Online prediction of electrical load for distributed management of PEV based on Grey-Markov model

In order to improve the prediction accuracy of distributed management of Plug-in Electric Vehicles (PEV) to the change of the future electrical load, we proposed an improved algorithm which based on Grey-Markov model. This method makes full use of the advantages of grey model and Markov chain model, where, the grey model is used to reveal the total trend and principle of object change while the Markov chain model is used to indicate the objective random fluctuation and then determine the disturbance rule. The prediction model can be established according to the real value which obtained by distributed management system, then comparison of the model predictions with the improved and traditional prediction algorithms. the results show that improved algorithm is better than traditional prediction algorithm.