{"id":"W3189204686","doi":"10.1109/icc42927.2021.9500463","title":"Structure-aware reinforcement learning for node-overload protection in mobile edge computing","year":2021,"lang":"en","type":"article","venue":"","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); McGill University","funders":"Mitacs","keywords":"Reinforcement learning; Computer science; Edge computing; Latency (audio); Distributed computing; Enhanced Data Rates for GSM Evolution; Mobile edge computing; Node (physics); Server; Computer network; Admission control; Artificial intelligence; Quality of service; Engineering; Telecommunications","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":[0.0002775224,0.0001524165,0.0001876543,0.0001073115,0.0002732766,0.0002100544,0.0003014378,0.00007891017,0.00001083768],"category_scores_gemma":[0.0000655469,0.0001517114,0.00007299428,0.0004753959,0.00001149871,0.0002782653,0.0003716052,0.0002580089,0.00001065278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001223867,"about_ca_system_score_gemma":0.0001112306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000551641,"about_ca_topic_score_gemma":0.00001292649,"domain_scores_codex":[0.9985537,0.0000594432,0.0003255005,0.0004513107,0.0001927928,0.0004172805],"domain_scores_gemma":[0.9993286,0.00008597098,0.0001031408,0.0002737481,0.0001538594,0.00005464174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002091498,0.00007461139,0.002634978,0.0002564767,0.00003451828,0.00003205497,0.004338533,0.4495638,0.01044182,0.002531763,0.001860121,0.5282104],"study_design_scores_gemma":[0.0005580588,0.00009559834,0.000677555,0.00006570318,0.000002340895,0.00001865944,0.0001064061,0.9685853,0.01780895,0.0003825256,0.01147473,0.0002241942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06509166,0.00006546614,0.9297644,0.0001282579,0.00328556,0.0004489339,6.942869e-8,0.0001993008,0.001016329],"genre_scores_gemma":[0.9710339,0.000002241171,0.02721408,0.0001970329,0.0007627666,0.00002476063,0.00001045957,0.00001268986,0.0007420563],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9059423,"threshold_uncertainty_score":0.6186611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01708083754356533,"score_gpt":0.2508311499529023,"score_spread":0.233750312409337,"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."}}