Device security threat prediction method and device through adaptive integration

Abstract

The invention discloses a device security threat prediction method and device through adaptive integration, and the method comprises the steps: collecting abnormal data sets during the operation of a plurality of devices, inputting the abnormal data sets into n preset neural networks, and obtaining n prediction results, n being a positive integer greater than 1; performing weight distribution and integration on the n prediction results to obtain an initial integration result; repeatedly carrying out weight iteration updating by utilizing the initial integration result to obtain a target integration result; and predicting potential security threats of the equipment based on the target integration result. According to the method, the multiple neural networks are iteratively updated and predicted, so that manual feature extraction and a complex mathematical modeling process can be avoided, high-precision end-to-end potential security threat prediction of equipment is realized, the weight is adaptively adjusted according to an individual model prediction result, and the prediction accuracy of the potential security threat of the equipment is improved. The method has better data adaptability for different data, and the prediction accuracy is further improved.

Description

technical field [0001] The invention relates to the technical field of equipment security prediction, in particular to a method and device for equipment security threat prediction through self-adaptive integration. Background technique [0002] The power industry is closely related to people's living standards. The development of the times and the advancement of science and technology have led to more and more power equipment being put into the power grid system, making the power grid structure more and more complex. At the same time, various uncertain risks such as external force factors, operational factors, equipment factors and management factors also affect the safe and stable operation of the power grid and increase the operational risk of the power grid. [0003] In order to allow each device to work safely and normally, so that the power grid can operate safely and stably, the current common method is to record the various operating data of the equipment during the o...

AI Technical Summary

Problems solved by technology

[0004] However, the currently commonly used security threat prediction methods have the following technical problems: the use of a single trained neural network requires manual feature extraction and the single model is not robust enough, and the prediction accuracy cannot be guaranteed. If multiple neural networks are used for prediction, multiple neural networks The network is difficult to coordinate, which increases the difficulty of forecasting and reduces the accuracy rate

Images