{"id":"W3080073809","doi":"10.1109/tccn.2020.3018157","title":"Dynamic Resource Scaling for VNF Over Nonstationary Traffic: A Learning Approach","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive Communications and Networking","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Provisioning; Quality of service; Resource allocation; Scalability; Computer network; Software-defined networking; Markov decision process; Markov process; Traffic generation model; Distributed computing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000942449,0.0008640576,0.0009646611,0.0005667426,0.0003852206,0.0006972124,0.00135203,0.001114232,0.001166602],"category_scores_gemma":[0.003190889,0.0004469531,0.0005264184,0.000624088,0.0007705127,0.001090011,0.0008892387,0.001588129,0.0001996408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001001127,"about_ca_system_score_gemma":0.001319902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007535289,"about_ca_topic_score_gemma":0.00583008,"domain_scores_codex":[0.9996781,0.00007163793,0.0000177898,0.0001002563,0.00006510813,0.00006711847],"domain_scores_gemma":[0.9988579,0.000698788,0.0001268203,0.00005580936,0.0001990289,0.00006173187],"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":[0.00003278773,0.00006014213,0.0007276459,0.00003046506,0.00002064391,0.00004068865,0.00003396854,0.9501237,0.0008623153,0.003740891,0.0005527266,0.04377416],"study_design_scores_gemma":[9.089162e-7,0.000005049364,0.00002512754,0.000001172702,0.000001291796,0.000002319443,0.000001486051,0.9992238,0.00006193047,0.0006329892,0.00004287537,0.000001028959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03640464,0.000440333,0.9609073,0.0004199812,0.00004110182,0.00003362137,0.00003997482,0.0003145676,0.001398544],"genre_scores_gemma":[0.9010738,0.0004528406,0.09478382,0.0002705332,0.0001203456,0.0001354172,0.0001450012,0.00006797555,0.002950275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007535289,"threshold_uncertainty_score":0.01498282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04431378056773156,"score_gpt":0.2776108599146176,"score_spread":0.2332970793468861,"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."}}