{"id":"https://openalex.org/W7155406392","doi":"https://doi.org/10.31449/inf.v50i11.12252","title":"Hierarchical Multi-Agent Deep Reinforcement Learning for Coordinated Optimization of Aggregated Virtual Power Plants in Smart Microgrids","display_name":"Hierarchical Multi-Agent Deep Reinforcement Learning for Coordinated Optimization of Aggregated Virtual Power Plants in Smart Microgrids","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155406392","doi":"https://doi.org/10.31449/inf.v50i11.12252"},"language":null,"primary_location":{"id":"doi:10.31449/inf.v50i11.12252","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i11.12252","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/12252/6655","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/12252/6655","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134403657","display_name":"Junxiong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092267","display_name":"Guangdong Industry Technical College","ror":"https://ror.org/00dre6z66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092267"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junxiong Zhang","raw_affiliation_strings":["Anhui Technical College of Industry and Economy, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Technical College of Industry and Economy, China","institution_ids":["https://openalex.org/I4210092267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134380356","display_name":"Jiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I118987531","display_name":"Anhui Jianzhu University","ror":"https://ror.org/0108wjw08","country_code":"CN","type":"education","lineage":["https://openalex.org/I118987531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao Wang","raw_affiliation_strings":["Anhui Jianzhu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Jianzhu University, China","institution_ids":["https://openalex.org/I118987531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134373096","display_name":"Qihang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092267","display_name":"Guangdong Industry Technical College","ror":"https://ror.org/00dre6z66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092267"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihang Wang","raw_affiliation_strings":["Anhui Technical College of Industry and Economy, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Technical College of Industry and Economy, China","institution_ids":["https://openalex.org/I4210092267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134424032","display_name":"Qi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092267","display_name":"Guangdong Industry Technical College","ror":"https://ror.org/00dre6z66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092267"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhou","raw_affiliation_strings":["Anhui Technical College of Industry and Economy, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Technical College of Industry and Economy, China","institution_ids":["https://openalex.org/I4210092267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5134403657"],"corresponding_institution_ids":["https://openalex.org/I4210092267"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68842715,"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/T10454","display_name":"Optimal Power Flow Distribution","score":0.569599986076355,"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/T10454","display_name":"Optimal Power Flow Distribution","score":0.569599986076355,"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":0.1370999962091446,"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":0.11460000276565552,"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/distributed-generation","display_name":"Distributed generation","score":0.5058000087738037},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5026000142097473},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.44940000772476196},{"id":"https://openalex.org/keywords/virtual-power-plant","display_name":"Virtual power plant","score":0.4041000008583069},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.35740000009536743},{"id":"https://openalex.org/keywords/electric-power-system","display_name":"Electric power system","score":0.350600004196167},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.3456000089645386},{"id":"https://openalex.org/keywords/power-flow","display_name":"Power flow","score":0.3343000113964081},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794000267982483},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5631999969482422},{"id":"https://openalex.org/C544738498","wikidata":"https://www.wikidata.org/wiki/Q861135","display_name":"Distributed generation","level":3,"score":0.5058000087738037},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C2776033628","wikidata":"https://www.wikidata.org/wiki/Q785102","display_name":"Virtual power plant","level":4,"score":0.4041000008583069},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2986056383","wikidata":"https://www.wikidata.org/wiki/Q556030","display_name":"Power flow","level":4,"score":0.3343000113964081},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2779438525","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Demand response","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C2776854237","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information sharing","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C10558101","wikidata":"https://www.wikidata.org/wiki/Q689855","display_name":"Smart grid","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C188573790","wikidata":"https://www.wikidata.org/wiki/Q12705","display_name":"Renewable energy","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C73916439","wikidata":"https://www.wikidata.org/wiki/Q837718","display_name":"Energy storage","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31449/inf.v50i11.12252","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i11.12252","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/12252/6655","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.v50i11.12252","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i11.12252","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/12252/6655","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":0.7733263373374939,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155406392.pdf","grobid_xml":"https://content.openalex.org/works/W7155406392.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Computational":[0],"efficiency,":[1],"Data":[2],"privacy,":[3],"and":[4,97,126,141,149,164,199,218,229,266],"equitable":[5],"benefit":[6],"assessment":[7],"are":[8,247],"some":[9],"of":[10,19,23,35,53,92,151],"the":[11,20,33,50,82,90,108,157,167,180,189,254,258],"issues":[12],"that":[13,46,246,257],"have":[14,29],"arisen":[15],"as":[16],"a":[17,41,113,133,262],"result":[18],"fast":[21],"expansion":[22],"distributed":[24,162,250],"energy":[25,251],"resources":[26,252],"(DERs),":[27,253],"which":[28,131],"added":[30],"complexity":[31],"to":[32,71,85,111,156,186],"functioning":[34],"distribution":[36,183,244],"networks.":[37],"This":[38],"paper":[39],"presents":[40],"two-tiered":[42],"VPP":[43,134,271],"coordination":[44],"architecture":[45,104],"takes":[47],"into":[48,107],"account":[49],"operational":[51,232],"interests":[52],"both":[54],"Distribution":[55],"System":[56],"Operators":[57],"(DSOs)":[58],"or":[59,94],"VPPs":[60],"under":[61],"AC":[62],"optimum":[63,136],"power":[64],"flow":[65],"(AC-OPF)":[66],"limitations.":[67],"The":[68],"goal":[69],"is":[70,79,105,236],"solve":[72],"these":[73],"challenges.":[74],"A":[75],"penalty-function-enhanced":[76],"OPF":[77],"mechanism":[78],"used":[80],"in":[81,89,144,175,249],"upper":[83],"layer":[84,110],"guarantee":[86],"network":[87,213],"security":[88],"event":[91],"voltage":[93,209],"branch-limit":[95],"violations,":[96],"an":[98],"Asynchronous":[99],"Advantage":[100],"Actor-Critic":[101],"(A3C)":[102],"multi-agent":[103],"integrated":[106],"lower":[109],"utilize":[112],"parameter-sharing":[114],"Twin-Delayed":[115],"Deep":[116],"Deterministic":[117],"Policy":[118],"Gradient":[119],"(PS-TD3)":[120],"algorithm.":[121],"Through":[122],"lightweight":[123],"parameter":[124,187],"sharing":[125],"decentralized":[127],"execution,":[128],"every":[129],"agent\u2014":[130],"represents":[132],"subsystem\u2014learns":[135],"judgments":[137],"for":[138,269],"energy-dispatch,":[139],"storage,":[140],"flexibility,":[142],"resulting":[143],"dramatically":[145],"reduced":[146],"computational":[147],"cost":[148,220],"preservation":[150],"data":[152],"privacy.":[153],"When":[154],"compared":[155],"non-cooperative":[158],"TD3":[159],"baseline,":[160],"traditional":[161],"OPF,":[163],"independent":[165],"Q-learning,":[166],"suggested":[168,259],"dual-layer":[169],"MARL":[170],"approach":[171,268],"outperforms":[172],"all":[173],"three":[174],"simulation":[176],"tests":[177],"conducted":[178],"on":[179],"IEEE":[181],"33-node":[182],"network.":[184],"Thanks":[185],"sharing,":[188],"PS-TD3":[190],"+":[191],"A3C":[192],"hybrid":[193],"improves":[194],"convergence":[195],"speed":[196],"through":[197],"42%":[198],"reduces":[200,208],"per-step":[201],"computing":[202],"time":[203],"by":[204,211,216,221,238],"37%.":[205],"It":[206],"also":[207],"variation":[210],"31.4%,":[212],"real-power":[214],"losses":[215],"26.7%,":[217],"operating":[219],"18.2%.":[222],"Since":[223],"agents":[224],"only":[225],"share":[226],"compressed":[227],"gradients":[228],"not":[230],"raw":[231],"data,":[233],"privacy":[234],"leakage":[235],"minimized":[237],"more":[239],"than":[240],"80%.":[241],"In":[242],"contemporary":[243],"systems":[245],"rich":[248],"findings":[255],"show":[256],"framework":[260],"provides":[261],"computationally":[263],"efficient,":[264],"scalable,":[265],"privacy-preserving":[267],"coordinated":[270],"operation.":[272]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-04-24T00:00:00"}
