An Approach for Parallel Genetic Algorithms in the Cloud using Software Containers
This work addresses scalability problems for developers using genetic algorithms in cloud environments, but it is incremental as it builds on existing parallelization models with container technology.
The paper tackles the scalability and communication overhead issues of parallel genetic algorithms (GAs) in the cloud by proposing an approach using software containers and cloud orchestration, resulting in a conceptual workflow for efficient deployment and execution.
Genetic Algorithms (GAs) are a powerful technique to address hard optimisation problems. However, scalability issues might prevent them from being applied to real-world problems. Exploiting parallel GAs in the cloud might be an affordable approach to get time efficient solutions that benefit of the appealing features of the cloud, such as scalability, reliability, fault-tolerance and cost-effectiveness. Nevertheless, distributed computation is very prone to cause considerable overhead for communication and making GAs distributed in an on-demand fashion is not trivial. Aiming to keep under control the communication overhead and support GAs developers in the construction and deployment of parallel GAs in the cloud, in this paper we propose an approach to distribute GAs using the global parallelisation model, exploiting software containers and their cloud orchestration. We also devised a conceptual workflow covering each cloud GAs distribution phase, from resources allocation to actual deployment and execution, in a DevOps fashion.