Prediction of performance degradation in telecommunication networks using Joint Clustering and association analysis techniques

Abstract

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.

Efficient failure prediction in autonomic networks based on trend and frequency analysis of anomalous patterns

“…The sequences of alarms obtained from the different points in the network are modeled as states of an FSM, and alarms are assumed to contain information such as the device name as well as the symptom and time of occurrence. The probability of transitions between the states is estimated by conditioning on prior events within historical failure data.…”

“…Within the state machine paradigm, researchers previously developed a system based on ‘topographical proximity’ , which leverages topographical information embedded in alarm data in order to evaluate the implausibility of mined sequences. In their research work, event correlation is used to extract significance and semantics from the wealth of alarm data generated by the network.…”

“…In this class of approach, anomalies are considered deviations from normal behavior and are modeled in terms of variability in the network environment . Online machine learning is used to build a traffic profile for a given network, using symptom‐specific feature vectors such as link utilization, packet loss and number of collisions . These traffic profiles are then categorized by time of day, day of week, and special days such as weekends and holidays.…”

“…Fundamentally, the value of intelligent fault management lies in its ability to help identify the root causes of failures, in order to facilitate effective corrective response. Typical fault management approaches use observations of the system to detect a failure, isolate (locate) the source of failure and diagnose the root cause by analyzing event traces . Based on traces, system behavior is modeled as a finite state machine, in which failure events form a part of the event set.…”

Study on Network Behavior Assessment Using Amazon Web and Cloud Computing Services

“…The proposed approach demonstrated the ability to improve the quality of predication by discovering the root cause of network failure and proactively correct the network drawbacks in a timely manner. [1].…”