چکیده مقاله
Software Defined Networking SDN has revolutionized how networks are managed andoptimized However, as SDNs scale in size and complexity, traffic optimization becomesa challenging task This paper presents a novel approach to hierarchical traffic optimizationin SDNs using Graph Neural Networks GNNs and Particle Swarm Optimization PSO By combining the topological learning capabilities of GNNs with the global optimizationpower of PSO, the proposed method aims to improve network performance in terms ofthroughput, latency, load balancing, and quality of service QoS The model is evaluatedthrough extensive simulations, showing significant improvements over conventional SDNtraffic management methods
کلیدواژهها
نویسندگان
Somayeh Azizi
Department of Computer Engineering, Isfahan Khorasgan Branch, Islamic Azad University,Isfahan, Iran
Mohammadreza Soltanaghaei
Department of Computer Engineering, Isfahan Khorasgan Branch, Islamic Azad University,Isfahan, Iran
Hossein Ghaffarian
Department of Computer Engineering, Faculty of Engineering, Arak University, Arak, Iran
شیوه ارجاع
Azizi, Somayeh and Soltanaghaei, Mohammadreza and Ghaffarian, Hossein,1403,Hierarchical Traffic Optimization in SDN with Graph NeuralNetworks and PSO Techniques,The 4th international conference on artificial intelligence and its future prospects in electrical, computer, mechanical and telecommunication engineering sciences,Mashhad
ارائهشده در
مجموعه مقالات چهارمین کنفرانس بین المللی هوش مصنوعی و چشم انداز آینده آن در علوم مهندسی برق ، کامپیوتر ، مکانیک و مخابرات18 آذر 1403 · مشهد