A.I. model forecast of building cooling load demand for the reduction of energy consumption to work towards carbon neutrality

The world needs to achieve carbon neutrality or net zero emissions of greenhouse gases (GHG) by 2050. Buildings are major sources GHG emissions. Applications the latest innovative technologies machine learning/A.I. algorithms have opened up new opportunities. optimal control cooling plant systems is important reduce energy consumption and therefore Knowing load demand in advance can help facility managers operate plants much more efficiently. This paper presents a real-life application nine A.I. models for time-series forecasting commercial building. LSTM neural networks, Facebook Prophet time series model, DeepAR recurrent network found be most accurate with Mean Absolute Percentage Error (MAPE) range 15 16 computing 294 319 seconds respectively. LightGBM learning model on other hand proves fastest MAPE 18.96 just 7 seconds. Thus, different deployed requirements. Optimising operation as per forecast bring enormous savings that essential achieving neutrality.