A voted based random forests algorithm for smart grid distribution network faults prediction

ABSTRACT

In this paper, we focus on fault prediction in the smart distribution network. modified version of voted random forest algorithm (VRF) is proposed for enhancing the predicting accuracy of the faults. We change the decision process by redesigning the voting algorithm by introducing multiple SVM models for voting model training. Based on the trained models, a simple NSGA algorithm is applied to find the best voting model. Results showed that the new algorithm could improve the accuracy and recall rate of the fault prediction, especially for the recall rate of the negative samples.

KEYWORDS:

• Random forests (RF)
• voting algorithm
• fault prediction
• smart distribution network

Acknowledgments

Thanks to the team members in the state key lab, they give some feedback on the experiment.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work is supported by the State Grid Corporation of China (520940180016) and Beijing Municipal Natural Science Foundation  [L171010].