{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T16:35:05Z","timestamp":1766507705916,"version":"3.48.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Manipal Academy of Higher Education, Manipal"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>With the explosion of diverse mobile applications, there are many critical issues to be solved in achieving the Quality of Experience (QoE) oriented and resource-efficient task offloading in container based Mobile Edge Computing (MEC) environments. In modern computing, users are all too frequently left behind the curve by incomplete computing techniques. As such, the aim of this study is to present a new framework that can overcome the limitations with current systems. Thus, this work, proposes a model-based machine teaching approach in the context of Federated Deep Reinforcement Learning (FDRL) to facilitate intelligent, adaptive and secure task offloading for heterogeneous edge nodes. With this design, an extensive optimization approach is embedded in containerized MEC systems to strike a balance between latency, energy and service disruption. This lightweight model enables Knowledge Distillation (KD) and efficient offloading of a task to devices with limited resources, without the need for full retraining. Because this is federated and using KD the framework provides a more advanced model to perform offloading in intricate and dynamic settings. Furthermore, the paper shows that this approach to offloading allows secure federated updates, making them efficient in both communication terms and in terms of bandwidth usage. In this way the time for convergence is greatly reduced. There is evidence to show that the framework incorporating FDRL with KD as presented in the paper can be found to be 20 percent higher in QoE, has an average task completion delay of 42 percent less, and 43 percent reduction for energy consumption per task compared with traditional methods. These are the results the paper found and thus underscore framework's correctness for high-performance, next-generation edge intelligence in mobile computing systems.<\/jats:p>","DOI":"10.1007\/s44163-025-00606-0","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T14:32:50Z","timestamp":1766500370000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Federated deep reinforcement learning with knowledge distillation for QoE-aware task offloading in containerized MEC"],"prefix":"10.1007","volume":"5","author":[{"given":"V. K.","family":"Vishwanath","sequence":"first","affiliation":[]},{"given":"A. B.","family":"Rajendra","sequence":"additional","affiliation":[]},{"given":"H. L.","family":"Gururaj","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,23]]},"reference":[{"issue":"5","key":"606_CR1","doi-asserted-by":"publisher","first-page":"2795","DOI":"10.1109\/TNET.2015.2487344","volume":"24","author":"X Chen","year":"2016","unstructured":"Chen X, Jiao L, Li W, Fu X. Efficient multi-user computation offloading for mobile-edge cloud computing. IEEE ACM Trans Netw. 2016;24(5):2795\u2013808.","journal-title":"IEEE ACM Trans Netw"},{"issue":"12","key":"606_CR2","doi-asserted-by":"publisher","first-page":"3590","DOI":"10.1109\/JSAC.2016.2611964","volume":"34","author":"Y Mao","year":"2016","unstructured":"Mao Y, Zhang J, Letaief KB. Dynamic computation offloading for mobile-edge computing with energy harvesting devices. IEEE J Sel Areas Commun. 2016;34(12):3590\u2013605.","journal-title":"IEEE J Sel Areas Commun"},{"issue":"2","key":"606_CR3","first-page":"89","volume":"1","author":"S Sardellitti","year":"2015","unstructured":"Sardellitti S, Scutari G, Barbarossa S. Joint optimization of radio and computational resources for multicell mobile-edge computing. IEEE Trans Signal Inf Process Netw. 2015;1(2):89\u2013103.","journal-title":"IEEE Trans Signal Inf Process Netw"},{"key":"606_CR4","first-page":"39611","volume":"6","author":"D Wu","year":"2018","unstructured":"Wu D, Wang W, Wang D. Multi-objective optimization for computation offloading in mobile-edge computing. IEEE Access. 2018;6:39611\u201324.","journal-title":"IEEE Access"},{"issue":"3","key":"606_CR5","doi-asserted-by":"publisher","first-page":"3424","DOI":"10.1109\/TVT.2020.2968343","volume":"69","author":"Q Fan","year":"2020","unstructured":"Fan Q, Ansari N, Sun X. Energy driven offloading and resource allocation for mobile edge computing. IEEE Trans Veh Technol. 2020;69(3):3424\u201337.","journal-title":"IEEE Trans Veh Technol"},{"issue":"11","key":"606_CR6","doi-asserted-by":"crossref","first-page":"5636","DOI":"10.1109\/TCOMM.2018.2848910","volume":"66","author":"H Wang","year":"2018","unstructured":"Wang H, Li Y, Jin D, Chen S. Deep reinforcement learning for dynamic mobile edge caching and computing in ultra dense networks. IEEE Trans Commun. 2018;66(11):5636\u201349.","journal-title":"IEEE Trans Commun"},{"key":"606_CR7","first-page":"20520","volume":"5","author":"M Chen","year":"2017","unstructured":"Chen M, Hao Y, Hu L, Hossain MS, Ghoneim A. Edge-cooperative caching for mobile edge computing systems with virtualization. IEEE Access. 2017;5:20520\u201333.","journal-title":"IEEE Access"},{"key":"606_CR8","unstructured":"Xu J, Chen L, Zhou P. A deep reinforcement learning based offloading decision model for edge computing. In: IEEE ICC; 2018, pp. 1\u20136."},{"issue":"8","key":"606_CR9","doi-asserted-by":"crossref","first-page":"5115","DOI":"10.1109\/TWC.2021.3065748","volume":"20","author":"Y Li","year":"2021","unstructured":"Li Y, Shi Y, Letaief KB. Learning and adapting to non-stationarity in distributed federated learning for edge intelligence. IEEE Trans Wireless Commun. 2021;20(8):5115\u201328.","journal-title":"IEEE Trans Wireless Commun"},{"issue":"4","key":"606_CR10","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MPRV.2009.82","volume":"8","author":"M Satyanarayanan","year":"2009","unstructured":"Satyanarayanan M, Bahl P, Caceres R, Davies N. The case for VM-based cloudlets in mobile computing. IEEE Pervas Comput. 2009;8(4):14\u201323.","journal-title":"IEEE Pervas Comput"},{"issue":"10","key":"606_CR11","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/JPROC.2018.2867029","volume":"106","author":"M Bennis","year":"2018","unstructured":"Bennis M, Debbah M, Poor HV. Ultrareliable and low-latency wireless communication: tail, risk, and scale. Proc IEEE. 2018;106(10):1834\u201353.","journal-title":"Proc IEEE"},{"key":"606_CR12","unstructured":"Wang H, Liu A, Gomes PH. Federated learning with personalization layers for edge-assisted collaborative computing systems. IEEE Trans Network Sci Eng. 2022."},{"key":"606_CR13","doi-asserted-by":"crossref","unstructured":"Nishio T, Yonetani R. Client selection for federated learning with heterogeneous resources in mobile edge. In: IEEE ICC; 2019. pp. 1\u20137.","DOI":"10.1109\/ICC.2019.8761315"},{"issue":"18","key":"606_CR14","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1002\/wcm.1203","volume":"13","author":"HT Dinh","year":"2013","unstructured":"Dinh HT, Lee C, Niyato D, Wang P. A survey of mobile cloud computing: architecture, applications, and approaches. Wirel Commun Mob Comput. 2013;13(18):1587\u2013611.","journal-title":"Wirel Commun Mob Comput"},{"issue":"no. 8","key":"606_CR15","first-page":"6954","volume":"7","author":"Y Kang","year":"2020","unstructured":"Kang Y, Xie J, Sun L. Collaborative learning for privacy-preserving and efficient edge computing: a survey. IEEE Internet Things J. 2020;7(8):6954\u201370.","journal-title":"IEEE Internet Things J"},{"key":"606_CR16","unstructured":"Zhao Y, Li M, Gong W, Liu W. Resource allocation and offloading optimization in mobile edge computing with deep reinforcement learning. In: IEEE GLOBECOM; 2018. pp. 1\u20136."},{"issue":"10","key":"606_CR17","first-page":"4268","volume":"64","author":"Y Wang","year":"2016","unstructured":"Wang Y, Sheng M, Wang X, Wang L, Li J. Mobile-edge computing: partial computation offloading using dynamic voltage scaling. IEEE Trans Commun. 2016;64(10):4268\u201382.","journal-title":"IEEE Trans Commun"},{"issue":"1","key":"606_CR18","first-page":"1","volume":"2","author":"AS Avestimehr","year":"2023","unstructured":"Avestimehr AS, Zhu S, Diggavi S. Communication-efficient federated learning: a comprehensive survey. IEEE Trans Mach Learn Commun Netw. 2023;2(1):1\u201320.","journal-title":"IEEE Trans Mach Learn Commun Netw"},{"key":"606_CR19","unstructured":"Bousselmi A, Gharbaoui M, Merghem-Boulahia L. Knowledge distillation: a survey. arXiv:2206.02572, 2022."},{"issue":"1","key":"606_CR20","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MNET.2018.1700202","volume":"32","author":"H Li","year":"2018","unstructured":"Li H, Ota K, Dong M. Learning IoT in edge: deep learning for the internet of things with edge computing. IEEE Netw. 2018;32(1):96\u2013101.","journal-title":"IEEE Netw"},{"key":"606_CR21","first-page":"101902","volume":"8","author":"Y Zhang","year":"2020","unstructured":"Zhang Y, Liu C, Peng J. Energy-efficient task offloading in mobile edge computing using transfer reinforcement learning. IEEE Access. 2020;8:101902\u201311.","journal-title":"IEEE Access"},{"key":"606_CR22","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1016\/j.future.2017.07.058","volume":"96","author":"S Wang","year":"2019","unstructured":"Wang S, Wang Y, Zhang X. Adaptive offloading strategy in edge computing with deep reinforcement learning. Futur Gener Comput Syst. 2019;96:410\u20137.","journal-title":"Futur Gener Comput Syst"},{"issue":"5","key":"606_CR23","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/MC.2016.145","volume":"49","author":"W Shi","year":"2016","unstructured":"Shi W, Dustdar S. The promise of edge computing. Computer. 2016;49(5):78\u201381.","journal-title":"Computer"},{"issue":"2","key":"606_CR24","first-page":"1","volume":"55","author":"T Lan","year":"2023","unstructured":"Lan T, Liu R, Li Y, Ren Y. Knowledge distillation for neural network compression: a survey. ACM Comput Surv. 2023;55(2):1\u201332.","journal-title":"ACM Comput Surv"},{"key":"606_CR25","volume":"105","author":"F Ramezani","year":"2020","unstructured":"Ramezani F, Safari A, Javadi B. Container-based cloud resource management: a survey. J Syst Architect. 2020;105:101684.","journal-title":"J Syst Architect"},{"key":"606_CR26","first-page":"89","volume":"124","author":"M Khoshkholghi","year":"2018","unstructured":"Khoshkholghi M, Naji HR, Goudarzi H. Energy-aware container placement for data-intensive applications in cloud data centers. J Netw Comput Appl. 2018;124:89\u2013101.","journal-title":"J Netw Comput Appl"},{"key":"606_CR27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3416300","author":"G Sun","year":"2024","unstructured":"Sun G, Wang Z, Su H, Yu H, Lei B, Guizani M. Profit maximization of independent task offloading in MEC-enabled 5G internet of vehicles. IEEE Trans Intell Transp Syst. 2024. https:\/\/doi.org\/10.1109\/TITS.2024.3416300.","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"606_CR28","doi-asserted-by":"publisher","first-page":"111180","DOI":"10.1016\/j.comnet.2025.111180","volume":"240","author":"M Bilal","year":"2025","unstructured":"Bilal M, Rehman SU, Javed F, Hussain SA. Deep reinforcement learning and SQP-driven task offloading decisions in vehicular edge computing Networks. Comput Netw. 2025;240:111180. https:\/\/doi.org\/10.1016\/j.comnet.2025.111180.","journal-title":"Comput Netw"},{"key":"606_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-025-07009-z","author":"A Mustafa","year":"2025","unstructured":"Mustafa A, Ahmad H, Ullah R. Computation offloading in vehicular communications using PPO-based deep reinforcement learning. J Supercomput. 2025. https:\/\/doi.org\/10.1007\/s11227-025-07009-z.","journal-title":"J Supercomput"},{"key":"606_CR30","doi-asserted-by":"publisher","first-page":"10674878","DOI":"10.1155\/2023\/10674878","volume":"2023","author":"H Guo","year":"2023","unstructured":"Guo H, Zhang Y, Wang L. Computing offloading based on TD3 algorithm in cache-enabled MEC. Wirel Commun Mob Comput. 2023;2023:10674878. https:\/\/doi.org\/10.1155\/2023\/10674878.","journal-title":"Wirel Commun Mob Comput"},{"key":"606_CR31","doi-asserted-by":"crossref","unstructured":"Wang S, Tuor T, Salonidis T, Leung KK, Makaya C, He T, Chan K. When edge meets learning: Adaptive control for resource-constrained distributed machine learning. In: IEEE INFOCOM; 2018. pp. 63\u201371.","DOI":"10.1109\/INFOCOM.2018.8486403"},{"key":"606_CR32","volume":"165","author":"L He","year":"2022","unstructured":"He L, Ren Z, Wang J. A survey on federated learning and its applications for accelerating industrial artificial intelligence. Comput Ind Eng. 2022;165:107936.","journal-title":"Comput Ind Eng"},{"key":"606_CR33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2020.09.009","volume":"420","author":"Y Cheng","year":"2021","unstructured":"Cheng Y, Wang D, Zhou P, Zhang T. A survey of model compression and acceleration for deep neural networks. Neurocomputing. 2021;420:1\u201324.","journal-title":"Neurocomputing"},{"key":"606_CR34","unstructured":"Yang S, Guo Y, Liu Y. Task offloading in edge computing: review, challenges and new developments. Future Internet. 2021;13(2)."},{"key":"606_CR35","unstructured":"Abadi M et al. TensorFlow: a system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16). 2016. pp. 265\u201383."},{"key":"606_CR36","unstructured":"Deng L, Yu D, Platt J. Scalable deep learning on distributed GPUs with a GPU cluster for speech recognition. In: Interspeech. 2014."}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00606-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-025-00606-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00606-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T14:32:54Z","timestamp":1766500374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-025-00606-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,23]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["606"],"URL":"https:\/\/doi.org\/10.1007\/s44163-025-00606-0","relation":{},"ISSN":["2731-0809"],"issn-type":[{"type":"electronic","value":"2731-0809"}],"subject":[],"published":{"date-parts":[[2025,12,23]]},"assertion":[{"value":"7 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"393"}}