Data validation with machine learning for storage area networking utilities: a thesis in Computer Engineering
Abstract
"For storage area networking (SAN) devices and utilities, the traditional rule-based approach to validate the data displayed by multiple utilities is no longer practical due to the inconsistencies in semantics, variations in developer interpretation of specifications, and frequent updates to the data in different utilities. Using machine learning to validate the data for SAN devices and utilities shows promise with its capability for recognizing patterns and making predictions based on the comparative properties of the data provided by these SAN utilities. This research proposes an innovative data validation approach driven by machine learning that is applied to validate static Host Bus Adapter (HBA) information collected from SAN utilities such as the Distributed Management Task Force (DMTF) Redfish Interface and the Fabric Device Management Interface (FDMI). The machine learning driven framework consists of a data preprocessing stage and a neural network training stage. Multiple alternatives during both stages are examined to determine the optimal configuration. The outcome expects to substitute the current manual process of data validation that takes an excessive amount of time and effort for little return. The trained model has the ability to validate the data collected from the SAN utilities in a few seconds as opposed to weeks’ worth of man-hours with manual validation. The future work of the proposed framework will expand the variety of SAN utilities being validated and develop a weight analysis mechanism that allows the user to gain more insight about the data."
Keywords
Not available
Specialisations
Similar theses
- Predictive Maintenance in Modern Radar Systems using Machine Learning Klas Thorgren · Lund University · 2026
- A Novel Explainable Artificial Intelligence Framework with Improved Learning Mechanisms Kabir, Sami · Luleå University of Technology · 2025
- Image analysis and machine learning in patients with brain tumors Alice Neimantaite · Gothenburg University · 2026
- Hybrid Machine Learning and Time-Series Modelling to Forecast Product Demand: A CRISP-DM Approach Niklas Virtanen · University of Vaasa · 2026
- Predictive Scheduling of Incoming Goods Using Machine Learning and Deep Learning Methods Johannes Simon Michael Rechenauer · TU Wien · 2026
- Computational biology in plant tissue culture: Systematic evaluation of machine learning approaches for callus induction in Solanum L.: A thesis submitted in partial fulfilment of the requirements for the Degree of Doctor of Philosophy at Lincoln University Sadegh Mohajer · Lincoln University · 2026
