Evaluation of gossip Vs. broadcast as communication strategies for multiple swarms solving MaOPs

In this work we evaluate the application of multiple independent swarms to solve Many-Objective Problems (MaOPs). Solving MaOPs is often a challenge, as these problems do not have a single best solution, but a set of solutions. Furthermore, the objectives to be optimized are usually conflicting among themselves. Employing multiple independent swarms that evolve independently from each other is an effective optimization strategy, that pushes convergence while preserving the diversity of the solutions. One of the key decisions for organizing a set of swarms is to define the communication strategy they use to share solutions. The strategy defines how particles migrate among the swarms, and how much interaction they feature among themselves. We evaluate two multi-swarm communication strategies, broadcast and the probabilistic gossip to 1-neighbor. Extensive simulation results are presented for two members of the DTLZ family with 2, 3, 4, 5, 10, 15, and 20 objectives. A set of quality indicators were evaluated for both communication strategies as well as for a baseline reference execution based on a single swarm. Results show that both distributed strategies outperform the centralized alternative. It is also possible to conclude that the higher level of interactivity of the broadcast alternative proved to be the best for several scenarios.