{"id":"W4206787406","doi":"10.1109/tsg.2022.3142087","title":"Multi-Agent Reinforcement Learning for Decentralized Resilient Secondary Control of Energy Storage Systems Against DoS Attacks","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Smart Grid","topic":"Microgrid Control and Optimization","field":"Engineering","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Science Foundation of Zhejiang Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Controller (irrigation); Asynchronous communication; Distributed computing; Decentralised system; Computer network; Control (management); Artificial intelligence","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":[0.00021418,0.0002093434,0.0003215908,0.0001902003,0.0003252724,0.0000270252,0.0001380776,0.00006088755,0.0001554334],"category_scores_gemma":[0.000003212713,0.0002303971,0.0002076338,0.0001650172,0.00001993714,0.00008499219,0.000001825376,0.0002692386,0.000004513322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002698109,"about_ca_system_score_gemma":0.00004424411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004418745,"about_ca_topic_score_gemma":0.00002061164,"domain_scores_codex":[0.9986071,0.0001001823,0.0005032648,0.0002245787,0.0002451212,0.0003197545],"domain_scores_gemma":[0.9994149,0.00008697448,0.0001030738,0.0002245794,0.00007697306,0.00009354853],"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":[0.000235094,0.00008971303,0.000008878755,0.0000902581,0.0001984662,0.000002803546,0.0001639191,0.9833035,0.01180712,0.000008454002,0.0005868148,0.003504982],"study_design_scores_gemma":[0.004023582,0.0001971063,0.00001608756,0.00002303963,0.00007422219,0.000003676955,0.0001358754,0.9155865,0.00531501,3.300382e-7,0.07441451,0.0002100664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005560246,0.0009985729,0.9890536,0.00002485648,0.003200365,0.0006724012,0.0002118922,0.0002002388,0.00007782415],"genre_scores_gemma":[0.9975835,0.0004592648,0.0004167595,0.00007472446,0.00006159325,0.0007872292,0.0001134816,0.0000529237,0.0004505339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9920232,"threshold_uncertainty_score":0.9395323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00936356611258179,"score_gpt":0.2060475913565014,"score_spread":0.1966840252439196,"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."}}