等规模虚拟网络映射问题的反向和双向灌水方法

Reversed and Bidirectional Irrigation Methods for Equal-Scale Virtual Network Embedding Problem

Previous Virtual Network (VN) embedding researches mostly focus on developing heuristic algo-rithms to enhance the efficiency of a physical re-source. However, in the equal-scale condition, where the scale of a VN is similar to that of a substrate net-work, the number of successfully mapped VNs de-creases sharply since bottlenecks form easily in the substrate network and disturb the embedding process. In this paper, reversed and bidirectional irrigation methods are proposed for the equal-scale and all-scale conditions. The two proposed methods can be com-bined with most of the existing heuristic algorithms and map a relatively large number of VNs by reducing the potential substrate bottlenecks. The simulation re-sults show that the reversed irrigation method almost doubles the successfully mapped Revenue than the traditional one in the equal-scale condition. Mean-while, the bidirectional irrigation method achieves the synthetically best performance in almost all scale con-ditions.