권역별 인공신경망 모델을 이용한 전국 기상관측소의 일사량 추정
Estimation of Solar Irradiance at Weather Stations in Korea Using Regionally Trained Artificial Neural Network Models
0
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
일사량을 파악하는 것은 태양광 발전 시스템을 설치하고 운영하는 데 있어서 필수적이다. 본 연구에서는 기상청에서 운영하고 있는 94개 기상관측소의 일사량을 추정하기 위해 기상 관측 자료와 천리안 위성영상을 이용하였다. 우선, 천리안 위성의 가시광 채널 영상으로부터 산출한 구름지수에 K-평균 군집화를 적용하여 한국을 13개의 권역으로 분류하였으며, 이 중 일사량 관측값이 존재하는 10개 권역의 일사량 추정을 위해 인공신경망 모델을 훈련시켰다. 인공신경망의 입력변수로는 상호정보량 특징선택을 통해 총 10개의 변수가 선택되었고, MATLAB 소프트웨어를활용하여 인공신경망 모델을 구축하였다. 교차검증 결과, 본 연구의 모델은 상관계수 0.96, RMSE 80.87 W/m2 (22.62%)의 오차를 보였으며, 권역 분류를 적용하지 않은 전국적 훈련모델에 비해 오차가 약 2%p 감소하는 효과가있었다. 이러한 권역별 일사량 모델을 활용하여 기상청의 기상관측소 94개 지점의 일사량을 추정하였다. 본 연구의권역별 인공신경망 모델을 활용하면 일사계는 없지만 기본적인 기상요소가 관측되고 있는 관측소의 실시간 일사량을 20% 초반대의 오차 수준으로 추정할 수 있을 것으로 기대된다.
Abstract
The ability to estimate solar irradiance is necessary for efficient installation and management of solar photovoltaic systems. Weather observation data and Communication, Ocean and Meteorological Satellite (COMS) images were used to estimate solar irradiance at 94 Korea Meteorological Administration (KMA) weather stations. First, Korea was divided into 13 regions by applying K-means clustering to cloud indices derived from visible channel images of COMS, and artificial neural network (ANN) models were trained in 10 regions. Ten variables were selected as inputs for ANN by mutual information feature selection to build multi-layer perceptron networks in MATLAB. The cross validation resulted in a 0.96 correlation coefficient and 80.87 W/m2 (22.62%) root mean square error (RMSE). The regionally trained ANN models could reduce the relative RMSE by 2%p compared to non-regionally trained models. The solar irradiances at the 94 KMA weather stations were estimated by applying these models. The solar irradiance of points that have no measured data from a pyranometer can be estimated using these regional ANN models.
참고문헌 (43)
- Assouline, D., "Quantifying rooftop photovoltaic solar energy potential : A machinelearning approach", Solar Energy, 141, pp.278~296 (2017)
- Battiti, R., "Using mutual information for selecting feat ures in supervised neural net learning", IEEE Transactions on Neural Networks, 5(4), pp.537~550 (1994)
- Bechini, L., "Modelling, interpolation and stochastic simulation in space and time of global solar radiation, Argriculture", Ecosystem and Environment, 8, pp.29~42 (2000)
- Bezzi, M., "A comprison of some kriging interpolation methods for the production of solar radiation maps", pp.1~17 (2005), Geomatics Workbooks
- Bishop, C. M., "Neural Networks for Pattern Recognition", pp.482~ (1995), Oxford University Press
- Calinski, T., "A dendrite method for cluster analysis", Communications in Statistics, 3, pp.1~27 (1974)
- 최원석, "수정된 Heliosat-II 방법과 COMS-MI 위성 영상을 이용한 한반도 일사량 추정", 한국측량학회지, 33(5), pp.463~472 (2015), 한국측량학회[DOI]
- Dorvlo, A. S. S., "Solar radiation estimatino using artificial neural networks", Applied Energy, 71, pp.307~319 (2002)
- Eissa, Y., "Artificial neural network based model for retrieval of the direct normal, diffuse horizontal and global horizontal irradiances using SEVIRI images", Solar Energy, 89, pp.1~16 (2013)
- Gardner, M. W., "Artificial neural networks(the multilayer perceptron)-a review of applications in the atmosphere sciences", Atmospheric Environment, 32(14), pp.2627~2636 (1998)
- Hammer, A., "Solar energy assessment using remote sensing technologies", Remote Sensing of Environment, 86, pp.423~432 (2003)
- Haykin, S. O., "Neural Network and Learning Machines", pp.936~ (2009), Pearson
- Jamaly, M., "Spatiotemporal interpolation and forecast of irradiance data using Kriging", Solar Energy, 158, pp.407~423 (2017)
- Jolliffe, I. T., "Principal Component Analysis", pp.487~ (1986), Springer
- Journee, M., "Improving the spatio-temporal distribution of surface solar radiation data by merging ground and satellite measurements", Remote Sensing of Environment, 114, pp.2692~2704 (2010)
- Kaastra, L., "Designing a neural network for forecasting financial and economic time series", Neurocomputing, 10, pp.215~236 (1996)
- Kim, C. K., "Toward improved solar irradiance forecasts : comparison of the global horizontal irradiances derived from the COMS satellite imagery over the Korean peninsula", Pure Applied Geophysics, 174, pp.2773~2792 (2017)
- 김하양, "국내의 시간에 따른 수평면전일사량 상관식 제안 및 정확성 평가(I)", 신재생에너지, 12, pp.30~35 (2016), 한국신·재생에너지학회
- 김진솔, "울릉도 녹색섬 조성을 위한 태양광 발전 잠재량 평가", 한국자원공학회지, 51(4), pp.513~524 (2014), 한국자원공학회[DOI]
- 이정호, "천리안 기상영상기 영상을 이용한 한반도 지역의 수평면 전일사량 추정", 대한원격탐사학회지, 29(1), pp.151~160 (2013), 대한원격탐사학회[DOI]
- Linares-Rodriguez, A., "An artificial neural network ensemble model for estimating global solar radiation from Meteosat satellite images", Energy, 61, pp.636~645 (2013)
- Liou, K. N., "An Introductin to Atmospheric Radiation", pp.583~ (2002), Academic Press
- MacKay, D. J. C., "Bayesian interpolation", Neural computation, 4(3), pp.415~447 (1992)
- MacQueen, J. B., "Some Methods for classification and analysis of multivariate observations", Proceeding of 5th Berkeley Symposium on Mathematical Statistics and Probability, 1, pp.281~297 (1967)
- May R., "Review of Input Variables Selection Methods for Artificial Neural Networks In Artificial Neural Networks - Methodological Advance and Biomedical Applications", pp.19~44 (2011), IntechOpen
- Noia, M, "Solar irradiance estimation from geostationary satellite data : Statistical models", Solar Energy, 51(6), pp.449~456 (1993)
- Noia, M, "Solar irradiance estimation from geostationary satellite data : Physical models", Solar Energy, 51(6), pp.457~465 (1993)
- Palmer, D., "Interpolating and estimating horizontal diffuse solar irradiation to provide UK-Wide coverage : selection of the best performing models", Energies, 10(181), pp.1~23 (2017)
- Peng H., "Feture selection based on mutual information : criteria ofmax-dependency, max-relevance, and min-redundancy", IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), pp.1226~1238 (2005)
- Perez, R., "A new operational model for satellite-derived irradiances : description and validation", Solar Energy, 73(5), pp.307~317 (2002)
- Rigollier, C., "On the clear sky model of the ESRA-European solar radiation atlas-with respect to the heliosat method", Solar Energy, 68(1), pp.33~48 (2000)
- Rigollier, C., "The method Heliosat-2 for deriving shortwave solar radiation from satellite images", Solar Energy, 77, pp.159~169 (2004)
- Salvador, S., "Learning states and rules for detecting anomalies in time series", Applied Intelligence, 23(3), pp.2170~2176 (2005)
- Sen, Z., "Spatial interpolation and estimation of solar irradiation by cumulative semivariograms", Solar Energy, 71(1), pp.11~21 (2001)
- Shannon, C. E., "A mathematical theory of communication", Bell System Technological J, 27, pp.379~423 (1948)
- 송진영, "그린캠퍼스 조성을 위한 부경대학교 옥상 태양광 발전 시스템의 잠재성 평가", 한국자원공학회지, 49(3), pp.369~378 (2012), 한국자원공학회[DOI]
- 송진영, "어안 렌즈 카메라와 SOLPOS 계산기를 이용한태양광 발전 시스템 부지 적합성 평가", 한국자원공학회지, 50(6), pp.789~798 (2013), 한국자원공학회[DOI]
- 송진영, "강원도 연곡, 물노, 부영 폐광산 지역에서의 풍력발전과 태양광발전의 잠재성 비교", 한국자원공학회지, 51(4), pp.525~536 (2014), 한국자원공학회[DOI]
- Tapakis, R., "Enhanced values of global irradiance due to the presence of clouds in Eastern Mediterranean", Renewable Energy, 62, pp.459~467 (2014)
- Verbois, H., "Solar irradiance forecasting in the tropics using numerical weather prediction and statistical learning", Solar Energy, 162, pp.265~277 (2018)
- Yang, D., "Solar irradiance forecasting using spatial-temporal covariance structures and time-forward kriging", Renewable Energy, 60, pp.235~245 (2013)
- Zagouras, A., "On the determination of coherent solar microclimates for utility planning and operations", Solar Energy, 102, pp.173~188 (2014)
- Zagouras, A., "Determination of measuring sites for solar irradiance, based on cluster analysis of satellite-derived cloud estimations", Solar Energy, 97, pp.1~11 (2013)