{"id":"W3180293405","doi":"10.1109/access.2021.3095420","title":"Load Forecasting Under Concept Drift: Online Ensemble Learning With Recurrent Neural Network and ARIMA","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":112,"is_retracted":false,"has_abstract":true,"ca_institutions":"London Hydro; Western University","funders":"Ontario Centres of Excellence","keywords":"Computer science; Concept drift; Autoregressive integrated moving average; Recurrent neural network; Ensemble learning; Artificial intelligence; Machine learning; Energy consumption; Adaptation (eye); Adaptive learning; Artificial neural network; Energy (signal processing); Electricity; Time series; Data stream mining; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008478727,0.000212577,0.0002289424,0.00002856252,0.0001626549,0.0001962782,0.0001320162,0.00007452788,0.00003090283],"category_scores_gemma":[0.00002676358,0.0001966727,0.00003614655,0.0002971155,0.00004019691,0.0003121797,0.00006934084,0.0004117962,0.000001589592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004408915,"about_ca_system_score_gemma":0.00004170639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003328192,"about_ca_topic_score_gemma":0.0004354845,"domain_scores_codex":[0.9988805,0.00003678378,0.0002133609,0.0002638691,0.0001768895,0.0004286182],"domain_scores_gemma":[0.9994741,0.0001386217,0.00005473418,0.0001419168,0.00008277428,0.000107822],"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":[0.00001028143,0.00001240224,0.005197811,0.00004974647,0.00004572746,0.00007836948,0.0002887477,0.9491531,0.0004098874,0.00008464506,0.0003833932,0.04428586],"study_design_scores_gemma":[0.001278593,0.0001396242,0.00454204,0.0007426327,0.00008510944,0.0003625279,0.000322123,0.9744757,0.007772531,0.0002971464,0.009111534,0.0008704339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9815732,0.002534562,0.01113601,0.00005978957,0.001024981,0.0000607901,0.000004505059,0.0002636446,0.003342566],"genre_scores_gemma":[0.9976044,0.00009550317,0.001243366,0.0001143532,0.0006533732,0.000005868626,0.00003444528,0.00005348515,0.0001952632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04341543,"threshold_uncertainty_score":0.802008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03371358459248409,"score_gpt":0.2559262365046391,"score_spread":0.222212651912155,"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."}}