{"id":"W2915629347","doi":"10.1109/tpwrs.2018.2872822","title":"Very Short-Term Wind Power Prediction Interval Framework via Bi-Level Optimization and Novel Convex Cost Function","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Power Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematical optimization; Benchmark (surveying); Prediction interval; Term (time); Electric power system; Interval (graph theory); Computer science; Minification; Wind power; Convex optimization; Differentiable function; Hyperparameter; Function (biology); Operator (biology); Power (physics); Engineering; Mathematics; Regular polygon; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001091644,0.001048057,0.001030867,0.0003213575,0.0002509032,0.001325806,0.001457019,0.0009703896,0.002118386],"category_scores_gemma":[0.001694131,0.0004967639,0.0006898814,0.0005560573,0.0004763235,0.001407759,0.00109078,0.001857561,0.0004898044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006487772,"about_ca_system_score_gemma":0.001195216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005814927,"about_ca_topic_score_gemma":0.003893655,"domain_scores_codex":[0.9995276,0.0001536058,0.00002460793,0.0000798871,0.0001593935,0.00005488383],"domain_scores_gemma":[0.9994628,0.0002554998,0.00006529555,0.00005186568,0.0001280073,0.00003660045],"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":[0.00002771211,0.00002884925,0.0002407843,0.00004207978,0.00002209596,0.00003185923,0.00001671849,0.9746946,0.0008196567,0.008288723,0.0007633061,0.01502365],"study_design_scores_gemma":[8.794687e-7,0.000004991866,0.00001580302,9.492381e-7,0.000001131272,0.000001162068,6.687762e-7,0.999387,0.00005399557,0.0004670674,0.0000653668,0.000001006611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006920074,0.0002395663,0.9905638,0.000146631,0.00002465204,0.00002057735,0.00006235252,0.0001991989,0.001823212],"genre_scores_gemma":[0.7377606,0.0006828227,0.2550089,0.0001737676,0.0001097658,0.0003035846,0.0005482123,0.0002332321,0.005179082],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005814927,"threshold_uncertainty_score":0.01156217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01623981703473089,"score_gpt":0.2075407497859328,"score_spread":0.1913009327512019,"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."}}