{"id":"W3195830083","doi":"10.1016/j.jnca.2021.103181","title":"Deep Q-Network and Traffic Prediction based Routing Optimization in Software Defined Networks","year":2021,"lang":"en","type":"article","venue":"Journal of Network and Computer Applications","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; École de Technologie Supérieure","funders":"Fonds Unique Interministériel","keywords":"Computer science; Emulation; Quality of service; Software-defined networking; Reinforcement learning; Network traffic control; Computer network; Heuristic; Packet loss; Flexibility (engineering); Network performance; Distributed computing; Routing (electronic design automation); Traffic engineering; Network congestion; Network packet; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005541252,0.0001963406,0.0003463379,0.00009520913,0.0002979315,0.0002811646,0.0002982217,0.0001436705,0.000004468697],"category_scores_gemma":[0.00001587373,0.0001936351,0.00008592511,0.001111388,0.00004243076,0.0003224218,0.0001722264,0.000368424,5.234389e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004387437,"about_ca_system_score_gemma":0.0001040993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001362411,"about_ca_topic_score_gemma":0.00001378697,"domain_scores_codex":[0.9982105,0.0001444748,0.0006821671,0.0003715281,0.0002124044,0.0003789421],"domain_scores_gemma":[0.9983872,0.0005162718,0.0003751384,0.0003059664,0.0002410079,0.000174414],"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":[0.000009603125,0.00005577099,0.008091707,0.000008816888,0.00002138563,0.0000137201,0.00005510231,0.8827717,2.346916e-7,0.001885622,0.0009928757,0.1060935],"study_design_scores_gemma":[0.0007028367,0.00008808077,0.01394949,0.0001430209,0.00003074175,0.0001931151,0.000006979868,0.9820676,4.397046e-7,0.001213901,0.001438415,0.0001654128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001746804,0.004805771,0.9923341,0.0004427484,0.00037279,0.0001907936,8.222077e-7,0.00008524304,0.0000209606],"genre_scores_gemma":[0.2774285,0.0009582869,0.7187952,0.0008073846,0.001929182,0.00003299987,0.00002070496,0.0000210926,0.000006585815],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2756817,"threshold_uncertainty_score":0.7896212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008357360873976056,"score_gpt":0.2066400596587064,"score_spread":0.1982826987847303,"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."}}