Harmonic Prediction Algorithm Based on Optimized Neural Network

In response to the increasingly serious problem of harmonic pollution in the power grid, which urgently requires massive harmonic data support analysis and governance, this paper proposes an improved SABO optimization algorithm and BP neural network to achieve harmonic prediction to alleviate the current shortage of harmonic data. In order to overcome the problem of SABO optimization algorithm being prone to falling into local optima, a logistic chaotic map is used to replace random numbers during initialization, and the golden sine optimization algorithm is used in iterative search to assist SABO in jumping out of local optima, thereby improving the prediction accuracy of the BP neural network. Subsequently, the improved SABAO-BP model proposed in this paper was verified to have high accuracy in predicting harmonic voltage distortion rate and single harmonic voltage content rate through actual operating data from a certain province.