Most Valuable Player Algorithm: a novel optimization algorithm inspired from sport

In this paper a new metaheuristic called the Most Valuable Player Algorithm (MVPA) is proposed for solving optimization problems. The developed algorithm is inspired from sport where players form teams, then these players compete collectively (in teams) in order to win the championship and they compete also individually in order to win the MVP trophy. The performances of MVPA are evaluated on a set of 100 mathematical test functions. The obtained results are compared with the ones obtained using 13 well-known optimization algorithms. These results demonstrate that, the MVPA is a very competitive optimization algorithm, it converges rapidly (with smaller number of functions evaluations) and more successfully (with higher overall success percentage) than the compared algorithms. Therefore, further developments and applications of MVPA would be worth investigating in future studies.