엘만 순환 신경망을 사용한 전력 에너지 시계열의 예측 및 분석
The Prediction and Analysis of the Power Energy Time Series by Using the Elman Recurrent Neural Network
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
In this paper, we propose an Elman recurrent neural network to predict and analyze a time series of power energy consumption. To this end, we consider the volatility of the time series and apply the sample variance and the detrended fluctuation analyses to the volatilities. We demonstrate that there exists a correlation in the time series of the volatilities, which suggests that the power consumption time series contain a non-negligible amount of the non-linear correlation. Based on this finding, we adopt the Elman recurrent neural network as the model for the prediction of the power consumption. As the simplest form of the recurrent network, the Elman network is designed to learn sequential or time-varying pattern and could predict learned series of values. The Elman network has a layer of “context units” in addition to a standard feedforward network. By adjusting two parameters in the model and performing the cross validation, we demonstrated that the proposed model predicts the power consumption with the relative errors and the average errors in the range of 2%~5% and 3kWh~8kWh, respectively. To further confirm the experimental results, we performed two types of the cross validations designed for the time series data. We also support the validity of the model by analyzing the multi-step forecasting. We found that the prediction errors tend to be saturated although they increase as the prediction time step increases. The results of this study can be used to the energy management system in terms of the effective control of the cross usage of the electric and the gas energies.
Abstract
In this paper, we propose an Elman recurrent neural network to predict and analyze a time series of power energy consumption. To this end, we consider the volatility of the time series and apply the sample variance and the detrended fluctuation analyses to the volatilities. We demonstrate that there exists a correlation in the time series of the volatilities, which suggests that the power consumption time series contain a non-negligible amount of the non-linear correlation. Based on this finding, we adopt the Elman recurrent neural network as the model for the prediction of the power consumption. As the simplest form of the recurrent network, the Elman network is designed to learn sequential or time-varying pattern and could predict learned series of values. The Elman network has a layer of “context units” in addition to a standard feedforward network. By adjusting two parameters in the model and performing the cross validation, we demonstrated that the proposed model predicts the power consumption with the relative errors and the average errors in the range of 2%~5% and 3kWh~8kWh, respectively. To further confirm the experimental results, we performed two types of the cross validations designed for the time series data. We also support the validity of the model by analyzing the multi-step forecasting. We found that the prediction errors tend to be saturated although they increase as the prediction time step increases. The results of this study can be used to the energy management system in terms of the effective control of the cross usage of the electric and the gas energies.
참고문헌 (21)
- 안병훈, "계절 ARIMA 모형을 이용한 국내 지역별 전력사용량 중장기수요예측", 한국산학기술학회논문지, 16(12), pp.8576~8584 (2015), 한국산학기술학회[DOI]
- Bergmeir, C., "A note on the validity of cross-validation for evaluating autoregressive time series prediction", Computational Statistics and Data Analysis, 120(C), pp.70~83 (2018)[DOI]
- Black, F., "The Pricing of Options and Corporate Liabilities", J. Polit. Econ, 81(3), pp.637~654 (1973)
- Bontempi, G., "Machine Learning Strategies for Time Series Forecasting;Business Intelligence, eBISS 2012", Lecture Notes in Business Information Processing, 138 (2012)
- Box, G., "Time Series Analysis : Forecasting and Control" (2008), Wiley
- Cox, J., "Option pricing : A simplified approach", J. Financial Econ., 7, pp.229~263 (1979)[DOI]
- Elman, J., "Finding Structure in Time", Cognitive Science, 14, pp.179~211 (1990)[DOI]
- Hochreiter, S., "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)[DOI]
- 정현우, "전력계통 유지보수 및 운영을 위한 향후 4주의 일 최대 전력수요예측", 전기학회논문지, 63(11), pp.1497~1502 (2014), 대한전기학회[DOI]
- 김시연, "계절 ARIMA 모형을 이용한 104주 주간 최대 전력수요예측", 조명.전기설비학회논문지, 28(1), pp.50~56 (2014), 한국조명.전기설비학회
- 이창용, "자동차 건조 공정 에너지 예측 모형을 위한 공조기 온도 시계열 데이터의 상관관계 분석", 한국산업경영시스템학회지, 37(2), pp.27~34 (2014), 한국산업경영시스템학회
- 이형로, "Support Vector Regression에 기반한 전력 수요 예측", 산업공학(IE interfaces), 24(4), pp.351~361 (2011), 대한산업공학회
- 남봉우, "다중회귀분석법을 이용한 지역전력수요예측 알고리즘", 조명.전기설비학회논문지, 22(2), pp.63~70 (2008), 한국조명.전기설비학회
- Pagan, A., "The econometrics of financial markets", J. Empirical Finance, 3(1), pp.15~102 (1996)[DOI]
- 박영진, "뉴로-퍼지 모델 기반 전력 수요 예측 시스템: 시간,일간,주간 단위 예측", 한국지능시스템학회 논문지, 14(5), pp.533~538 (2004), 한국지능시스템학회
- Peng, C., "Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series", Chaos, 49(1), pp.82~87 (1994)
- Schmidhuber, J., "Deep Learning in Neural Networks : An Overview", Neural Networks, 61, pp.85~117 (2015)[DOI]
- 심성철, "제한적 시장을 가지는 천연자원의 가격예측 모형에 관한 연구", 한국산업경영시스템학회지, 37(4), pp.82~89 (2014), 한국산업경영시스템학회
- Sohn, K., "Fuzzy Time Series Models with Triangular Fuzzy Numbers as Parameters", Journal of Korean Data Analysis Society, 3(2), pp.149~162 (2001)
- J. Beran, "Statistics for Long- Memory Processes", pp.1994, Chapman & Hall