Day-Ahead Scheduling of Hydrogen-Based Chemical Industry Park: A Bayesian Nonparametric Two-Sided Chance Constraint Method

Uncertainties introduced by renewable energy pose significant challenges to the scheduling of chemical industry park that integrates an electricity-heat-hydrogen microgrid on the supply level and ammonia-based process chemical industry loads (APCIL) on the demand level. This paper proposes a day-ahead scheduling framework based on Bayesian nonparametric two-sided chance constraint (BNTCC) to address these challenges. Firstly, a refined operation model for electricity-heat-hydrogen microgrid and an energy-material integrated model for APCIL are developed, incorporating the security constraints of hydrogen equipment and chemical production process. Secondly, a Dirichlet process mixture model (DPMM) is utilized to construct Gaussian mixture (GM) distribution from historical uncertainty data to characterize renewable energy uncertainties. Based upon this GM model, a two-sided chance constraint (TCC) scheduling method is proposed for the scheduling of chemical industry park to reduce the conservatism while ensuring that operational limits are jointly satisfied with a specified confidence level. Finally, to solve the TCC problem efficiently, a second-order cone programming (SOCP) formulation is derived using a piecewise linear (PWL) approximation. An additional algorithm is introduced to accelerate computation by optimally selecting the PWL segments. Case studies illustrate the effectiveness of the proposed method for the day-ahead scheduling of chemical industry park. Besides, the proposed method has the advantage of achieving 45% lower violation probability compared to the existing one-sided chance constraint (OCC) method.