AI-Enabled Intelligent Energy Optimisation for Smart Commercial Infrastructure Using IoT and Digital Twin Technologies

Intelligent, sustainable management systems are needed to address rapid urbanisation and rising energy consumption in commercial facilities. Traditional Building Management Systems (BMS) are reactive, non-predictive, and non-automated, and they lack AI support for decision-making. This paper introduces EcoMind, an Internet of Things (IoT)- based intelligent energy optimisation framework for smart commercial infrastructures, supported by artificial intelligence. It is implemented in a cloud-native system that incorporates IoT telemetry simulation, predictive analytics, Digital Twin monitoring, sustainability assessment, and a telemetry-based conversational AI module. Anomaly detection, predictive maintenance, occupancy-aware intelligence, and rule-based optimisation mechanisms provide real-time analysis of HVAC, lighting, elevator, escalator, parking, and environmental sensor data. The definitions used for this study are as follows: occupancy utilisation: ratio of actual occupancy over maximum occupancy; total energy consumption: total energy consumed by HVAC, lighting, elevator, escalator and parking systems; anomaly deviation: dif erence between the current sensor reading and the historical normal behaviour; optimisation efficiency: ratio of reduction in energy consumption after applying optimisation strategies to the total energy consumption. The major innovation is using the Gemini APIs large language model to integrate live infrastructure telemetry data into a pipeline, enabling real-time reasoning without relying on static datasets. Experimental results show a decrease in total energy consumption of 18–22 parcent, improved response to anomaly detection and improved operational decision making. The results confirm that Digital Twin intelligence and Telemetry AI is a powerful complement that enhances scalability, adaptability, and sustainability in smart commercial infrastructure systems.