Linear Programming and Genetic Algorithms Methods for Creation of Groups in Networks of Excellence

摘要

Creation of groups in Networks of Excellence (NoEs) based on knowledge mapping and expertise is a set covering problem known to be non-polynomial. Therefore it is usually approached by heuristic methods which yield good but not necessarily optimal coverage. Selecting teams to form a group within NoEs that are comprised of tens of teams can also be formulated and solved as an integer linear programming (ILP) problem whose solution is guaranteed to be optimal. This paper presents the ILP solution for team selection with typical objective functions. Several genetic algorithm-based methods are also compared to the optimal solution in terms of convergence (time and solution). The compared methods differ in selecting next-generation population schemes. The plain vanilla method is shown to be superior to both the roulette-based and the SUS methods.