{"id":"W4226019773","doi":"10.1109/jiot.2022.3205051","title":"Reinforcement Learning Framework for Server Placement and Workload Allocation in Multiaccess Edge Computing","year":2022,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Server; Computer science; Reinforcement learning; Edge computing; Markov decision process; Distributed computing; Cloud computing; Enhanced Data Rates for GSM Evolution; Optimization problem; Computer network; Markov process; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001792716,0.0001341554,0.000207838,0.0002308135,0.0002830131,0.0002481477,0.000759696,0.000044114,0.000008061476],"category_scores_gemma":[0.00009985994,0.000139533,0.00007701537,0.0002094309,0.00002100967,0.0004809444,0.0005986673,0.0007842256,0.00000100302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001954452,"about_ca_system_score_gemma":0.00005121039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000051176,"about_ca_topic_score_gemma":5.838216e-7,"domain_scores_codex":[0.9983816,0.0001150008,0.0005711074,0.0002439437,0.000371578,0.0003167897],"domain_scores_gemma":[0.9988975,0.0002738664,0.000525774,0.000133486,0.0001002938,0.00006909432],"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":[0.0002980004,0.0002505302,0.01775234,0.000234419,0.0001828305,0.00004797611,0.1047009,0.6872685,0.001386199,0.004097261,0.003783863,0.1799972],"study_design_scores_gemma":[0.0008200806,0.0003296772,0.0006513791,0.000478088,0.000007423889,0.00009304688,0.0004248199,0.9921638,0.001841184,0.001717535,0.001280252,0.0001927508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.338943,0.0001556842,0.6562582,0.0002395919,0.004190587,0.0001241034,2.002502e-8,0.00002221227,0.0000666044],"genre_scores_gemma":[0.9457069,0.00000962637,0.05340092,0.0002981052,0.0004370881,0.000006467185,7.572451e-7,0.00001059814,0.0001295425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6067639,"threshold_uncertainty_score":0.5689992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02349005077857558,"score_gpt":0.2855333825615915,"score_spread":0.2620433317830159,"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."}}