An abnormal power load correction method based on fuzzy C-means（ FCM） and neural network is proposed. Firstly

the method uses adaptive fuzzy C-means（ AFCM） to cluster the power load data to determine the cluster center and the number of clusters. Secondly

based on the category of abnormal data

genetic algorithm is used to optimize BP neural network to correct abnormal power load data. Experiments show that the proposed method has a good clustering effect. The average corrected relative error of single anomaly data and continuous anomaly data is 0. 34 % and 1. 1 %

respectively. The correction result is better than the method using fuzzy clustering and neural network alone.