{"id":"W3091178637","doi":"10.1109/camad50429.2020.9209254","title":"Correlated Deep Q-learning based Microgrid Energy Management","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Microgrid Control and Optimization","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Microgrid; Computer science; Renewable energy; Energy management; Energy management system; Photovoltaic system; Artificial intelligence; Deep learning; Artificial neural network; Q-learning; Energy (signal processing); Electrical engineering; Engineering; Mathematics; Reinforcement learning","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":[0.00005095844,0.0003235877,0.0002932075,0.0001304064,0.00004448974,0.0001059686,0.0002412243,0.0002567371,0.0005695667],"category_scores_gemma":[0.000004631813,0.0003445012,0.0001468676,0.0001430352,0.00001108537,0.00002857133,0.0002087556,0.0005132378,0.00009647764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008312366,"about_ca_system_score_gemma":0.00001032889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002710056,"about_ca_topic_score_gemma":0.00001095946,"domain_scores_codex":[0.9989097,0.00003318806,0.000302961,0.0003571064,0.0001351721,0.0002619283],"domain_scores_gemma":[0.9995393,0.00001860139,0.00005456157,0.0002474245,0.00003771643,0.0001023859],"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":[0.00001009008,0.000009528067,0.00002041281,0.0001878072,0.0001905615,0.00002782769,0.00002694435,0.9389182,0.0001916883,0.0001351515,0.002027775,0.05825398],"study_design_scores_gemma":[0.000410434,0.00001068808,0.00005896699,0.00005781708,0.00009362656,9.218579e-7,0.00001264273,0.9237022,0.0005245087,0.00006567674,0.07471642,0.0003460432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001502792,0.005104366,0.9702926,0.0001941776,0.001132223,0.0002566444,0.000007019923,0.002221625,0.02064106],"genre_scores_gemma":[0.9013491,0.01291187,0.07778987,0.001541287,0.0006848216,0.0003249232,0.00281478,0.0004235337,0.002159822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9011988,"threshold_uncertainty_score":0.9999007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004040243392849088,"score_gpt":0.1605783274012046,"score_spread":0.1565380840083555,"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."}}