{"id":"W2888896501","doi":"10.1109/tsc.2018.2867482","title":"A Double Deep Q-Learning Model for Energy-Efficient Edge Scheduling","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Services Computing","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"National Science Foundation of Sri Lanka","keywords":"Computer science; Sigmoid function; Edge device; Energy consumption; Frequency scaling; Deep learning; Efficient energy use; Scheduling (production processes); Energy (signal processing); Algorithm; Artificial intelligence; Mathematical optimization; Artificial neural network; Mathematics; Electrical engineering","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":[0.0004653705,0.0007547447,0.0006113362,0.0002462664,0.0002815191,0.0005991342,0.001499899,0.0007645448,0.003114281],"category_scores_gemma":[0.001102915,0.0003480068,0.0004589359,0.0003593618,0.0004513679,0.001071541,0.0006802826,0.001349648,0.0004985888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008687493,"about_ca_system_score_gemma":0.001128406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009441471,"about_ca_topic_score_gemma":0.01223459,"domain_scores_codex":[0.9997912,0.00003026497,0.00001157488,0.00007398584,0.00004156151,0.00005138871],"domain_scores_gemma":[0.9997272,0.00008944725,0.00002453703,0.00002441244,0.0001158639,0.00001856593],"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":[0.00009475432,0.00007999656,0.001040737,0.00005656696,0.00002710992,0.0000572759,0.00004354475,0.9052005,0.003131887,0.00495263,0.002603549,0.08271138],"study_design_scores_gemma":[0.000002772973,0.00001101524,0.00004446423,0.000002153407,0.000002877799,0.000003984545,0.000002102591,0.9985239,0.0003545813,0.000831948,0.0002186662,0.000001543142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03871896,0.0005528194,0.954625,0.0004934733,0.00009959488,0.00005435156,0.0001924809,0.001124996,0.004138412],"genre_scores_gemma":[0.8896839,0.0003903918,0.1004903,0.0004868428,0.00004527574,0.0001919587,0.0004927243,0.0001060933,0.008112526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009441471,"threshold_uncertainty_score":0.01877302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02310774106076888,"score_gpt":0.2503590141494647,"score_spread":0.2272512730886958,"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."}}