Journal of IKEEE (전기전자학회논문지)

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

DOI QR Code

Prediction of Power Consumptions Based on Gated Recurrent Unit for Internet of Energy

에너지 인터넷을 위한 GRU기반 전력사용량 예측

  • Lee, Dong-gu (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Sun, Young-Ghyu (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Sim, Is-sac (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Hwang, Yu-Min (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Kim, Sooh-wan (Co. Gridwiz) ;
  • Kim, Jin-Young (Dept. of Electronic Convergence Engineering, Kwangwoon University)
  • Received : 2019.03.13
  • Accepted : 2019.03.19
  • Published : 2019.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, accurate prediction of power consumption based on machine learning techniques in Internet of Energy (IoE) has been actively studied using the large amount of electricity data acquired from advanced metering infrastructure (AMI). In this paper, we propose a deep learning model based on Gated Recurrent Unit (GRU) as an artificial intelligence (AI) network that can effectively perform pattern recognition of time series data such as the power consumption, and analyze performance of the prediction based on real household power usage data. In the performance analysis, performance comparison between the proposed GRU-based learning model and the conventional learning model of Long Short Term Memory (LSTM) is described. In the simulation results, mean squared error (MSE), mean absolute error (MAE), forecast skill score, normalized root mean square error (RMSE), and normalized mean bias error (NMBE) are used as performance evaluation indexes, and we confirm that the performance of the prediction of the proposed GRU-based learning model is greatly improved.

최근 에너지 인터넷에서 지능형 원격검침 인프라를 이용하여 확보된 대량의 전력사용데이터를 기반으로 효과적인 전력수요 예측을 위해 다양한 기계학습기법에 관한 연구가 활발히 진행되고 있다. 본 연구에서는 전력량 데이터와 같은 시계열 데이터에 대해 효율적으로 패턴인식을 수행하는 인공지능 네트워크인 Gated Recurrent Unit(GRU)을 기반으로 딥 러닝 모델을 제안하고, 실제 가정의 전력사용량 데이터를 토대로 예측 성능을 분석한다. 제안한 학습 모델의 예측 성능과 기존의 Long Short Term Memory (LSTM) 인공지능 네트워크 기반의 전력량 예측 성능을 비교하며, 성능평가 지표로써 Mean Squared Error (MSE), Mean Absolute Error (MAE), Forecast Skill Score, Normalized Root Mean Squared Error (RMSE), Normalized Mean Bias Error (NMBE)를 이용한다. 실험 결과에서 GRU기반의 제안한 시계열 데이터 예측 모델의 전력량 수요 예측 성능이 개선되는 것을 확인한다.

Keywords

JGGJB@_2019_v23n1_120_f0001.png 이미지

Fig. 1. Structure of artificial neuron and deep neural network. 그림 1. 인공뉴런과 인공신경망의 구조

JGGJB@_2019_v23n1_120_f0002.png 이미지

Fig. 2. Structure of Recurrent Neural Network. 그림 2. 순환 신경망의 구조

JGGJB@_2019_v23n1_120_f0003.png 이미지

Fig. 3. Structure of GRU. 그림 3. GRU의 구조

JGGJB@_2019_v23n1_120_f0004.png 이미지

Fig. 4. Prediction result of GRU. 그림.4 GRU의 예측결과

JGGJB@_2019_v23n1_120_f0005.png 이미지

Fig. 5. Prediction result of LSTM. 그림 5. LSTM의 예측결과

Table 1. Parameters of experiments. 표 1. 실험 파라미터

JGGJB@_2019_v23n1_120_t0001.png 이미지

Table 2. Performance evaluation of LSTM and GRU. 표 2. LSTM과 GRU의 성능평가

JGGJB@_2019_v23n1_120_t0002.png 이미지

References

  1. Y. Cheng, C. Xu, D. Mashima, V. L. L. Thing and Y. Wu, "PowerLSTM: Power demand forecasting using long short-term memory neural network," in Proc. of Advanced Data Mining and Applications: 13th International Conference, Singapore, Singapore, pp. 727-740, 2017. DOI: 10.1007/978-3-319-69179-4_51
  2. J. Y. Choi and B. Lee, "Combining LSTM network ensemble via adaptive weighting for improved time series forecasting," Mathematical Problems in Engineering, vol. 2018, pp. 1-8, 2018. DOI: 10.1155/2018/2470171
  3. W. He, "Load forecasting via deep neural networks," in Proc. of 5th International Conference on Information Technology and Quantitative Management, ITQM 2017, New Delhi, India, vol. 122, pp. 308-314, 2017. DOI: 10.1016/j.procs.2017.11.374
  4. S. P. Kim, Deep Learning First Step, Hanbit media, 2016.
  5. I. Goodfellow, Deep Learning, MIT Press, 2016.
  6. K. Cho, B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk and Y. Bengio, "Learning phrase representations using RNN encoder-decoder for statistical machine translation," in Proc. of 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, pp. 1724-1734, 2014. DOI: 10.3115/v1/D14-1179
  7. R. Jozefowicz, W. Zaremba and I. Sutskever, "An empirical exploration of recurrent network architectures," in Proc. of ICML'15 32nd International Conference on Machine Learning, Lille, France, pp. 2342-2350, 2015.
  8. J. Chung, C. Gulcehre, K. Cho and Y. Bengio, "Empirical evaluation of gated recurrent neural networks on sequence modeling," in Proc. of NIPS 2014 Workshop on Deep Learning, Montreal, Canada, pp. 1-9, 2014.
  9. M. Liberatore and P. Shenoy, "UMass Trace Respository," http://traces.cs.umass.edu/
  10. S. Hansun, "A new approach of moving average method in time series analysis," in Proc. of 2013 Conference on New Media Studies (ConMedia), Tangerang, Indonesia, pp. 1-4, 2013. DOI: 10.1109/CoNMedia.2013.6708545
  11. Z. Wang and A. C. Bovik, "Mean squared error: love it or leave it? A new look at signal fidelity measures," IEEE Signal Processing Magazine, vol. 26, no. 1, pp. 98-117, 2009. DOI: 10.1109/MSP.2008.930649
  12. T. Chai and R. R. Draxler, "Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature," Geoscientific Model Development, vol. 7, no. 3, pp.1247-1250, 2014. DOI: 10.5194/gmd-7-1247-2014
  13. S. Srivastava and S. Lessmann, "A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data," Solar Energy, vol. 162, pp. 232-247, 2018. DOI: 10.1016/j.solener.2018.01.005
  14. B. Yildiz, J. I. Bilbao, J. Dore and A. Sproul, "Household electricity load forecasting using historical smart meter data with clustering and classification techniques," in Proc. of 2018 IEEE Innovative Smart Grid Technologies - Asia(ISGT Asia), Singapore, Singapore, pp. 873-879, 2018. DOI: 10.1109/ISGT-Asia.2018.8467837