{"id":"W3098810376","doi":"10.1109/tvt.2020.3038918","title":"Preemptive SDN Load Balancing With Machine Learning for Delay Sensitive Applications","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Autoregressive integrated moving average; Scalability; Benchmark (surveying); Forwarding plane; Latency (audio); Distributed computing; Schedule; Load balancing (electrical power); Grid; Time series; Machine learning; Computer network","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":[0.00009619574,0.0002062118,0.0002422336,0.0001531098,0.0003744676,0.00004073009,0.000398601,0.0002079143,0.000004343641],"category_scores_gemma":[0.00001245749,0.0001857817,0.00009298642,0.0010133,0.00009888861,0.0001386291,0.000006859164,0.000573779,0.00003803245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007994392,"about_ca_system_score_gemma":0.0000847674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001495216,"about_ca_topic_score_gemma":0.00003886811,"domain_scores_codex":[0.9986712,0.00003535696,0.0001856998,0.0005905066,0.0001856262,0.0003315832],"domain_scores_gemma":[0.9990878,0.0001585951,0.00008961984,0.0003710914,0.0002002603,0.00009266603],"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":[0.0002797026,0.0003667467,0.0003322058,0.00008116744,0.0005439145,0.0001264089,0.001486972,0.6507447,0.007896888,0.01237198,0.0001774959,0.3255918],"study_design_scores_gemma":[0.001645301,0.001662604,0.00003796457,0.00006218773,0.0001117481,0.0001940924,0.0001687796,0.9119496,0.06435888,0.0009412908,0.01828698,0.0005805222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003683282,0.0001306435,0.9898599,0.004294811,0.00006075995,0.0006778288,0.00001373893,0.00122531,0.00005375663],"genre_scores_gemma":[0.935688,0.0000296474,0.06309598,0.0005796101,0.00003565693,0.000490738,0.000004274223,0.00002720067,0.00004885559],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9320047,"threshold_uncertainty_score":0.7575957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009302616735514888,"score_gpt":0.2107770817193736,"score_spread":0.2014744649838587,"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."}}