베이지안 네트워크 기반 계층적 CPV 태양광 추적 시스템

A Hierarchical CPV Solar Generation Tracking System based on Modular Bayesian Network

  • 박수상 (연세대학교 컴퓨터과학과) ;
  • 양견모 (연세대학교 컴퓨터과학과) ;
  • 조성배 (연세대학교 컴퓨터과학과)
  • 투고 : 2014.02.05
  • 심사 : 2014.05.16
  • 발행 : 2014.07.15

초록

지구 온난화 문제와 화석 연료 양의 한계 때문에 재생 가능한 전력 생산에 대한 관심이 증가하고 있다. 특히 재생 에너지 중 태양광 에너지의 전력 생산 비율은 점차 증가함에 따라 집광형 태양광발전 시스템은 높은 전력 생산량으로 각광받고 있다. 하지만 이 시스템은 태양광 중첩률이 높을 때 가장 높은 발전 효율을 내기 때문에 허용 오차 범위가 작은 정밀 태양 추적 시스템이 필요하다. 본 논문에서는 복잡한 환경에 대응할 수 있는 베이지안 네트워크와 나이브 베이즈 분류기를 이용한 계층적 추적 시스템을 제안한다. 베이지안 네트워크는 불완전하고 불확실한 상황을 모델링 하는데 강력한 모델로 충분한 양의 데이터가 없을 경우에도 도메인 지식을 바탕으로 네트워크를 설계할 수 있다는 장점이 있다. 제안하는 계층적 확률 시스템에서는 불확실한 하늘 상황을 9개로 분류하고 모듈형 베이지안 네트워크를 이용하여 현재 날씨 상황을 추론한다. 또한 나이브 베이즈 분류기를 이용하여 추론된 날씨 상황을 고려한 효율적인 추적 방법을 분류하고 선택한다. 베이지안 네트워크의 유용성을 평가하기 위해 실제 날씨 데이터를 수집하였고 평균 93.9%의 정확도(Accuracy)를 보였다. 또한, 제안하는 시스템과 핀홀 카메라 시스템의 태양광발전 효율을 비교한 결과 약 16.58%의 성능이 향상됨을 확인하였다.

The power production using renewable energy is more important because of a limited amount of fossil fuel and the problem of global warming. A concentrative photovoltaic system comes into the spotlight with high energy production, since the rate of power production using solar energy is proliferated. These systems, however, need to sophisticated tracking methods to give the high power production. In this paper, we propose a hierarchical tracking system using modular Bayesian networks and a naive Bayes classifier. The Bayesian networks can respond flexibly in uncertain situations and can be designed by domain knowledge even when the data are not enough. Bayesian network modules infer the weather states which are classified into nine classes. Then, naive Bayes classifier selects the most effective method considering inferred weather states and the system makes a decision using the rules. We collected real weather data for the experiments and the average accuracy of the proposed method is 93.9%. In addition, comparing the photovoltaic efficiency with the pinhole camera system results in improved performance of about 16.58%.

키워드

과제정보

연구 과제번호 : 서비스 효과 증강을 위한 다감각 서비스 공통기술개발

연구 과제 주관 기관 : 산업통상자원부

참고문헌

  1. G.Y. Lee, J.T. Moon, and N.Y. Jung, "Economic analysis for the photovoltaic system," Conf. on Korean Institute of Industrial Engineers, pp.742- 746, 2008. (in Korean)
  2. B.D. Oh, "Efficient concentrating photovoltaic," Physics and High Technology, pp.37-41, 2008. (in Korean)
  3. H.C. Jun, L. Yi, and H. Yu, "A solar ray automatic tracking device based on image sensor," IEEE Control Conference, pp.5187-5190, 2011.
  4. M. Davis, J. Lawler, J. Coyle, A. Reich, and T. Williams, "Machine vision as a method for characterizing solar tracker performance," IEEE Photo Voltaic Specialists Conference, vol.33, pp.1-6, 2008.
  5. P. Sansoni, F. Francini, and D. Fontani, "Optical characterisation of solar concentrator," Optics and Lasers in Engineering, vol.45, no.3, pp.351-359, 2007. https://doi.org/10.1016/j.optlaseng.2005.02.009
  6. M.M. Arturo and G.P. Alejandro, "High-precision solar tracking system," Proc. of World Congress on Engineering, vol.2, pp.844-846, 2010.
  7. J. Xu, K. Wu, and L. Ma, "All-weather automatic solar tracking method applied in forest fire prevention," IEEE Electronic Measurement and Instruments, pp.1-805, 2009.
  8. M.M. Alata, M.A. Al-Nimr and Y. Qaroush, "Developing a multipurpose sun tracking system using fuzzy control," Energy Conversion and Management, vol.46, no.7, pp.1229-1245, 2005. https://doi.org/10.1016/j.enconman.2004.06.013
  9. G.D. Kleiter, "Propagating imprecise probabilities in Bayesian networks," Artificial Intelligence, vol.88, no.1-2, pp.143-161, 1996. https://doi.org/10.1016/S0004-3702(96)00021-5
  10. H.-S. Park and S.-B. Cho, "A modular design of Bayesian networks using expert knowledge: Contextaware home service robot," Expert Systems with Applications, vol.39, no.3, pp.2629-2642, 2012. https://doi.org/10.1016/j.eswa.2011.08.118
  11. S.H. Chen and C.A. Pollino, "Good practice in Bayesian network modelling," Environmental Modelling and Software, vol.37, pp.134-145, 2012. https://doi.org/10.1016/j.envsoft.2012.03.012
  12. J.-K. Min and S.-B. Cho, "Mobile human network management and recommendation by probabilistic social mining," IEEE Trans.on Systems, Man, and Cybernetics, Part B: Cybernetics, vol.41, no.3, pp. 761-771, 2011. https://doi.org/10.1109/TSMCB.2010.2092424
  13. A.J. Jakeman, R.A. Letcher and J.P. Norton, "Ten iterative steps in development and evaluation of environmental models," Environmental Modelling and Software, vol.21, no.5, pp.602-614, 2006. https://doi.org/10.1016/j.envsoft.2006.01.004
  14. V.K. Namasivayam and V.K. Prasanna, "Salable parallel implementation of exact inference in Bayesian networks," Int. Conf. on Parallel and Distributed Systems, 2006.
  15. J. Canny "A computational approach to edge detection," Pattern Analysis and Machine Intelligence, IEEE Transactions, vol.6, pp.679-698, 1986.
  16. J. Kittler, "the accuracy of the Sobel edge detector," Image and Vision Computing, vol.1, pp.37-42, 1983. https://doi.org/10.1016/0262-8856(83)90006-9
  17. H. Bay, T. Tuytelaars, and L. Van Gool, "Surf: Speeded up robust features," Computer Vision- ECCV, 2006. Springer Berlin Heidelberg, pp. 404- 417, 2006.
  18. B.K. Horn and B.G. Schunck, "Determining optical flow," Artificial intelligence, vol.17, no.1, pp.185- 203, 1981. https://doi.org/10.1016/0004-3702(81)90024-2
  19. K.A. Buch, C.-H. Sun, and L.R. Thorne, "Cloud classification using whole-sky image data," Ninth Symposium on Meteoriological Observations and Instrumentation, vol.7, pp.35-39, 1995.
  20. M. L. Lopez, G. G. Palancar, and N. M. Toselli, "Effect of different types of clouds on surface UV-B and total solar irradiance at southern mid-latitudes: CMF determinations at Córdoba, Argentina," Atmospheric Environment, vol.43(19), pp.3130-3136. 2009. https://doi.org/10.1016/j.atmosenv.2009.02.065
  21. M. Roser, and F. Moosmann," Classification of weather situations on single color images," Intelligent Vehicles Symposium, pp.798-803, 2008.
  22. S. C. Scott, "The redevelopment of a weather‐type classification scheme for North America," Int. Journal of Climatology, vol.22, no.1, pp.51-68, 2002. https://doi.org/10.1002/joc.709
  23. M. Martínez-Chico, F. Batlles and J. Bosch, "Cloud classification in a mediterranean location using radiation data and sky images," Energy, vol.36, no.7, pp.4055-4062, 2011. https://doi.org/10.1016/j.energy.2011.04.043