양방향 LSTM을 활용한 전력수요 데이터 예측 기법 연구
Electronic Demand Data Prediction using Bidirectional Long Short Term Memory Networks
0
조회
0
다운로드
14
인용
0
참고문헌
키워드
초록
산업 분야에서 전력수요 예측은 예측 전력량보다 실측 전력량이 일정 범위에서 벗어나면 이상 징후로 판별하여 기계 오작동, 전원 꺼짐 등의 이상 현상을 탐지하는데 활용되기도 한다. 전력 데이터는 계절성과 추세성이 강한 시계열 데이터이기 때문에 예측이 어려운 편이다. 본 연구에서는 딥 러닝 기반의 알고리즘인 LSTM과 더불어 최근에 각광받고 있는 알고리즘인 양방향(Bi-Directional) LSTM 알고리즘을 활용한 전력 예측 모형을 수립하였으며, 해당 모형은 4년간의 전력 데이터를 활용하여 학습, 평가, 검증하였다.
Abstract
Power demand prediction is used to detect anomalies such as machine malfunction and power off when the measured power amount deviates from the predicted power amount by a certain range in the industrial sector. Power data is difficult to predict because it is time series data with strong seasonality and trend. In this paper, a power prediction model based on bi-directional LSTM algorithm, which is a deep learning based algorithm and the most popular algorithm in recent years, has been established along with LSTM. The model was learned, evaluated, and verified using four years of power data.
참고문헌 (15)
- 단기 전력수요 예측 기법 및 적용 방안에 관한 연구, "한국전력거래소", ~ (2011)
- Box, George EP, "Time series analysis: forecasting and control" (1976), Holden-Day
- Zhang, G. Peter, "Time series forecasting using a hybrid ARIMA and neural network model", Neurocomputing, 50, pp.159~175 (2003)
- Contreras, Javier, "ARIMA models to predict next-day electricity prices", IEEE transactions on power systems, 18(3), pp.1014~1020 (2003)
- Pai, Ping-Feng, "A hybrid ARIMA and support vector machines model in stock price forecasting", Omega, 33(6), pp.497~505 (2005)
- Kong, Weicong, "Short-Term Residential Load Forecasting based on Resident Behaviour Learning", IEEE Transactions on Power Systems, 33(1), pp.1087~1088 (2018)
- Marino, Daniel L., "Building energy load forecasting using deep neural networks", Industrial Electronics Society, IECON 2016-42nd Annual Conference of the IEEE (2016), IEEE
- Zheng, Huiting, "Short-term load forecasting using EMD-LSTM neural networks with a Xgboost algorithm for feature importance evaluation", Energies, 10(8), pp.1168~ (2017)
- Pezzulli, Sergio, "The seasonal forecast of electricity demand: A hierarchical Bayesian model with climatological weather generator", Applied Stochastic Models in Business and Industry, 22(2), pp.113~125 (2006)
- Yuan, Xiaohui, "Short-term wind power prediction based on LSSVM–GSA model", Energy Conversion and Management, 101, pp.393~401 (2015)
- P.J. Brockwell, "Time Series: Theory and Methods, Springer Series in Statistics", ~ (1986)
- Adam Gibson, "Deep Learning : A Practitioner’s Approach" (2016), O’REILLY & Associates Inc.
- 방성혁, "순환신경망 기반의 사용자 의도 예측 모델", 정보과학회논문지, 45(4), pp.360~369 (2018), 한국정보과학회[DOI]
- ÖzalYildirim, "A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification", Computers in Biology and Medicine, 96, pp.189~202 (2018)
- T. Robinson, "An application of recurrent nets to phone probability estimation", IEEE Transactions on Neural Networks, 5(2), pp.298~305 (1994)