{"id":"W4406331660","doi":"10.3390/electronics14020288","title":"Model-Free Resilient Grid-Forming and Grid-Following Inverter Control Against Cyberattacks Using Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"Electronics","topic":"Smart Grid Security and Resilience","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Renewable Energy Laboratory; Università degli Studi di Firenze; Office of Energy Efficiency; Division of Electrical, Communications and Cyber Systems; Manitoba Hydro; U.S. Department of Energy; Office of Energy Efficiency and Renewable Energy; National Science Foundation","keywords":"Grid; Inverter; Computer science; Control (management); Fault detection and isolation; Set (abstract data type); Engineering; Real-time computing; Electrical engineering; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000626119,0.0004899823,0.0004713855,0.0002094155,0.0003030766,0.0005144615,0.0006911274,0.0003789864,0.001224297],"category_scores_gemma":[0.001455718,0.0002060628,0.0003286328,0.0001319631,0.0005054505,0.0004664522,0.0004977313,0.0007826593,0.0001944691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005363374,"about_ca_system_score_gemma":0.0007132018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005708056,"about_ca_topic_score_gemma":0.004863668,"domain_scores_codex":[0.9997454,0.00005602674,0.00001209158,0.00006580701,0.00008253615,0.00003815972],"domain_scores_gemma":[0.9994133,0.0002511738,0.0001178495,0.00007173324,0.0001213096,0.00002471],"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":[0.00009378525,0.00007231173,0.0006008175,0.00003771003,0.00002147938,0.00003899393,0.00004961545,0.9429629,0.003647939,0.001994433,0.0004013489,0.05007868],"study_design_scores_gemma":[0.000006509711,0.00002835193,0.00006671235,0.000002125373,0.000002628263,0.000006032924,0.000002045896,0.9989443,0.0005457471,0.0002962612,0.0000972551,0.000001893029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05834363,0.0001293444,0.9358773,0.0001696862,0.00004243385,0.00006072655,0.00001511128,0.001140037,0.004221808],"genre_scores_gemma":[0.9731674,0.00003305453,0.02570623,0.00003445743,0.000008837306,0.00003257359,0.00001500671,0.00001872182,0.0009837502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005708056,"threshold_uncertainty_score":0.01134968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006732770091512072,"score_gpt":0.2210553741010105,"score_spread":0.2143226040094985,"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."}}