A method for intelligent estimation of service flow in otn network

Abstract

The invention belongs to the field of the OTN network, and specifically discloses a service flow intelligent estimation method in an OTN network. The method comprises the following steps: step one, constructing an optimal model through a covariance matrix C and performing analysis in consideration of space-time related OD traffic, and intelligently acquiring an initial estimation value of the OD flow; step two, taking the acquired initial estimation value of the OD flow as an initial value in a simulated annealing algorithm SA iteration process, estimating the deviation by using an OD flow matrix, and intelligently acquiring a global optimal OD flow estimation value by using iteration optimizing from high temperature to low temperature through a simulated annealing process; and step three,based on the OD flow estimation result in the previous step, acquiring a more accurate estimation result of the OD flow through iterative proportional fitting process IPFP by using the OD traffic matrix network tomography constraint condition. By using the estimation method disclosed by the invention, a direction of moving towards the global optimal solution in the SA iteration process can be fast selected, the modified SA method is simple, and the service intelligent estimation in the OTN network can be fast executed, and the dynamic state can be tracked.

Description

Technical field: [0001] The invention belongs to the field of OTN networks, and particularly provides a method for intelligently estimating service flow in the OTN network. Background technique: [0002] With the exponential growth of IP network scale, there is an urgent need for network management and maintenance, forcing network operators to know the forwarding of data packets between different nodes in the network, so as to better perform load balancing, traffic detection, and routing. Estimation of traffic matrix for network activities such as optimization, network maintenance, network design and network planning. The traffic matrix represents the network traffic flowing between the source and destination (OD) nodes in the network (that is, the size of the OD flow). The dimension of the traffic matrix is ​​equal to the number of all OD flows in the network. It describes the data flow of the entire network from a global perspective. The situation is an important basis fo...

AI Technical Summary

Problems solved by technology

Therefore, due to the randomness of the traditional SA method to generate a new solution, it is difficult to quickly find the global optimal solution

Images