6. Conclusion
In this paper, we introduced the concept of Comprehensive Pareto Efficiency in robust counterpart optimization which includes Pareto Robust Optimality (PRO), Global Pareto Robust Optimality (GPRO) and Elite Pareto Robust Optimality (EPRO). We theoretically proved that RC2 under Normal distribution and RC∞ under Cauchy distribution achieve the best performance, with all PRO solutions generated are GPRO and EPRO. The numerical results of two applications show that PRO solutions can improve the performance compare with non-PRO solutions. By considering GPRO and EPRO solutions, we can have a deep understanding of the quality of the robust solutions and the difference between different robust counterparts. In general, the Comprehensive Pareto Efficiency provides a new perspective for robust counterpart optimization and has important significance in practice which can help us to find high quality solutions and make better decisions. We only consider single uncertain constraint in this paper, it is interesting to consider multiple uncertain constraints in robust counterpart optimization, many researchers have worked on this which is known as joint chance constraint. Future work will be conducted to extend the current concept to the multiple uncertain constraints case.
