Adequacy assessment of a wind-integrated system using neural network-based interval predictions of wind power generation and load

In this paper, a modeling and simulation framework is presented for conducting the adequacy assessment of a wind-integrated power system accounting for the associated uncertainties. A multi-layer perceptron artificial neural network (MLP NN) is trained by the non-dominated sorting genetic algorithm-II (NSGA-II) to forecast prediction intervals (PIs) of the wind power and load. The output of the adequacy assessment is given in terms of point-valued and interval-valued Expected Energy Not Supplied (EENS). Different scenarios of wind power and load levels are considered to explore the influence of uncertainty in wind and load predictions on the estimation of system adequacy.