Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering
Abstract In modern power systems, predicting the time when peak loads will occur is crucial for improving efficiency and minimising the possibility of network sections becoming overloaded. However, most works in the load forecasting field are not focusing on a dedicated peak time forecast and are no...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-04-01
|
| Series: | IET Smart Grid |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/stg2.12137 |
| _version_ | 1797205965955661824 |
|---|---|
| author | Leo Semmelmann Oliver Resch Sarah Henni Christof Weinhardt |
| author_facet | Leo Semmelmann Oliver Resch Sarah Henni Christof Weinhardt |
| author_sort | Leo Semmelmann |
| collection | DOAJ |
| description | Abstract In modern power systems, predicting the time when peak loads will occur is crucial for improving efficiency and minimising the possibility of network sections becoming overloaded. However, most works in the load forecasting field are not focusing on a dedicated peak time forecast and are not dealing with load data privacy. At the same time, developing methods for forecasting peak electricity usage that protect customers' data privacy is essential since it could encourage customers to share their energy usage data, leading to more data points for the effective management and planning of power grids. Hence, the authors employ a dedicated Learning to Rank XGBoost algorithm to forecast peak times with only ranks of loads instead of absolute load magnitudes as input data, thereby offering potential privacy‐preserving properties. We show that the presented Learning to Rank XGBoost model yields comparable results to a benchmark XGBoost load forecasting model. Additionally, we describe our extensive feature engineering process and a state‐of‐the‐art Bayesian hyperparameter optimisation for selecting model parameters, which leads to a significant improvement of forecasting accuracy. Our method was used in the context of the final round of the international BigDEAL load forecasting challenge 2022, where we consistently achieved high‐ranking results in the peak time track and an overall fourth rank in the peak load forecasting track with our general XGBoost model. |
| first_indexed | 2024-04-24T08:59:31Z |
| format | Article |
| id | doaj.art-4289589d31284d05b761bff8df672363 |
| institution | Directory Open Access Journal |
| issn | 2515-2947 |
| language | English |
| last_indexed | 2024-04-24T08:59:31Z |
| publishDate | 2024-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Smart Grid |
| spelling | doaj.art-4289589d31284d05b761bff8df6723632024-04-16T02:46:16ZengWileyIET Smart Grid2515-29472024-04-017217218510.1049/stg2.12137Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineeringLeo Semmelmann0Oliver Resch1Sarah Henni2Christof Weinhardt3Karlsruher Institut für Technologie Karlsruhe GermanyKarlsruher Institut für Technologie Karlsruhe GermanyKarlsruher Institut für Technologie Karlsruhe GermanyKarlsruher Institut für Technologie Karlsruhe GermanyAbstract In modern power systems, predicting the time when peak loads will occur is crucial for improving efficiency and minimising the possibility of network sections becoming overloaded. However, most works in the load forecasting field are not focusing on a dedicated peak time forecast and are not dealing with load data privacy. At the same time, developing methods for forecasting peak electricity usage that protect customers' data privacy is essential since it could encourage customers to share their energy usage data, leading to more data points for the effective management and planning of power grids. Hence, the authors employ a dedicated Learning to Rank XGBoost algorithm to forecast peak times with only ranks of loads instead of absolute load magnitudes as input data, thereby offering potential privacy‐preserving properties. We show that the presented Learning to Rank XGBoost model yields comparable results to a benchmark XGBoost load forecasting model. Additionally, we describe our extensive feature engineering process and a state‐of‐the‐art Bayesian hyperparameter optimisation for selecting model parameters, which leads to a significant improvement of forecasting accuracy. Our method was used in the context of the final round of the international BigDEAL load forecasting challenge 2022, where we consistently achieved high‐ranking results in the peak time track and an overall fourth rank in the peak load forecasting track with our general XGBoost model.https://doi.org/10.1049/stg2.12137artificial intelligence and data analyticsdata privacyload forecasting |
| spellingShingle | Leo Semmelmann Oliver Resch Sarah Henni Christof Weinhardt Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering IET Smart Grid artificial intelligence and data analytics data privacy load forecasting |
| title | Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering |
| title_full | Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering |
| title_fullStr | Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering |
| title_full_unstemmed | Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering |
| title_short | Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering |
| title_sort | privacy preserving peak time forecasting with learning to rank xgboost and extensive feature engineering |
| topic | artificial intelligence and data analytics data privacy load forecasting |
| url | https://doi.org/10.1049/stg2.12137 |
| work_keys_str_mv | AT leosemmelmann privacypreservingpeaktimeforecastingwithlearningtorankxgboostandextensivefeatureengineering AT oliverresch privacypreservingpeaktimeforecastingwithlearningtorankxgboostandextensivefeatureengineering AT sarahhenni privacypreservingpeaktimeforecastingwithlearningtorankxgboostandextensivefeatureengineering AT christofweinhardt privacypreservingpeaktimeforecastingwithlearningtorankxgboostandextensivefeatureengineering |