GRAP: Grey risk assessment based on projection in ad hoc networks
Journal of Parallel and Distributed Computing
| Hi-index | 0.00 |
In this paper, we study the performance evaluation method applying Principle Component Analysis (PCA) theory. Due to the self-organizing and distributed character, each metric has its representative character evaluation method. Metrics while considering various network scenarios reflect different aspects of routing protocol efficiency in mobile ad hoc network. By now, there isn’t any ad hoc routing protocol can outperform others in any network conditions. Principle Component Analysis method is successfully applied in analyzing different impact of routing metric on network overall performance. Considering the suggestions in RFC 2501, PCA method tackle the performance evaluation problem as different types of metrics may lead to confusing evaluation results. It proves to be reliable and rational. Statistical results provided by PCA show that different types of routing protocol, such as proactive routing and reactive routing, has different principle components and routing metrics will have different impact on them. A synthetic method in evaluating metric representing the overall performance of the network is proposed after the PCA procedure, and routing performance comparison could clearly and reasonably be done with it.