A stop-and-start adaptive cellular genetic algorithm for mobility management of GSM-LTE cellular network users

• Published in: Expert systems with applications Vol. 106; pp. 290 - 304
• Main Authors: Dahi, Zakaria Abdelmoiz, Alba, Enrique, Draa, Amer
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 15.09.2018; Elsevier BV
• Subjects: Adaptation; Adaptive algorithms; Cellular communication; Cellular Genetic Algorithms; Cellular networks; Communications networks; Complexity; Genetic algorithms; Mobile communication systems; Mobility management; Optimization; Population (statistical); Solvers; State of the art; Statistical analysis; Toruses; Wireless communications; Cellular networks; Cellular Genetic Algorithms; Adaptation
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2018.02.041

•An adaptive metaheuristic to solve the user’s mobility problem in cellular networks.•Uses a mechanism to dynamically stop the algorithm and start it again.•Uses a low-complexity formula to adapt dynamically the algorithm’s parameters.•Tests over 25 realistic networks and comparison against 26 top-ranked algorithms.•Experiments showed that the proposed approach is more efficient and less complex. The optimisation of the user tracking process is one of the most challenging tasks in today’s advanced cellular networks. In this paper, we propose a new low-complexity adaptive cellular genetic algorithm to solve this problem. The proposed approach uses a torus-like structured population of candidate solutions and regulates interactions inside it by using a bi-dimensional neighbourhood. It also automatically adapts the algorithm’s parameters and regenerates the algorithm’s population using two algorithmically-light operators. In order to draw reliable conclusions and perform an encompassing assessment, extensive experiments have been conducted on 25 differently-sized realistic networks. The proposed approach has been compared against 26 state-of-the-art algorithms previously designed to solve the mobility management problem, and a thorough statistical analysis of results has been performed. The obtained results have shown that our proposal is more efficient and algorithmically less complex than most of the state-of-the-art solvers.