{"id":"W3033589589","doi":"10.1016/j.scs.2020.102285","title":"Performance of a self-learning predictive controller for peak shifting in a building integrated with energy storage","year":2020,"lang":"en","type":"article","venue":"Sustainable Cities and Society","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hydro-Québec; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"TRNSYS; Thermal energy storage; Load shifting; Peak demand; Environmental science; Electricity; Demand response; Computer science; Automotive engineering; Controller (irrigation); Energy storage; Electricity pricing; Heating system; Simulation; Thermal; Electricity market; Engineering; Meteorology; Electrical engineering; Mechanical engineering; Power (physics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001040221,0.0001005814,0.0001714461,0.00002435223,0.0001077532,0.00002279689,0.00004338966,0.00006354062,0.000002051332],"category_scores_gemma":[0.00001513502,0.00009109416,0.0000367146,0.0001988871,0.0000290986,0.0001611553,0.00002051741,0.0001197278,4.783649e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006966012,"about_ca_system_score_gemma":0.00003471844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004684853,"about_ca_topic_score_gemma":0.000001416899,"domain_scores_codex":[0.999481,0.00001145358,0.0001257904,0.0001091106,0.00006012056,0.0002125141],"domain_scores_gemma":[0.9997699,0.00004647211,0.00003539052,0.00003020692,0.00008511209,0.00003286953],"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":[0.00007537963,0.000005358895,0.001227501,0.0004910063,0.00006510583,8.961784e-7,0.00859426,0.9848567,0.00007456842,0.004217547,0.00005454308,0.0003371417],"study_design_scores_gemma":[0.0007661663,0.0001956431,0.0002134892,0.00005092239,0.00001498625,5.643522e-7,0.0291449,0.96808,0.000193437,0.00003776036,0.001198151,0.0001039339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8930781,0.0002944657,0.1059561,0.00002890174,0.00001258154,0.0001219112,0.000002503515,0.0001506808,0.0003547477],"genre_scores_gemma":[0.9959364,0.0002254396,0.003557297,0.00004400213,0.00002914851,0.00005170938,0.000007040488,0.0000212814,0.0001277056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1028583,"threshold_uncertainty_score":0.3714712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002785421375309326,"score_gpt":0.159642851342808,"score_spread":0.1568574299674987,"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."}}