Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning Based Short-Term Electric Load Forecasting Models using One-Hot Encoding

원-핫 인코딩을 이용한 딥러닝 단기 전력수요 예측모델

  • Kim, Kwang Ho (Dept. of Electrical and Electronics Engineering, Kangwon National University) ;
  • Chang, Byunghoon (Hankook Electric Power Information Co.) ;
  • Choi, Hwang Kyu (Dept. of Computer Science and Engineering, Kangwon National University)
  • Received : 2019.09.05
  • Accepted : 2019.09.23
  • Published : 2019.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In order to manage the demand resources of project participants and to provide appropriate strategies in the virtual power plant's power trading platform for consumers or operators who want to participate in the distributed resource collective trading market, it is very important to forecast the next day's demand of individual participants and the overall system's electricity demand. This paper developed a power demand forecasting model for the next day. For the model, we used LSTM algorithm of deep learning technique in consideration of time series characteristics of power demand forecasting data, and new scheme is applied by applying one-hot encoding method to input/output values such as power demand. In the performance evaluation for comparing the general DNN with our LSTM forecasting model, both model showed 4.50 and 1.89 of root mean square error, respectively, and our LSTM model showed high prediction accuracy.

분산자원 집합 거래시장에 참여를 원하는 소비자나 사업자를 위한 가상발전소의 전력거래 플랫폼에서 사업참여자의 수요 자원을 관리하고, 이에 적절한 전략을 제공하기 위해 익일 개별 참여자의 수요와 전체 계통의 전력수요를 예측하는 것이 대단히 중요하다. 이러한 전력거래 플랫폼에서 활용하는 것을 목표로 본 논문은 우선 익일의 24시간 전력계통 전력수요예측 모델을 개발하였다. 본 논문에서는 전력수요예측 데이터의 시계열 특성을 고려하여 딥러닝 기법 중 LSTM 알고리즘을 사용하였고, 전력수요량 등의 입출력 값에 원-핫 인코딩 기법을 적용하는 새로운 시도를 하였다. 성능평가에서 일반 DNN과 본 논문에서 구현된 LSTM 예측모델은 각각 평균 제곱근 오차 4.50, 1.89를 나타내어 LSTM 모델이 예측정확도가 높게 나타났다.

Keywords

References

  1. A. Tokgoz and G. Unal, "A RNN based time series approach for forecasting turkish electricity load," in Proc. of the 2018 26th Signal Processing and Communications Applications Conference (SIU), 2018. DOI: 10.1109/SIU.2018.8404313
  2. Y. I, Son and S. K. Han, "Demand power forecasting with data mining method," The 47th KIEE Summer Conference, Pyongchang, pp.208-209, 2016. DOI: 10.1109/ISGT-Asia.2017.8378423
  3. H. S. Tak, T. Y. Kim, H, K, Cho, and H. J. Kim, "A new prediction model for power consumption with local weather information," Journal of The Korea Contents Association, vol.16, no.11, pp. 488-498, 2016. DOI: 10.5392/JKCA.2016.16.11.488
  4. K. H. Kim, R. J. Park, S. W. Cho, and K. B. Song, "24-Hour load forecasting algorithm using artificial neural network in summer weekdays," Journal of The Korean Institute of Illuminating and Electrical Installation Engineers, vol.31, no.9, pp.103-119, 2017. DOI: 10.5207/JIEIE.2017.31.12.113
  5. C. H. Park, M. S. Cho, J. U. Park, H. C. Noh, J. U. Lee, and S. H. Park, "Electric load forecasting based on short-and long-term modeling of time series data," in Proc. of the KCC 2019, pp.409-411, 2019.
  6. S. W. Cho, B. S. Kwon, and K. B. Song, "Day ahead 24-hours load forecasting algorithm using latest weather forecasting," The Transactions of The Korean Institute of Electrical Engineers, vol.68, no.3, pp.416-422, 2019. DOI: 10.5370/KIEE.2019.68.3.416
  7. D. H. Kang, J. D. Park, and K. B. Song, "24-hour load forecasting for anomalous weather days using hourly temperature," The Transactions of The Korean Institute of Electrical Engineers, vol.65, no.7, pp.1144-1150, 2016. DOI: 10.5370/KIEE.2016.65.7.1144
  8. M. Q. Raza and A, Khosravi, "A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings," ELSEVIER Renewable and Sustainable Energy Reviews, vol.50, pp.1352-1372, 2015. DOI: 10.1016/j.rser.2015.04.065
  9. F. J. Ordonez and D. Roggen, "Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition," Sensors, pp.3-9, 2016. DOI: 10.3390/s16010115
  10. C. Olah, "Understanding LSTM networks," https://colah.github.io/posts/2015-08-Understanding-LSTMs.
  11. H. C. Chung et al., "Prediction for energy demand using 1D-CNN and bidirectional LSTM in Internet of energy," Journal of Institute of Korean Electrical and Electronics Engineers, vol.23, no.1, pp.134-142, 2019. DOI: 10.7471/ikeee.2019.23.1.134
  12. Google, "Tensorflow Tutorial," https://www.tensorflow.org/tutorials.
  13. H. K. Choi, B. H. Chang, and K. H. Kim, "Comparative study of short-term load forecasting with deep learning algorithm," The 50th KIEE Summer Conference, pp.664-665, 2019. DOI: 10.1109/GTSD.2018.8595514

Cited by

  1. Catboost 알고리즘을 통한 교통흐름 예측에 관한 연구 vol.22, pp.3, 2021, https://doi.org/10.5762/kais.2021.22.3.58
  2. 가전제품 전력 사용 분류를 위한 장단기 메모리 기반 비침입 부하 모니터링 기법 vol.21, pp.4, 2019, https://doi.org/10.7236/jiibc.2021.21.4.109