A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Abnormal Power Consumption Detection of Charging Pile Users based on GBDT Model
With the popularity of new energy vehicles, charging piles are increasingly being used in public transportation and private electricity consumption. However, due to the diversity of charging pile usage scenarios and user identities, there are abnormal phenomena in the electricity consumption behavior of charging pile users. Based on this, this paper proposes a method for detecting abnormal electricity consumption of charging pile users based on the GBDT (Gradient Boosting Decision Tree) model. This method is mainly divided into four parts: feature engineering, model training, model evaluation, and anomaly detection. First, by analyzing the characteristics of charging pile user data, this paper proposes a feature selection method based on feature extraction; then, the GBDT model is used to train the data; finally, the test data is used to evaluate the algorithm. The experimental results show that the method proposed in this article can improve the accuracy of electrical anomaly detection from 84.9% to 91.4%, and the effect is very significant.
Abnormal Power Consumption Detection of Charging Pile Users based on GBDT Model
With the popularity of new energy vehicles, charging piles are increasingly being used in public transportation and private electricity consumption. However, due to the diversity of charging pile usage scenarios and user identities, there are abnormal phenomena in the electricity consumption behavior of charging pile users. Based on this, this paper proposes a method for detecting abnormal electricity consumption of charging pile users based on the GBDT (Gradient Boosting Decision Tree) model. This method is mainly divided into four parts: feature engineering, model training, model evaluation, and anomaly detection. First, by analyzing the characteristics of charging pile user data, this paper proposes a feature selection method based on feature extraction; then, the GBDT model is used to train the data; finally, the test data is used to evaluate the algorithm. The experimental results show that the method proposed in this article can improve the accuracy of electrical anomaly detection from 84.9% to 91.4%, and the effect is very significant.
Abnormal Power Consumption Detection of Charging Pile Users based on GBDT Model
Dou, Jing (author) / Qiao, Jianfeng (author) / Zhang, Bo (author) / Duan, Yafan (author) / Zhang, Jiaru (author)
2024-02-23
360647 byte
Conference paper
Electronic Resource
English
Flame detection based on GBDT feature for building
| IEEE | 2017
| DOAJ | 2023
Landslide Susceptibility Evaluation Based on Coupling of GBDT-LR Model and Information Model
| DOAJ | 2023