{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002428866,0.0007257243,0.001208035,0.0006899409,0.0005454824,0.001177829,0.001755411,0.001210139,0.002306006],"category_scores_gemma":[0.005690896,0.0005389824,0.0005078698,0.0009866816,0.001018924,0.001751507,0.001190447,0.001315965,0.0001893645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002315918,"about_ca_system_score_gemma":0.002270537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01726681,"about_ca_topic_score_gemma":0.01507204,"domain_scores_codex":[0.9993564,0.0002815065,0.00002469173,0.0001119791,0.0001007037,0.000124703],"domain_scores_gemma":[0.9970526,0.002081188,0.0001562051,0.0001268208,0.0004613917,0.0001218044],"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":[0.00005646799,0.00003441432,0.0004518182,0.00002230005,0.00001671979,0.0000146263,0.00001664019,0.9728643,0.0002261079,0.01136381,0.000835071,0.01409786],"study_design_scores_gemma":[0.000001491088,0.000003183734,0.00001733693,8.385186e-7,0.000001096634,8.871501e-7,0.00000141179,0.9972759,0.00002994733,0.002633787,0.00003350269,6.61593e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05801405,0.0006394793,0.9375634,0.0009319582,0.0001235556,0.00004324992,0.0001323557,0.00033897,0.002213096],"genre_scores_gemma":[0.8946687,0.0004083168,0.0997638,0.0002866092,0.00009679727,0.00008114229,0.0002212867,0.00008701753,0.00438636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01726681,"threshold_uncertainty_score":0.03433263,"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."}}