Behavioral analytics for optimized self-scheduling in sustainable local multi-carrier energy systems: A prospect theory approach

Abstract

The transition towards sustainable energy systems demands innovative solutions to overcome the challenges of integrating diverse energy carriers, fluctuating market dynamics, and operator decision-making complexities. The active involvement of local multi-carrier energy systems (LMCES) as virtual power plants in upstream energy markets is particularly hindered by the limitations of conventional optimization methods, which fail to capture the nuanced behavioral aspects of decision-making. This paper presents a novel prescriptive behavioral analytics framework for LMCES self-scheduling, integrating insights from prospect theory to address the operator's behavioral tendencies, including loss aversion, subjective risk attitudes, and mental reference points. By embedding these behavioral considerations into a mixed integer linear programming (MILP) model, the proposed approach accounts for real-world decision-making complexities often overlooked in conventional economic theories based on rationality. Comparative analyses demonstrate that the proposed framework not only enhances the modeling of LMCES operators’ decision-making processes but also improves energy scheduling efficiency and supports sustainable energy transitions. The findings provide actionable insights for optimizing LMCES operations, advancing their role in achieving energy sustainability goals.