제조업 전력량 예측 정확성 향상을 위한 Double Encoder-Decoder 모델 = Double Encoder-Decoder Model for Improving the Accuracy of the Electricity Consumption Prediction in Manufacturing

국문 초록 (Abstract)

본 연구는 기존 전력량 예측 모델의 구조를 변경하여 모델의 예측 능력을 향상 시킬 수 있는 방법에 관하여 연구하였다. 전기에 대한 수요는 그 어느 때보다 증가하고 있다. 산업 부문에서는 그 어느 부문 보다 전기 소모량이 많음으로, 더욱 정확한 공장 지역의 전력량 소모 예측 모델이 잉여 에너지 생산을 줄이기 위해 주목을 받고 있다. 우리는 2개의 개별 encoder와 한개의 decoder를 사용하여, 장기와 단기 데이터를 모두 사용하는 double encoder-decoder 모델을 제안한다. 우리는 제안된 모델을 세홍(주)의 생산 구역에서 2019년 1월 1일부터 2019년 6월 30일 까지 모집된 전력 소모량 데이터에서 평가 하였다. double encoder-decoder 모델은 기존의 encoder-decoder 모델을 사용했을 때와 비교하여 약 10 %의 평균 절대 비율 오차의 감소를 기록 하였다. 본 결과는 제안한 모델이 encoder-decoder 모델에 비해 생산 지역의 전력 사용량의 예측을 더 정확하게 하는 모델임을 보여준다.

다국어 초록 (Multilingual Abstract)

This paper investigated methods to improve the forecasting accuracy of the electricity consumption prediction model. Currently, the demand for electricity has continuously been rising more than ever. Since the industrial sector uses more electricity than any other sectors, the importance of a more precise forecasting model for manufacturing sites has been highlighted to lower the excess energy production. We propose a double encoder-decoder model, which uses two separate encoders and one decoder, in order to adapt both long-term and short-term data for better forecasts. We evaluated our proposed model on our electricity power consumption dataset, which was collected in a manufacturing site of Sehong from January 1st, 2019 to June 30th, 2019 with 1 minute time interval. From the experiment, the double encoder-decoder model marked about 10% reduction in mean absolute error percentage compared to a conventional encoder-decoder model. This result indicates that the proposed model forecasts electricity consumption more accurately on manufacturing sites compared to an encoder-decoder model.

참고문헌 (Reference)

1 J. Redmon, "You only look once: Unified, real-time object detection" 2016

2 F. Rosenblatt, "The perceptron : A probabilistic model for information storage and organization in the brain" 65 (65): 386-408, 1958

3 T. Hastie, "The Elements of statistical learning: data mining, inference, and prediction" Springer 2017

4 M. Abadi, "TensorFlow: learning functions at scale" 2016

5 S. -Y. Shih, "Temporal pattern attention for multivariate time series forecasting" 108 (108): 1421-1441, 2019

6 Drucker, Harris, "Support vector regression machines" 155-161, 1997

7 A. Graves, "Supervised sequence labelling with recurrent neural networks" Springer 2012

8 W. Kong, "Short-term residential load forecasting based on LSTM recurrent neural network" 10 (10): 841-851, 2019

9 G. Dudek, "Short-Term Load Forecasting Using Random Forests" 821-828, 2015

10 Sutskever, Ilya, "Sequence to sequence learning with neural networks" 3104-3112, 2014

11 Y. Bengio, "Representation Learning : A Review and New Perspectives" 35 (35): 1798-1828, 2013

12 L. Breiman, "Random Forests" 45 (45): 5-32, 2001

13 L. Bottou, "On-Line Learning in Neural Networks" 9-42, 1999

14 D. Bahdanau, "Neural Machine Translation by Jointly Learning to Align and Translate" 2015

15 M. Leshno, "Multilayer feedforward networks with a nonpolynomial activation function can approximate any function" 6 (6): 861-867, 1993

16 G. Lai, "Modeling Longand Short-Term Temporal Patterns with Deep Neural Networks" 2018

17 R. K. Agrawal, "Long term load forecasting with hourly predictions based on long-short-term-memory networks" 2018

18 Hochreiter, Sepp, "Long shortterm memory" 9 (9): 1735-1780, 1997

19 J. Cheng, "Long Short-Term Memory-Networks for Machine Reading" 2016

20 K. Cho, "Learning phrase representations using RNN encoder–decoder for statistical machine translation" 2014

21 G. E. P. Box, "Jenkins, Time series analysis : forecasting and control" Holden-Day 1976

22 El Hihi, Salah, "Hierarchical recurrent neural networks for long-term dependencies" 493-499, 1996

23 Song, Fengxi, "Feature selection using principal component analysis" IEEE 1 : 27-30, 2010

24 Y. Cho, "Energy info. Korea"

25 E. Erdogdu, "Electricity demand analysis using cointegration and ARIMA modelling : A case study of Turkey" 35 (35): 1129-1146, 2007

26 J. Zheng, "Electric load forecasting in smart grids using Long-Short-Term-Memory based Recurrent Neural Network" 2017

27 E. E. Elattar, "Electric Load Forecasting Based on Locally Weighted Support Vector Regression" 40 (40): 438-447, 2010

28 T. Luong, "Effective Approaches to Attention-based Neural Machine Translation" 2015

29 G. Huang, "Densely connected convolutional networks" 2017

30 K. He, "Deep residual learning for image recognition" 2016

31 J. Bedi, "Deep learning framework to forecast electricity demand" 238 : 1312-1326, 2019

32 I. Goodfellow, "Deep learning" MIT Press 2017

33 Hall, Mark A, "Correlation-based Feature Selection for Machine Learning" The University of Waikato 1999

34 D. Barber, "Bayesian reasoning and machine learning" Cambridge University Press 2018

35 D. P. Kingma, "Adam: A method for stochastic optimization" 2015

36 T. He, "Accelerating Multi-layer Perceptron based short term demand forecasting using Graphics Processing Units" 2009

37 A. Parikh, "A Decomposable Attention Model for Natural Language Inference" 2016