{"id":"W4310252819","doi":"10.1016/j.est.2022.106147","title":"Optimal dispatch of an energy hub with compressed air energy storage: A safe reinforcement learning approach","year":2022,"lang":"en","type":"article","venue":"Journal of Energy Storage","topic":"Microgrid Control and Optimization","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Compressed air energy storage; Reinforcement learning; Mathematical optimization; Computer science; Energy storage; Scheduling (production processes); Integer programming; Renewable energy; Engineering; Artificial intelligence; Algorithm; Mathematics","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":[0.000280468,0.0002709597,0.0005118019,0.0003181199,0.0001870807,0.00003343984,0.0003909009,0.00007217107,0.0001608173],"category_scores_gemma":[0.000008099738,0.000244897,0.0001528808,0.0003465305,0.0000398936,0.0003419702,0.00009154762,0.0003695323,1.231633e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002119642,"about_ca_system_score_gemma":0.00008852261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002266177,"about_ca_topic_score_gemma":0.00002646476,"domain_scores_codex":[0.9980546,0.0001787103,0.0006475314,0.0001868263,0.0006096115,0.000322716],"domain_scores_gemma":[0.9988742,0.00003844171,0.0004911862,0.0002522663,0.0001687895,0.0001751184],"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":[0.0003854162,0.0001398976,0.00002107936,0.00002510316,0.0002340948,0.00008146762,0.0002565584,0.9907985,0.003783486,0.0008211288,0.0004662696,0.002987044],"study_design_scores_gemma":[0.001752871,0.000969464,0.00006068746,0.00002537031,0.00007838544,0.0001532598,0.0002998523,0.9308626,0.001878847,0.000007145922,0.06362171,0.0002898248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07457278,0.002391069,0.9202092,0.00003714881,0.0003789434,0.00004541355,0.000009066282,0.00007835426,0.002277986],"genre_scores_gemma":[0.9921074,0.0002644335,0.00645043,0.00008135969,0.0002634382,0.00002226562,0.00008135291,0.00007063089,0.0006586845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9175346,"threshold_uncertainty_score":0.9986609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004413846853917366,"score_gpt":0.1726353331701681,"score_spread":0.1682214863162507,"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."}}