Title: Traffic anomaly detection with wild geese dwarf mongoose optimisation_DQNN

Authors: M. Ahsan Shariff; C. Nelson Kennedy Babu

Addresses: Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, 602105, Tamil Nadu, India ' Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, 602105, Tamil Nadu, India

Abstract: Traffic anomaly detection plays a critical role in ensuring the security and reliability of modern networks, particularly in the context of software-defined networking (SDN). This paper proposes the wild geese dwarf mongoose optimisation based deep quantum neural network (WGDMO_DQNN) for traffic flow detection in SDN. The SDN is initially simulated and packet transmission is conducted. The traffic flow detection at data plane is accomplished, wherein feature extraction and traffic flow detection utilising deep quantum neural network (DQNN) are carried out. The control attack mechanism is executed in three phases: identifying, executing, and composition. If the controller is overloaded, switches are swapped to underloaded controller employing WGDMO. Moreover, WGDMO is an amalgamation of wild geese algorithm (WGA) and dwarf mongoose optimisation algorithm (DMOA). Additionally, WGDMO_DQNN achieved maximal TPR of 91.6%, TNR of 87.5%, accuracy of 93.7%, minimal switch migration cost of 0.668 and load of controller 0.437.

Keywords: DQNN; deep quantum neural network; WGA; wild geese algorithm; DMOA; dwarf mongoose optimisation algorithm; SDN; software-defined networking; packet transmission.

DOI: 10.1504/IJHVS.2026.153659

International Journal of Heavy Vehicle Systems, 2026 Vol.33 No.2, pp.147 - 172

Received: 07 Aug 2024
Accepted: 11 Oct 2024
Published online: 21 May 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article