صورة الغلاف

Dynamic Multi-Objective Controller Placement in SD-WAN: A GMM-MARL Hybrid Framework

محفوظ في:
الحاوية / القاعدة:Network vol. 5, no. 4 (2025), p. 52-83
المؤلف الرئيسي: Abdulghani, Abdulrahman M
مؤلفون آخرون: Azizol, Abdullah, Rahiman, A R, Abdul Hamid Nor Asilah Wati, Akram Bilal Omar
منشور في:
MDPI AG
الموضوعات:
Mathematical programming
Machine learning
Software
Integer programming
Wide area networks
Network topologies
Artificial intelligence
Optimization techniques
Real time
Adaptation
Linear programming
Algorithms
Clustering
Fault tolerance
Efficiency
Business metrics
الوصول للمادة أونلاين:Citation/Abstract
Full Text + Graphics
Full Text - PDF
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
مستخلص:Modern Software-Defined Wide Area Networks (SD-WANs) require adaptive controller placement addressing multi-objective optimization where latency minimization, load balancing, and fault tolerance must be simultaneously optimized. Traditional static approaches fail under dynamic network conditions with evolving traffic patterns and topology changes. This paper presents a novel hybrid framework integrating Gaussian Mixture Model (GMM) clustering with Multi-Agent Reinforcement Learning (MARL) for dynamic controller placement. The approach leverages probabilistic clustering for intelligent MARL initialization, reducing exploration requirements. Centralized Training with Decentralized Execution (CTDE) enables distributed optimization through cooperative agents. Experimental evaluation using real-world topologies demonstrates a noticeable reduction in the latency, improvement in network balance, and significant computational efficiency versus existing methods. Dynamic adaptation experiments confirm superior scalability during network changes. The hybrid architecture achieves linear scalability through problem decomposition while maintaining real-time responsiveness, establishing practical viability.
تدمد:2673-8732
DOI:10.3390/network5040052
المصدر:Publicly Available Content Database