Management of container-based genetic algorithm workloads over cloud infrastructure

This paper proposes two approaches to managing the workload of multiple instances of genetic algorithms (GAs) running as containers over a cloud environment. The aim of both approaches is to obtain, for as many instances as possible, a GA output which achieves a user-defined fitness level by a user-defined deadline. To reach such a goal, the proposed approaches allocate the GA containers to cloud nodes and carefully control the execution of every GA instance by forcing them to run in stages. The paper proposes two approaches, fitness tracking (FT) and fitness prediction (FP), with both approaches compared against state-of-the-art container-based orchestration approaches.