Date of Graduation

5-2022

Document Type

Thesis

Degree Name

Master of Science in Computer Science (MS)

Degree Level

Graduate

Department

Computer Science & Computer Engineering

Advisor/Mentor

Brajendra Panda

Committee Member

Dale Thompson

Second Committee Member

Qinghua Li

Keywords

Critical Infrastructure, Damage Assessment, Data Lineage, Data Provenance, Graph Reachability, Temporal Graphs

Abstract

Rapid and accurate damage assessment is crucial to minimize downtime in critical infrastructure. Dependency on modern technology requires fast and consistent techniques to prevent damage from spreading while also minimizing the impact of damage on system users. One technique to assist in assessment is data lineage, which involves tracing a history of dependencies for data items. The goal of this thesis is to present one novel model and an algorithm that uses data lineage with the goal of being fast and accurate. In function this model operates as a directed graph, with the vertices being data items and edges representing dependencies. Additionally, data is grouped into multiple layers which allows for faster partial damage assessment. Lower layers of the graph consist of more granular data items, while higher layers consist of containers of lower layer data items. By assessing a higher layer, one can immediately conclude that certain portions of the system are undamaged, and those portions may begin operation again. In practice, graph creation is a front-loaded operation that allows immediate action at the time of damage assessment. Depending on the system, this graph will often be cyclic which causes standard assessment to be a computationally slow problem. By tracking the time of dependencies, our graph operates as a subclass of temporal graph, which are graphs that change over time. By taking advantage of unique properties of this subclass, our algorithm is able to function in a way that is nearly only dependent on the number of edges. Put together, the model can run quickly, free up undamaged portions of the system during assessment, and find the minimum amount of damage which needs to be manually assessed.

Share

COinS