The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Comparison of Machine Learning in the Prediction for Amount of Power Market

전력 거래량 예측에서의 머신 러닝 성능 비교

  • 최정곤 (조선대학교 전기공학과)
  • Received : 2019.09.16
  • Accepted : 2019.10.15
  • Published : 2019.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Machine learning can greatly improve the efficiency of work by replacing people. In particular, the importance of machine learning is increasing according to the requests of fourth industrial revolution. This paper predicts monthly power transactions using MLP, RNN, LSTM, and ANFIS of neural network algorithms. Also, this paper used monthly electricity transactions for mount and money, final energy consumption, and diesel fuel prices for vehicle provided by the National Statistical Office, from 2001 to 2017. This paper learns each algorithm, and then shows predicted result by using time series. Moreover, this paper proposed most excellent algorithm among them by using RMSE.

머신 러닝은 인력을 대체함으로써 업무 효율성을 크게 높일 수 있다. 특히 4차 산업혁명 시대의 요청에 따라 인공지능을 포함한 머신 러닝의 중요성은 점점 커지고 있다. 본 논문은 MLP, RNN, LSTM, ANFIS 신경망 알고리즘 이용하여, 월별 전력 거래량을 예측한다. 본 논문에서는 통계청에서 제공하는 월별 전력 거래량과 월별 전력 거래금액, 최종에너지 소비량, 자동차용 경유 가격에 대한 2001~2017년까지의 공공 데이터를 사용하였다. 본 논문은 제시하는 각각의 알고리즘들을 학습시키고, 알고리즘이 예측하는 시계열 그래프를 이용하여 예측 결과를 보여주고 RMSE를 이용하여 이들 중에서 가장 우수한 알고리즘 제시한다.

Keywords

References

  1. C. Jung, R. Jang, D. Nyang, and K. Lee, "A Study of User Behavior Recognition-Based PIN Entry Using Machine Learning Technique," Korea Information Processing Society review, computer and communication systems, vol. 7, no. 2, 2018, pp. 127-136.
  2. G. Lee, H. Ha, H. Hong, and H. Kim, "Exploratory Research on Automating the Analysis of Scientific Argumentation Using Machine Learning," J. of the Korean Association for Science Education, vol. 38, no. 2, 2018, pp. 219-234. https://doi.org/10.14697/JKASE.2018.38.2.219
  3. Y. Bang, C. Lee, and H. Park, "Electricity Load Forecasting by using a Normalized Fuzzy System," J. of Fuzzy Logic and Intelligent Systems, vol. 28, no. 1, Feb. 2018, pp. 57-64.
  4. B. Wang, "Short-term Electrical Load Forecasting Using Neuro-Fuzzy Model with Error Compensation," J. of Fuzzy Logic and Intelligent Systems, vol. 9, no. 4, Dec. 2009, pp. 327-332. https://doi.org/10.5391/IJFIS.2009.9.4.327
  5. Y. Bae and N. Kim, "Classification of Motor status using K-nearest neighbors," J. of the Korea Institute of Electronic Communication Sciences, vol. 13, no. 6, Dec. 2018, pp. 1249-1256. https://doi.org/10.13067/JKIECS.2018.13.6.1249
  6. Y. Kim, G. Mun, and S. Choi, "Future Trend Impact Analysis Based on Adaptive Neuro-Fuzzy Inference System," J. of The Korea Institute of Electronic Communication Sciences, vol. 10, no. 4, Apr. 2015, pp. 499-506. https://doi.org/10.13067/JKIECS.2015.10.4.499
  7. H. Yoon, Y. Kim, K. Ha, and G. Kim "Application of groundwater-level prediction models using data-based learning algorithms to National Groundwater Monitoring Network data," J. of Engineering Geology, vol. 23, no. 2, June 2013, pp. 137-147. https://doi.org/10.9720/kseg.2013.2.137
  8. A. Graves, Supervised Sequence Labelling with Recurrent Neural Networks. Heidelberg New York: Springer, 2012.
  9. S. Kim, Coding Chef's 3 Minute Deep Learning, Keras flavor. seoul Korea: HanbitMedia, 2018.
  10. J. R. Jang, "ANFIS: Adaptive-Network-Based-Fuzzy Inference System," IEEE Transactions on systems, man, and cybernetics, vol. 23, 1993, pp. 665-685. https://doi.org/10.1109/21.256541
  11. J. Yi and C. Choi, "Flood Forecasting and Warning Using Neuro-Fuzzy Inference Technique," J. of Korea Water Resources Association, vol. 41, no. 3, 2008, pp.341-351. https://doi.org/10.3741/JKWRA.2008.41.3.341
  12. K. Lee, H. Lee, and K. Oh, "Using fuzzy-neural network to predict hedge fund survival," J. of the Korean Data & Information Science Society, vol. 26, no. 6, 2015, pp. 1189-1198. https://doi.org/10.7465/jkdi.2015.26.6.1189
  13. G. Lee, Artificial Intelligence : from Turing test to Deep Learning. seoul Korea: saengneung, 2018.