KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Peak Load Prediction Using TCN Deep Learning Model

TCN 딥러닝 모델을 이용한 최대전력 예측에 관한 연구

  • Received : 2023.03.06
  • Accepted : 2023.04.26
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

It is necessary to predict peak load accurately in order to supply electric power and operate the power system stably. Especially, it is more important to predict peak load accurately in winter and summer because peak load is higher than other seasons. If peak load is predicted to be higher than actual peak load, the start-up costs of power plants would increase. It causes economic loss to the company. On the other hand, if the peak load is predicted to be lower than the actual peak load, blackout may occur due to a lack of power plants capable of generating electricity. Economic losses and blackouts can be prevented by minimizing the prediction error of the peak load. In this paper, the latest deep learning model such as TCN is used to minimize the prediction error of peak load. Even if the same deep learning model is used, there is a difference in performance depending on the hyper-parameters. So, I propose methods for optimizing hyper-parameters of TCN for predicting the peak load. Data from 2006 to 2021 were input into the model and trained, and prediction error was tested using data in 2022. It was confirmed that the performance of the deep learning model optimized by the methods proposed in this study is superior to other deep learning models.

안정적으로 전력을 공급하고 전력계통을 운영하기 위해서는 최대전력을 정확히 예측해야 한다. 특히, 최대전력이 높게 발생하는 겨울과 여름에는 그 중요성이 매우 커진다. 최대전력을 실제 수요보다 높게 예측하면 발전소 기동 비용이 증가하여 경제적 손실이 발생하고, 최대전력을 실제 수요보다 낮게 예측하면 기동이 가능한 발전소가 부족하여 정전이 발생할 수 있다. 최대전력의 예측 오차를 최소화함으로써 경제적 손실과 정전을 예방할 수 있다. 본 논문에서는 최대전력 예측의 오차를 최소화하기 위하여 최신 딥러닝 모델인 TCN을 이용한다. 딥러닝 모델은 하이퍼 파라미터를 어떻게 설정하느냐에 따라 성능 차이가 발생하므로, TCN의 하이퍼 파라미터를 최적화하는 방법을 제안한다. 2006년부터 2021년까지의 데이터를 입력하여 모델을 훈련하고, 2022년의 데이터를 이용하여 예측 오차를 실험하였다. 실험을 수행한 결과 본 논문에서 제안한 최적화 방법을 이용한 TCN 모델의 성능이 다른 딥러닝 모델보다 성능이 우수한 것을 확인하였다.

Keywords

Acknowledgement

이 논문은 한국전력공사 전력연구원의 디지털 플랫폼 정합화 및 전력 AI엔진 기술 개발 연구과제에 의하여 연구되었음.

References

  1. G.-C. Lee and J. Han, "Forecasting daily peak load of domestic electricity demand," Journal of Industrial Economics and Business, Vol.30, No.4, pp.1205-1218, 2017. https://doi.org/10.22558/jieb.2017.08.30.4.1205
  2. J.-Y. Ahn, S.-M. Park, and C.-B. Kim, "A study on neural network model for winter electric power demand prediction," The Journal of Korean Institute of Information Technology, Vol.15, No.9, pp.1-9, 2017. https://doi.org/10.14801/jkiit.2017.15.9.1
  3. B.-S. Kwon and K.-B. Song, "An ensemble forecasting method of winter and summer peak load using deep neural networks," The transactions of The Korean Institute of Electrical Engineers, Vol.69, No.6, pp.765-771, 2020. https://doi.org/10.5370/KIEE.2020.69.6.765
  4. H.-S. Yoo and S.-B. Jeong, "Electric power demand prediction using deep learning model with temperature data," KIPS Transactions on Software and Data Engineering, Vol.11, No.7, pp.307-314, 2022. https://doi.org/10.3745/KTSDE.2022.11.7.307
  5. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, Vol.9, No.8, pp.1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  6. A. V. D. Oord et al., "Wavenet: A generative model for raw audio," arXiv preprint arXiv:1609.03499, 2016.
  7. Electric Power Statistics Information System [Internet], https://epsis.kpx.or.kr/epsisnew/
  8. P., Liashchynskyi and P. Liashchynskyi, "Grid search, random search, genetic algorithm: A big comparison for NAS," arXiv preprint arXiv:1912.06059, 2019.
  9. D. P. Kingma and J. ba, "Adam: A Method for Stochastic Optimization," arXiv preprint arXiv:1412.6980, 2014.
  10. K. Cho et al., "Learning phrase representations using RNN encoder-decoder for statistical machine translation", Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp.1724-1734, 2014.
  11. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770-778, 2016.
  12. H. Zhou, S. Zhang, J. Peng, S. Zhang, J. Li, H. Xiong, and W. Zhang, "Informer: Beyond efficient transformer for long sequence time-series forecasting," In Proceedings of the AAAI Conference on Artificial Intelligence, Vol.35, No.12, pp.11106-11115, 2021.