Sample average approximation for risk-averse problems: A virtual power plant scheduling application

In this paper, we address the decision-making problem of a virtual power plant (VPP) involving self-scheduling and market involvement under uncertainty in wind speed electricity prices. The is modeled using risk-neutral two risk-averse two-stage stochastic programming formulations, where conditional value at risk used to represent risk. A sample average approximation methodology integrated with an adapted L-Shaped solution method, which can solve specific problems. This provides framework understand quantify impact size on variability results. numerical results include analysis computational performance for case studies, estimators bounds true optimal solutions problems, assessment quality obtained. particular, experiences indicate that when adequate used, obtained close one.