{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T02:30:07Z","timestamp":1792463407467,"version":"4.5.0"},"reference-count":56,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Unmanned Aerial Vehicle (UAV) networks are increasingly deployed in dynamic environments where reliable and low\u2010latency communication is critical. However, high mobility, intermittent connectivity, spectrum limitations, and energy constraints make conventional static communication protocols inadequate for maintaining stable, dependable links. To address these challenges, this paper proposes TRC\u2010MAPPO, a topology\u2010aware reliability\u2010constrained multi\u2010agent deep reinforcement learning framework for adaptive UAV swarm communication. The routing problem is formulated as a constrained decision\u2010making task that jointly considers packet delivery reliability, end\u2010to\u2010end delay, link stability, bandwidth usage, and energy consumption. Unlike single\u2010agent DRL baselines, TRC\u2010MAPPO represents the swarm as a dynamic communication graph and combines local relay selection with centralized training, enabling cooperative routing decisions under time\u2010varying network conditions. Simulations are conducted in a controlled, dynamic UAV environment, with the same mobility and traffic settings used for all methods. The proposed framework is compared with DQN and PPO over different swarm densities. Results show that TRC\u2010MAPPO achieves a higher packet delivery ratio, lower end\u2010to\u2010end delay, and more efficient energy behaviour, particularly in dense deployments. These findings indicate that topology\u2010aware cooperative learning can provide a scalable and practical solution for reliable UAV communication in future intelligent aerial and 6G\u2010enabled networks.<\/jats:p>","DOI":"10.1111\/exsy.70368","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T08:13:27Z","timestamp":1784016807000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Intelligent\n                    <scp>DRL<\/scp>\n                    \u2010Based Framework for Reliable\n                    <scp>UAV<\/scp>\n                    Swarm Communications in Dynamic Environments"],"prefix":"10.1111","volume":"43","author":[{"given":"Vi Hoai","family":"Nam","sequence":"first","affiliation":[{"name":"Faculty of Information Technology Hung Yen University of Technology and Education  Hungyen Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4193-6062","authenticated-orcid":false,"given":"Abdellah","family":"Chehri","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science Royal Military College of Canada  Kingston Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0953-5047","authenticated-orcid":false,"given":"Weiwei","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering Beijing University of Posts and Telecommunications  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chu Thi Minh","family":"Hue","sequence":"additional","affiliation":[{"name":"Faculty of Software Engineering FPT University  Hanoi Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tan N.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Advanced Intelligent Technology Research Group, Faculty of Electrical and Electronics Engineering Ton Duc Thang University  Ho Chi Minh City Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0242-5606","authenticated-orcid":false,"given":"Vu Khanh","family":"Quy","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology Hung Yen University of Technology and Education  Hungyen Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MAES.2025.3577147"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70067"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2100889"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3631889"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3588162"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3331722"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3420697"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2025.3639171"},{"key":"e_1_2_13_10_1","unstructured":"Fujimoto S. H.vanHoof andD.Meger.2018.\u201cAddressing Function Approximation Error in Actor\u2010Critic Methods.\u201dhttps:\/\/arxiv.org\/abs\/1802.09477."},{"key":"e_1_2_13_11_1","first-page":"1","volume-title":"IEEE INFOCOM 2024\u2014IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","author":"Gao Y.","year":"2024"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3367624"},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3553442"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3438946"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3480248"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3434971"},{"key":"e_1_2_13_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3579780"},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3617646"},{"key":"e_1_2_13_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3644352"},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436723"},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.010.2300200"},{"key":"e_1_2_13_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3519722"},{"key":"e_1_2_13_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2023.3338368"},{"key":"e_1_2_13_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3427686"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3645407"},{"key":"e_1_2_13_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3494738"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70192"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3148364"},{"key":"e_1_2_13_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3547975"},{"key":"e_1_2_13_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3357086"},{"key":"e_1_2_13_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3217888"},{"key":"e_1_2_13_32_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13647"},{"key":"e_1_2_13_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2025.3579626"},{"key":"e_1_2_13_34_1","unstructured":"Schulman J. F.Wolski P.Dhariwal A.Radford andO.Klimov.2017.\u201cProximal Policy Optimization Algorithms.\u201dhttps:\/\/arxiv.org\/abs\/1707.06347."},{"key":"e_1_2_13_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2500209"},{"key":"e_1_2_13_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3432491"},{"key":"e_1_2_13_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSENS.2023.3307121"},{"key":"e_1_2_13_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70143"},{"key":"e_1_2_13_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.003.2400047"},{"key":"e_1_2_13_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2026.3668740"},{"key":"e_1_2_13_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAA64256.2024.00022"},{"key":"e_1_2_13_42_1","first-page":"2094","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Hasselt H.","year":"2016"},{"key":"e_1_2_13_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3170458"},{"key":"e_1_2_13_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3610631"},{"key":"e_1_2_13_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2300111"},{"key":"e_1_2_13_46_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70004"},{"key":"e_1_2_13_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3438854"},{"key":"e_1_2_13_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3370553"},{"key":"e_1_2_13_49_1","first-page":"1","volume-title":"2025 IEEE 101st Vehicular Technology Conference (VTC2025\u2010Spring)","author":"Yan M.","year":"2025"},{"key":"e_1_2_13_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3336535"},{"key":"e_1_2_13_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3146881"},{"key":"e_1_2_13_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2902559"},{"key":"e_1_2_13_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3628608"},{"key":"e_1_2_13_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3563426"},{"key":"e_1_2_13_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2400351"},{"key":"e_1_2_13_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3296613"},{"key":"e_1_2_13_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3581912"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70368","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70368","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T09:34:11Z","timestamp":1784194451000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70368"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"references-count":56,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1111\/exsy.70368"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70368","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"2026-03-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70368"}}