{"id":"W4405599777","doi":"10.1109/access.2024.3520357","title":"Safe Deep Reinforcement Learning-Based Real-Time Multi-Energy Management in Combined Heat and Power Microgrids","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; SaskPower","keywords":"Reinforcement learning; Computer science; Energy management; Power (physics); Energy (signal processing); Power management; Reinforcement; Artificial intelligence; 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":[0.0007162925,0.0005577969,0.000566749,0.0001678317,0.0002326955,0.0004833694,0.0007063497,0.0004867472,0.0009679751],"category_scores_gemma":[0.001116504,0.0002955116,0.0002752146,0.0001550819,0.0005551613,0.0006439185,0.0007153446,0.0009556299,0.0001429006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008128823,"about_ca_system_score_gemma":0.001210441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008933115,"about_ca_topic_score_gemma":0.007258697,"domain_scores_codex":[0.9997986,0.00006223723,0.000008342732,0.00004260419,0.00004611473,0.0000421534],"domain_scores_gemma":[0.9997085,0.0001336752,0.00004567518,0.00002462028,0.00005954543,0.00002795612],"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":[0.00003731424,0.00002619242,0.0003003461,0.00001845192,0.00001128537,0.00003645131,0.00002096247,0.9774061,0.0007615037,0.002239153,0.0002957272,0.0188465],"study_design_scores_gemma":[0.00000220768,0.000006329067,0.00002383265,9.961649e-7,0.000001064167,0.000001730417,0.000001195329,0.9992099,0.000144487,0.0005476897,0.00005968631,7.8298e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06974331,0.0005087234,0.9247595,0.0003459116,0.00005178325,0.00003970628,0.00004164688,0.0009088109,0.003600545],"genre_scores_gemma":[0.9757106,0.00009385732,0.02272702,0.00007034872,0.000009007729,0.00003621709,0.00003322357,0.00002551675,0.001294067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008933115,"threshold_uncertainty_score":0.01776224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008669508604361359,"score_gpt":0.236029509902652,"score_spread":0.2273600012982906,"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."}}