{"id":"https://openalex.org/W7214019486","doi":"https://doi.org/10.48550/arxiv.2609.23590","title":"Cost-Aware Reinforcement Learning with Action Masking and Projection for Battery Energy Storage Dispatch under Suppressed-Spread Market Shifts","display_name":"Cost-Aware Reinforcement Learning with Action Masking and Projection for Battery Energy Storage Dispatch under Suppressed-Spread Market Shifts","publication_year":2026,"publication_date":"2026-09-20","ids":{"openalex":"https://openalex.org/W7214019486","doi":"https://doi.org/10.48550/arxiv.2609.23590"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.23590","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.23590","pdf_url":"https://arxiv.org/pdf/2609.23590","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.23590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152481494","display_name":"Kuanlin Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen, Kuanlin","raw_affiliation_strings":["Independent Researcher Taoyuan , Taiwan","National Tsing Hua University Hsinchu , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher Taoyuan , Taiwan","institution_ids":[]},{"raw_affiliation_string":"National Tsing Hua University Hsinchu , Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152477807","display_name":"Chen-Wei Kuo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo, Chen-Wei","raw_affiliation_strings":["National Tsing Hua University Hsinchu , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University Hsinchu , Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5152475777","display_name":"Cheng-En Ou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ou, Cheng-En","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10424","display_name":"Electric Power System Optimization","score":0.36910000443458557,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10424","display_name":"Electric Power System Optimization","score":0.36910000443458557,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.30489999055862427,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10223","display_name":"Microgrid Control and Optimization","score":0.1200999990105629,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action-masking","display_name":"action masking","score":0.8399999737739563},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.8420000076293945},{"id":"https://openalex.org/keywords/economic-dispatch","display_name":"economic dispatch","score":0.3330000042915344},{"id":"https://openalex.org/keywords/state-of-charge","display_name":"state of charge","score":0.8339999914169312},{"id":"https://openalex.org/keywords/model-predictive-control-comparison","display_name":"model predictive control comparison","score":0.5590000152587891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6215999722480774},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.590399980545044},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C2779777834","wikidata":"https://www.wikidata.org/wiki/Q4202277","display_name":"Enforcement","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C73916439","wikidata":"https://www.wikidata.org/wiki/Q837718","display_name":"Energy storage","level":3,"score":0.4268999993801117},{"id":"https://openalex.org/C189560676","wikidata":"https://www.wikidata.org/wiki/Q1187906","display_name":"Profit margin","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C187633118","wikidata":"https://www.wikidata.org/wiki/Q1317949","display_name":"Economic dispatch","level":4,"score":0.40549999475479126},{"id":"https://openalex.org/C555008776","wikidata":"https://www.wikidata.org/wiki/Q267298","display_name":"Battery (electricity)","level":3,"score":0.39969998598098755},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3452000021934509},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C2776789725","wikidata":"https://www.wikidata.org/wiki/Q1572221","display_name":"Spot market","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2685000002384186},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C2983735921","wikidata":"https://www.wikidata.org/wiki/Q1832610","display_name":"Battery storage","level":4,"score":0.2619999945163727},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.23590","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.23590","pdf_url":"https://arxiv.org/pdf/2609.23590","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.23590","doi":"https://doi.org/10.48550/arxiv.2609.23590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.23590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.23590","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.23590","pdf_url":"https://arxiv.org/pdf/2609.23590","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9853000044822693}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214019486.pdf","grobid_xml":"https://content.openalex.org/works/W7214019486.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7213260587","https://openalex.org/W4320061183","https://openalex.org/W4388756751","https://openalex.org/W7139064441","https://openalex.org/W7108456080","https://openalex.org/W4366112267","https://openalex.org/W7102648334","https://openalex.org/W7169057646","https://openalex.org/W3171908814","https://openalex.org/W2261625295"],"abstract_inverted_index":{"Battery":[0],"energy":[1],"storage":[2],"system":[3],"(BESS)":[4],"dispatch":[5],"must":[6],"preserve":[7],"operational":[8],"feasibility":[9,173],"while":[10,101,159],"declining":[11],"price":[12],"spreads":[13],"reduce":[14],"the":[15,50,136],"margin":[16],"available":[17],"to":[18,98,135,157],"pay":[19],"for":[20,81],"cycling.":[21],"We":[22],"study":[23],"a":[24,41],"proximal":[25],"policy":[26],"optimization":[27],"(PPO)":[28],"controller":[29],"whose":[30],"pre-selection":[31],"physical":[32,162],"action":[33],"mask":[34,150],"and":[35,55,67,73,78,119,126],"emergency":[36],"projection":[37],"are":[38],"separated":[39],"from":[40,96,172],"causal,":[42],"forecast-informed":[43],"economic":[44,170],"advisory.":[45],"All":[46],"forecast-dependent":[47],"methods":[48],"receive":[49],"same":[51],"causal":[52],"24-step":[53],"forecast":[54],"grid-side":[56],"settlement.":[57],"Across":[58],"five":[59],"PPO":[60,84,113],"seeds,":[61],"advice-on":[62],"net":[63],"profit":[64,95],"is":[65,105,114],"30.59":[66],"18.04":[68,99],"USD":[69,80,100],"per":[70],"336-hour":[71],"T1":[72],"T2":[74,94],"window,":[75],"versus":[76],"36.77":[77],"22.94":[79],"proxy-cost":[82,129],"MPC;":[83],"remains":[85,127],"below":[86,128],"this":[87],"reference":[88],"in":[89,107],"both":[90,161],"periods.":[91],"Advice":[92],"raises":[93],"16.45":[97],"reducing":[102],"throughput,":[103],"but":[104],"immaterial":[106],"T1.":[108],"On":[109],"disjoint":[110],"weekly":[111],"blocks,":[112],"stable":[115],"under":[116,124],"daily,":[117],"weekly,":[118],"blended":[120],"seasonal":[121],"forecasts,":[122],"weakens":[123],"persistence,":[125],"MPC.":[130],"Paired":[131],"diagnostics":[132],"localize":[133],"changes":[134],"observed":[137],"5-10":[138],"USD/MWh":[139],"regime":[140],"with":[141],"mixed":[142],"SoC-dependent":[143],"effects.":[144],"An":[145],"M0-M6":[146],"ablation":[147],"shows":[148],"that":[149],"removal":[151],"sends":[152],"thousands":[153],"of":[154],"infeasible":[155],"requests":[156],"projection,":[158],"removing":[160],"layers":[163],"exposes":[164],"ramp":[165],"violations.":[166],"The":[167],"evidence":[168],"separates":[169],"screening":[171],"enforcement":[174],"without":[175],"claiming":[176],"formal":[177],"safety,":[178],"lifecycle-optimal":[179],"aging,":[180],"or":[181],"RL":[182],"dominance.":[183]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-23T00:00:00"}