2023ICERD8-C05 -- Optimizing HVAC System of Kuwaiti Residential Building Based on Internet of Energy (IoE) Concept

The high energy consumption of Heating, Ventilation, and Air Conditioning (HVAC) systems in Kuwaiti buildings, accounting for approximately 50% of total energy usage, has become a pressing concern in alignment with the sustainability vision of Kuwait 2035. This study aims to address this issue by proposing optimal cooling strategies that leverage the Internet of Energy (IoE) concept to simultaneously reduce energy consumption and carbon emissions while ensuring occupant comfort. To achieve these objectives, a Model Predictive Controller (MPC) integrated with an IoE framework is introduced as a solution for controlling the HVAC system in a residential building located in Kuwait, serving as a case study. The MPC operates as an online closed-loop feedback controller, optimizing both indoor thermal comfort and energy consumption. In order to simulate the energy performance of the building, an Artificial Neural Network (ANN) model is developed and incorporated into the MPC. Leveraging the IoE paradigm, Application Programming Interfaces (APIs) are generated to acquire real-time weather conditions and electricity prices via the Internet. These dynamic inputs are utilized to dynamically adjust temperature settings, further enhancing the energy efficiency of the HVAC system. The results of this study demonstrate that the MPC controller surpasses the hysteresis controller in terms of energy consumption, while still maintaining satisfactory thermal comfort levels. The integration of the IoE concept and the utilization of the ANN model in the MPC contribute to the achievement of optimal control strategies, yielding significant energy savings and a reduction in carbon emissions.