{"id":"https://openalex.org/W7155419595","doi":"https://doi.org/10.31449/inf.v50i11.9617","title":"Scalable Data Lake Architecture with Apache Spark for Predictive Maintenance and Optimization in Energy Storage Systems","display_name":"Scalable Data Lake Architecture with Apache Spark for Predictive Maintenance and Optimization in Energy Storage Systems","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155419595","doi":"https://doi.org/10.31449/inf.v50i11.9617"},"language":null,"primary_location":{"id":"doi:10.31449/inf.v50i11.9617","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i11.9617","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/9617/6641","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.informatica.si/index.php/informatica/article/download/9617/6641","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134413053","display_name":"Shaofeng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I74872605","display_name":"China Southern Power Grid (China)","ror":"https://ror.org/03hkh9419","country_code":"CN","type":"company","lineage":["https://openalex.org/I74872605"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofeng Yu","raw_affiliation_strings":["Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China","institution_ids":["https://openalex.org/I74872605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134412115","display_name":"Jianxu Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I74872605","display_name":"China Southern Power Grid (China)","ror":"https://ror.org/03hkh9419","country_code":"CN","type":"company","lineage":["https://openalex.org/I74872605"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxu Zhong","raw_affiliation_strings":["Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China","institution_ids":["https://openalex.org/I74872605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134377982","display_name":"Xin Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I74872605","display_name":"China Southern Power Grid (China)","ror":"https://ror.org/03hkh9419","country_code":"CN","type":"company","lineage":["https://openalex.org/I74872605"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yan","raw_affiliation_strings":["Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China","institution_ids":["https://openalex.org/I74872605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031843709","display_name":"Jinpeng You","orcid":null},"institutions":[{"id":"https://openalex.org/I74872605","display_name":"China Southern Power Grid (China)","ror":"https://ror.org/03hkh9419","country_code":"CN","type":"company","lineage":["https://openalex.org/I74872605"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinpeng You","raw_affiliation_strings":["Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China","institution_ids":["https://openalex.org/I74872605"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053376510","display_name":"Zehan Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I74872605","display_name":"China Southern Power Grid (China)","ror":"https://ror.org/03hkh9419","country_code":"CN","type":"company","lineage":["https://openalex.org/I74872605"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehan Cai","raw_affiliation_strings":["Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Communication Branch of China Southern Power Grid Energy Storage Co., Ltd, Guangzhou Guangdong, 511400, China","institution_ids":["https://openalex.org/I74872605"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74872605"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52780667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.6306999921798706,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.6306999921798706,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.04910000041127205,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.035999998450279236,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.758400022983551},{"id":"https://openalex.org/keywords/predictive-maintenance","display_name":"Predictive maintenance","score":0.5659000277519226},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.46369999647140503},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4636000096797943},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.44760000705718994},{"id":"https://openalex.org/keywords/distributed-data-store","display_name":"Distributed data store","score":0.4327999949455261},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4171999990940094},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.38760000467300415},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.3758000135421753}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.758400022983551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7197999954223633},{"id":"https://openalex.org/C70452415","wikidata":"https://www.wikidata.org/wiki/Q3182448","display_name":"Predictive maintenance","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5297999978065491},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4636000096797943},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C73916439","wikidata":"https://www.wikidata.org/wiki/Q837718","display_name":"Energy storage","level":3,"score":0.36970001459121704},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3158999979496002},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C7817414","wikidata":"https://www.wikidata.org/wiki/Q1779504","display_name":"Energy management","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C23725684","wikidata":"https://www.wikidata.org/wiki/Q616377","display_name":"Maintenance engineering","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C65813073","wikidata":"https://www.wikidata.org/wiki/Q1622420","display_name":"High availability","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C2778820799","wikidata":"https://www.wikidata.org/wiki/Q3454688","display_name":"Cost reduction","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31449/inf.v50i11.9617","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i11.9617","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/9617/6641","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.31449/inf.v50i11.9617","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i11.9617","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/9617/6641","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8995270729064941,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155419595.pdf","grobid_xml":"https://content.openalex.org/works/W7155419595.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,84,177],"fast":[1],"development":[2],"of":[3,97,192],"energy":[4,34,91,148],"storage":[5,92,160],"power":[6,93],"stations":[7],"in":[8,14,45,136,140,153],"current":[9],"smart":[10],"grids":[11],"has":[12],"resulted":[13],"massive":[15],"and":[16,23,32,42,51,77,109,112,119,155,158,165,174,182,195,201],"complicated":[17],"datasets":[18,129],"that":[19,71],"require":[20],"effective":[21],"management":[22],"analysis":[24],"to":[25,198],"maintain":[26],"battery":[27],"performance,":[28],"optimize":[29],"maintenance":[30,117,145],"schedules,":[31],"reduce":[33],"expenditures.":[35],"Existing":[36],"centralized":[37,74],"systems":[38],"suffer":[39],"with":[40],"scalability":[41,181],"latency,":[43],"resulting":[44,135],"delayed":[46],"analysis,":[47,111],"lower":[48],"prediction":[49],"accuracy,":[50,146],"ineffective":[52],"pricing":[53],"schemes.":[54],"This":[55],"study":[56],"presents":[57],"DCDL-ESM":[58],"(Distributed":[59],"Computing":[60],"over":[61,100],"Data":[62],"Lake":[63],"for":[64,116,170,189],"Energy":[65],"Storage":[66],"Management),":[67],"a":[68,73,137],"scalable":[69],"architecture":[70],"combines":[72],"data":[75,88,106],"lake":[76],"an":[78],"Apache":[79],"Spark-based":[80],"distributed":[81,104],"computing":[82,197],"framework.":[83],"system":[85],"collects":[86],"raw":[87],"from":[89],"100":[90],"plants":[94],"(a":[95],"total":[96],"2.8":[98],"TB":[99],"12":[101],"months),":[102],"performs":[103],"preprocessing,":[105],"purification,":[107],"normalization,":[108],"trend":[110],"uses":[113],"predictive":[114,144],"modeling":[115],"scheduling":[118],"charge":[120],"optimization.":[121],"Validation":[122],"was":[123],"carried":[124],"out":[125],"using":[126,172],"historical":[127],"operational":[128],"(80%":[130],"training,":[131],"20%":[132],"testing":[133],"split),":[134],"42%":[138],"reduction":[139],"processing":[141],"time,":[142],"91.3%":[143],"24.7%":[147],"cost":[149],"savings,":[150],"38%":[151],"improvement":[152],"CPU":[154],"memory":[156],"utilization,":[157],"31%":[159],"efficiency":[161],"gains":[162],"through":[163],"partitioning":[164],"compression.":[166],"Results":[167],"were":[168],"tested":[169],"robustness":[171],"cross-validation":[173],"bias":[175],"analysis.":[176],"suggested":[178],"solution":[179],"closes":[180],"performance":[183],"gaps":[184],"while":[185],"setting":[186],"the":[187],"framework":[188],"future":[190],"integration":[191],"real-time":[193],"analytics":[194],"edge":[196],"minimize":[199],"latency":[200],"support":[202],"autonomous":[203],"control.":[204]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-04-24T00:00:00"}
