Short-term load forecasting with Radial Basis Functions and Singular Spectrum Analysis for residential Electric Vehicles recharging control

Larger Electric Vehicles´ penetration can change significantly load profiles in distribution grids. In order to protect the grid against peak demand caused by Electric Vehicles, cooperative techniques are developed, providing the ability to coordinate Electric Vehicles charging and thus shift power demand to off-peak periods. Therefore reliable prediction of future energy demand considering generation and profiles of other uncontrollable loads on distribution grid, can help better exploiting Electric Vehicle flexibility. This paper proposes a novel hybrid short-term load forecasting model coupling Singular Spectrum Analysis with Radial Basis Function network to improve electric power prediction accuracy regarding the existing radial basis function approach. These two techniques are compared and evaluated by absolute forecast errors and time span consistency. Then the hybrid model is exploited in a demand response strategy to optimize the charging timing of Electric Vehicles whereby the charging load is shifted and hence the overall peak demand reduced.