{"id":"W3170969450","doi":"10.1109/tpwrs.2021.3088376","title":"Real-Time Resilience Optimization Combining an AI Agent With Online Hard Optimization","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Power Systems","topic":"Infrastructure Resilience and Vulnerability Analysis","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Control reconfiguration; Resilience (materials science); Convergence (economics); Computer science; Interdependence; Fault (geology); Electric power system; Distributed computing; Node (physics); Optimization problem; Multi-agent system; Electricity; Reliability engineering; Mathematical optimization; Engineering; Power (physics); Artificial intelligence; Algorithm; Embedded system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001663175,0.0002358116,0.0003091735,0.0001817643,0.0002289425,0.0001708768,0.0001554123,0.0001388744,0.0003552157],"category_scores_gemma":[0.000004815905,0.000221882,0.00008240938,0.0007103774,0.00005115198,0.0005123652,9.310704e-7,0.0002630352,0.00002000998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001658781,"about_ca_system_score_gemma":0.00007722536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006763118,"about_ca_topic_score_gemma":0.00004443735,"domain_scores_codex":[0.9984171,0.0001372596,0.0003885874,0.0003838134,0.0003940902,0.0002791619],"domain_scores_gemma":[0.9989938,0.00004482059,0.00005631404,0.000528491,0.0002374505,0.0001391502],"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":[0.00002295746,0.0001065553,0.0000164583,0.00004330084,0.00008026232,0.00001422602,0.0002963363,0.9963425,0.002867543,0.00001104487,0.00005982013,0.0001389522],"study_design_scores_gemma":[0.0002982296,0.0001350132,0.00003769596,0.0001076639,0.00008037281,0.00004152352,0.0005899193,0.9932181,0.005169749,0.000001312698,0.00005770455,0.0002626811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02359986,0.00003590313,0.9745231,0.0000501474,0.0005855339,0.000194066,0.00005233474,0.0003570943,0.0006020163],"genre_scores_gemma":[0.9845054,0.0001097663,0.01474695,0.00004161177,0.00002092601,0.00003196308,0.00007838165,0.00004884322,0.0004161572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9609056,"threshold_uncertainty_score":0.9048085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007875328487512812,"score_gpt":0.2253656502985479,"score_spread":0.2174903218110351,"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."}}