{"id":"W4221020555","doi":"10.1016/j.apenergy.2022.118861","title":"Real-time out-of-step prediction control to prevent emerging blackouts in power systems: A reinforcement learning approach","year":2022,"lang":"en","type":"article","venue":"Applied Energy","topic":"Power System Optimization and Stability","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Blackout; Reinforcement learning; Electric power system; Process (computing); Markov decision process; Computer science; Partially observable Markov decision process; Power (physics); Artificial intelligence; Control (management); Markov process; Machine learning; Reliability engineering; Engineering; Control engineering; Markov chain; Markov model","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":[0.0004893816,0.0001652336,0.0003196037,0.0001853891,0.00007412914,0.00001619157,0.0001465381,0.00005193034,0.0001786641],"category_scores_gemma":[0.00001155716,0.0001875282,0.00005017981,0.000304786,0.000009268883,0.00004322051,0.00007092134,0.0001367204,0.000008650434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003390619,"about_ca_system_score_gemma":0.00002625939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001164469,"about_ca_topic_score_gemma":0.000004952133,"domain_scores_codex":[0.9984779,0.0001024351,0.0005679459,0.0002515686,0.0003284972,0.0002715986],"domain_scores_gemma":[0.9994937,0.00003074278,0.00008381592,0.000264895,0.00002540703,0.000101427],"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":[0.00003941429,0.00005949465,0.0000637086,0.00006226253,0.00004506012,7.996011e-7,0.001538328,0.992802,0.002555591,0.002274194,0.0004640643,0.0000951391],"study_design_scores_gemma":[0.0006653082,0.00007826292,0.0000777271,0.00001724093,0.00001193993,0.000001252321,0.0009880194,0.9807988,0.0001504974,0.00000398476,0.01701585,0.0001910851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02203094,0.00008822747,0.8060544,0.00001767624,0.0007756231,0.0009778752,0.00002265234,0.0005262463,0.1695064],"genre_scores_gemma":[0.997896,0.000009334297,0.0003314758,0.0000166692,0.0000142542,0.0007605409,0.00005856903,0.00003669152,0.0008764361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9758651,"threshold_uncertainty_score":0.7647178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005499356965380159,"score_gpt":0.191124445418849,"score_spread":0.1856250884534689,"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."}}