Power communication network business reliability prediction method based on dynamic Bayesian network

Abstract

The invention relates to a power communication network service reliability prediction method based on a dynamic Bayesian network. Based on the topological structure of the power communication network, aiming at various factors affecting service reliability and combining municipal information, the Marko model of equipment and optical cable state conversion is established. According to the husband model, the dynamic Bayesian network model of service reliability based on the topological structure of the service channel is established. The present invention has the following advantages: 1. Considering the relationship between the main service channel and the backup channel, the reliability of the service is predicted more accurately. 2. While establishing equipment and optical cable state models, the influence of failure rate and repair rate is introduced at the same time, which is more in line with the actual situation of the power communication network. 3. When calculating the reliability of equipment and optical cables, it not only considers the change of its own state, but also combines the influence of environment and equipment port occupancy, and also introduces the influence of municipal information of optical cable sections, making the results more accurate.

Description

technical field [0001] The invention belongs to the research category of communication network service reliability prediction, and relates to the application of big data in electric power communication network, dynamic Bayesian network, reliability research of topological structure of service channel, reliability analysis of optical cable, and reliability analysis of network elements. Performance analysis, the relationship between equipment load and reliability, and the impact of dynamic and environmental factors on business reliability. A multi-layer and multi-dimensional power communication network service reliability dynamic prediction model based on dynamic Bayesian network is proposed. Background technique [0002] Based on massive data and using big data means, the prediction of service reliability of power communication network is an emerging research field. The main research objects, key technologies and practical application values ​​involved in this field mainly i...

AI Technical Summary

Problems solved by technology

[0013] Aiming at the complicated network topology and various influencing factors in power communication network business reliability prediction, the present invention aims to establish a state Markov model of equipment and optical cables in power communication network business channels and a dynamic Bayesian network for channel reliability. The Bayesian network model for model and business reliability prediction automatically learns model parameters through historical data, taking into account the environment in which the equipment is located and the impact of port occupancy, and at the same time considers the environment of optical cables, whether they cross rivers and lakes, and political factors such as construction. According to the current state of the power communication network business channel and the above factors, the reliability of the business in the next period is predicted

Images