{"id":"W4254335427","doi":"10.32920/ryerson.14649609.v1","title":"Deep Reinforcement Learning based Active Queue Management for IoT Networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Ontario Stroke Network","funders":"","keywords":"Active queue management; Computer science; Computer network; Reinforcement learning; Queueing theory; Network congestion; Edge computing; Edge device; Queuing delay; Network traffic control; Queue; Q-learning; Throughput; Queue management system; Enhanced Data Rates for GSM Evolution; Distributed computing; Network packet; Wireless; Telecommunications; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004258784,0.000454604,0.0004765044,0.0001567223,0.0002549587,0.0006383047,0.001305111,0.000337332,0.0001327421],"category_scores_gemma":[0.00003445143,0.0004424714,0.0003756098,0.0003159473,0.00002621451,0.000111312,0.00234183,0.0007575164,0.000009006011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002248952,"about_ca_system_score_gemma":0.0001618505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007041894,"about_ca_topic_score_gemma":0.00004912169,"domain_scores_codex":[0.9971596,0.0001026538,0.0004740362,0.001179883,0.0004112261,0.0006726125],"domain_scores_gemma":[0.9978056,0.0003405363,0.0003006492,0.001176749,0.0002170587,0.0001594062],"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":[0.00002124301,0.00003561257,0.000031991,0.0001163742,0.0001605434,0.00002201557,0.0001191257,0.91775,2.863396e-7,0.01059414,0.001404776,0.06974389],"study_design_scores_gemma":[0.0005714768,0.00008801501,0.0001857503,0.0002386012,0.00005240806,0.00000135862,0.00008426078,0.9906339,0.00006204248,0.0008535979,0.006707196,0.0005214071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005835172,0.0003719371,0.991127,0.0006794249,0.001404605,0.0011134,3.536246e-7,0.0005449723,0.004699966],"genre_scores_gemma":[0.3712164,0.0003173596,0.6166428,0.004256774,0.0006704947,0.001464908,0.0003725347,0.0000899068,0.004968812],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3744842,"threshold_uncertainty_score":0.9998027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.016798799361134,"score_gpt":0.2444783955073817,"score_spread":0.2276795961462477,"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."}}