{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005295514,0.000996187,0.001029631,0.001003101,0.0002441157,0.0002271449,0.0008176753,0.0005791771,0.0004625065],"category_scores_gemma":[0.00001363629,0.001053427,0.0003443006,0.00135385,0.0001289195,0.0005758876,0.0004358862,0.0004614391,0.00001416638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008970902,"about_ca_system_score_gemma":0.0000779919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004110705,"about_ca_topic_score_gemma":0.0002797314,"domain_scores_codex":[0.9948649,0.0003202831,0.00230062,0.001021568,0.0004668683,0.001025716],"domain_scores_gemma":[0.9977427,0.00003878879,0.0004390043,0.001121323,0.0004208827,0.0002372688],"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":[0.0001027587,0.0002089394,0.00001836261,0.0009723202,0.001522266,0.00001258347,0.0006135582,0.8457691,0.002656687,0.1115055,0.0003598674,0.03625807],"study_design_scores_gemma":[0.001780891,0.0002473328,0.00001958806,0.001094617,0.0002760063,0.000008774832,0.00309027,0.9536822,0.02327871,0.00004297902,0.01564203,0.0008366223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003604575,0.001907513,0.8633624,0.00002750708,0.001167492,0.0003343232,0.000001597187,0.0003651928,0.1324735],"genre_scores_gemma":[0.8766661,0.002556771,0.07417852,0.000162956,0.00007694703,0.0002213693,0.0003790838,0.0001635202,0.04559475],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8763056,"threshold_uncertainty_score":0.9991916,"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."}}