탄소중립이행을 위한 기계학습 기반의 전력수요예측 방법론 고도화 연구

• 영문명: Research on Advancing Electricity Demand Forecasting Method Using Machine Learning to Implement Carbon Neutrality
• 발행기관: 한국IT서비스학회
• 저자명: 신우영(Woo Young Shin) 박창대(Chang Dae Park)
• 간행물 정보: 『한국IT서비스학회지』제24권 제1호, 1~13쪽, 전체 13쪽
• 주제분류: 경제경영 > 경영학
• 파일형태: PDF
• 발행일자: 2025.02.28

국문 초록

As concerns over climate change and greenhouse gas emissions intensify, carbon neutrality has emerged as a critical global goal. Achieving this goal requires accurate electricity demand forecasting, which plays a pivotal role in maintaining grid stability and managing the variability of renewable energy. However, traditional models that focus on the mean often fail to capture the complexity of modern electricity demand patterns. To address this issue, this study proposes the Composite Variation Method(CVM) based on quantile regression. This approach reduces the bias in mean-based electricity demand forecasts and provides higher accuracy, particularly in scenarios with outliers or complex conditions. The CVM is applied to Random Forest and XGBoost models using hourly electricity demand data from Ontario, Canada. The results demonstrate a 9.75% performance improvement for Random Forest and a 1.31% improvement for XGBoost. These findings suggest that CVM enhances the precision of electricity demand forecasting, contributing to more effective energy management strategies essential for carbon neutrality.

목차

1. 서론

2. 이론적 배경과 관련 연구

3. 연구 과제 목표 및 연구 수행

4. 결론 및 향후 연구

참고문헌

키워드

Electricity Demand Forecast Machine Learning Quantile Regression XGBoost Random Forest Composite Variation Method