Data-driven scheme for optimal day-ahead operation of a wind/hydrogen system under multiple uncertainties

Hydrogen is believed as a promising energy carrier that contributes to deep decarbonization, especially for the sectors hard be directly electrified. A grid-connected wind/hydrogen system typical configuration hydrogen production. For such system, critical barrier lies in poor cost-competitiveness of produced hydrogen. Researchers have found flexible operation possible thanks excellent dynamic properties electrolysis. This finding implies owner can strategically participate day-ahead power markets reduce production cost. However, uncertainties from imperfect prediction fluctuating market price and wind effectiveness offering strategy market. In this paper, we proposed decision-making framework, which based on data-driven robust chance constrained programming (DRCCP). framework also includes multi-layer perception neural network (MLPNN) spot electricity prediction. Such DRCCP-based decision (DDF) then applied make system. It effectively handle uncertainties, manage risks The results show that, daily selected 30 days, reduces overall cost by 24.36%, compared Besides, elaborate parameter selections DRCCP reveal best combination obtain better optimization performance. efficacy method highlighted comparison with chance-constrained method.