Research on performance measures of multi-objective optimization evolutionary algorithms

A large number of multi-objective optimization evolutionary algorithms(MOEAs) have been developed in the past two decades. To compare these methods rigorously, or to measure the performance of a particular MOEA quantitatively, a variety of performance measures have been proposed. In this paper, some existing widely-used performance measures are briefly reviewed and compared according different properties. Two new performance measures computing the convergence towards the Pareto front and the solution diversity on the Pareto front are proposed. And an outlook on how to further deepen insight in performance measures of MOEAs is given.