연구동향 분석
박사

전력 데이터 분석을 위한 딥 러닝 : 수요 예측, 부하 특징 분석과 결측 처리 = Deep Learning for Electric Load Data Analytics: Forecasting, Feature Extraction, and Missing Imputation

류승형 2020년

논문상세정보
인용/피인용
' 전력 데이터 분석을 위한 딥 러닝 : 수요 예측, 부하 특징 분석과 결측 처리 = Deep Learning for Electric Load Data Analytics: Forecasting, Feature Extraction, and Missing Imputation' 의 주제별 논문영향력
논문영향력 선정 방법
논문영향력 요약
주제
  • 딥 러닝
  • 부하 데이터 분석
  • 스마트 그리드
동일주제 총논문수 논문피인용 총횟수 주제별 논문영향력의 평균
2,006 0

0.0%

' 전력 데이터 분석을 위한 딥 러닝 : 수요 예측, 부하 특징 분석과 결측 처리 = Deep Learning for Electric Load Data Analytics: Forecasting, Feature Extraction, and Missing Imputation' 의 참고문헌

  • [90] D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” arXiv preprint arXiv:1312.6114, Dec. 2013.
  • [88] C. C. Aggarwal and C. K. Reddy, Data Clustering: Algorithms and Applications. CRC press, 2013.
  • [81] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016, http: //www.deeplearningbook.org.
  • [72] Y. S. Abu-Mostafa, M. Magdon-Ismail, and H.-T. Lin, Learning from data. AMLBook, 2012.
  • [70] G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science, vol. 313, no. 5786, pp. 504–507, Jul. 2006.
  • [61] G. Mateos and G. B. Giannakis, “Load curve data cleansing and imputation via sparsity and low rank,” IEEE Trans. on Smart Grid, vol. 4, no. 4, pp. 2347–2355, Dec. 2013.
  • [4] M. H. Albadi and E. El-Saadany, “A summary of demand response in electricity markets,” Electric Power Systems Research, vol. 78, no. 11, pp. 1989–1996, Nov. 2008.
  • [27] “China maintains lead in global smart meter market.” [Online]. Available: https://www.smart-energy.com/industry-sectors/data analytics/ global-smart-meter-market-navigant/
  • [25] “How many smart meters are installed in the United States, and who has them?” [Online]. Available: https://www.eia.gov/tools/faqs/faq.php?id=108&t=3
  • [1] A. Ipakchi and F. Albuyeh, “Grid of the future,” IEEE Power and Energy Magazine, vol. 7, no. 2, pp. 52–62, Mar.-Apr. 2009.
  • Wind turbine blade breakage monitoring with deep autoencoders
    vol . 9 , no . 4 , pp . 2824–2833 [2018]
  • Why does unsupervised pre-training help deep learning ?
    vol . 11 , pp . 625–660 , [2010]
  • Wavelet-based load profile representation for smart meter privacy
    pp . 1–6 . [2013]
  • Wasserstein auto-encoders
    [2017]
  • Two-stage load pattern clustering using fast wavelet transformation ,
    vol . 7 , no . 5 , pp . 2250–2259 , [2016]
  • Topology-based estimation of missing smart meter readings
    vol . 11 , no . 1 , p. 224 , [2018]
  • The time series approach to short term load forecasting
    vol . 2 , no . 3 , pp . 785–791 , [1987]
  • The path of the smart grid
    vol . 8 , no . 1 , pp . 18–28 , [2010]
  • The daily and hourly energy consumption and load forecasting using artificial neural network method : a case study using a set of 93 households in Portugal ,
    vol . 62 , pp . 220–229 , [2014]
  • Tensorflow : A system for large-scale machine learning
    pp . 265–283 . [2016]
  • Sparse and redundant representation-based smart meter dataCompression and pattern extraction
    vol . 32 , no . 3 , pp . 2142–2151 [2017]
  • Smart metering load dataCompression based on load feature identification
    vol . 7 , no . 5 , pp . 2414–2422 [2016]
  • Smart meter deployment in Europe : AComparativeCase study on the impacts of national policy schemes
    vol . 144 , pp . 22–32 , [2017]
  • Short-term load forecasting for microgrids based on artificial neural networks
    vol . 6 , no . 3 , pp . 1385–1408 , [2013]
  • Short-term load forecasting based on an adaptive hybrid method
    vol . 21 , no . 1 , pp . 392–401 , [2006]
  • Short-term load forecasting based on ResNet and LSTM ,
    pp . 1–6 . [2018]
  • Short-term electricity demand forecasting using double seasonal exponential smoothing
    vol . 54 , no . 8 , pp . 799–805 [2003]
  • Short term electricity load forecasting on varying levels of aggregation ,
    [2014]
  • Seasonal variation in household electricity demand : AComparison of monitored and synthetic daily load profiles
    vol . 179 , pp . 292–300 [2018]
  • Robust real-time load profile encoding andClassification framework for efficient power systems operation
    vol . 30 , no . 4 , pp . 1897–1904 [2015]
  • Residential load profileClustering via deepConvolutional autoencoder
    pp . 1–6 [2018]
  • Rectifier nonlinearities improve neural network acoustic models
    vol . 30 , [2013]
  • Reconstruction of power system measurements based on enhanced denoising autoencoder
    [2019]
  • Overview and performance assessment of the clustering methods for electrical load pattern grouping
    vol . 42 , no . 1 , pp . 68–80 [2012]
  • Neural networks for short-term load forecasting : A review and evaluation
    vol . 16 , no . 1 , pp . 44–55 , [2001]
  • Neural network based short term load forecasting
    vol . 8 , no . 1 , pp . 336–342 , [1993]
  • Multilayer feedforward networks with a nonpolynomial activation function can approximate any function
    vol . 6 , no . 6 , pp . 861–867 [1993]
  • Multi-resolution load profile clustering for smart metering data
    vol . 31 , no . 6 , pp . 4473–4482 , [2016]
  • Machine learning-based Lithium-Ion battery capacity estimation exploiting multi-channel charging profiles
    vol . 7 , pp . 75 143–75 152 [2019]
  • Load profiling and its application to demand response : A review
    vol . 20 , no . 2 , pp . 117–129 [2015]
  • Load forecastingin Applied Mathematics for Restructured Electric Power Systems
    pp . 269–285 . [2005]
  • Learning-based adaptive imputation methodwith knn algorithm for missing power data
    vol . 10 , no . 10 , p. 1668 , [2017]
  • K-means based load estimation of domestic smart meter measurements
    vol . 194 , pp . 333–342 [2017]
  • Intelligent neural network based STLF
    vol . 4 , no . 1 , pp . 17–27 , [2009]
  • Implementierung und Analyse von tiefen Architekturen in R
    [2013]
  • Image inpainting for irregular holes using partial convolutions
    pp . 85–100 . [2018]
  • Household monthly electricity consumption pattern mining : A fuzzy clustering-based model and a case study
    vol . 141 , pp . 900–908 [2017]
  • Household energy consumption segmentation using hourly data
    vol . 5 , no . 1 , pp . 420–430 , [2014]
  • Handling bad or missing smart meter data through advanced data imputation
    pp . 1–5 [2016]
  • From Data Mining to Knowledge Discovery in Databases
    vol . 17 , no . 3 , p. 37 [1996]
  • Extracting and composing robust features with denoising autoencoders
    pp . 1096–1103 . [2008]
  • Extensions to the k-means algorithm for clustering large data sets with categorical values .
    vol . 2 , no . 3 , pp . 283– 304 [1998]
  • Ensemble deep learning for regression and time series forecasting.
    pp . 21–26 . [2014]
  • Electric load forecasting using an artificial neural network
    vol . 6 , no . 2 , pp . 442–449 , [1991]
  • Dropout : a simple way to prevent neural networks from overfitting.
    vol . 15 , no . 1 , pp . 1929–1958 [2014]
  • Detection and classification of transmission line faults based on unsupervised feature learning and convolutional sparse autoencoder
    vol . 9 , no . 3 , pp . 1748–1758 [2018]
  • Denoising criterion for variational auto-encoding framework
    pp . 2059–2065 . [2017]
  • Deep neural networks for ultra-short-term wind forecasting
    pp . 1657–1663 . [2015]
  • Deep neural network based load forecast
    vol . 18 , no . 3 , pp . 258–262 [2014]
  • Deep neural network based demand side short term load forecasting
    vol . 10 , no . 1 , pp . 1–20 , [2017]
  • Deep learning for solar power forecasting – an approach using autoencoder and LSTM neural networks ,
    pp . 2858–2865 . [2016]
  • Deep belief network based electricity load forecasting : An analysis of Macedonian case
    vol . 115 , pp . 1688–1700 , [2016]
  • Data-driven baseline estimation of residential buildings for demand response
    vol . 8 , no . 9 , pp . 10 239–10 259 , [2015]
  • Data-based ¨ method for creating electricity use load profiles using large amount of customerspecific hourly measured electricity use data
    vol . 87 , no . 11 , pp . 3538–3545 , [2010]
  • Data mining based framework for exploring household electricity consumption patterns : A case study in China context
    vol . 195 , pp . 773–785 [2018]
  • Data compression in smart distribution systems via singular value decomposition
    vol . 8 , no . 1 , pp . 275–284 , [2017]
  • Convolutional autoencoder based feature extraction and clustering for customer load analysis
    to appear [2019]
  • Convolutional Neural Networks for Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control
    vol . 9 , no . 4 , pp . 3259–3269 [2018]
  • Compression of smart meter big data : A survey
    vol . 91 , pp . 59–69 , [2018]
  • Clustering of residential electricity customers using load time series
    vol . 237 , pp . 11–24 [2019]
  • Clustering of connection points and load modeling in distribution systems
    vol . 28 , no . 2 , pp . 1255–1265 [2013]
  • Cleaning method for status monitoring data of power equipment based on stacked denoising autoencoders
    vol . 5 , pp . 22 863–22 870 [2017]
  • Best practices for convolutional neural networks applied to visual document analysis
    pp . 958–962 . [2003]
  • AutoImpute : Autoencoder based imputation of single-cell RNA-seq data
    vol . 8 , no . 1 , p. 16329 , [2018]
  • Applying wavelets to short-term load forecasting using PSO-based neural networks ,
    vol . 24 , no . 1 , pp . 20–27 , [2009]
  • Analysis of PCA based compression and denoising of smart grid data under normal and fault conditions
    pp . 1–6 . [2013]
  • An efficient realization of deep learning for traffic data imputation
    vol . 72 , pp . 168–181 , [2016]
  • An efficient data characterization and reduction scheme for smart metering infrastructure
    vol . 14 , no . 10 , pp . 4300–4308 , [2018]
  • Adam : A Method for Stochastic Optimization
    pp . 1–15 . [2015]
  • ANN-based short-term load forecasting in electricity markets ,
    vol . 2 ,
  • A study on the use of imputation methods for experimentation with Radial Basis Function Network classifiers handling missing attribute values : The good synergy between RBFNs and EventCovering method
    vol . 23 , no . 3 , pp . 406–418 [2010]
  • A shape-based clustering method for pattern recognition of residential electricity consumption
    vol . 212 , pp . 475–488 [2019]
  • A review of electric load classification in smart grid environment
    vol . 24 , pp . 103–110 [2013]
  • A practical guide to training restricted Boltzmann machines
    pp . 599–619 [2012]
  • A novel load clustering method based on entropy features considering longitudinal characteristics
    pp . 1–5 [2018]
  • A novel approach to shortterm load forecasting using fuzzy neural networks ,
    vol . 13 , no . 2 , pp . 480–492 , [1998]
  • A novel approach for load profiling in smart power grids using smart meter data
    vol . 165 , pp . 191–198 , [2018]
  • A neural network short term load forecasting model for the Greek power system
    vol . 11 , no . 2 , pp . 858–863 [1996]
  • A framework for baseline load estimation in demand response : Data mining approach
    pp . 638–643 . [2014]
  • A direct adaptive method for faster backpropagation learning : The RPROP algorithm
    pp . 586–591 [1993]
  • A comparison of univariate methods for forecasting electricity demand up to a day ahead ,
    vol . 22 , no . 1 , pp . 1–16 , [2006]
  • A clustering-based fuzzy wavelet neural network model for short-term load forecasting
    vol . 23 , no . 05 , p. 1350024 [2013]