Abnormal load data detection and correction method and system based on model optimization

Abstract

The invention relates to an abnormal load data detection and correction method and system based on model optimization, and the system comprises a load data preprocessor, an abnormal load data detector, and an abnormal load data corrector.The load data processor is connected with the abnormal load data detector; and the abnormal load data detector is connected with the abnormal load data corrector. According to the method, parameter optimization is carried out on an SVDD algorithm by adopting gene expression programming, abnormal load data detection is carried out by utilizing an SVDD model established by an optimal parameter, and then load prediction is carried out by utilizing a depth long-short-term memory network, the predicted load value is taken as a replacement value of the abnormal data. The method is used for processing the abnormal load of the power grid, and abnormal load data in the power load can be accurately detected through the method, so that accurate load prediction, planned power utilization management and reasonable power supply construction planning are facilitated, and the economic benefit and social benefit of a power system are improved.

Description

technical field [0001] The invention belongs to the technical field of power system data mining, and specifically relates to a method for detecting and correcting abnormal load data based on improved SVDD and a deep long-short-term memory network, which is mainly used for detecting and correcting abnormal load data in the electric power field. Background technique [0002] In order to meet the ever-increasing energy demand, establishing a safe, reliable, environmentally friendly, efficient and friendly power network has become a research hotspot. The concept of smart grid provides a good solution for the construction of new power grids. At the same time, the development of smart grids has promoted the establishment of grid automation information platforms, and the amount of various types of data transmitted and collected by power system equipment has also increased exponentially. The scale, type and structure of load data have undergone major changes. In the actual operatio...

AI Technical Summary

Problems solved by technology

With the development of data mining technology, a series of intelligent algorithms such as neural network, density analysis, and cluster analysis have been applied to the abnormal load detection of electric power, but these methods still have the disadvantages of difficult selection of initial parameters and low accuracy of abnormal detection

Images