A Stochastic Queuing Network Model for MPLS Adaptive Traffic Engineering

作者：He Xiaoming^*; Zhu Mingying; Chu Qingxin

来源：China Communications, 2010, 7(1): 115-119.

• traffic engineering
• M/Pareto/1
• queuing model
• load balancing
• optimization formulation

Load balancing is a key technique for improving the performance and scalability of the Internet. Our focus on this paper was to apply adaptive traffic engineering to utilize network resource more efficiently and minimize congestion. In the light of the suggestion that Internet traffic can be modeled as a stationary stochastic process where statistical variations occur about an underlying constant intensity, we present a stochastic queuing network model for multi-path adaptive load balancing at flow-level. The optimization formulation based on M/Pareto/1 queuing model can shed some light on traffic distribution for minimizing network congestion in statistical terms.

• 出版日期2010-1
• 单位华南理工大学