조건적 제한된 볼츠만머신을 이용한 중기 전력 수요 예측
Mid-Term Energy Demand Forecasting Using Conditional Restricted Boltzmann Machine
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
미래에 스마트 그리드 도입을 위해 전력수요예측은 중요한 연구 분야 중 하나이다. 하지만 전력데이터는 많은 외부적 요소들에 영향을 받기 때문에 예측하기 어렵다. 기존의 전력수요예측 방법들은 가공되지 않은 전력데이터를 그대로 이용하기 때문에 정확도 높은 예측을 하는데 한계가 있어왔다. 본 논문에서는 가공되지 않은 전력데이터를 이용하는 전력수요예측의 문제를 해결하기 위해 확률기반 학습알고리즘을 제안한다. 확률 모델은 전력데이터의 확률적 특성을 분석하기에 적합하다. 제안한 모델의 중기 전력수요예측 성능을 비교하기 위해 신경망 네트워크 중 하나인 순환신경망과 성능 비교를 해보았다. 매사추세츠 대학에서 제공한 전력데이터를 이용하여 성능 비교를 한 결과 본 논문에서 제안한 확률기반 학습알고리즘이 중기 수요예측에 더 좋은 성능을 나타냄을 확인하였다.
Abstract
Electric power demand forecasting is one of the important research areas for future smart grid introduction. However,It is difficult to predict because it is affected by many external factors. Traditional methods of forecasting power demandhave been limited in making accurate prediction because they use raw power data. In this paper, a probability-basedCRBM is proposed to solve the problem of electric power demand prediction using raw power data. The stochastic modelis suitable to capture the probabilistic characteristics of electric power data. In order to compare the mid-term powerdemand forecasting performance of the proposed model, we compared the performance with Recurrent NeuralNetwork(RNN). Performance comparison using electric power data provided by the University of Massachusetts showedthat the proposed algorithm results in better performance in mid-term energy demand forecasting.
참고문헌 (12)
- Y. Fu, "Multi-level load forecasting system based on power grid planning platform with integrated information", Proc. of 2017 Chinese Automation Congress(CAC), pp.933~938 (2017), IEEE
- D. Zhang, "Mid-long term electricity demand forecasting based on markov chain screening combination forecasting models", Power System Protection and Control, 44(12), pp.63~67 (2016)[DOI]
- I. E. Kafazi, "Modeling and forecasting energy demand", Proc. of 2016 International Renewable and Sustainable Energy Conference (IRSEC), pp.746~750 (2016), IEEE
- L. Wei, "Prediction of energy production and energy consumption based on BP neural networks", Proc. of 2008 IEEE International Symposium on Knowledge Acquisition and Modeling Workshop, pp.15~19 (2008)
- Mauri Aparecido de Oliveira, "The influence of ARIMA-GARCH parameters in feed forward neural networks prediction", Neural Computing and Applications, 20(5), pp.687~701 (2011), Springer Science and Business Media LLC[DOI]
- "UMass website"[URL]
- A. Fischer, "An introduction to restricted boltzmann machines" (2012), Springer
- G. W. Taylor, "Modeling human motion using binary latent variables", Proc. of Twentieth Annual Conference on Neural Information Processing Systems, pp.1345~1352 (2006)
- G. E. Hinton, "A practical guide to training restricted boltzmann machines" (2012), Springer
- Geoffrey E. Hinton, "Training Products of Experts by Minimizing Contrastive Divergence", Neural Computation, 14(8), pp.1771~1800 (2002), MIT Press - Journals[DOI]
- S. Wang, "A differentiated DBN model based on CRBM for time series forecasting", Proc. of 2017 IEEE 17th International Conference on Communication Technology (ICCT), pp.1926~1931 (2017)
- X. Cai, "Forecasting high dimensional volatility using conditional restricted boltzmann machine on GPU", Proc. of Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW), pp.1979~1986 (2012)