Deterministically-Adaptive Genetic Algorithm To Solve Binary Communication Problems

Abstract

Global optimisation plays a critical role in today's scientific and industrial fields. Optimisation problems are either continuous or combinatorial depending on the nature of the parameters to optimise. In the class of combinatorial problems, we find a sub-category which is the binary optimisation problems. Due to the complex nature of optimisation problems, exhaustive search-based methods are no longer a good choice. So, metaheuristics are more and more being opted in order to solve such problems. On the other hand, most of the proposed metaheuristics were hand-tuned through a long and exhaustive process that requires advanced knowledge. This fact makes them sensitive to any change of the problem properties, that probably might decrease their efficiency. So, their further application in real-life scenarios will be restricted or impossible. One of the most active topic of research of nowdays is the adaptation strategies. These last ones appear as a promising alternative to the hand-tuned approach. Deterministic adaptation is one of the several adaptation schemes that exist. Based on the latter, in this paper we propose several variants of one of the most studied metaheuristics; the Genetic Algorithm (GA). The efficiency of the variants was assessed for solving a complex optimisation problem in cellular networks which is the Error Correcting Code Problem (ECCP). They were compared against a classical hand-tuned genetic algorithm. The experiments gave promising results and encourage further investigation.