Organic Rankine Cycles (ORCs) are of key-importance when exploiting energy systems, such as power plants, with a high efficiency. Flexibility with respect to the characteristics of the heat source requires a design fitted to maximize the overall performance. The variability of renewable heat sources makes more complex the global performance prediction of a cycle. The thermodynamic properties of the complex fluids used in the process are another source of uncertainty. The need for a predictive and robust simulation tool of ORCs remains strong. Because of the strong existing sources of uncertainty in ORC cycles, the main challenge in literature is to take into account uncertainty quantification to increase the reliability and the robustness of the proposed designs. This talk is focused on the assessment and propagation of the uncertainties through the design process of an ORC. In particular, two innovative techniques for sensitivity analysis and optimization under uncertainties, respectively, will be introduced and applied to the design of an ORC system. Concerning the first technique, starting from the classical ANalysis Of VAriance (ANOVA), we illustrate how third and fourth-order moments, i.e. skewness and kurtosis, respectively, can be decomposed mimicking the ANOVA approach. New sensitivity indices, based on the contribution to the skewness and kurtosis, are proposed. Moreover, the ranking of the sensitivity indices is shown to vary according to their statistics order and the problem of formulating a truncated polynomial representation of the original function is treated. The second technique is conceived to deal with the error affecting the objective functions in uncertainty-based multi-objective optimization, in particular referring to the problems where the objective functions are the statistics of a quantity of interest computed by an uncertainty quantification technique that propagates some uncertainties of the input variables through the system under consideration. The novel method relies on the exchange of information between the outer loop based on the optimization algorithm and the inner uncertainty quantification loop. In particular, in the inner uncertainty quantification loop, a control is performed to decide whether a refinement of the bounding box for the current design is appropriate or not.