{"id":"W4360584207","doi":"10.1109/isgt51731.2023.10066398","title":"Power Management in Smart Buildings Using Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Reinforcement learning; Schedule; Computer science; Markov decision process; Particle swarm optimization; Mathematical optimization; Energy storage; Energy management; Metaheuristic; Battery (electricity); Microgrid; Markov process; Power (physics); Energy (signal processing); Artificial intelligence; Machine learning; 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":[0.0002679002,0.0001561237,0.0001252842,0.0004905987,0.00004444744,0.00003923711,0.0001425807,0.00003721988,0.0003056598],"category_scores_gemma":[0.000005878955,0.0001702421,0.00004056164,0.0007955285,0.00000992755,0.0001269089,0.0001845262,0.0001236665,0.0003532577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002013589,"about_ca_system_score_gemma":0.000002253228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004352849,"about_ca_topic_score_gemma":0.00000860445,"domain_scores_codex":[0.9988926,0.00001098154,0.0002483425,0.0001952944,0.000224128,0.0004286617],"domain_scores_gemma":[0.9997134,0.0000146572,0.00001511354,0.000204553,0.000008162068,0.00004407919],"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":[0.00000193457,0.000003782606,0.001496127,0.00003747798,0.00005130054,0.00005031206,0.00009239927,0.9900475,0.0003585643,0.004123147,0.002921124,0.0008163134],"study_design_scores_gemma":[0.0004004508,0.00001480419,0.005971245,0.00004280216,0.000009658483,0.000001216224,0.0004075119,0.8497012,0.0006214826,0.00007069266,0.1424839,0.0002750049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5786344,0.0000320814,0.04307998,0.0000683716,0.001025706,0.000304136,1.381954e-7,0.002045027,0.3748102],"genre_scores_gemma":[0.9924507,0.00007592842,0.002179237,0.00008858707,0.00003244687,0.00003758511,0.000005957203,0.00005090739,0.005078675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4138163,"threshold_uncertainty_score":0.6942272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01223427902924419,"score_gpt":0.2205747348603178,"score_spread":0.2083404558310736,"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."}}