{"id":"W4387789936","doi":"10.1109/tce.2023.3325941","title":"Energy Consumption Prediction Model for Smart Homes via Decentralized Federated Learning With LSTM","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Consumer Electronics","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Energy consumption; Edge device; Enhanced Data Rates for GSM Evolution; Process (computing); Smart grid; Edge computing; Data modeling; The Internet; Demand response; Distributed computing; Efficient energy use; Big data; Adaptation (eye); Pace; Machine learning; Artificial intelligence; Data mining; Electricity; Cloud computing; Database; 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":[0.0006879662,0.000434066,0.0006115743,0.0002373955,0.0003259827,0.0005050645,0.0008044131,0.0008448046,0.001960768],"category_scores_gemma":[0.001105422,0.000282747,0.0003981427,0.0003186211,0.0003563163,0.000931285,0.0005141664,0.001065428,0.0003705743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007454096,"about_ca_system_score_gemma":0.0009134088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007894748,"about_ca_topic_score_gemma":0.009278453,"domain_scores_codex":[0.9997993,0.00004332862,0.00001044798,0.00007535028,0.00003560602,0.00003595345],"domain_scores_gemma":[0.9997199,0.0001188477,0.00003414154,0.00003127063,0.0000808314,0.00001505444],"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":[0.0001452392,0.00007332146,0.0007299366,0.00002474417,0.00002493082,0.00005261867,0.00003766028,0.9550401,0.001886094,0.001877617,0.0008631853,0.03924466],"study_design_scores_gemma":[0.000002540947,0.000005981529,0.00004831628,7.645849e-7,0.000001451045,0.000002427585,0.000001877645,0.9990242,0.0002261248,0.0006387086,0.00004654798,0.000001013204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1187786,0.0001876788,0.8753899,0.0005110701,0.00007563796,0.00005035951,0.0002017193,0.001844587,0.002960441],"genre_scores_gemma":[0.963329,0.00004830257,0.03380985,0.00008655927,0.00002163942,0.00007555725,0.0001809626,0.00002777479,0.002420383],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007894748,"threshold_uncertainty_score":0.0156976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01245058869502185,"score_gpt":0.2136616554523204,"score_spread":0.2012110667572985,"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."}}