IP/DWDM光Internet中基于软计算的智能多约束波长分配算法的研究

Research on Soft-Computing-Based Intelligent Multi-Constrained Wavelength Assignment Algorithms in IP/DWDM Optical Internet

波长分配问题是影响IP/DWDM光Internet中网络资源利用的关键问题之一。本文提出了两种基于软计算的多限制的波长分配算法,使得波长源分配适应实际的网络特征。事实上,由于考虑到多种限制问题,包括成本,功率和网络性能等,因此采用分层解决方案。因为每一层都是NP完全问题,所以采用软计算和启发式相结合的方法进行求解,设计并实现了一个仿真软件,仿真表明该算法既是可行的又是有效的。

Wavelength assignment is one of the most important research areas in IP/DWDM optical Internet. Taking multiple constraints into account,including cost,power,network performance etc., the wavelength assignment is made much fit to the actual network configurations,however,the problem complexity increases correspondingly,leading to the adoption of a layered solution framework. As each layer sub-problem is NP complete,soft-computing algorithms, including SAA (Simulated Annealing Algorithm) and SGA (Simulated-annealing-Genetic Algorithm),and heuristic algorithms are used jointly to design the intelligent multi-constrained wavelength assignment algorithms respectively. Simulation results have shown that these proposed algorithms are feasible and effective.