Optimizing Edge Network Performance with Software-Defined Technologies for Secure 6G Integration

Abstract

An SDN-based edge network optimization framework incorporating AI is proposed to improve performance and security in 6G networks. Software-Defined Networking (SDN) and edge computing can be combined to enable dynamic resource allocation and thus optimize throughput, decrease latency, and minimize packet loss. Algorithms based on AI, especially reinforcement learning, can control network traffic most effectively and allow real-time adjustments to network settings based on current needs. This integration will allow the system to quickly adjust to the conditions and optimize performance independently. Also, the AI-enabled security module is integrated to identify and prevent possible threats in real-time to overcome security issues associated with 6G networks that are likely to use enormous IoT devices and complicated autonomous systems. The findings of the simulation prove that the proposed framework provides better performance than conventional 6G models. Throughput is increased by 47% (620 Mbps vs. 420 Mbps), while latency is reduced by 37% (24 ms vs. 38 ms). The 50% reduction (1.7% vs. 3.6) in packet loss also creates a more reliable network. The accuracy of intrusion detection in the proposed model is 15% better (97 % vs. 82 %), and the false positive rate is lower by 32 % (7.8 % vs. 11.5 %). These enhancements show that the framework not only maximizes network performance but also makes 6G networks a lot more secure. By combining SDN and AI with edge computing, it offers a scalable and efficient solution that meets the high requirements of future communication systems, including smart cities, autonomous vehicles, and other AI-driven services in the 6G era.