{"id":"W4396796403","doi":"10.2139/ssrn.4819143","title":"A Generalised Deep Reinforcement Learning Model for Distribution Network Reconfiguration with Powerflow-Based Action Space Sampling","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Optimal Power Flow Distribution","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Control reconfiguration; Reinforcement learning; Space (punctuation); Computer science; Action (physics); Sampling (signal processing); Distribution (mathematics); Artificial intelligence; Mathematics; Telecommunications; Physics; Embedded system; Mathematical analysis","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001332302,0.0005316912,0.0004027451,0.0001375608,0.00032952,0.0003701402,0.000216257,0.0004226397,0.0000124757],"category_scores_gemma":[0.00004967672,0.000533301,0.0002884457,0.0002231945,0.00002392364,0.0001867419,0.00005783593,0.005041147,0.00001171264],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006655326,"about_ca_system_score_gemma":0.001784549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000175744,"about_ca_topic_score_gemma":0.0003483433,"domain_scores_codex":[0.9962408,0.00005583902,0.0005996346,0.0004573214,0.000386162,0.00226027],"domain_scores_gemma":[0.9990165,0.00004526382,0.0002869235,0.0002592808,0.0002662822,0.0001257733],"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":[0.0002693932,0.00001217402,0.000009516816,0.0002207148,0.0003581399,0.000001095819,0.00005656794,0.9888253,0.0005894981,0.005997695,0.0002971416,0.003362749],"study_design_scores_gemma":[0.000723367,0.000334641,0.000006171917,0.0003629567,0.0003147403,0.00004206334,0.000103731,0.9699559,0.0003858129,0.02662954,0.0005877253,0.0005533249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0323743,0.002215659,0.9626631,0.00029227,0.001068428,0.0007809066,0.00004475197,0.0004567316,0.0001038418],"genre_scores_gemma":[0.9898168,0.001321727,0.003392661,0.00001462647,0.001048317,0.0001756232,0.003833981,0.0001472974,0.0002489633],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9592704,"threshold_uncertainty_score":0.9997119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768170334723483,"score_gpt":0.2517405206785217,"score_spread":0.2340588173312869,"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."}}