{"id":"W4400420714","doi":"10.1016/j.procs.2024.06.137","title":"Enhancing Security and Energy Efficiency of Cyber-Physical Systems using Deep Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Smart Grid Security and Resilience","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Polytechnique Montréal","keywords":"Computer science; Reinforcement learning; Flexibility (engineering); Efficient energy use; Energy consumption; Anomaly detection; Reliability (semiconductor); Cyber-physical system; Adaptation (eye); Resource efficiency; Risk analysis (engineering); Distributed computing; 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":[0.0003003679,0.0001273472,0.0001595127,0.0001781328,0.0001491891,0.000172813,0.0002381977,0.000033099,9.673157e-7],"category_scores_gemma":[0.00002098109,0.0001133986,0.00002985828,0.0007487616,0.0002512806,0.0003873324,0.0001558062,0.000156714,0.000002174054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000058379,"about_ca_system_score_gemma":0.00008163992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003076885,"about_ca_topic_score_gemma":0.000003010074,"domain_scores_codex":[0.9987975,0.00001176951,0.0002015865,0.000305535,0.0003724722,0.0003111218],"domain_scores_gemma":[0.9996154,0.0000794199,0.0000257058,0.0001136661,0.0000640454,0.0001018184],"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":[0.00000119777,0.00001267711,0.0001034346,0.0006641588,0.000007988523,0.000008358811,0.008359929,0.9433941,0.03919262,0.005139045,0.000004828903,0.003111681],"study_design_scores_gemma":[0.00003807844,0.00004881224,0.00003423574,0.0002277076,0.000006274542,0.00003590494,0.00007008239,0.9729964,0.02619852,0.00007129494,0.0001394776,0.0001332055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5390601,0.001220238,0.458425,0.000003272122,0.000914584,0.00004154268,1.711682e-7,0.0001409449,0.0001941844],"genre_scores_gemma":[0.9987288,0.00005705378,0.0009160741,0.000005631276,0.0002736112,0.000004359546,3.438649e-7,0.000009211314,0.000004875636],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4596688,"threshold_uncertainty_score":0.4624261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005340990691195734,"score_gpt":0.2101705828227352,"score_spread":0.2048295921315395,"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."}}