{"id":"W3211338353","doi":"10.1016/j.ijepes.2021.107669","title":"Distributed load forecasting using smart meter data: Federated learning with Recurrent Neural Networks","year":2021,"lang":"en","type":"article","venue":"International Journal of Electrical Power & Energy Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":199,"is_retracted":false,"has_abstract":false,"ca_institutions":"London Hydro; Western University","funders":"","keywords":"Smart meter; Computer science; Smart grid; Real-time computing; Metre; Artificial neural network; Scale (ratio); Gradient descent; Machine learning; Data mining; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00190955,0.0006608038,0.001250447,0.0004774038,0.0003662235,0.001076899,0.001309717,0.001007954,0.0006444197],"category_scores_gemma":[0.004616903,0.0004401304,0.000582597,0.0006610448,0.0004131083,0.002011279,0.0009229621,0.001191603,0.0002632845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006420393,"about_ca_system_score_gemma":0.0007137395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005661781,"about_ca_topic_score_gemma":0.006552618,"domain_scores_codex":[0.9993578,0.0001813371,0.00004835398,0.0002060839,0.0001143605,0.00009210833],"domain_scores_gemma":[0.9983174,0.0007664399,0.0002037795,0.0003774735,0.000272757,0.00006226562],"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":[0.0005760253,0.0003618487,0.00482764,0.00003655246,0.000149466,0.0001173391,0.00006302133,0.8538561,0.001892168,0.003199182,0.001688002,0.1332326],"study_design_scores_gemma":[0.0000040164,0.000009437926,0.0001204031,0.000001059933,0.000004602701,0.000004338923,0.000003022186,0.9985541,0.0002572689,0.001003727,0.00003635396,0.000001660536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2671696,0.0006337453,0.7272368,0.0008383101,0.0001965731,0.00004619654,0.0002909729,0.001696816,0.001891054],"genre_scores_gemma":[0.978272,0.00007215264,0.02066044,0.00005854143,0.00004779899,0.00001520106,0.000196964,0.00001949206,0.0006574308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005661781,"threshold_uncertainty_score":0.01125765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.050177199457022,"score_gpt":0.284355475228485,"score_spread":0.234178275771463,"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."}}