Gaussian Process Learning-Based Probabilistic Optimal Power Flow

In this letter, we present a novel Gaussian Process Learning-based Probabilistic Optimal Power Flow (GP-POPF) for solving POPF under renewable and load uncertainties of arbitrary distribution. The proposed method relies on non-parametric Bayesian inference-based uncertainty propagation approach, called (GP). We also suggest new type sensitivity Subspace-wise Sensitivity, using observations the interpretability GP-POPF hyperparameters. simulation results 14-bus 30-bus systems show that provides reasonably accurate solutions when compared with Monte-Carlo Simulations (MCS) at different levels uncertain penetration uncertainties. requires lesser number samples elapsed time. nature is manifested by testing injections follow various distributions in 118-bus system. low error value verify method's capability working types input distributions.