{"id":"W4387883701","doi":"10.1109/icc45041.2023.10278981","title":"Intelligent O-RAN Traffic Steering for URLLC Through Deep Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Ran; Queueing theory; Reinforcement learning; Computer network; C-RAN; Artificial intelligence; Low latency (capital markets); Intelligent Network; Deep learning; Distributed computing; Real-time computing; Radio access network; 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":[0.000744689,0.0006698208,0.0005176816,0.0003128636,0.0003172855,0.0005573722,0.001004122,0.0005793609,0.00138642],"category_scores_gemma":[0.001622343,0.0001978113,0.0002394792,0.0002253951,0.000468569,0.0007219504,0.0006281566,0.001039639,0.0003893221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007838865,"about_ca_system_score_gemma":0.001330549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008263114,"about_ca_topic_score_gemma":0.009402703,"domain_scores_codex":[0.9997036,0.00006218973,0.00001184395,0.00006840218,0.00006640523,0.00008757552],"domain_scores_gemma":[0.9994443,0.0001797269,0.00008899876,0.0000541916,0.0001693183,0.00006349376],"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":[0.000265033,0.0003940942,0.002995277,0.00004391921,0.00003645482,0.00007574085,0.00005530902,0.806685,0.01485267,0.002571624,0.002904295,0.1691206],"study_design_scores_gemma":[0.000004571524,0.00002355906,0.00006745076,0.000001200832,0.000002322937,0.000003264828,0.00000347972,0.9985286,0.0009490919,0.000304503,0.0001096442,0.000002376385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1628255,0.0002290891,0.82635,0.0004099498,0.00008220864,0.00009833438,0.00005890716,0.004859276,0.005086742],"genre_scores_gemma":[0.9537321,0.00004176974,0.04400313,0.0001291349,0.00001948654,0.0000414588,0.0000726592,0.00005418986,0.001906152],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008263114,"threshold_uncertainty_score":0.01643002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03780339781618514,"score_gpt":0.2707132354695981,"score_spread":0.2329098376534129,"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."}}