Cooperative Co-Evolution and MapReduce

Abstract

Real-word large-scale optimisation problems often result in local optima due to their large search space and complex objective function. Hence, traditional evolutionary algorithms (EAs) are not suitable for these problems. Distributed EA, such as a cooperative co-evolutionary algorithm (CCEA), can solve these problems efficiently. It can decompose a large-scale problem into smaller sub-problems and evolve them independently. Further, the CCEA population diversity avoids local optima. Besides, MapReduce, an open-source platform, provides a ready-to-use distributed, scalable, and fault-tolerant infrastructure to parallelise the developed algorithm using the map and reduce features. The CCEA can be distributed and executed in parallel using the MapReduce model to solve large-scale optimisations in less computing time. The effectiveness of CCEA, together with the MapReduce, has been proven in the literature for large-scale optimisations. This article presents the cooperative co-evolution, MapReduce model, and associated techniques suitable for large-scale optimisation problems.

Infrequent Pattern Detection for Reliable Network Traffic Analysis Using Robust Evolutionary Computation

“…The current digital ecosystem, bolstered by the innovations and advancements of new technologies produces a massive amount of data continuously. The devices and technological settings that generate the data include the sensor networks, Internet of Things (IoT), healthcare, cybersecurity, and many other domains [1][2][3]. The massive amount of generated data is termed Big Data.…”