{"id":"W4412860334","doi":"10.1016/j.apenergy.2025.126465","title":"Comparison of machine learning and MPC methods for control of home battery storage systems in distribution grids","year":2025,"lang":"en","type":"article","venue":"Applied Energy","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Mitacs","keywords":"Battery (electricity); Control (management); Battery storage; Model predictive control; Computer science; Control engineering; Engineering; Control theory (sociology); Artificial intelligence; Thermodynamics; Power (physics); Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003030229,0.0001197097,0.000410531,0.0001328349,0.00001982177,0.000008437421,0.00007678452,0.0000662894,0.000002159847],"category_scores_gemma":[0.00001422561,0.000127298,0.00003080552,0.0001918938,0.00002563019,0.00002349261,0.00003585895,0.0000744519,1.063197e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006431956,"about_ca_system_score_gemma":0.000005175442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001409531,"about_ca_topic_score_gemma":0.00001873738,"domain_scores_codex":[0.9992415,0.00004431561,0.0003618636,0.0001359953,0.00006337945,0.0001529562],"domain_scores_gemma":[0.9995381,0.0002367153,0.00006457395,0.0001211302,0.00001822831,0.00002126413],"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":[0.00003367058,0.00002519101,0.00208452,0.000338964,0.00008663684,1.690454e-7,0.00002754625,0.9298127,0.01149004,0.04895705,0.0001726198,0.006970857],"study_design_scores_gemma":[0.001064071,0.00003238735,0.002291966,0.0000475121,0.00004229027,1.533231e-7,0.00008390056,0.9568658,0.01117482,0.000174992,0.02810435,0.0001177789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02550178,0.002025452,0.9710302,0.00001190012,0.0003135782,0.000129016,0.00001801258,0.00005945218,0.0009105982],"genre_scores_gemma":[0.9982318,0.00006168825,0.001383064,0.000006946869,0.00002732662,0.0001391163,0.00008783245,0.0000160783,0.00004610319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.97273,"threshold_uncertainty_score":0.5191061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008306682692800882,"score_gpt":0.2695116495401016,"score_spread":0.2612049668473008,"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."}}