Data-Driven Stochastic Scheduling of Renewable-Rich Oilfield Microgrids Based on Electric-to-Thermal Flexibility and Thermo-Hydraulic Safety

Renewable-rich industrial microgrids require scheduling strategies that convert uncertain renewable generation into reliable and physically feasible decisions. This challenge is particularly significant in oilfield microgrids, where photovoltaic (PV) uncertainty is coupled with crude-oil transportation and temperature requirements. This paper proposes a data-driven stochastic scheduling framework for PV-integrated oilfield microgrids using electric thermal storage boilers (ETSBs) as industrial flexibility resources. A convolutional neural network-gated recurrent unit (CNN-GRU) model is combined with probabilistic scenario generation and reduction to characterize PV uncertainty, while a physics-informed multi-objective model coordinates grid-interaction smoothing, operating cost, PV absorption, ETSB dynamics, and pipeline temperature safety. To improve schedule executability, an oilfield-specific non-dominated sorting genetic algorithm II (NSGA-II) solver is developed with thermo-hydraulic simulation, feasibility projection, ramping correction, and terminal sustainability evaluation. Case studies show that the proposed stochastic strategy reduces net-load variance by 56.82% and increases PV absorption by 17.58 percentage points, while maintaining pipeline temperature within 42.0–42.3 °C. Compared with deterministic scheduling, it limits the real-time cost deviation to 0.11%, indicating stronger day-ahead-to-real-time consistency under PV uncertainty. The proposed framework provides practical decision support for renewable-rich oilfield microgrids balancing renewable accommodation, operating economy, and thermo-hydraulic safety.