Method and device for predicting and evaluating operation state of electric power information acquisition system

Abstract

The invention provides a method and a device for predicting and evaluating the running state of an electric power information acquisition system. The method comprises the following steps of acquiring power grid data information arranged at each place in real time; carrying out labeling processing on existing data and data acquired in real time according to the actual condition of the power grid, and endowing different weights to different labeled data; fusing a deep residual network Resnet-50 with a multi-scale convolutional network, and extracting multi-scale electricity consumption information features from the labeled data set; inputting the extracted feature vectors into a prediction model, wherein he prediction model is a model combining BiLSTM and Attention networks, and outputting state prediction and scores thereof. According to the method, the weights of the new and old data sets are adjusted in real time, the features of the shallow layer and the deep layer of the power consumption data are extracted by using the multi-scale convolutional network, and the combination of prediction models more pays more attention to the part useful for performance improvement, so that the state of the power consumption information acquisition system can be predicted and evaluated in time, and safe and reliable operation of power production is effectively ensured.

Description

technical field [0001] The invention relates to the operation and maintenance of a power information collection system, in particular to a method and device for predicting and evaluating the running state of the power information collection system. Background technique [0002] The power consumption information collection system of power users is a system for collecting, processing and real-time monitoring of power consumption information of power users, realizing automatic collection of power consumption information, abnormal measurement monitoring, power quality monitoring, power consumption analysis and management, and related information release , distributed energy monitoring, intelligent electrical equipment information interaction and other functions. The operating environment of an information system mainly refers to the internal environmental elements of various personnel, software and hardware facilities, and related external environmental elements. The impact of ...

AI Technical Summary

Problems solved by technology

The power information collection system collects more and more operation and maintenance work orders, which far exceeds the working ability of the operation and maintenance personnel, so that the system cannot obtain equipment characteristics in a timely and efficient manner, and cannot timely understand the equipment operating status

Images