{"id":"W4415821121","doi":"10.1109/tnse.2025.3628244","title":"Adaptive Resilient Control Against False Data Injection Attacks for a Multi-Energy Microgrid Integrating Power and Hydrogen Energy Systems Using Deep Reinforcement Learning","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Smart Grid Security and Resilience","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"Japan Science and Technology Agency; Natural Sciences and Engineering Research Council of Canada","keywords":"Microgrid; Reinforcement learning; Resilience (materials science); Electric power system; Electricity; Automatic frequency control; Energy (signal processing); Power (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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001139134,0.0005548421,0.0005401032,0.0006292696,0.001636907,0.000457136,0.0004924003,0.0002708499,0.000001676057],"category_scores_gemma":[0.00005933702,0.0005873884,0.00009631048,0.001538957,0.0003234132,0.0009269363,0.00003265438,0.0006233418,4.179281e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000446978,"about_ca_system_score_gemma":0.0002301375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003471643,"about_ca_topic_score_gemma":0.0001831721,"domain_scores_codex":[0.9966787,0.00006393171,0.0007341653,0.001031006,0.0004272648,0.001064998],"domain_scores_gemma":[0.9985043,0.0003167035,0.000132358,0.0005263044,0.0002335981,0.0002867787],"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":[0.00009066726,0.00003729114,0.00001667501,0.0001511868,0.0001818032,0.000004069077,0.0004779892,0.9808541,0.00780775,0.000342199,0.00002000422,0.01001628],"study_design_scores_gemma":[0.001041599,0.0002278908,0.00001627526,0.001276962,0.0001628778,0.00002764037,0.00102424,0.9922777,0.00175978,0.000002839804,0.001639808,0.0005423341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02479572,0.008433629,0.9628981,0.00001683957,0.003134365,0.0004962027,0.00002103235,0.0001591991,0.00004486751],"genre_scores_gemma":[0.9943269,0.002299287,0.002871295,0.00007351667,0.0002207966,0.00009585874,0.000006515625,0.00004867425,0.00005711652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9695312,"threshold_uncertainty_score":0.9996628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01691439725399992,"score_gpt":0.2408900165718036,"score_spread":0.2239756193178037,"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."}}