A Survey of Diversity Oriented Optimization: Problems, Indicators, and Algorithms.

In this chapter it is discussed, how the concept of diversity plays a crucial role in contemporary (multi-objective) optimization algorithms. It is shown that diversity maintenance can have a different purpose, such as improving global convergence reliability or finding alternative solutions to a (multi-objective) optimization problem. Moreover, different algorithms are reviewed that put special emphasis on diversity maintenance, such as multicriteria evolutionary optimization algorithms, multimodal optimization, artificial immune systems, and techniques from set oriented numerics. Diversity maintenance enters in different search operators and is used for different reasons in these algorithms. Among them we highlight evolutionary, swarm-based, artificial immune system-based, and indicator-based approaches to diversity optimization. In order to understand indicator-based approaches, we will review some of the most common diversity indices that can be used to quantitatively assess diversity. Based on the discussion, ’diversity oriented optimization’ is suggested as a term encompassing optimization techniques that adress diversity maintainance as a major ingredient of the search paradigm. To bring order into all these different approaches, an ontology on diversity oriented optimization is proposed. It provides a systematic overview of the various concepts, methods, and applications and it can be extended in future work.