{"id":"W4200161548","doi":"10.3390/en14248365","title":"Co-Optimizing Battery Storage for Energy Arbitrage and Frequency Regulation in Real-Time Markets Using Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"Energies","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Brock University","funders":"Brock University; National Science Foundation","keywords":"Markov decision process; Flexibility (engineering); Arbitrage; Reinforcement learning; Computer science; Mathematical optimization; Electricity; Battery (electricity); Energy storage; Electricity market; Stability (learning theory); Revenue; Renewable energy; Markov process; Power (physics); Engineering; Economics; Artificial intelligence; Mathematics; Machine learning","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":[0.00009858425,0.0001394038,0.0001697478,0.0001044984,0.00008430122,0.00005442784,0.00004294174,0.00009076047,0.00008987013],"category_scores_gemma":[0.00001938734,0.0001549368,0.00003533664,0.0001401428,0.00001382117,0.0001994159,0.00001469916,0.0001241224,3.873226e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001092747,"about_ca_system_score_gemma":0.00002339477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005357523,"about_ca_topic_score_gemma":0.00001595827,"domain_scores_codex":[0.9992475,0.00003166807,0.0002147557,0.0001668439,0.00009242591,0.0002468039],"domain_scores_gemma":[0.9997289,0.00005994982,0.00003915787,0.0001081506,0.00002734776,0.00003653001],"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":[0.000004337923,0.000001542854,0.0001332586,0.00003308312,0.00001481798,0.000008849538,0.0001662049,0.725113,0.272011,0.0004066482,0.00007134705,0.002035917],"study_design_scores_gemma":[0.0003135077,0.00002096099,0.001940015,0.00005822209,0.00001173021,0.00001651797,0.0001160645,0.9227178,0.073533,0.0004818613,0.0005842761,0.0002060251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9349606,0.001121568,0.05890525,0.00002758893,0.0001013706,0.00006476677,0.000001484759,0.0001430487,0.004674322],"genre_scores_gemma":[0.9866391,0.0004154222,0.01242165,0.00003588609,0.00008539874,0.00001104516,0.000058079,0.00003610145,0.0002973045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.198478,"threshold_uncertainty_score":0.6318138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00628536237606657,"score_gpt":0.2049458746535307,"score_spread":0.1986605122774641,"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."}}