Book Title: Advanced Studies in Multidisciplinary Research and Innovation (ASMRI)
Chief Editors: Dr. Jagdish Kumar Sahu and Dr. Krishna Ashutoshbhai Vyas
Associate Editors: Dr. N. Ramesh Chandra Srikanth and Dr. Lourdu Vesna J
Co-Editors: Dr. Aarti Sharma and Dr. Pushpa Mamoria
ISBN: 978-93-7183-010-2
Chapter: 18
DOI: https://doi.org/10.59646/745/18
Author: Sujatha S
Abstract
The advent of AI in energy management has transformed the way AI plays a role in achieving energy efficiency and net zero goals in modern educational institutions. This research paper explores how the integration of hybrid AI–based energy management systems can enhance the efficiency, flexibility, and sustainability of energy use in smart campuses. The study is a mixed-method study, using qualitative data from facility manager, sustainability officer, and technology providers involved in campus energy operations, and quantitative data from energy consumption data obtained from smart building systems. The results reveal that energy efficiency achieved by the hybrid AI systems, which integrate machine learning algorithms, rule-based optimization and real-time sensor networks, is greatly enhanced over the traditional building management systems. Advanced infrastructure, predictive analytics, and automated control mechanisms mean that smart campuses can achieve higher levels of energy optimization, resulting in more advanced integration of IoT. However, there are still implementation challenges, especially for older campus infrastructures that lack widespread deployment of sensors, integration of data and interoperability between different systems. Despite these challenges, hybrid AI systems play a significant role in decreasing energy waste, with features that optimize energy use for heating, cooling, lighting, and equipment based on occupancy and environmental data. The study shows that there are institutional variations in the extent to which the sustainability outcomes are achieved with advanced campuses outperforming those constrained by financial and technical resources. Facility stakeholders appreciate the use of AI systems for enhancing efficiency and cost reduction, but face challenges with system complexity, maintenance, and data privacy issues. The paper also recommends investing in smart infrastructure, developing interoperable AI frameworks, and introducing policy incentives to support green campus initiatives. The comparative impact adds to the existing body of research on smart campus buildings that are sustainable and brings practical guidance for policymakers, university management and technology developers in the pursuit of scalable, energy-saving smart campus buildings.
Keywords: Hybrid AI, energy management systems, net-zero campuses, smart campuses, IoT, machine learning, energy efficiency, sustainable infrastructure, predictive analytics, green buildings