Short-term load demand forecasting using nonlinear dynamic grey-black-box and kernel optimization models: A new generation learning algorithm

In this study, new learning algorithms were employed viz: grey-black-box (GBB) and kernel optimization(K-SVR) for short-term load demand forecasting. The obtained data is randomly categorized into calibration and verification phases. The prediction accuracy of the algorithm is assessed using Correlation Coefficient (R), Coefficient of Determination (R2), Mean Square Error (MSE), and Root Mean Square Error (RMSE). The model combinations were achieved using the input variables feature selection approach. The GBB model has the highest goodness-of-fit (99%) and lowest prediction error (0.0). The results for both GBB, K-SVR models proved promising despite outstanding reliability of GBB model. The results show that the new learning algorithms are capable of forecasting load demand with simultaneous accuracy higher than 80%.