Total views : 228

Correlation and Wavelet-based Short-Term Load Forecasting using Anfis

Affiliations

  • Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, 81310, Johor, Malaysia

Abstract


Objective: This paper addresses the issue of model inputs selection before the forecasting exercise. Appropriate data analysis is one of the basic steps in obtaining accurate load forecast. It shapes the forecasting data in to working data by reducing the variation between the individual forecasting variables, or reduces the number of the model inputs. Also, the information received from data analysis determines the method to be used, or how to use it. Methods/Statistical Analysis: It employs the use of correlation analysis to select the forecasting variables, and wavelet transforms to decompose the selected data in to a number of approximations. The purpose is to select the actual forecasting variables, and to limit the variation between them (model inputs). ANFIS was used to forecast the load using the processed data. Findings: From the result obtained, it was observed that selecting the data based on correlation analysis, and wavelet transform improve the accuracy of the forecast, and enhanced the forecasting speed. Applications/Improvements: Improving the forecasting accuracy will save the utility economically, and improving the speed will enhance the time taken to make crucial decisions in power system operation

Keywords

ANFIS, Correlation Analysis, Short-term Load Forecasting, Wavelet Transform.

Full Text:

 |  (PDF views: 209)

References


  • Ranaweera DK, Karady GG, Richard CF. Economic impact analysis of load forecasting. IEEE Transaction on Power System 1997; 12(3). p. 1388–92.
  • Feinberg EA, Genethliou D, Chao, JH, Wu FF, Momoh JA. Load Forecasting. In: editor. Applied Mathematics for restructured Electric Power System. 2006. p. 269–85.
  • Dragomir OE, Dragomir F, Gouriveau R, Monica E.Medium term load forecasting using ANFIS predictor. In: 18th Mediterranean Conference on Control & Automation.2010. p. 551–6.
  • Chakravorty A, Rong C, Wlodarczyk E P, Wiktor T. A Distributed Gaussian-Means clustering algorithm for forecasting domestic energy usage. In: International Conference on Smart Computing. IEEE; 2014. p. 229–36.
  • Chen Y, Luh PB, Guan C, Zhao Y, Michel LD, Coolbeth MA. Short-term load forecasting : Similar day-based wavelet neural networks. IEEE Transaction on Power System.2010; 25(1). p. 322–30.
  • Mahmoud T, Lachowicz SW, Member TSM, Habibi D, Member S, Bass O. Load demand forecasting: Model inputs selection load demand forecasting: Model Inputs Selection. IEEE Conference and Innovation Smart Grid Technology Asia; 2011.
  • Sovann N, Nallagownden P, Baharudin Z. A method to determine the input variable for the neural network model of the electrical system. 5th International Conference on Intellectual Advanced System. Jun 2014. p. 1–6.
  • Quilumba FL, Lee W, Huang H, Wang DY, Member S, Szabados RL. Using smart meter data to improve the accuracy of intraday load forecasting considering customer behaviour similarities. IEEE Transaction on Smart Grid.2015; 6(2):911–8.
  • Koprinska I, Rana M, Agelidis VG. Correlation and instance based feature selection for electricity load forecasting.Knowledge-Based System. Elsevier B.V. 2015; 82:29–40.
  • Tiong SK, Ahmed SK. Electrical Power Load Forecasting using Hybrid Self-Organizing Maps and Support Vector Machines.In: The 2nd International Power Engineering Optimization Conference (PEOCO). Selangor: IEEE. 2008. p. 51–6.
  • Hernandez L, Baladron C, Aguiar JM, Calaavia L, Carro B, Esguevillas AS. A study of the relationship between weather variables and electric power demand inside a smart grid/ smart world framework. SENSORS. 2012; 12:11571–91.
  • Bashir ZA, El-Hawary ME. Applying wavelets to shortterm load forecasting using PSO-based neural networks.IEEE Transaction on Power System. 2009; 24(1):20–7.
  • Li S, Wang P, Goel L. A Novel Wavelet-based ensemble method for short-term load forecasting with hybrid neural Networks and Feature Selection. IEE Transaction on Power System. 2016; 31(3):1788–98.
  • Pousinho HMI, Mendes VMF. Hybrid Wavelet-PSOANFIS approach for short-term wind power forecasting in Portugal. IEEE Transaction Sustainable Energy. 2010; 2(1):50–9.
  • Jang JR. ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transaction on System Management Cybernetic. 1993; 23(3):65–85.
  • Ghomsheh VS, Shoorehdeli MA, Teshnehlab M. Training ANFIS structure with modified PSO algorithm. In: Mediterranean Conference on Control and Automation.Athens. 2007. p. 1–6.
  • Cheng C-H, Wei L. One step-ahead ANFIS time series model for forecasting electricity loads. Optimal Engineering. 2010; 11(2):303–17.
  • Nguyen T, Liao Y. Short-Term Load Forecasting Based on Adaptive Neuro-Fuzzy Inference System. Journal of Computing. 2011; 6(11):2267–71.
  • Jang JR, Sun C-T, Mizutani E. Neuro-Fuzzy and Soft Computing. NJ: Prentice Hall: New York. 1997. p. 611–4.
  • Bezdek JC, Ehrlich R, Full W. FCM : The fuzzy c-means clustering algorithm. Computer Geoscience. 1984; 10(2):191–203.
  • Chiu SL. Fuzzy model identification based on cluster estimation. Journal of Intellectual Fuzzy System. 1994; 2:267–78.
  • Mustapha M, Mustafa MW, Khalid SN. Data selection and fuzzy-rules generation for short- term load forecasting using ANFIS. Telekomnika. 2016; 14(3):791–9.
  • Hong T, Wang P. Fuzzy interaction regression for short term load forecasting. Fuzzy Optimal Decision Making.Sep 2013; 13(1):91–103.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.