{"id":"W3109963969","doi":"10.1515/auto-2020-0072","title":"Artificial intelligence and optimization: a way to speed up the security constraint optimal power flow","year":2020,"lang":"en","type":"article","venue":"at - Automatisierungstechnik","topic":"Power System Optimization and Stability","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Mathematical optimization; Constraint (computer-aided design); Computer science; Power flow; Electric power system; Power (physics); Artificial neural network; Optimization problem; Flow (mathematics); Mathematics; Artificial intelligence","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":[0.0003023185,0.0002626518,0.0002992857,0.00005600124,0.0001790191,0.0001375477,0.0002879308,0.0001379089,0.0007656727],"category_scores_gemma":[0.0001721385,0.000222119,0.00006875624,0.0004975609,0.000130253,0.0001508079,0.0001764435,0.0002049709,0.0001139679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009802153,"about_ca_system_score_gemma":0.00002259281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005483514,"about_ca_topic_score_gemma":0.00001072584,"domain_scores_codex":[0.9984406,0.00006432232,0.0005337315,0.0003614593,0.000276679,0.0003232163],"domain_scores_gemma":[0.9991159,0.00009953507,0.00005431343,0.0003718965,0.00007557571,0.0002827577],"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":[0.00002562853,0.00001650557,0.00004766858,0.00007849312,0.00004279189,0.00001028576,0.007567972,0.9812622,0.0003870998,0.001941604,0.004112242,0.004507483],"study_design_scores_gemma":[0.00006716303,0.00006566397,0.0001146245,0.00002594467,0.0000153589,0.00003260027,0.0005119048,0.9935184,0.002908591,0.00007610165,0.002387385,0.0002762304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02701957,0.0002171794,0.9637212,0.002943099,0.0005212094,0.001010069,0.00009711943,0.001546973,0.002923625],"genre_scores_gemma":[0.9685536,0.00002339812,0.0308589,0.0004234317,0.00003552907,0.00003083223,0.00001340852,0.00003791552,0.00002296837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.941534,"threshold_uncertainty_score":0.9057751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0179133342329395,"score_gpt":0.2296009385013358,"score_spread":0.2116876042683963,"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."}}