Dublin Core
Title
ResolveNet - Optimizing IT Service Desk Operations Using Agent-Based Modeling in NetLogo
Abstract
IT service desks are an important aspect of maintaining IT systems by processing user reported problems, managing service requests, and assigning resources efficiently. Real world service desks, nonetheless, suffer from inefficiencies including high backlog of tickets, uneven staff workload, and slow response time. In this thesis, we introduce ResolveNet, an agent-based model (ABM) in NetLogo to model and optimize the operations of an IT service desk. The model recognizes the ticket processing dynamics, workload distribution, and user satisfaction to understand performance improvement.
Through a comparative study of simulated data and real world IT service desk logs, this study identifies critical inefficiencies in ticket resolution workflows. The results are that priority-based ticket assignment, automated workload leveling, and predictive analytics yield significant efficiency improvements, reducing average ticket resolution time by up to 40% and improving user satisfaction ratings. Scenario-based performance evaluation also identifies staff shortage, ticket spikes, and lack of automation as primary drivers of backlog accumulation.
The findings of this study have practical implications for IT service management by providing data driven strategies to enhance operational performance. Future upgrades may involve real-time integration with live IT service desks, machine learning driven optimization models, and further automation of routine ticket resolutions.
Through a comparative study of simulated data and real world IT service desk logs, this study identifies critical inefficiencies in ticket resolution workflows. The results are that priority-based ticket assignment, automated workload leveling, and predictive analytics yield significant efficiency improvements, reducing average ticket resolution time by up to 40% and improving user satisfaction ratings. Scenario-based performance evaluation also identifies staff shortage, ticket spikes, and lack of automation as primary drivers of backlog accumulation.
The findings of this study have practical implications for IT service management by providing data driven strategies to enhance operational performance. Future upgrades may involve real-time integration with live IT service desks, machine learning driven optimization models, and further automation of routine ticket resolutions.
Keywords
IT service desk, Agent-Based Modeling, NetLogo, ticket resolution, workload balancing, user satisfaction, service optimization.