Adaptive fault diagnosis for data replication systems

Wee, Chee Keong and Wee, Nathan (2021) Adaptive fault diagnosis for data replication systems. In: 32nd Australasian Database Conference: Database Theory and Applications (ADC 2021), 29 Jan - 5 Feb 2021, Dunedin, New Zealand.


Abstract

Data replication among multiple IT systems is ubiquitous among large organizations and keeping them running is a critical success factor for their IT departments. When services are disrupted, IT administrators must be able to find the faults and rectify them quickly. Due to the scale and complexity of the data replication environment, the fault diagnostic effort is both tedious and laborious. This paper proposes an approach to fault diagnosis of the data replication software through deep reinforcement learning. Empirical results show that the new method can identify and deduce the software faults quickly with high accuracy.


Statistics for USQ ePrint 47000
Statistics for this ePrint Item
Item Type: Conference or Workshop Item (Commonwealth Reporting Category E) (Paper)
Refereed: Yes
Item Status: Live Archive
Faculty/School / Institute/Centre: No Faculty
Faculty/School / Institute/Centre: No Faculty
Date Deposited: 10 Mar 2022 03:00
Last Modified: 16 Mar 2022 05:21
Uncontrolled Keywords: database systems; deep learning; failure analysis; reinforcement learning
Fields of Research (2008): 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080105 Expert Systems
08 Information and Computing Sciences > 0806 Information Systems > 080604 Database Management
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080101 Adaptive Agents and Intelligent Robotics
Fields of Research (2020): 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460201 Artificial life and complex adaptive systems
46 INFORMATION AND COMPUTING SCIENCES > 4605 Data management and data science > 460505 Database systems
46 INFORMATION AND COMPUTING SCIENCES > 4605 Data management and data science > 460501 Data engineering and data science
Identification Number or DOI: https://doi.org/10.1007/978-3-030-69377-0_11
URI: http://eprints.usq.edu.au/id/eprint/47000

Actions (login required)

View Item Archive Repository Staff Only