The power communication network is a communication network which serves the power system. Its reliability has an important influence on the safe and stable operation of the power system. It is of great practical significance to study the reliability of the power communication network. However, the current research on the power communication network lag, the reliability of the quantitative measurement, in practice, mostly artificial evaluation of the business, subjective and arbitrariness. In order to achieve the transition from expert to data-driven, this paper is based on the business segment, with two sites and between a cable as a research object. Based on the construction of the index system, BP neural network and genetic algorithm optimization BP neural network prediction model are established respectively. Using the real data and simulation data of the national grid in Jiangxi Province, the empirical experiment is carried out to compare the effect of the model. The example shows the effectiveness of the model.

No abstract