{"id":"W3184945381","doi":"10.1109/siu53274.2021.9477869","title":"A hybrid deep learning algorithm for short-term electric load forecasting","year":2021,"lang":"en","type":"article","venue":"","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Centre","funders":"","keywords":"Computer science; Electricity; Electrical load; Mean absolute percentage error; Feature selection; Electric power system; Artificial neural network; Artificial intelligence; Term (time); Electric power; Feature (linguistics); Algorithm; Machine learning; Power (physics); Engineering; Voltage; Electrical engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0001570347,0.0001975667,0.0002088889,0.00006743451,0.0001482633,0.000081156,0.00009795497,0.00006091213,0.0001154561],"category_scores_gemma":[0.00009711541,0.0002085673,0.0001279032,0.0002241306,0.000007379326,0.0001306388,0.00003448238,0.0002339401,0.00001158542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009598638,"about_ca_system_score_gemma":0.0000375763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000454187,"about_ca_topic_score_gemma":0.00002137399,"domain_scores_codex":[0.9988083,0.00001514909,0.0002532055,0.0002458493,0.0001546302,0.0005228724],"domain_scores_gemma":[0.9994708,0.0001631175,0.00001937483,0.0001325258,0.0001152656,0.0000988965],"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":[0.000001993751,0.00001206808,0.0003008864,0.00006024748,0.00006496754,0.00007564065,0.0001091789,0.02260422,0.007261456,0.000160099,0.0002574383,0.9690918],"study_design_scores_gemma":[0.0002209847,0.00003903883,0.00004109692,0.00003971154,0.00002243007,0.0001879251,0.00003119202,0.928743,0.06100975,0.0001349126,0.009250018,0.0002799089],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09102787,0.002048092,0.8556644,0.00001104863,0.0006107548,0.0001253128,0.000005291742,0.0008461445,0.04966103],"genre_scores_gemma":[0.9404806,0.0001013009,0.05677089,0.00004085554,0.0005023277,0.00005155777,0.00007088504,0.00009762459,0.001883911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9688119,"threshold_uncertainty_score":0.8505129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01549045768573133,"score_gpt":0.2162893943395264,"score_spread":0.2007989366537951,"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."}}