Deep excavation of the impact from endogenous and exogenous uncertaintieson long-term energy planning

Endogenous and exogenous uncertainties exert significant influences on energy planning. In this study,we propose a systematic methodology to excavate the uncertainty space, by combining mix-integer linearprogramming (MILP), Monte Carlo simulation, and machine learning for quantification of the uncertaintyimpacts on a national-level energy system from global and local perspectives. This approach allows in-depthcorrelation analysis highlighting potential synergies and risks in the energy transition, and can be easily applie for assisting policy making. The case study for Switzerland shows that both carbon neutrality (even negativeemissions) and energy autonomy can be achieved by 2050, but the energy system’s configuration variessignificantly under uncertainty. Through conditional distribution analyses, carbon capture and storage (CCS),Photovoltaic (PV), and wood gasification show the most strong correlation for decarbonization. This study isbased on the whole uncertainty space taking into account heterogeneous uncertainties, leading to increasedreliability compared to sensitivity analysis from single scenarios’ comparisons. The synergy between energymodels and artificial intelligence (AI) is promising to be widely applied in energy planning area, particularlyfor emerging technologies with large uncertainty in development.