Abstract

Transmission line icing causes great harm to the safety of power system in the whole line. The prediction of transmission line icing thickness can effectively guide line ice melting. In order to predict the icing thickness of transmission lines, a new icing prediction model based on improved sparrow search algorithm (ISSA) optimized wavelet neural network (WNN) is proposed. In the standard sparrow algorithm, tent chaotic map is introduced to increase the diversity of initial population of the algorithm and makes it easier for improved sparrow search algorithm to jump out of the local optimum; Use t-distribution variation of sparrow individual position at the end of the algorithm to make the algorithm search the ideal value faster. Use the improved sparrow search method to search and optimize the initial weight and wavelet factors of wavelet neural network, effectively avoid the shortcomings of unstable prediction results and fall into local optimal number. Finally, combined with the on-site monitoring data of icing in East China Power Grid in 2021, through the simulation and comparison of different prediction models, it is proved that the prediction accuracy of the proposed model has been greatly improved.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call