Content area
The Quality of Service (QoS) paradigm plays a vital role within the context of Software-Defined Networking (SDN), as it facilitates the efficient allocation of network resources to satisfy the diverse performance demands of various applications and services. Concurrently, it is imperative to address security concerns within the SDN framework, given that the distinctive architecture of SDN introduces novel vulnerabilities and associated risks, including control plane vulnerabilities, data plane vulnerabilities, and threats such as Distributed Denial-of-Service attacks. Nevertheless, the trade-off between security and QoS in SDN is daunting because the traditional QoS management methods, which rely primarily on static configuration and heuristics, cannot manage to optimize the allocation of resources to SDN traffic patterns with dynamic security controls, influencing the overall user experience (Bagaa et al., 2022). The incapacity to properly distribute resources for the implementation of security mechanisms under different network situations is a serious risk, which can leave the network vulnerable to intrusion and security breach.
This paper introduces ResSDN, a framework that incorporates Machine Learning into SDN network traffic routing and management to enhance both QoS and security in the scenario of complicated SDN. Through the joint use of novel Machine Learning algorithms, ResSDN preemptively blocks the malicious traffic and offers instructions on routing decisions on the benign traffic, thus protecting against the cyber threats while ensuring a smooth user experience.