| abstract |
Disclosed is a method for evaluating a risk of an electric power communications network in the technical field of electric power communications. The present invention comprises: first, collecting risk evaluation parameters of an electric power communications network; then, creating an indicator data base and a sample data base using the risk evaluation parameters; and finally, training a neural network according to sample data in the sample data base, and invoking the trained neural network to calculate a risk value for the electric power communications network corresponding to the indicator data in the indicator data base. In the present invention, subjective factors in artificially provided indicator weights are avoided by training the indicator data by using a neural network algorithm, interference of irregular data is avoided by means of network structure learning and network parameter learning, the number of redundancies in hidden layer nodes is reduced, neural network learning time is reduced, network learning speed is improved, corresponding indicator weights are adjusted automatically when a new risk factor appears, and therefore, the method has good adaptivity and high precision. |