Open AccessEffective fault detection approach for cloud computing
Author(s) -
Pola Ashritha,
M. Banusri,
R. Namitha,
J. Shiny Duela
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1979/1/012061
Subject(s) - cloud computing , computer science , data mining , task (project management) , decision tree , support vector machine , fault (geology) , algorithm , logistic regression , artificial intelligence , machine learning , engineering , systems engineering , seismology , geology , operating system
In cloud computing, accessibility to data anytime is crucial, acquiring data and maintaining that data without any loss or incursion is an essential task. A cloud service must have the potential to recognize unexpected faults and respond effectively. Hence, a system to identify faults is developed which recognizes anomalies using various techniques and algorithms. Several different types of faults occur in cloud computing which causes the poor performance of cloud computing. The various types of faults occurred are collected and classified using a fuzzy one class support vector machine and long short term memory(LSTM) algorithm. Comparative analysis of accuracy and precision is done with various algorithms like Naive Baye Algorithm, Decision Tree Algorithm, K-Neighbors Algorithm, and Logistic Regression Algorithm. Experimental results show that Logistic regression gives the best accuracy, precision and performance for detecting faults among the aforementioned algorithms. The efficacy of our model is illustrated in experimental results.