Detecting Shared Congestion Paths Based On Sparse Representation

Most existing techniques detecting shared congestion paths are based on pair-wise comparison of paths with a common source or destination point. It is difficult to extend them to classify paths with different sources and destinations. In this paper, we propose a scalable approach to classify shared congestion paths based on spare representation. According to the sparse representation theory, target data sample can be sparsely represent by selected correlative data samples. The sparse items corresponding to the sampled paths are not correlated to the target paths, which means they do not share congestion paths. In this case, elastic net-based ISC-SR is applied to identify shared common congestion paths. This algorithm is evaluated by NS2 simulations. Experimental results show that this algorithm has high accuracy.