Method and device for predicting electric quantity of agent electricity purchasing user, and storage medium

The invention relates to an agent electricity purchasing user electricity quantity prediction method based on an echo state machine and error checking. The method comprises the following steps that a novel reserve pool is constructed according to historical electricity consumption and time sequence data of electricity consumption influence factors; based on the constructed novel reserve pools, constructing a multi-reserve pool correlation vector echo state machine model; and based on the constructed multi-reserve-pool correlation vector echo state machine model, establishing a multi-reserve-pool correlation vector echo state machine model based on error checking, inputting historical electricity consumption data of different granularities and influence factor data of electricity consumption in a matrix form, and finally outputting an electricity consumption prediction result. The method can effectively improve the accuracy of predicting the electricity consumption of the agent electricity purchasing user. 本发明