Enhanced Resource Allocation System Using IoT, Feedback-Driven Optimization and Collision Resolution for Sustainable Event Management

Abstract

Resource allocation using IoT and Feedback-Driven Optimization introduces a new way to transform existing halls into smart, sustainable and intelligent environments through the implementation of IoT sensing, machine learning and automated scheduling for event management. Halls that are used in a traditional way often face problems of underutilization, bottlenecks associated with manual scheduling, and inefficiencies in energy consumption. This paper’s approach solves those problems by retrofitting existing infrastructure with IoT sensors to capture real-time data for occupancy (measured with carbon dioxide concentration), lighting, temperature, humidity, and other parameters representing the environment. The data is used by a regression machine learning model that has been trained to predict lighting needs based on conditions and occupancy of the hall, and the model continues to retrain itself until it achieves an accuracy of 0.9 or higher. By connecting to a central dashboard and ERP system, the hall can now be equipped to handle automated scheduling, energy-saving lighting, and role-based approvals, thus reducing the human element and enhancing transparency. By turning the conventional hall into a data-enabled smart space, the system offers potential for real-time resource optimization, an enhanced user experience, and seamless integration of green practices. The outcome of this research emphasizes the ease with which facilities already in place can be retrofitted on a scalable and controllable basis to meet the event management imperatives of sustainability.