{"id":"W4402764848","doi":"10.1115/es2024-130538","title":"Enhancing Battery Storage Energy Arbitrage With Deep Reinforcement Learning and Time-Series Forecasting","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Reinforcement learning; Arbitrage; Revenue; Electricity; Computer science; Battery (electricity); Electricity price forecasting; Deep learning; Artificial intelligence; Electricity market; Econometrics; Economics; Engineering; Finance; Electrical engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.0002341441,0.0005877739,0.000454528,0.000315334,0.0001010091,0.0003191963,0.0001787219,0.0001918454,0.000335245],"category_scores_gemma":[0.00001530941,0.0005410246,0.00008035847,0.0001489414,0.00004569175,0.0001305605,0.001218697,0.0009540683,0.00003941325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000225587,"about_ca_system_score_gemma":0.00003162605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009504346,"about_ca_topic_score_gemma":0.0001958824,"domain_scores_codex":[0.9981167,0.00002902434,0.0004387798,0.0005847075,0.0003205545,0.0005102709],"domain_scores_gemma":[0.9993556,0.00006569744,0.00007398509,0.0003499372,0.00003292074,0.0001219219],"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":[0.00001066157,0.000003121692,0.00002614186,0.001083766,0.0003759204,0.0001423284,0.0002947099,0.9948498,0.0004923604,0.001083118,0.0004849772,0.001153083],"study_design_scores_gemma":[0.0001512945,0.00008093872,0.00001734492,0.0008436375,0.0001457205,0.00003569198,0.0001841786,0.982426,0.006075014,0.0003552603,0.008899595,0.0007852592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02851693,0.001936226,0.7824529,0.0001158458,0.001562089,0.0003316239,0.000002048587,0.002665574,0.1824167],"genre_scores_gemma":[0.9714973,0.0003232208,0.008545407,0.00008904703,0.0005887901,0.0002139551,0.0001055126,0.0002760086,0.01836079],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9429803,"threshold_uncertainty_score":0.9997041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006391332218540322,"score_gpt":0.1775917264410149,"score_spread":0.1712003942224746,"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."}}