{"id":"W3191423952","doi":"10.36227/techrxiv.15124416.v1","title":"LSTM-based Multi-Step SOC Forecasting of Battery Energy Storage in Grid Ancillary Services","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Chonnam National University","keywords":"Computer science; Mean squared error; Battery (electricity); Grid; Hyperparameter optimization; Artificial intelligence; State of charge; Machine learning; Deep learning; Time series; Domain (mathematical analysis); State (computer science); Data mining; Support vector machine; Algorithm","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":[0.0002652255,0.0005132417,0.0007260327,0.0003339231,0.00003764237,0.00007310833,0.000399147,0.0004923405,0.0001379858],"category_scores_gemma":[0.00002135823,0.0005536549,0.0002422276,0.0002743913,0.00002972902,0.0001294119,0.0004045925,0.000614649,0.00000155933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001394426,"about_ca_system_score_gemma":0.0001158546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00160424,"about_ca_topic_score_gemma":0.006404752,"domain_scores_codex":[0.9978595,0.00006179082,0.0007836283,0.0005035933,0.0002846243,0.000506909],"domain_scores_gemma":[0.9988992,0.0001691241,0.0001770157,0.0005467912,0.0001006208,0.0001072909],"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":[0.000006515555,0.00005241791,0.003206348,0.002690535,0.00008234727,0.0001341877,0.0003837312,0.9854274,0.001048085,0.0000198112,0.0001236931,0.006824893],"study_design_scores_gemma":[0.0004991209,0.00001403921,0.0006236859,0.002065634,0.00002608257,0.000006651802,0.0002866726,0.9832372,0.0112799,0.000006701135,0.00137092,0.0005834044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9098822,0.004865674,0.06860813,0.00003369656,0.005109247,0.0001782217,0.0001250404,0.0005657508,0.01063199],"genre_scores_gemma":[0.9767393,0.000132366,0.02167936,0.0001611843,0.0004569367,0.00004322312,0.0005313889,0.0001262366,0.0001299656],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06685708,"threshold_uncertainty_score":0.9996915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02430109633861848,"score_gpt":0.2154813348640905,"score_spread":0.191180238525472,"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."}}