A Discussion of Non-Gaussian Price Processes for Energy and Commodity Operations

Energy sources and commodities exhibit high price risk. This risk is thus an important feature of operational models of the value chains for these goods. These models typically employ Gaussian-based representations of the evolution of this uncertainty. This approach facilitates the optimization of operational policies but is at odds with empirical facts about energy and commodity prices, which are better captured by non-Gaussian processes. We discuss this alternative modeling strategy, focusing on Lévy processes. As an illustration, we show that it substantially increases the optimal policy value in a simplified merchant natural gas storage setting. Further, we highlight potential implications of using this approach to formulate realistic energy and commodity operations models. Our work has broader relevance for modeling the dynamics of both other market variables and operational quantities, such as exchange rates and demand forecasts. The study of how the adoption of non-Gaussian processes may impact energy and commodity operations is an appealing area for future research.