Earticle

본 연구는 2030 국가 온실가스 감축 목표(NDC) 달성 및 취약계층 이용 공공건축물의 에너지 효율 향상에 주목하여, 그린리모델링(GR) 사업의 실질적 효과를 BEOP(Building Energy Optimization Program) 방법론과 통합하여 분석하였다. 그 린리모델링을 완료한 공공 어린이집 10개소를 대상으로 2018-2024년 에너지 데이터를 기반으로 GR 효과, 계약전력 적정성, 온실가스 배출량 변화 및 투자비용 효율성을 분석하였다. 연구 결과, GR은 에너지 사용량 절감에 일부 기여했으나, GR 직후 온실가스 배출량이 오히려 증가하는 사례가 다수 확인되었다. 특히 BEOP 분석을 통해 대부분의 시설에서 실제 사용량과 괴리된 계약전력 설정으로 인해 불필요한 예산 낭비(과도한 계약) 또는 추징금 발생(과소 계약) 문제가 심각함을 입증하였다. 이는 BEOP 기반 계약전력 최적화가 그린리모델링 효과를 극대화하고 에너지 예산 효율성을 혁신적으로 개선할 수 있음을 의미한다. 본 연구 는 BEOP와 GR의 통합 시너지가 2030 NDC 달성 기여 및 취약계층 시설의 사회적 가치 증대에 기여할 수 있고, 이를 토대로 GR 사업시 BEOP-CNPP 연계형 시스템 구축의 정책적 제안을 하였다.

This study analyzed the practical effects of the Green Remodeling (GR) project by integrating it with the Building Energy Optimization Program(BEOP) methodology, focusing on achieving the 2030 National Greenhouse Gas Reduction Target(NDC) and improving the energy efficiency of public buildings used by vulnerable groups. Focusing on 10 public childcare centers that underwent GR, the study analyzed energy data from 2018-2024 to assess GR effects, the appropriateness of contracted power capacity, changes in greenhouse gas (GHG) emissions, and cost-effectiveness of investments. The findings indicate that while GR contributed to some energy consumption reduction, a significant number of cases showed an increase in GHG emissions immediately after GR completion. In particular, BEOP analysis has proven that most facilities have serious problems with unnecessary budget waste (over-contracting) or additional charges (under-contracting) due to contract power settings that are different from actual usage. This demonstrates that BEOP-based optimization of contracted power capacity can maximize GR effectiveness and revolutionize energy budget efficiency. The study found that the integrated synergy of BEOP and GR can contribute to achieving the 2030 NDC and increasing the social value of facilities for vulnerable groups, and based on this, proposed a policy proposal for establishing a BEOP-CNPP linked system for GR projects.

This study proposes a model for predicting contracted power using electric power data collected in real time from convenience stores nationwide. By optimizing the prediction model using machine learning, it will be possible to predict the contracted power required to renew the contract of the existing convenience store. Contracted power is predicted through the XGBoost regression model. For the learning of XGBoost model, the electric power data collected for 16 months through a real-time monitoring system for convenience stores nationwide were used. The hyperparameters of the XGBoost model were tuned using the GridesearchCV, and the main features of the prediction model were identified using the xgb.importance function. In addition, it was also confirmed whether the preprocessing method of missing values and outliers affects the prediction of reduced power. As a result of hyperparameter tuning, an optimal model with improved predictive performance was obtained. It was found that the features of power.2020.09, power.2021.02, area, and operating time had an effect on the prediction of contracted power. As a result of the analysis, it was found that the preprocessing policy of missing values and outliers did not affect the prediction result. The proposed XGBoost regression model showed high predictive performance for contract power. Even if the preprocessing method for missing values and outliers was changed, there was no significant difference in the prediction results through hyperparameters tuning.