AI-assisted traffic matrix prediction using GA-enabled deep ensemble learning for hybrid SDN

• Published in: Computer communications Vol. 203; pp. 298 - 311
• Main Authors: Etengu, Richard, Tan, Saw Chin, Chuah, Teong Chee, Lee, Ying Loong, Galán-Jiménez, Jaime
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2023
• Subjects: Deep ensemble learning model; Genetic algorithms; Hybrid software defined networking and traffic engineering; Machine learning; Hybrid software defined networking and traffic engineering; Deep ensemble learning model; Machine learning; Genetic algorithms
• ISSN: 0140-3664; 1873-703X
• DOI: 10.1016/j.comcom.2023.03.014

A hybrid software-defined network (SDN), which is a network where traditional routers and SDN protocols coexist during the incremental deployment of SDNs, requires real-time link traffic information for effective deployment. This has called for the need of accurate real-time data analytics and traffic prediction methods. To date, various traffic prediction frameworks have been studied to facilitate analysis and extraction of valuable information from huge sets of incomplete and noisy data. However, due to the linear nature of network design, mainly characterized by manual control plane forwarding configurations, existing traffic prediction frameworks cannot perform consistent traffic prediction over multiple datasets in modern dynamic networks. To address this issue, ensemble-driven approaches based on deep learning (DL) have recently been suggested as a promising solution. Nevertheless, determining the most appropriate combination of baseline DL architectures to be adopted for accurate traffic prediction remains a challenge. This paper proposes a novel DL framework for improved traffic prediction in hybrid SDNs. The framework combines a deep ensemble learning model utilizing multiple dimensionality reduction algorithms and a genetic algorithm (GA). The multi-objective GA is used to perform dynamic optimization of the connection weights and thresholds of the deep ensemble learning model while overcoming the local optima problem. Experimental results show that the proposed approach can achieve more accurate forecast of link traffic than the traditional baseline DL frameworks.