{"id":"W4406939161","doi":"10.2139/ssrn.5117155","title":"Deep Reinforcement Learning for the Joint Dispatch of Battery Energy Storage Systems and Gas Turbines in Microgrids with Renewable Energy","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Microgrid Control and Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Renewable energy; Reinforcement learning; Energy storage; Battery (electricity); Joint (building); Computer science; Energy (signal processing); Environmental science; Engineering; Electrical engineering; Artificial intelligence; Civil engineering; Power (physics); Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0006803484,0.0002975904,0.000460921,0.0002338378,0.0001098852,0.0001043893,0.0002228154,0.0001639665,0.000003224016],"category_scores_gemma":[0.00001552266,0.0002144808,0.00010631,0.0001297585,0.00003044477,0.00006880486,0.00009764358,0.001064447,5.249346e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000590596,"about_ca_system_score_gemma":0.0005289493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002332753,"about_ca_topic_score_gemma":0.005608236,"domain_scores_codex":[0.9980017,0.00006654926,0.0005341129,0.0002197043,0.0001605883,0.001017333],"domain_scores_gemma":[0.9993083,0.00008585682,0.0002473651,0.0002052815,0.0001122575,0.00004089115],"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":[0.00007990445,0.00001016245,0.0001286605,0.0002209169,0.0004163788,0.000001328271,0.0001088048,0.9896132,0.0002666732,0.0009632921,0.00006299223,0.008127707],"study_design_scores_gemma":[0.0009060935,0.0001566839,0.00002033169,0.0004682619,0.0001363718,0.00005620781,0.000450092,0.9934611,0.00031083,0.001345446,0.002446699,0.000241866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002172728,0.08268095,0.9142696,0.000127528,0.0003766532,0.0002202502,0.000002408776,0.00003478232,0.0001151459],"genre_scores_gemma":[0.9006672,0.09750976,0.0001698426,0.00001956178,0.0002664741,0.0001310628,0.00004262119,0.00004365117,0.001149826],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9140997,"threshold_uncertainty_score":0.8746274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003966251911224186,"score_gpt":0.1757702566267212,"score_spread":0.171804004715497,"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."}}