Supply chain energy sustainability with artificial intelligence

Supply chain (SC) processes are complex and have been the subject of many optimization studies. The optimization of the SC is pivotal for the success of a business. optimizing SC usually requires rapid responses and additional resources, resulting in increased energy demand that in turn yields augmented CO2 emission. The advent of the Artificial Intelligence (AI) has delivered alternative optimization opportunities when adopted as a digital tool. This research provides insights into AI application for optimizing SC processes in order to decrease energy demand and CO2 emission. The AI engine is based on a Cyber Physical System (CPS) developed using business activities as defined by business processes. A Monte Carlo simulation is adopted to ensure that the baseline (CPS) model is statistically representative. The probability functions and results of2400 runs are extracted and inputted into Python code to generate ordinary least square (OLS) multiple linear regression model. The results of the OLS are used to create energy optimization formula to reduce CO2 emission and yield sustainable energy in the SC.