one of the significant problems that high-tech companies are facing is the management and monitoring of networks in order to provide better and more reliable services for their customers. This paper introduces a new approach for the prediction of network failure and performance degradation using Joint Clustering and Association Analysis approach (JCAA). JCAA differs from existing prediction techniques in terms of exploiting the clustering and association analysis techniques in order to improve the quality of prediction. The role of clustering is to classify the input data into groups of k-means clusters, while the association analysis technique discovers the causal relationships between the groups. The experimental results demonstrate that the proposed system is truly effective in enhancing the quality of prediction.Index Terms-joint clustering and association analysis, autonomic network management, failure prediction.

No abstract

SUMMARYWe describe an efficient failure prediction system based on new algorithms that model and detect anomalous behaviors using multi-scale trend analysis of multiple network parameters. Our approach enjoys many advantages over prior approaches. By operating at multiple timescales simultaneously, the new system achieves robustness against unreliable, redundant, incomplete and contradictory information. The algorithms employed operate with low time complexity, making the system scalable and feasible in real-time environments. Anomalous behaviors identified by the system can be stored efficiently with low space complexity, making it possible to operate with minimal resource requirements even when processing high-rate streams of network parameter values. The developed algorithms generate accurate failure predictions quickly, and the system can be deployed in sa distributed setting. Prediction quality can be improved by considering larger sets of network parameters, allowing the approach to scale as network complexity increases. The system is validated by experiments that demonstrate its ability to produce accurate failure predictions in an efficient and scalable manner.

No abstract