Intelligent evaluation method for power transmission and transformation quantities based on isolation forest and multi-layer perceptron

Abstract

To evaluate quantities in power transmission and transformation projects， an intelligent evaluation method of quantity threshold based on isolated forest and multi-layer perceptron is proposed. Firstly， the Pearson correlation coefficient and permutation feature importance are applied to explore the relationship between various quantities and related technical features and select the features. On this basis， a neural network predictive model is trained by using five-year historical data. Aiming at the problem that the historical data may contain a lot of noises， a data rationality selection method based on isolation forest is proposed and the accuracy of using the proposed to evaluate quantities is verified in test set. The case simulation shows that the proposed feature selection method can improve the evaluation accuracy of neural network. At the same time， the proposed method can provide both rough estimation and intelligent evaluation on the rationality of quantities and can automatically evaluate the quantity rationality for promoting the digital transformation of power grid infrastructure.

Keywords

• power transmission and transformation quantities
• rationality threshold
• isolation forest
• multi-layer perceptron network
• pearson correlation coefficient
• ridge regression
• permutation feature importance
• automated assessment