An EV Charging Station Load Prediction Method Considering Distribution Network Upgrade
Xueping Li, Qi Han
Abstract
The continuous growth of the number of electric vehicles (EVs) increases the proportion of charging station load in the power grid, which has accelerated the distribution network upgrade including the topology structure change and the line renovation. As a result, the load prediction accuracy without considering the distribution network upgrade will be reduced. For the EV charging station load prediction considering the distribution network upgrade, this article proposes an EGAT-LSTM prediction method integrating edge aggregation graph attention network (EGAT) model and long short-term memory network (LSTM) model. The EGAT model can extract the key system information to a new node characteristic set integrating adjacency relationship, line impedance (R/X) and node data. The EGAT-LSTM prediction method through training learnable parameters captures the spatio-temporal correlations to reduce the non-regression learning of the prediction model. This method is tested on IEEE 33 and IEEE 69 bus distribution network systems. Simulation results show that for the EV charging station load prediction considering the distribution network upgrade, the proposed method improves training efficiency and prediction accuracy compared with the other methods without considering line characteristic.