A Holistic Multi‐Objective Optimisation Model for Energy Efficiency Improvement and Cost Savings in Smart Buildings

ABSTRACT This paper proposes a holistic multi‐objective framework that jointly models lighting technology, appliance efficiency, HVAC efficiency, building‐envelope measures, natural‐light strategy, PVT generation, and storage to improve building energy efficiency while accounting for annualised total cost. The weather data is forecasted for 24 h by a deep‐learning method in Python, and the electricity generation of the PVT system is calculated by System Advisor Model (SAM) software. This paper presents a building energy efficiency improvement (BEEI) index based on different energy‐saving technologies. The proposed multi‐objective optimisation problem is solved by the epsilon‐constraint method and the CPLEX solver in the GAMS environment to maximise the BEEI index and minimise the total annual cost. Unlike studies that investigate these measures separately, the proposed framework integrates demand‐side efficiency programmes, renewable generation, thermal and electrical storage, weather forecasting, and sensitivity analysis within one techno‐economic optimisation model for smart buildings. The main contribution of this paper is to propose a unified metric for energy efficiency to quantify the combined impact of different energy‐saving technologies. The results show that, after using the energy‐saving programmes, the BEEI increases significantly from 2.36% to 37.40%, while the total cost increases from $34,719 to $37,362 per year.