{"id":"W4298201932","doi":"10.48550/arxiv.2110.00492","title":"Dynamic CU-DU Selection for Resource Allocation in O-RAN Using\\n Actor-Critic Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ciena (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Resource allocation; C-RAN; Function (biology); Distributed computing; Latency (audio); Resource (disambiguation); Computer network; Radio access network; Artificial intelligence; Telecommunications; Base station","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001616113,0.0009245503,0.001165403,0.0004810725,0.0004257805,0.0009288821,0.001115192,0.00111095,0.001842302],"category_scores_gemma":[0.00417231,0.0004286365,0.0003561043,0.0003374667,0.001272472,0.0008139675,0.0009088195,0.00138184,0.000287532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001214495,"about_ca_system_score_gemma":0.00147221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00802194,"about_ca_topic_score_gemma":0.007901402,"domain_scores_codex":[0.9995273,0.0001781438,0.00001934031,0.0001008947,0.00007709764,0.00009722586],"domain_scores_gemma":[0.9982547,0.001168376,0.0001594175,0.00006903979,0.000225541,0.0001228594],"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":[0.00007965865,0.00003903719,0.0004177341,0.00001914415,0.00002074456,0.00004344713,0.00002585055,0.9826285,0.0005511275,0.003721669,0.0005286908,0.01192439],"study_design_scores_gemma":[0.000004091125,0.000006162921,0.0000199732,0.000001520103,0.000001476077,0.000002212193,0.000001784437,0.9992355,0.00007205766,0.0005996724,0.00005440017,0.000001107631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04185258,0.000357098,0.9513384,0.000520068,0.00008871609,0.00006259113,0.0000281764,0.0004363537,0.005316089],"genre_scores_gemma":[0.9489952,0.0001222116,0.04696668,0.0001827503,0.00003766151,0.00009358946,0.00004059431,0.00005575248,0.003505521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00802194,"threshold_uncertainty_score":0.0159505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04966036022474589,"score_gpt":0.1989771095473425,"score_spread":0.1493167493225966,"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."}}