Electric power communication operation trend and business risk analyzing method based on deep learning

Abstract

Provided is an electric power communication operation trend and business risk analyzing method based on deep learning. According to the deep learning theory, a multilayer deep confidence network architecture is constructed; electric power communication network history operation and monitoring data and related business system data governed by a district are used as training data of a learning model; all kinds of possible combinations of operation trend prediction and business risk evaluation are used as different output modes; finally a deep model which is capable of comprehensively judging electric power communication operation modes of the district is trained; history operation data and real-time business system data of the electric power communication network are used as test data of the model; and by using the trained deep network model parameters, operation trend prediction and business risk evaluation results of the electric power communication network can be obtained. The analyzing method is advantageous in that operation states of the electric power communication network can be more precisely evaluated; evidences are provided for business risks of the electric power communication network; and utilization efficiency of the electric power communication network is increased and safety of the electric power communication network is improved.

Description

technical field [0001] The invention belongs to the field of power communication network security, and in particular relates to a deep learning-based power communication network operation trend and business risk analysis method. Background technique [0002] The power system communication network is one of the national special communication networks, an important part of the power system, the basis for power grid dispatching automation, marketization of power grid operation and informatization of power grid management, and an important means to ensure safe, stable and economical operation of the power grid. At present, the power system communication network is mainly based on optical fiber and digital microwave transmission, and various communication methods such as satellite, power line carrier, cable, and radio coexist. It has achieved coverage of all provinces, autonomous regions, and municipalities except Taiwan. The business carried involves Voice, data, telecontrol, re...

AI Technical Summary

Problems solved by technology

Currently commonly used evaluation methods include: AHP, fuzzy comprehensive evaluation method, principal component analysis and neural network methods, etc., but due to the complexity of the power communication network and the uncertainty of some risk factors, the current evaluation methods are very It is difficult to make an accurate assessment, and the index system is unscientific, and the number of indicators is large, which cannot well reflect the correlation between the evaluation objects, and the evaluation process is relatively subjective

Images