A multipopulation multitasking evolutionary scheme with adaptive knowledge transfer to solve the clustered minimum routing cost tree problem

Abstract

The advancement in communication technology nowadays has increased the number of networked devices exponentially. Thus, network applications begin to cluster terminals to address scalability, privacy, and device connectivity with low routing costs. A recently introduced NP-hard problem called the Clustered Minimum Routing Cost Tree (CluMRCT) problem is assessed to be a fundamental key in designing an efficient network with low routing costs. Lately, some evolutionary multitasking meta-heuristics have been proposed to tackle multiple CluMRCT problems concurrently. However, these previous studies still have some limitations, such as only being applicable to complete graphs or there is no mechanism for effective knowledge transfer between problems when solving them simultaneously. To overcome these limitations, this paper proposes a novel multi-population multitasking evolutionary framework to address the problem. The individual representation is developed based on Network random key scheme and can be applied to both sparse and complete graphs. Moreover, our proposal can adaptively exploit positive knowledge transfer by adjusting the number of individuals migrating from other populations to a particular task. Then, the proposed algorithm is experimented on various data types and compared with other state-of-the-art algorithms. The experimental results show the proposal's effectiveness in most cases of the dataset, followed by detailed comparison, evaluation, and analysis.