{"id":"W4312410281","doi":"10.1109/tnsm.2022.3221670","title":"Deep Reinforcement Learning-Based Joint User Association and CU–DU Placement in O-RAN","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Network and Service Management","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"C-RAN; Computer science; Radio access network; Cloud computing; Reinforcement learning; Markov decision process; Software deployment; Computer network; Ran; Cellular network; Distributed computing; Optimization problem; Base station; Markov process; Operating system; Artificial intelligence; Algorithm","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":[0.001505467,0.0008601541,0.001551491,0.0003233039,0.0005098478,0.0008223954,0.001708486,0.001275036,0.001865059],"category_scores_gemma":[0.003453958,0.0005522444,0.0004120085,0.0005044898,0.001102956,0.00135655,0.0013704,0.001592119,0.0002910602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001333346,"about_ca_system_score_gemma":0.002152751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01079189,"about_ca_topic_score_gemma":0.0125157,"domain_scores_codex":[0.9991069,0.0002902058,0.00003209776,0.0002013391,0.0001123782,0.0002570607],"domain_scores_gemma":[0.9978245,0.001321936,0.0002356004,0.0001131915,0.0002863862,0.0002182556],"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":[0.000187589,0.0001100153,0.001005184,0.00003256036,0.00002813691,0.00005858891,0.00004212293,0.9601378,0.0007798776,0.002929746,0.0009775982,0.03371073],"study_design_scores_gemma":[0.000008342578,0.00001964812,0.00004917404,0.000001546498,0.00000310373,0.00000631252,0.000005037443,0.9989232,0.000135793,0.0007745039,0.00007126818,0.000002038479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09185214,0.0005541228,0.902642,0.0005923255,0.0001114518,0.00008495205,0.00006500976,0.000633744,0.003464229],"genre_scores_gemma":[0.9578078,0.00009618369,0.03987628,0.0002042664,0.00003293713,0.00005060826,0.00005538186,0.00003209857,0.001844496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01079189,"threshold_uncertainty_score":0.02145815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0093893842766279,"score_gpt":0.1944271524326629,"score_spread":0.185037768156035,"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."}}