IntelliQueue: An AI-Driven Adaptive Queue Orchestration Framework Using Machine Learning and Cloud–Edge Synergy

Abstract

Public service oriented areas such as hospitals, banks, schools and government offices are often characterized by some inefficiency in operation since long waiting time for the people, inadequacy of space because of overcrowding use to cum lack of transparency during queue processing. Traditional queue management systems are based on static rules or manual interventions, which cannot adapt to variable traffic pattern and peak-hour crowdiness. In response to these challenges, in this paper, we develop IntelliQueue, an AI-powered adaptive queue orchestration framework which leverages ML-based prediction with unified queue management and run-time user interaction.

The system provides online token booking and offline walk-in registration allowing universal access by all users. A timestamp queue integration scheme combines tokens generated at different access points into a single common queue, so that fairness and first-come-first-served principle is achieved. Data of the queue, such as arrival pattern, state of the queue (number waiting), rate at which the customers are served and temporal aspect are used and analyzed. In this context, we apply supervised machine learning regression models of waiting time and queue length for real-time prediction, thereby achieving proactive congestion monitoring and service flow enhancement.

IntelliQueue utilizes a cloud-based architecture for multiuser scalability, energy-efficient decision-making support mechanisms, as well as automated notifications regarding queue status and estimated wait time to avoid unneeded physical waiting and overcrowding. Experimental results with synthetic data show that the proposed framework not only is a better predictor than traditional rule based queue management methods but also has significantly reduced waiting time and system utilization. The findings suggest that data-driven queue orchestrators have potential to improve transparency, operational effectiveness and user satisfaction in contemporary public service settings