Day-Ahead Electricity Demand Forecasting Using a Hybrid Method

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 355)

Abstract

Nowadays, artificial intelligence is commonly used in many fields including medicine, chemistry, and forecasting. In this paper, artificial intelligence is applied to electricity demand forecasting due to the demand for this from both providers and consumers at this time. In order to seek accurate demand forecasting methods, this article proposes a new combined electric load forecasting method (SPLSSVM), which is based on seasonal adjustment (SA) and least square support vector machine (LSSVM) optimized by the particle swarm optimization (PSO) algorithm, to forecast electricity demand. The effectiveness of SPLSSVM is tested with a dataset from New South Wales (NSW) in Australia. Experimental results demonstrate that the SPLSSVM model can offer more precise results than other methods mentioned in the literature.

Keywords

Electricity demand forecasting Particle swarm optimization Least square support vector machine 

References

  1. 1.
    Li DC, Chang CJ, Chen CC, Chen WC. Forecasting short-term electricity consumption using the adaptive grey-based approach: an Asian case. Omega. 2012;40(6):767–73.CrossRefGoogle Scholar
  2. 2.
    Hsu LC. Using improved grey forecasting models to forecast the output of opto-electronics industry. Expert Syst Appl. 2011;38(11):13879–85.Google Scholar
  3. 3.
    Kheirkhah A, Azadeh A, Saberi M, Azaron A, Shakouri H. Improved estimation of electricity demand function by using of artificial neural network, principal component analysis and data envelopment analysis. Comput Ind Eng. 2013;64(1):425–41.CrossRefGoogle Scholar
  4. 4.
    Chang PC, Fan CY, Lin JJ. Monthly electricity demand forecasting based on a weighted evolving fuzzy neural network approach. Int J Electr Power Energy Syst. 2011;33(1):17–27.CrossRefGoogle Scholar
  5. 5.
    Moghram IS, Rahman S. Analysis and evaluation of five short-term load forecasting techniques. IEEE Trans Power Syst. 1989;4(4):1484–91.CrossRefGoogle Scholar
  6. 6.
    Bates JM, Granger CW. The combination of forecasts. Oper Res Q. 1969;20(4):451–68.CrossRefGoogle Scholar
  7. 7.
    Dickinson JP. Some comments on the combination of forecasts. Oper Res Q. 1975;26(1):205–10.CrossRefMathSciNetMATHGoogle Scholar
  8. 8.
    Eberhart R, Kennedy J. New optimizer using particle swarm theory. In: Proceeding of the Sixth International Symposium on Micro Machine and Human Science; IEEE, Piscataway; 1995. p. 39–43.Google Scholar
  9. 9.
    Suykens JAK, Vandewalle J. Least squares support vector machine classifiers. Neural Process Lett. 1999;9(3):293–300.CrossRefMathSciNetGoogle Scholar
  10. 10.
    Iplikci S. Dynamic reconstruction of chaotic systems from inter-spike intervals using least squares support vector machines. Physica D. 2006;216(2):282–93.CrossRefMathSciNetMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.School of Information and Engineering, Gansu University of Traditional Chinese MedicineGansuChina
  2. 2.School of Information Science and Engineering, Lanzhou UniversityLanzhouChina

Personalised recommendations