A Survey of Common Challenges and Successes in Implementing Integrated Energy Management Systems in Existing School Buildings

This thesis considers the Integrated Energy Management Systems (IEMS) deployment in educational settings, focusing on critical barriers and examining the potential of AI-powered predictive models for improved energy management. Though immediately, while Integrated Energy Management Systems (IEMS) are commended for reducing both energy consumption and cost, educational institutions are faced with perpetual challenges that work around outdated infrastructure, technical problems, and lack of stakeholder involvement. To serve this purpose, the study includes such tools as case research, survey-based primary research, and predictive analysis using the LSTM technique. It emerges from the study that although, AI-based forecasting holds promise for real-time energy optimization; data quality problems, optimal model calibration and high computational demands continue to be major barriers. The introduction of IEMS depends on technological innovation and involvement of all interested parties and special training. Giving a hands-on perspective of approaching AI in IEMS, this research intends to enhance the level of energy efficiency in educational institutions under resource constraints whilst highlighting the important areas that require more attention.