{"id":"W3114334817","doi":"10.1109/tetci.2020.3044082","title":"Resource Offload Consolidation Based on Deep-Reinforcement Learning Approach in Cyber-Physical Systems","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"Deakin University","keywords":"Computer science; Reinforcement learning; Cloud computing; Server; Edge computing; Leverage (statistics); Cyber-physical system; Distributed computing; Workload; Latency (audio); Edge device; Computation; Real-time computing; Artificial intelligence; Computer network; Operating system; Telecommunications; Algorithm","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":[0.0003032477,0.0002199087,0.0002396127,0.000348846,0.0001961188,0.0001350994,0.0005126201,0.00007504867,0.000003642117],"category_scores_gemma":[0.00002623658,0.0002446338,0.00008682891,0.0009650902,0.00004712756,0.0002114525,0.00001037507,0.0006691378,0.00003913017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001884759,"about_ca_system_score_gemma":0.0000869171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004103179,"about_ca_topic_score_gemma":0.000001636268,"domain_scores_codex":[0.9978727,0.0001943741,0.0005146652,0.0005533393,0.0005398235,0.0003251009],"domain_scores_gemma":[0.999015,0.0004714555,0.0001184014,0.0002100732,0.0000838697,0.0001011464],"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":[0.00002274934,0.0001496603,0.00004975759,0.00003413513,0.000007639514,0.000007860257,0.002207924,0.9725712,0.000009234551,0.004224733,0.00002466657,0.02069044],"study_design_scores_gemma":[0.0002105405,0.0001631975,0.0000860105,0.00009597289,0.000003575553,0.000002273168,0.0001117331,0.9976369,0.0005033219,0.0004652852,0.0004873526,0.0002338228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006037554,0.00001289846,0.9896079,0.001257465,0.001183927,0.0002694027,2.549189e-7,0.0001392634,0.001491318],"genre_scores_gemma":[0.9877793,0.000002545281,0.01127154,0.0005394597,0.0003166465,0.00003411523,0.000008385524,0.00001364884,0.0000343316],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9817418,"threshold_uncertainty_score":0.9975876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0404690837579467,"score_gpt":0.2857800640484248,"score_spread":0.2453109802904781,"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."}}