{"id":"W4383340036","doi":"10.1016/j.apenergy.2023.121490","title":"A safe reinforcement learning-based charging strategy for electric vehicles in residential microgrid","year":2023,"lang":"en","type":"article","venue":"Applied Energy","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Microgrid; Markov decision process; Reinforcement learning; Curse of dimensionality; Scheduling (production processes); Computer science; Economic dispatch; Mathematical optimization; Electric power system; Engineering; Markov process; Power (physics); Control (management); Artificial intelligence; Operations management","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":[0.0001251634,0.0001839484,0.0001927243,0.0003300131,0.00008296307,0.00004342937,0.0001451219,0.0001217214,0.00003470607],"category_scores_gemma":[0.000006416223,0.0001976858,0.00006047219,0.0008226076,0.000009721374,0.0000437767,0.00001713843,0.0001961952,0.00001818026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00010225,"about_ca_system_score_gemma":0.00004089088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000850155,"about_ca_topic_score_gemma":0.00005348681,"domain_scores_codex":[0.9988058,0.000009819062,0.0002717704,0.0002168126,0.0001417418,0.0005540085],"domain_scores_gemma":[0.9996939,0.00006255278,0.00003722883,0.0001318787,0.00001739855,0.00005706158],"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":[0.00003249076,0.000004713113,0.00002574677,0.0000402316,0.000019027,0.000004165629,0.00002899272,0.8539372,0.1092,0.003730322,0.002760329,0.03021676],"study_design_scores_gemma":[0.001066168,0.0001007146,0.0007036472,0.00001562193,0.00001117238,0.000001334496,0.00003553191,0.7763047,0.1921121,0.001211971,0.02813188,0.0003051789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9466252,0.001098908,0.03844533,0.0001915945,0.0003193523,0.0006842232,0.000006720664,0.00186464,0.01076397],"genre_scores_gemma":[0.9988982,0.0001742117,0.000120081,0.00007893916,0.0001765983,0.0001779566,0.0001059483,0.00005745984,0.0002106017],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08291207,"threshold_uncertainty_score":0.8061393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007103791065192421,"score_gpt":0.204633056845839,"score_spread":0.1975292657806466,"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."}}