Journal of IKEEE (전기전자학회논문지)

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

DOI QR Code

Prediction for Energy Demand Using 1D-CNN and Bidirectional LSTM in Internet of Energy

에너지인터넷에서 1D-CNN과 양방향 LSTM을 이용한 에너지 수요예측

  • Jung, Ho Cheul (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Sun, Young Ghyu (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Lee, Donggu (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Kim, Soo Hyun (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Hwang, Yu Min (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Sim, Issac (Dept. of Electronic Convergence Engineering, Kwangwoon University) ;
  • Oh, Sang Keun (Dept. of Power Electronics, PLASPO Co., Ltd.) ;
  • Song, Seung-Ho (Dept. of Electric Engineering, Kwangwoon University) ;
  • Kim, Jin Young (Dept. of Electronic Convergence Engineering, Kwangwoon University)
  • Received : 2019.03.08
  • Accepted : 2019.03.26
  • Published : 2019.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

As the development of internet of energy (IoE) technologies and spread of various electronic devices have diversified patterns of energy consumption, the reliability of demand prediction has decreased, causing problems in optimization of power generation and stabilization of power supply. In this study, we propose a deep learning method, 1-Dimention-Convolution and Bidirectional Long Short-Term Memory (1D-ConvBLSTM), that combines a convolution neural network (CNN) and a Bidirectional Long Short-Term Memory(BLSTM) for highly reliable demand forecasting by effectively extracting the energy consumption pattern. In experimental results, the demand is predicted with the proposed deep learning method for various number of learning iterations and feature maps, and it is verified that the test data is predicted with a small number of iterations.

에너지인터넷 기술의 발전과 다양한 전자기기의 보급으로 에너지소비량이 패턴이 다양해짐에 따라 수요예측에 대한 신뢰도가 감소하고 있어 발전량 최적화 및 전력공급 안정화에 문제를 야기하고 있다. 본 연구에서는 고신뢰성을 갖는 수요예측을 위해 딥러닝 기법인 Convolution neural network(CNN)과 Bidirectional Long Short-Term Memory(BLSTM)을 융합한 1Dimention-Convolution and Bidirectional LSTM(1D-ConvBLSTM)을 제안하고, 제안한 기법을 활용하여 시계열 에너지소비량대한 소비패턴을 효과적으로 추출한다. 실험 결과에서는 다양한 반복학습 횟수와 feature map에 대해서 수요를 예측하고 적은 반복학습 횟수로도 테스트 데이터의 그래프 개형을 예측하는 것을 검증한다.

Keywords

JGGJB@_2019_v23n1_134_f0001.png 이미지

Fig. 1. Structure of 2-D CNN algorithm. 그림 1. 2차원 CNN알고리즘 구조

JGGJB@_2019_v23n1_134_f0002.png 이미지

Fig. 2. Structure of 1-D CNN algorithm. 그림 2. 1차원 CNN알고리즘 구조

JGGJB@_2019_v23n1_134_f0003.png 이미지

Fig. 3. Structure of Recurrent Neural Network. 그림 3. RNN 구조

JGGJB@_2019_v23n1_134_f0004.png 이미지

Fig. 4. Structure of LSTM. 그림 4. LSTM 구조

JGGJB@_2019_v23n1_134_f0005.png 이미지

Fig. 5. Structure of BRNN. 그림 5. BRNN의 구조도

JGGJB@_2019_v23n1_134_f0006.png 이미지

Fig. 6. Structure of BLSTM. 그림 6. BLSTM의 구조도

JGGJB@_2019_v23n1_134_f0007.png 이미지

Fig. 7. Structure of proposed energy consumption prediction model. 그림 7. 제안하는 에너지 소비량 예측 모델 구조도

JGGJB@_2019_v23n1_134_f0008.png 이미지

Fig. 8. Training data using experiment. 그림 8. 실험에 사용될 학습 데이터

JGGJB@_2019_v23n1_134_f0009.png 이미지

Fig. 9. Test data using experiment. 그림 9. 실험에 이용한 테스트 데이터

JGGJB@_2019_v23n1_134_f0010.png 이미지

Fig. 12. Result of simulation at the number of kernel: 128 and (a) epoch: 5 (b) epoch: 20 (c) epoch: 40. 그림 12. (a) epoch: 5 (b) epoch: 20 (c) epoch 40이고 kernel의 개수가 128일 때 시뮬레이션 결과

JGGJB@_2019_v23n1_134_f0011.png 이미지

Fig. 15. Result of simulation at the number of kernel: 2 and (a) epoch: 5 (b) epoch: 20 (c) epoch: 40. 그림 15. (a) epoch: 5 (b) epoch: 20 (c) epoch 40이고 kernel의 개수가 2일 때 시뮬레이션 결과

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

JGGJB@_2019_v23n1_134_t0001.png 이미지

References

  1. F. Milletari, N. Navab and S. Ahmad, "V-Net: Fully convolutional neural networks for volumetric medical image segmentation," in Proc of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA, pp. 25-28, 2016. DOI: 10.1109/3DV.2016.79
  2. A. Kumar and Gerhard P. Hancke, "An energy-efficient smart comfort-sensing system based on the ieee 1451 standard for green buildings," IEEE Sensors, vol. 14, no. 12, pp. 4245-4251, 2014. DOI: 10.1109/JSEN.2014.2356651
  3. J. Dequaire, P. Ondruska, D. Rao, D. wang and I. posner, "Deep tracking in the wild: Endto-end tracking using recurrent neural networks," The International Journal of Robotics Research, vol. 37, no. 4, pp. 492-512, 2018. DOI: 10.1177/0278364917710543
  4. M. O. Mario, "Human activity recognition based on single sensor square HV acceleration images and convolutional neural networks," IEEE Sensors, vol. 19, no. 4, pp. 1487-1498, 2018. DOI: 10.1109/JSEN.2018.2882943
  5. D. Jeong, M. Baek and S. Lee, "Long-term prediction of vehicle trajectory based on a deep neural network," in Proc. of the 2017 International Conference on Information and Communication Technology Convergence (ICTC), Jeju, South Korea, pp. 725-727, 2017. DOI: 10.1109/ICTC.2017.8190764
  6. A. Tokgoz and G. Unal, "A RNN based time series approch for forecasting turkish electricity load," in Proc. of the 2018 26th Signal Processing and Communications Applications Conference(SIU), Izmir, Turkey, 2018. DOI: 10.1109/SIU.2018.8404313
  7. Z. Chen, Y. Liu and S. Liu, "Mechanical state prediction based on LSTM neural network," in Proc. of the 2017 36th Chinese Control Conference (CCC), Dalian, China, pp. 3876-3881, 2018. DOI: 10.23919/ChiCC.2017.8027963
  8. R. FukuoKa, H. Suzuki, T. Kitajima, A. Kuwahara and T. Yasuno, "Wind speed prediction model using LSTM and 1D-CNN," J-STAGE, vol. 22, no. 4, pp. 207-210, 2018. DOI: 10.2299/jsp.22.207
  9. K. A. Althelaya, E. M. Alfy and S. Mohammed, "Evalutaion of bidirectional LSTM for short-and long-term stock market prediction," in Proc. of the 2018 9th International Conference on Information and Communication Systems(ICICS), Irbid, Jordan, pp. 151-156, 2018. DOI: 10.1109/IACS.2018.8355458
  10. D. Niu, Z. Xia, Y. Liu, T. Cai and Y. Zhan, "Alstm: Adaptiv LSTM for durative Sequential data," in Proc of the 2018 30th International Conference on Tools with Artificial Intelligence (ICTAI), Volos, Greece, pp. 151-157, 2018. DOI: 10.1109/ICTAI.2018.00032
  11. A. Graves, N. Jaitly and A. R. Mohamed, "Hybrid speech recognition with deep bidirectional LSTM," in Proc. of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Repulic, pp. 273-278, 2013. DOI: 10.1109/ASRU.2013.6707742
  12. Y. H. Chen, T. Krishna, J. S. Emer and V. Sze, "Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks," IEEE Journal of Solid-State Circuits, vol. 52, no. 1, pp. 127-138, 2017. DOI: 10.1109/JSSC.2016.2616357
  13. 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
  14. T. D. Do, M. T. Duong, Q. V Dang and M. H. Le, "Real-time self-driving car navigation using deep neural network," in Proc. of the 2018 4th International Conference on Green Technology and Sustainable Development(GTSD), pp. 7-12, 2018. DOI: 10.1109/GTSD.2018.8595590
  15. Y. Bengio, I. Goodfellow and A. Courville, Deep learning, MIT Press, 2016.

Cited by

  1. 딥러닝 기법을 활용한 가구 부자재 주문 수요예측 vol.5, pp.2, 2019, https://doi.org/10.36498/kbigdt.2020.5.2.111