{"id":"W4312307060","doi":"10.1109/ithings-greencom-cpscom-smartdata-cybermatics55523.2022.00020","title":"On the Benefits of Transfer Learning and Reinforcement Learning for Electric Short-term Load Forecasting","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing & Communications (GreenCom) and IEEE Cyber, Physical & Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics)","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Leverage (statistics); Artificial intelligence; Machine learning; Probabilistic forecasting; Time series; Transfer of learning; Term (time); Transformer; Engineering; Probabilistic logic","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.002115984,0.0008855016,0.001244054,0.0004717601,0.002108087,0.0005808559,0.002013358,0.0002326647,0.00001905208],"category_scores_gemma":[0.0003176837,0.0008354455,0.0002114385,0.0004415165,0.0006947,0.0006690128,0.0009416956,0.002289466,0.000003169902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001330546,"about_ca_system_score_gemma":0.0001007545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006872846,"about_ca_topic_score_gemma":0.0004254123,"domain_scores_codex":[0.9948571,0.0005921879,0.001764654,0.0009054167,0.0011284,0.0007522638],"domain_scores_gemma":[0.9929407,0.004493217,0.0008824707,0.000980406,0.000442506,0.0002607497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002402029,0.003367398,0.01804181,0.007371609,0.01093617,0.00002078654,0.1901745,0.2239055,0.03038987,0.06480663,0.04419699,0.4043868],"study_design_scores_gemma":[0.001536462,0.0005888992,0.0004392868,0.001782389,0.0003139545,0.00006052504,0.0008090502,0.981419,0.0006222281,0.000797707,0.01053365,0.001096888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819482,0.0003883172,0.01246844,0.0004230818,0.002144651,0.0007313391,0.0003909545,0.0001671918,0.001337844],"genre_scores_gemma":[0.9953425,0.0006973249,0.001814085,0.0003703696,0.0004273509,0.00003780385,0.0008758376,0.0001002925,0.0003344556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7575135,"threshold_uncertainty_score":0.9994096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08114227040189179,"score_gpt":0.3029475724956981,"score_spread":0.2218053020938063,"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."}}