Reliability Computation of Neuro-Fuzzy Model Based Short Term Electrical Load Forecasting

뉴로-퍼지 모델 기반 단기 전력 수요 예측시스템의 신뢰도 계산

  • Published : 2005.10.01

Abstract

This paper presents a systematic method to compute a reliability measure for a short term electrical load forecasting system using neuro-fuzzy models. It has been realized that the reliability computation is essential for a load forecasting system to be applied practically. The proposed method employs a local reliability measure in order to exploit the local representation characteristic of the neuro-fuzzy models. It, hence, estimates the reliability of each fuzzy rule learned. The design procedure of the proposed short term load forecasting system is as follows: (1) construct initial structures of neuro-fuzzy models, (2) store them in the initial structure bank, (3) train the neuro-fuzzy model using an appropriate initial structure, and (4) compute load prediction and its reliability. In order to demonstrate the viability of the proposed method, we develop an one hour ahead load forecasting system by using the real load data collected during 1996 and 1997 at KEPCO. Simulation results suggest that the proposed scheme extends the applicability of the load forecasting system with the reliably computed reliability measure.

Keywords

References

  1. D. C. Park, M. A. EI-Sharkawi, R. J. Marks II, L. E. Atlas, and M. J. Damborg, 'Electric load forecasting using an artifircial neural network,' IEEE Trans. Power Systems, vol. 6, no. 2, pp. 442-449, 1991 https://doi.org/10.1109/59.76685
  2. A. G. Bakirtzis, J. B. Theocharis, S. J. Kiartzis, and K. J. Satsios, 'Short Term Load Forecasting Using Fuzzy Neural Networks,' IEEE Trans. on Power Systems, Vol. 10, No. 3, pp. 1518-1524, Aug. 1995 https://doi.org/10.1109/59.466494
  3. T. Senjyu, H. Takara, K. Uezato, and T. Funabashi, 'One Hour Ahead Load Forecasting Using Neural Network,' IEEE Trans. on Power Systems, Vol. 17, No. 1, pp. 113-118, Feb. 2002 https://doi.org/10.1109/59.982201
  4. D. H. Wolpert, 'Stacked Generalization,' Neural Network 5, pp. 241-259, 1992 https://doi.org/10.1016/S0893-6080(05)80023-1
  5. C. Satchwell, 'Finding error bars (the easy way)', Neural Computing Applications Forum, Edition 5, 1994
  6. J. A. Leonard, M. A. Karmer and L. H. Ungar, 'A Neural Network Achitecture that Compute Its Own Reliability,' Computer Chem. Engng. Vol. 16, No. 9 pp. 819-835, 1992 https://doi.org/10.1016/0098-1354(92)80035-8
  7. R. Tibshirani, 'A Comparison of Some Error Estimates for Neural Network Models,' Neural computation 8, pp. 152-163, 1996 https://doi.org/10.1162/neco.1996.8.1.152
  8. 심현정, 박래정, 왕보현, '뉴로-퍼지 모델의 신뢰도 계산: 비교 연구,' 한국 퍼지 및 지능 시스템 학회 논문지, Vol. 11, No. 4, pp. 293-301, 2001
  9. 박영진, 심현정, 왕보현, '뉴로-퍼지 모델을 이용한 단기전력 수요 예측 시스템,' 대한전기학회 논문집, 49A권 3호, Mar. 2000
  10. M. Kubat, 'Decision Trees can Initialize Radial Basis Function Networks,' IEEE Trans. Neural Networks, Vol. 9, No. 5, pp. 813-821, Sept. 1998 https://doi.org/10.1109/72.712154
  11. H. Pomares, I. Rojas, J. Gonzalez, and A. Prieto, 'Structure Identification In Complete Rule-based Fuzzy Systems,' IEEE Trans. Fuzzy Systems, Vol. 10, No. 3, pp. 349-359, Jun. 2002 https://doi.org/10.1109/TFUZZ.2002.1006438
  12. H. Stark and J. W. Wood, 'Probability, Random Process and Estimation Theory for Engineers,' pp. 270-288, 1994
  13. N. R. Draper and H. Smith, Applied Regression Analysis, 2nd Eds., John Wiley & Sons, Inc., 1966
  14. 박영진, 심현정, 왕보현, '뉴로-퍼지 모델을 이용한 단기 전력 수요 예측 시스템,' 대한전기학회 하계학술대회 논문집. A권, pp. 102-106, July 2000
  15. I. Drezga and S. Rahman, 'Input Variable Selection for ANN-based Short-term Load Forecasting,' IEEE Trans. on Power Systems, Vol. 13, No. 4, pp. 1238-1244, Nov. 1998 https://doi.org/10.1109/59.736244
  16. 김광호, '특수일 전력 수요 예측을 위한 퍼지 전문가 시스템,' 전기학회논문지, 47권 7호, pp. 886-891, 1998
  17. 구본석, 백영식, 송경빈, '추석과 설날 연휴에 대한 전력수요예측 알고리즘 개선,' 전기학회논문지, 51권 10호, pp. 453-459, 2002