{"id":"W4416136699","doi":"10.1109/pesgm52009.2025.11225724","title":"Energy Management of Net-Zero Multi-energy Microgrids: An Interior-Point Safe Deep Reinforcement Learning Approach","year":2025,"lang":"","type":"article","venue":"","topic":"Integrated Energy Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Ministry of Higher Education","keywords":"Reinforcement learning; Markov decision process; Energy management; Constraint (computer-aided design); Process (computing); Stability (learning theory); Markov process; Optimization problem","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001119891,0.0008804133,0.0009834269,0.0003067357,0.0002781065,0.000784182,0.001096582,0.0009760672,0.002096507],"category_scores_gemma":[0.002208582,0.0004502519,0.000449451,0.0002485567,0.001001059,0.0007771671,0.001334857,0.00151623,0.0002416207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007277005,"about_ca_system_score_gemma":0.001431609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004701073,"about_ca_topic_score_gemma":0.004377793,"domain_scores_codex":[0.9996819,0.0001135477,0.00001145705,0.00006206425,0.0000718562,0.00005917301],"domain_scores_gemma":[0.9992232,0.0004552669,0.00009470437,0.00004120153,0.0001163693,0.00006927042],"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":[0.00002217842,0.00001421246,0.0002216143,0.00002054533,0.00001156285,0.00002443552,0.00001474819,0.9899228,0.0002692719,0.002835627,0.0002694695,0.00637348],"study_design_scores_gemma":[0.000003065634,0.00000761513,0.00001782797,0.000002550389,0.000001739251,0.000002295877,0.00000221031,0.9983956,0.00006935008,0.001400025,0.00009674039,0.000001043102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02450967,0.0002689322,0.9704301,0.0003768175,0.0000415476,0.00003779248,0.00005798698,0.0004093231,0.003867905],"genre_scores_gemma":[0.929309,0.0001569426,0.06737486,0.0002272799,0.00003511905,0.00009893648,0.00009173063,0.00008040242,0.002625747],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004701073,"threshold_uncertainty_score":0.009347439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007513226501832776,"score_gpt":0.2095453611506397,"score_spread":0.2020321346488069,"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."}}