Although sometimes these forecasts are available for every three hour of the following week, to avoid the loss of generality only minimum and maximum values of temperature and humidity are considered to be available to this framework at the time of forecasting.
- 6.
A list of Western Australian public holidays has been used to generate the holidays input variables.
References
Weron R (2006) Modeling and forecasting electricity loads and prices: a statistical approach. Wiley, London, p 178
Temraz HK, Salama MMA, Chikhani AY (1997) Review of electric load forecasting methods. In: IEEE Canadian conference on electrical and computer engineering, vol 1. pp 289–292
Kourtis G, Hadjipaschalis I, Poullikkas A (2011) An overview of load demand and price forecasting methodologies. Int J Energy Environ 2(1):123–150
Hahn H, Meyer-Nieberg S, Pickl S (2009) Electric load forecasting methods: tools for decision making. Eur J Oper Res 199(3):902–907
Sharaf A, Lie T, Gooi H (1993) A neural network based short term load forecasting model. In: IEEE Canadian conference on electrical and computer engineering, pp 325–328
Park DC, El-Sharkawi M, Marks R, Atlas L, Damborg M (1991) Electric load forecasting using an artificial neural network. IEEE Trans Power Syst 6(2):442–449
Amral N, King D, Ozveren CS (2008) Application of artificial neural network for short term load forecasting. In: 43rd international universities power engineering conference, pp 1–5
Munkhjargal S, Manusov VZ (2004) Artificial neural network based short-term load forecasting. In: The 8th Russian-Korean international symposium on science and technology, vol 1. pp 262–264
Peng T, Hubele N, Karady G (1993) An adaptive neural network approach to one-week ahead load forecasting. IEEE Trans Power Syst 8(3):1195–1203
Bala PK (2010) Decision tree based demand forecasts for improving inventory performance. In: IEEE international conference on industrial engineering and engineering management, pp 1926–1930
Lobato E, Ugedo A, Rouco R (2006) Decision trees applied to spanish power systems applications. In: IEEE 9th international conference on probabilistic methods applied to power systems, pp 1–6
Willis HL (2002) Spatial electric load forecasting, vol 71(2), 2nd edn. CRC Press, Boca Raton, p 760
Moghaddam M, Bahri P (2012) A novel approach for forecasting of residential, commercial and industrial electricity loads. In: Lecture notes in engineering and computer science: proceedings of the world congress on engineering and computer science, WCECS, vol. 2. pp 1365–1371
Asber D, Lefebvre S, Asber J, Saad M, Desbiens C (2007) Non-parametric short-term load forecasting. Int J Electr Power Energy Syst 29(8):630–635
Seppälä A (1996) Load research and load estimation in electricity distribution. Technical research centre of Finland
Hyndman RJ, Fan S (2010) Density Forecasting for Long-Term Peak Electricity Demand. IEEE Trans Power Syst 25(2):1142–1153
Chicco G, Napoli R, Piglione F (2001) Load pattern clustering for short-term load forecasting of anomalous days. In: IEEE porto power tech proceedings, vol 2
Jain A, Satish B (2009) Clustering based short term load forecasting using artificial neural network. In: IEEE/PES power systems conference and exposition, pp 1–7
Meng M, Chang Lu J, Sun W (2006) Short-term load forecasting based on ant colony clustering and improved BP neural networks. In: International conference on machine learning and cybernetics, pp 3012–3015
Dietterich T (2000) An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach Learn 22:1–22
Ranaweera DK, Karady GG, Farmer RG (1997) Economic impact analysis of load forecasting. IEEE Trans Power Syst 12(3):1388–1392
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Moghaddam, M.K., Bahri, P.A. (2014). Development of a Novel Approach for Electricity Forecasting. In: Kim, H., Ao, SI., Amouzegar, M., Rieger, B. (eds) IAENG Transactions on Engineering Technologies. Lecture Notes in Electrical Engineering, vol 247. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-6818-5_45
Download citation
DOI: https://doi.org/10.1007/978-94-007-6818-5_45
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-6817-8
Online ISBN: 978-94-007-6818-5
eBook Packages: EngineeringEngineering (R0)