{"id":"W4312320165","doi":"10.1109/tii.2022.3213603","title":"Energy-Efficient Collaborative Multi-Access Edge Computing via Deep Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Carleton University","funders":"Natural Science Foundation of Hunan Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Reinforcement learning; Server; Resource allocation; Computation offloading; Edge computing; Benchmark (surveying); Optimization problem; Mobile edge computing; Mathematical optimization; Distributed computing; Resource management (computing); Energy consumption; Enhanced Data Rates for GSM Evolution; Computer network; Artificial intelligence; Algorithm; Engineering","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":[0.0007731001,0.0006990014,0.001053061,0.000245589,0.0003929274,0.0007340861,0.001197942,0.0007461626,0.00120026],"category_scores_gemma":[0.001986843,0.0003479331,0.0003760474,0.0003563929,0.0005847917,0.001033917,0.001129072,0.001259663,0.0001666415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008317842,"about_ca_system_score_gemma":0.001193715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006729667,"about_ca_topic_score_gemma":0.008006224,"domain_scores_codex":[0.9996096,0.00009109789,0.00001672035,0.00009424797,0.00008218564,0.0001061589],"domain_scores_gemma":[0.9993106,0.0003790185,0.00006926062,0.00004888864,0.0001277493,0.00006457302],"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":[0.00008010762,0.00009283372,0.0007060835,0.00003929347,0.00002527988,0.00005011998,0.00003265864,0.9571395,0.001347462,0.002950569,0.000925976,0.03661019],"study_design_scores_gemma":[0.000003530241,0.000007630113,0.00002565471,0.000001057301,0.000001430228,0.000002856965,0.000002345374,0.9990557,0.0000969974,0.0007509051,0.00005095231,0.000001021273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05799344,0.0004909915,0.9368858,0.0003654077,0.00006289712,0.00004459814,0.00004088807,0.0004476426,0.003668458],"genre_scores_gemma":[0.9483839,0.0001169409,0.04965305,0.0001654954,0.00002244777,0.00005424178,0.00006065662,0.00003396217,0.001509277],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006729667,"threshold_uncertainty_score":0.013381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0474218169520934,"score_gpt":0.2750138922607855,"score_spread":0.2275920753086921,"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."}}