Random Forest, XGBoost, LGBM 조합형 Stacking 모델을 이용한 풍력 발전량 예측 성능 평가
Performance Evaluation of Stacking Models Based on Random Forest, XGBoost, and LGBM for Wind Power Forecasting
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Wind power is highly variable due to the intermittent nature of wind. This can lead to power grid instability and decreased efficiency. Therefore, it is necessary to improve wind power prediction performance to minimize the negative impact on the power system. Recently, wind power prediction using machine learning has gained popularity, and ensemble models in machine learning have shown high prediction accuracy. RF, GB, XGB and LGBM are decision tree-based ensemble models and have high predictive performance in wind power, but these models have problems from over-fitting and strong dependence on certain variables. However, the stacking model can improve prediction performance by combining individual models and compensate for the shortcomings of each model. In this study, The MAE of RF, XGB and LGBM is 310.42 kWh, 217.07 kWh and 265.20 kWh, respectively, while the stacking model based on RF, XGB and LGBM is 202.33 kWh. Stacking models can improve prediction performance. Finally, it is expected to contribute to electricity supply and demand planning.
Abstract
Wind power is highly variable due to the intermittent nature of wind. This can lead to power grid instability and decreased efficiency. Therefore, it is necessary to improve wind power prediction performance to minimize the negative impact on the power system. Recently, wind power prediction using machine learning has gained popularity, and ensemble models in machine learning have shown high prediction accuracy. RF, GB, XGB and LGBM are decision tree-based ensemble models and have high predictive performance in wind power, but these models have problems from over-fitting and strong dependence on certain variables. However, the stacking model can improve prediction performance by combining individual models and compensate for the shortcomings of each model. In this study, The MAE of RF, XGB and LGBM is 310.42 kWh, 217.07 kWh and 265.20 kWh, respectively, while the stacking model based on RF, XGB and LGBM is 202.33 kWh. Stacking models can improve prediction performance. Finally, it is expected to contribute to electricity supply and demand planning.
참고문헌 (14)
- Mingli, Z, "Study on application of the forecasting system for wind farm power", Proceedings of the 2010 2nd International Conference on Signal Processing Systems, pp.198~201 (2010)
- Optis, M, "The importance of atmospheric turbulence and stability in machine-learning models of wind farm power production", Renewable and Sustainable Energy Reviews, 112, pp.27~41
- Leo, B, "Bagging predictors", Machine learning, 24, pp.123~140
- Heinermann, J., "Machine learning ensembles for wind power prediction", Renewable Energy, 89, pp.671~679
- Demollia, H, "Wind power forecasting based on daily wind speed data using machine learning algorithms", Energy Conversion and Management, 198, pp.111823~
- Lee, J. H., "Wind power prediction using ensemble learning-based models", IEEE Access, 8, pp.61517~61527 (2020)
- Wangjie, L., "Wind Power Prediction Based on the Stacking Model of XGBoost and Random Forest", 2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS). IEEE (2022)
- Jeong, H. S, "Characteristics of Wind Environment in Dongbok･Bukchon Wind Farm on Jeju", New &Renewable Energy, 18(1), pp.1~16
- Kim, D. Y., "Changes in wind turbine power characteristics and annual energy production due to atmospheric stability, turbulence intensity, and wind shear", Energy Volume, 214, pp.119051~
- Leo, B., "Random forests", Machine learning, 45, pp.5~32 (2001)
- Singh, U, "SCADA system dataset exploration and machine learning based forecast for wind turbines", Results in Engineering, 16 (2022)
- Ke, G., "Lightgbm:A highly efficient gradient boosting decision tree", Advances in neural information processing systems, 30 (2017)
- Pavlyshenko, B., "Using stacking approaches for machine learning models", 2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP) (2018)
- Yang, L, "On hyperparameter optimization of machine learning algorithms:Theory and practice", Neurocomputing, 415, pp.295~316 (2020)