In view of the low calculation accuracy of physical analytical model of harmonic loss,a support vector regression (SVR) model based on crisscross optimization (CSO) algorithm is proposed to evaluate the harmonic loss of overhead lines. Firstly,the SVR model designed to minimize structural risk is used to fit the relationship between line characteristics and harmonic losses. Then,the SVR hyperparameters are globally searched by the CSO algorithm. The optimal hyperparameter group is obtained by dynamic optimization,and the CSO-SVR harmonic loss evaluation model is established. Based on a large power quality test platform,the harmonic test of low voltage overhead lines is carried out. And the proposed model is verified by the measured data of this test. The results show that using CSO algorithm to optimize hyperparameters of SVR can effectively improve the line loss evaluation performance of SVR model. Compared with other models,the proposed model presents higher accuracy.