{"id":"W3145208339","doi":"10.3390/designs5020027","title":"Medium-Term Regional Electricity Load Forecasting through Machine Learning and Deep Learning","year":2021,"lang":"en","type":"article","venue":"Designs","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Computer science; Support vector machine; Mean absolute percentage error; Demand response; Random forest; Artificial intelligence; Electricity; Renewable energy; Term (time); Artificial neural network; Electrical load; Machine learning; Environmental economics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.0003227188,0.0004795497,0.0003764801,0.0005043806,0.0002060011,0.0006166512,0.000751277,0.0003883161,0.0007939496],"category_scores_gemma":[0.0009431501,0.0002643641,0.0004380922,0.000638,0.0002069703,0.0007866331,0.0004082875,0.0005659965,0.0003904408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001584388,"about_ca_system_score_gemma":0.0008438295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1648298,"about_ca_topic_score_gemma":0.197771,"domain_scores_codex":[0.999849,0.00002313539,0.000007440885,0.00005457172,0.00003159176,0.00003432604],"domain_scores_gemma":[0.999777,0.00006234299,0.00003052039,0.00003198546,0.00008220685,0.0000159739],"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":[0.00005321947,0.00005229454,0.008824755,0.00001747498,0.00004235304,0.00003826815,0.0000197544,0.9462097,0.001264947,0.0003834818,0.001239519,0.04185427],"study_design_scores_gemma":[0.000001498335,0.000003312935,0.001324963,0.000001172823,0.000002534941,0.00000156789,0.000005630609,0.99814,0.0002054188,0.0001699278,0.0001416011,0.000002437281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.766661,0.0009427104,0.2186816,0.0006249691,0.00009887004,0.00004996223,0.002591193,0.002837314,0.007512303],"genre_scores_gemma":[0.9837571,0.0001239174,0.01306309,0.00003199952,0.00001692645,0.00001442187,0.001587741,0.00003452449,0.001370301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1648298,"threshold_uncertainty_score":0.3277407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03787378881506236,"score_gpt":0.2355935002248618,"score_spread":0.1977197114097995,"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."}}