DOI QR코드

DOI QR Code

Predicting the success of CDM Registration for Hydropower Projects using Logistic Regression and CART

로그 회귀분석 및 CART를 활용한 수력사업의 CDM 승인여부 예측 모델에 관한 연구

  • Park, Jong-Ho (Department of Civil Engineering, Seoul National University of Science and Technology) ;
  • Koo, Bonsang (Department of Civil Engineering, Seoul National University of Science and Technology)
  • Received : 2014.11.26
  • Accepted : 2015.02.13
  • Published : 2015.03.31

Abstract

The Clean Development Mechanism (CDM) is the multi-lateral 'cap and trade' system endorsed by the Kyoto Protocol. CDM allows developed (Annex I) countries to buy CER credits from New and Renewable (NE) projects of non-Annex countries, to meet their carbon reduction requirements. This in effect subsidizes and promotes NE projects in developing countries, ultimately reducing global greenhouse gases (GHG). To be registered as a CDM project, the project must prove 'additionality,' which depends on numerous factors including the adopted technology, baseline methodology, emission reductions, and the project's internal rate of return. This makes it difficult to determine ex ante a project's acceptance as a CDM approved project, and entails sunk costs and even project cancellation to its project stakeholders. Focusing on hydro power projects and employing UNFCCC public data, this research developed a prediction model using logistic regression and CART to determine the likelihood of approval as a CDM project. The AUC for the logistic regression and CART model was 0.7674 and 0.7231 respectively, which proves the model's prediction accuracy. More importantly, results indicate that the emission reduction amount, MW per hour, investment/Emission as crucial variables, whereas the baseline methodology and technology types were insignificant. This demonstrates that at least for hydro power projects, the specific technology is not as important as the amount of emission reductions and relatively small scale projects and investment to carbon reduction ratios.

청정개발체제(CDM) 사업은 신재생에너지사업의 보조를 통해 지구온난화 가스의 감축을 꾀하는 대표적인 국가 및 기업 간 배출권 거래(cap and trade)제도이다. 재래식 발전 방식에 비해 수익성이 낮은 태양광, 풍력, 수력 등의 사업이 CDM 사업으로 승인을 받으면 매년 탄소배출권(CER)을 제공받고, 이의 판매를 통해 발생한 추가 수익으로 인해 사업 타당성이 향상될 수 있다. 그러나 CDM 사업으로 인정받기 위해서는 환경적, 기술적, 경제적 추가성(Additionality)를 입증해야 하는데, 해당 적용 기술, 베이스라인 측정 방법론, 온실 가스 감축량, 사업 내부 수익률(IRR) 등 다수의 변수에 따라 결과가 달라지기 때문에 사전적으로 승인여부를 파악하기가 어렵다. 본 연구에서는 신재생에너지로 분류되는 수력 사업의 CDM 승인여부를 예측할 수 있는 모델을 개발하는 것을 목표로 하였다. 구체적으로 UNFCCC에서 제공하는 수력 사업 데이터를 활용하여 로그 회귀분석 및 CART 분석을 실시하여 예측모델을 개발하였으며 이와 함께 승인 여부에 유의하게 영향을 미치는 핵심 인자들을 파악하였다. 구축된 로그 회귀 및 CART 예측모델은 AUC가 각각 0.7674 및 0.7231로 예측 정확성이 비교적 높게 나왔다. 또한 수력 사업에서는 온실가스 저감량 대비 투자액, 시간당 발전량 및 내부수익률이 승인여부에 유의한 변수들로 파악되었고, 이에 비해 특정 기술이나 측정 방법론은 영향이 없는 것으로 드러났다. 즉, 특정 기술을 불문하고 온실가스를 투자 대비 가장 효율적으로 저감하는 사업과 수력사업들 중 상대적으로 소규모로 진행되는 사업이 CDM 사업으로 승인될 가능성이 높다는 것으로 해석된다.

Keywords

References

  1. Castro. P., and Michaelowa. A. (2008). "Empirical analysis of performance of CDM projects: FINAL REPORT." Climate Strategies Report.
  2. Chiba, M., and Kwak, S. H. (2006). "The Meaning of Additionality in CDM Project and the Potential Impacts of Additionality on the CDM Project". Journal of Energy & Climate Change, 1(2), pp. 92-98.
  3. Han. S., H. (2006). "Application of Approved Baseline Methodologies for CDM Projects in Korea(Case Study: Landfill Gas-to-Electricity Projects)", Korea Energy Management Corporation.
  4. Jun. C., H. (2012). "Data Mining Techniques." Seoul, Korea: Han Na Rae.
  5. KEMCO (2007). "Clean Development Mechanism." Korea Energy Management Corporation, KOTRA.
  6. Koo, B. (2013). "Evaluating the Economic Feasibility of Green Construction Projects using FiT and CDM Support Mechanisms." Korean Journal of Construction Engineering and Management, KICEM, 14(3), pp. 123-133. https://doi.org/10.6106/kJCEM.2013.14.3.123
  7. Koo, B., Park, J. H., and Kim, C. W. (2014). "Using the Binomial Option Pricing Model for Strategic Sales of CER's to Improve the Economic Feasibility of CDM projects." Korean Journal of Construction Engineering and Management, KICEM, 15(1), pp. 111-121. https://doi.org/10.6106/KJCEM.2014.15.1.111
  8. Lee, G., B. and Lee, E., W. (2005). "Overview and Trend of Small Hydropower Development in Korea." Korean Society for Fluid Machinery, pp. 735-741.
  9. Lee. J. H. (2010). "Status and Strategy of CDM projects." Journal of the Electrical World, 398, pp. 33-36.
  10. Park, J., H. and Koh, C. (2006) "An Efficient Data Mining Algorithm based on the Database Characteristics," Journal of the Korean Society for Industrial and Applied Mathematics, 10(1), pp. 107-119.
  11. Song, J. (2010). "The road to the successful clean development mechanism: lessons from the past." Doctoral dissertation, Massachusetts Institute of Technology.
  12. Swets, J. A., (1988). "Measuring the accuracy of diagnostic systems." Science, 240, pp. 1285-1293. https://doi.org/10.1126/science.3287615
  13. Van Buuren, S. (1999). "Flexible multivariate imputation by MICE, TNO Prevention and Health," report PG/VGZ/99.054.
  14. Yim, H. S., and Yun, S. J. (2009). "An Evaluation of Clean Development mechanism(CDM) From a Perspective of Sustainable Development," ECO, 13(2), pp. 141-174.