{"id":"W3199393712","doi":"10.1016/j.enbuild.2021.111459","title":"A compositional kernel based gaussian process approach to day-ahead residential load forecasting","year":2021,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Probabilistic forecasting; Computer science; Gaussian process; Probabilistic logic; Kernel (algebra); Set (abstract data type); Process (computing); Bayesian probability; Electricity; Kriging; Demand forecasting; Electric power system; Multivariate statistics; Gaussian; Data mining; Mathematical optimization; Power (physics); Machine learning; Artificial intelligence; Engineering; Operations research; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001183175,0.0004178048,0.0009822821,0.0006838624,0.0004510078,0.0009402743,0.001621182,0.000813372,0.001707489],"category_scores_gemma":[0.004157478,0.0004486129,0.0009334494,0.001153239,0.0004827174,0.001428387,0.0009962929,0.001306277,0.0005800494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006390741,"about_ca_system_score_gemma":0.0009995311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01569272,"about_ca_topic_score_gemma":0.01422411,"domain_scores_codex":[0.9996071,0.000127829,0.00002167011,0.0000751028,0.0001132621,0.00005502473],"domain_scores_gemma":[0.9989547,0.0005503779,0.00006738411,0.0001038139,0.0002811369,0.00004255922],"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":[0.0002304573,0.0001468356,0.001673416,0.00009340711,0.0001240786,0.00008479627,0.0001219349,0.8483536,0.003257874,0.03500792,0.001567293,0.1093385],"study_design_scores_gemma":[0.000001432333,0.000003353239,0.00009274449,9.433743e-7,0.00000352344,0.000002415165,0.000002276857,0.9979532,0.00009780658,0.001755581,0.00008416952,0.000002471015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02975679,0.0002412836,0.9685873,0.0001223292,0.0000594633,0.00001782834,0.00009318232,0.0003434666,0.000778377],"genre_scores_gemma":[0.8353263,0.0005901756,0.1567461,0.00008508605,0.0001557591,0.00006897454,0.0005043685,0.0001843413,0.006338967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01569272,"threshold_uncertainty_score":0.03120273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01294481911759966,"score_gpt":0.2129216787926551,"score_spread":0.1999768596750554,"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."}}