{"id":"W4381415965","doi":"10.1109/tia.2023.3287944","title":"Service Restoration Using Deep Reinforcement Learning and Dynamic Microgrid Formation in Distribution Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Industry Applications","topic":"Microgrid Control and Optimization","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"University of Saskatchewan","keywords":"Microgrid; Reinforcement learning; Markov decision process; Resilience (materials science); Reliability (semiconductor); Computer science; Service (business); Node (physics); Reliability engineering; Process (computing); Distributed computing; Markov process; Power (physics); Control engineering; Engineering; Artificial intelligence; Control (management)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001100041,0.0001381963,0.0001056348,0.0001852228,0.0002619732,0.00005526165,0.00005942185,0.0002633506,0.00001599954],"category_scores_gemma":[0.000001495373,0.0001688191,0.00002534812,0.001111772,0.00001698015,0.0002960968,0.000001501601,0.0005554167,0.00002316857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002409049,"about_ca_system_score_gemma":0.00001098164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002898776,"about_ca_topic_score_gemma":0.0001632712,"domain_scores_codex":[0.9992036,0.00002738549,0.0002937353,0.0001639105,0.00009400159,0.0002173455],"domain_scores_gemma":[0.9996732,0.00003574763,0.00005030699,0.0001296793,0.00005376576,0.00005733788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006907489,0.00001249483,0.00001646439,0.00002564652,0.000009201775,4.065866e-7,0.00009028659,0.965666,0.002897903,0.00001190502,0.00001873932,0.03124405],"study_design_scores_gemma":[0.0003059741,0.00001256509,0.000207452,0.00003309077,0.00002393189,0.000008353965,0.0002376869,0.9967439,0.00110001,0.00001727487,0.001159226,0.0001505794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04320225,0.0001126035,0.9555553,0.0001223358,0.00009807597,0.0004930403,0.00001346499,0.000372586,0.00003035841],"genre_scores_gemma":[0.9981059,0.0007250301,0.0003057971,0.00002626453,0.00003698559,0.000405055,0.0003477172,0.00002327612,0.00002401746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9552495,"threshold_uncertainty_score":0.6884241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009612915311639457,"score_gpt":0.2286484081076755,"score_spread":0.219035492796036,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}