A data-driven approach for microgrid distributed generation planning under uncertainties

The increasing demand for power system decarbonization and resilience raises the necessity of incorporating renewable distributed generation (DG) into microgrid planning. complexity DG planning largely roots from intermittent wind solar energy load variations throughout period. This paper proposes a novel two-stage data-driven adaptive robust (DDARDGP) framework considering both grid-connected islanded modes microgrids, wherein overall cost is minimized. By leveraging spatio-temporal property historical weather grid information, compact uncertainty set developed based on Bayesian nonparametric approach. problem further solved by modified column constraint (CC&G) algorithm. In study, effectiveness proposed demonstrated using IEEE 33-bus test system. case study considers optimal sizing, allocation mixtures. simulation results confirm that adapts well to increase data dimensions solves over-conservatism issue, leading 34.14% reduction in estimation compared with traditional budget set. Accordingly, total can achieve $23,185 under DDARDGP framework.