{"id":"W2964098968","doi":"10.1109/tvt.2018.2890685","title":"Learning-Based Computation Offloading for IoT Devices With Energy Harvesting","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Energy Harvesting in Wireless Networks","field":"Engineering","cited_by":545,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National Mobile Communications Research Laboratory, Southeast University; National Natural Science Foundation of China","keywords":"Computation offloading; Computer science; Energy consumption; Mobile edge computing; Edge computing; Mobile device; Wireless; Edge device; Reinforcement learning; Computation; Latency (audio); Energy harvesting; Real-time computing; Server; Computer network; Internet of Things; Energy (signal processing); Embedded system; Cloud computing; Artificial intelligence; Engineering; Electrical engineering; Telecommunications","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":[0.0002830278,0.0005944434,0.0005299084,0.0001664493,0.0003579982,0.0004361914,0.0008819679,0.0003201102,0.001175752],"category_scores_gemma":[0.001139811,0.0001669714,0.0002721344,0.0002211299,0.0004532311,0.0007687137,0.000825401,0.0005682056,0.0002035942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003749232,"about_ca_system_score_gemma":0.0005624973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001667161,"about_ca_topic_score_gemma":0.002213132,"domain_scores_codex":[0.9997833,0.00003125675,0.00001203963,0.0000509674,0.00006334544,0.00005914002],"domain_scores_gemma":[0.9996781,0.000150481,0.0000380713,0.00005336427,0.00005252341,0.00002745321],"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":[0.0002694676,0.0002815093,0.001761551,0.0001302697,0.00002840292,0.0002294076,0.0001199531,0.8167731,0.0251172,0.006447244,0.001745507,0.1470963],"study_design_scores_gemma":[0.000005896064,0.00003204881,0.0001267221,0.000003535222,0.000003618615,0.00001918261,0.000009942481,0.9963331,0.00173043,0.001463557,0.0002685442,0.000003354462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08376759,0.0004324875,0.9084134,0.0002097243,0.00008121356,0.00007700344,0.00002924449,0.0007405105,0.006248823],"genre_scores_gemma":[0.9786862,0.0001046985,0.0198194,0.00007617886,0.00001585887,0.00004131185,0.00002373827,0.00002593366,0.0012067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001667161,"threshold_uncertainty_score":0.003933311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005511984357834534,"score_gpt":0.1938710994734164,"score_spread":0.1883591151155818,"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."}}