Load Forecasting based on Fuzzy Time Series

Pei Ao
2015 Proceedings of the 3rd International Conference on Material, Mechanical and Manufacturing Engineering   unpublished
Load forecasting is a traditional research issue in the field of electric power system. In this paper, an improved fuzzy time series approach is used to forecast load. Firstly, a method of unequal-sized intervals partitioning based on K-means algorithm is proposed. Secondly, improved fuzzification method is proposed to overcome the defect of traditional fuzzification method. Finally, the model is used to forecast load and the relation between the number of clustering and the prediction accuracy
more » ... prediction accuracy and the relation between the order and the prediction accuracy are studied. The validity of model is verified by prediction results.
doi:10.2991/ic3me-15.2015.139 fatcat:43ttuxefffe67heb7zflotretq