Real Time Anomaly Detection Techniques Using PySpark Frame Work

Abstract

The identification of anomaly in a network is a process of observing keenly the minute behavioral changes from the usual pattern followed. These are often referred with different names malware, exceptions, and anomaly or as outlier according to the dominion of the application. Though many works have emerged for the detection of the outlier, the identification of the abnormality in the multiple source data stream structure is still under research. To identify the abnormalities in the cloud data center that is encompassed with the multiple-source VMWare, by observing the behavioral changes in the load of the CPU, utilization of the memory etc. consistently the paper has developed a real time identification process. The procedure followed utilizes the PySpark to compute the batches of data and make predictions, with minimized delay. Further a flat-increment based clustering is used to frame the normal attributes in the PySpark Structure. The latencies in computing the tuple while clustering and predicting, was compared for PySpark, Storm and other dispersed structure that were used in processing the batches of data and was experimentally found that the processing time of tuple in a PySpark was much lesser compared to the other methods.