Adaptive AI-Driven Traffic Routing in Software-Defined Networks for Predictive Load Balancing

Emerging applications that require large amounts of data and varying network specifications are creating unique challenges for traditional networks. As a result of its centralized network control and dynamic layer configuration abilities, intelligent SDN traffic management is possible. This paper proposes an adaptive AI model focused on augmenting predictive load balancing. To predict and respond to network congestion for dynamic routing optimization, the model captures real-time network data and applies machine learning. With the use of predictive histograms and real-time traffic data, the proposed framework reallocates network resources to manage congestion and latency, enhance network performance, and improve QoS. The framework's ability to efficiently load redistribute network resources to network performance optimization is driven by set network policies. Relative to traditional routing techniques, adaptive AI model demonstrated substantial improvements in performance, particularly in throughput, delay, and utilization of the network as a whole. This study enhances understanding of self-configuring networks with SDN frameworks incorporating intelligent AI and network traffic prediction algorithms for automated resource reallocation to sustain self-optimizing networks.

Ҳали таржима қилинмаган