{"id":"W4285081983","doi":"10.1016/j.epsr.2022.108353","title":"Constraint-guided Deep Neural Network for solving Optimal Power Flow","year":2022,"lang":"en","type":"article","venue":"Electric Power Systems Research","topic":"Power System Optimization and Stability","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Electric power system; Computer science; Artificial neural network; Mathematical optimization; Gauss–Seidel method; Power flow; AC power; Nonlinear system; Power (physics); Constraint (computer-aided design); Newton's method; Iterative method; Voltage; Control theory (sociology); Algorithm; Mathematics; Engineering; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004909017,0.0003023929,0.0005078555,0.00045761,0.0009895249,0.0002690603,0.0006934353,0.0001346298,0.0006935823],"category_scores_gemma":[0.0003400443,0.0003251565,0.0001913559,0.00181532,0.00006669738,0.0001773501,0.0001832048,0.0009599401,0.00003932261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008732599,"about_ca_system_score_gemma":0.0001977364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003921349,"about_ca_topic_score_gemma":0.00000732221,"domain_scores_codex":[0.995056,0.0006629028,0.0007799151,0.0005688302,0.001203814,0.001728517],"domain_scores_gemma":[0.9978188,0.0007105329,0.00007164477,0.0006607461,0.0004376021,0.0003006872],"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":[0.00005498404,0.00004974051,0.0002451853,0.0001178595,0.0001030915,0.00002411436,0.0006615457,0.9301608,0.0005308559,0.0009484621,0.0667074,0.0003960097],"study_design_scores_gemma":[0.0006338946,0.0003419849,0.0000886886,0.00001413603,0.000006616382,0.0001350326,0.0006040822,0.9440353,0.00005123913,0.00002235884,0.05373159,0.0003351032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06515776,0.01978382,0.8525012,0.0003301478,0.01183823,0.00776288,0.0002506373,0.00194155,0.04043374],"genre_scores_gemma":[0.9966872,0.0000110867,0.0009080931,0.00002919312,0.0001197992,0.001148872,0.00004173447,0.0001052377,0.0009487469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9315295,"threshold_uncertainty_score":0.9999201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03620467050488645,"score_gpt":0.2981233352004761,"score_spread":0.2619186646955897,"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."}}