{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:43:12Z","timestamp":1776836592011,"version":"3.51.2"},"reference-count":38,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2019,3,24]],"date-time":"2019-03-24T00:00:00Z","timestamp":1553385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61502428, 61572440"],"award-info":[{"award-number":["61502428, 61572440"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY19F020033,LR16F010003"],"award-info":[{"award-number":["LY19F020033,LR16F010003"]}]},{"name":"Young Talent Cultivation Project of Zhejiang Association for Science and Technology","award":["2016YCGC011"],"award-info":[{"award-number":["2016YCGC011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper studies mobile edge computing (MEC) networks where multiple wireless devices (WDs) offload their computation tasks to multiple edge servers and one cloud server. Considering different real-time computation tasks at different WDs, every task is decided to be processed locally at its WD or to be offloaded to and processed at one of the edge servers or the cloud server. In this paper, we investigate low-complexity computation offloading policies to guarantee quality of service of the MEC network and to minimize WDs\u2019 energy consumption. Specifically, both a linear programing relaxation-based (LR-based) algorithm and a distributed deep learning-based offloading (DDLO) algorithm are independently studied for MEC networks. We further propose a heterogeneous DDLO to achieve better convergence performance than DDLO. Extensive numerical results show that the DDLO algorithms guarantee better performance than the LR-based algorithm. Furthermore, the DDLO algorithm generates an offloading decision in less than 1 millisecond, which is several orders faster than the LR-based algorithm.<\/jats:p>","DOI":"10.3390\/s19061446","type":"journal-article","created":{"date-parts":[[2019,3,25]],"date-time":"2019-03-25T06:56:52Z","timestamp":1553497012000},"page":"1446","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":109,"title":["Multi-Server Multi-User Multi-Task Computation Offloading for Mobile Edge Computing Networks"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6924-4466","authenticated-orcid":false,"given":"Liang","family":"Huang","sequence":"first","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China"}]},{"given":"Xu","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China"}]},{"given":"Luxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6210-2617","authenticated-orcid":false,"given":"Liping","family":"Qian","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2777-7915","authenticated-orcid":false,"given":"Yuan","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China"}]}],"member":"1968","published-online":{"date-parts":[[2019,3,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1561\/1100000049","article-title":"A survey of augmented reality","volume":"8","author":"Billinghurst","year":"2015","journal-title":"Found. Trends Hum. Interact."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1109\/COMST.2016.2611524","article-title":"A comparative survey of VANET clustering techniques","volume":"19","author":"Cooper","year":"2017","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"7605","DOI":"10.1109\/ACCESS.2016.2590500","article-title":"A Survey on Cloud Gaming: Future of Computer Games","volume":"4","author":"Cai","year":"2016","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/SURV.2013.050113.00090","article-title":"Heterogeneity in Mobile Cloud Computing: Taxonomy and Open Challenges","volume":"16","author":"Sanaei","year":"2014","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"12244","DOI":"10.1109\/TVT.2018.2875337","article-title":"NOMA-Assisted Multi-Access Mobile Edge Computing: A Joint Optimization of Computation Offloading and Time Allocation","volume":"67","author":"Wu","year":"2018","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"5567","DOI":"10.1109\/TWC.2017.2664832","article-title":"Joint uplink base station association and power control for small-cell networks with non-orthogonal multiple access","volume":"16","author":"Qian","year":"2017","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Qian, L.P., Feng, A., Huang, Y., Wu, Y., Ji, B., and Shi, Z. (2018). Optimal SIC Ordering and Computation Resource Allocation in MEC-aware NOMA NB-IoT Networks. IEEE Internet Things J.","DOI":"10.1109\/JIOT.2018.2875046"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1671","DOI":"10.1109\/JIOT.2017.2689777","article-title":"Minimization of transmission completion time in wireless powered communication networks","volume":"4","author":"Chi","year":"2017","journal-title":"IEEE Internet Things J."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2591","DOI":"10.1109\/TMC.2018.2812722","article-title":"Optimal Power Allocation and Scheduling for Non-Orthogonal Multiple Access Relay-Assisted Networks","volume":"17","author":"Wu","year":"2018","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.1109\/TII.2017.2777846","article-title":"Collaborative Energy and Information Transfer in Green Wireless Sensor Networks for Smart Cities","volume":"14","author":"Lu","year":"2018","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1109\/TII.2017.2780116","article-title":"Adaptive Scheduling in Energy Harvesting Sensor Networks for Green Cities","volume":"14","author":"Huang","year":"2018","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liu, F., Huang, Z., and Wang, L. (2019). Energy-Efficient Collaborative Task Computation Offloading in Cloud-Assisted Edge Computing for IoT Sensors. Sensors, 19.","DOI":"10.3390\/s19051105"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1109\/MNET.2018.1700096","article-title":"On the Fundamental Characteristics of Ultra-Dense Small Cell Networks","volume":"32","author":"Ding","year":"2018","journal-title":"IEEE Netw."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4177","DOI":"10.1109\/TWC.2018.2821664","article-title":"Computation Rate Maximization for Wireless Powered Mobile-Edge Computing with Binary Computation Offloading","volume":"17","author":"Bi","year":"2018","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Guo, S., Xiao, B., Yang, Y., and Yang, Y. (2016, January 10\u201314). Energy-efficient dynamic offloading and resource scheduling in mobile cloud computing. Proceedings of the IEEE International Conference on Computer Communications (INFOCOM), San Francisco, CA, USA.","DOI":"10.1109\/INFOCOM.2016.7524497"},{"key":"ref_16","first-page":"3571","article-title":"Offloading in Mobile Edge Computing: Task Allocation and Computational Frequency Scaling","volume":"65","author":"Dinh","year":"2017","journal-title":"IEEE Trans. Commun."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sharma, A.R., and Kaushik, P. (2017, January 5\u20136). Literature survey of statistical, deep and reinforcement learning in natural language processing. Proceedings of the 2017 International Conference on Computing, Communication and Automation (ICCCA), Greater Noida, India.","DOI":"10.1109\/CCAA.2017.8229841"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Phaniteja, S., Dewangan, P., Guhan, P., Sarkar, A., and Krishna, K.M. (2017, January 5\u20138). A deep reinforcement learning approach for dynamically stable inverse kinematics of humanoid robots. Proceedings of the 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), Macau, China.","DOI":"10.1109\/ROBIO.2017.8324682"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/MCOM.2017.1700246","article-title":"Software-defined networks with mobile edge computing and caching for smart cities: A big data deep reinforcement learning approach","volume":"55","author":"He","year":"2017","journal-title":"IEEE Commun. Mag."},{"key":"ref_21","unstructured":"Min, M., Xu, D., Xiao, L., Tang, Y., and Wu, D. (arXiv, 2017). Learning-Based Computation Offloading for IoT Devices with Energy Harvesting, arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhang, H., Wu, C., Mao, S., Ji, Y., and Bennis, M. (arXiv, 2018). Performance Optimization in Mobile-Edge Computing via Deep Reinforcement Learning, arXiv.","DOI":"10.1109\/VTCFall.2018.8690980"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Huang, L., Feng, X., Feng, A., Huang, Y., and Qian, L.P. (2018). Distributed Deep Learning-based Offloading for Mobile Edge Computing Networks. Mobile Netw. Appl.","DOI":"10.1007\/s11036-018-1177-x"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wei, X., Wang, S., Zhou, A., Xu, J., Su, S., Kumar, S., and Yang, F. (2017, January 25\u201330). MVR: An Architecture for Computation Offloading in Mobile Edge Computing. Proceedings of the 2017 IEEE International Conference on Edge Computing (EDGE), Honolulu, HI, USA.","DOI":"10.1109\/IEEE.EDGE.2017.42"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1109\/JSAC.2016.2545382","article-title":"Energy Efficient Mobile Cloud Computing Powered by Wireless Energy Transfer","volume":"34","author":"You","year":"2016","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4738","DOI":"10.1109\/TVT.2014.2372852","article-title":"Optimization of Radio and Computational Resources for Energy Efficiency in Latency-Constrained Application Offloading","volume":"64","author":"Vidal","year":"2015","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_27","unstructured":"Huang, L., Bi, S., and Zhang, Y.A. (arXiv, 2018). Deep Reinforcement Learning for Online Offloading in Wireless Powered Mobile-Edge Computing Networks, arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2795","DOI":"10.1109\/TNET.2015.2487344","article-title":"Efficient Multi-User Computation Offloading for Mobile-Edge Cloud Computing","volume":"24","author":"Chen","year":"2016","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_29","first-page":"4268","article-title":"Mobile-Edge Computing: Partial Computation Offloading Using Dynamic Voltage Scaling","volume":"64","author":"Wang","year":"2016","journal-title":"IEEE Trans. Commun."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Dinh, T.Q., La, Q.D., Quek, T.Q.S., and Shin, H. (2018). Distributed Learning for Computation Offloading in Mobile Edge Computing. IEEE Trans. Commun., 1.","DOI":"10.1109\/TCOMM.2018.2866572"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, M., Liang, B., and Dong, M. (2017, January 1\u20134). Joint offloading and resource allocation for computation and communication in mobile cloud with computing access point. Proceedings of the IEEE INfocom 2017\u2014IEEE Conference on Computer Communications, Atlanta, GA, USA.","DOI":"10.1109\/INFOCOM.2017.8057150"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"13092","DOI":"10.1109\/ACCESS.2019.2893118","article-title":"Energy-Aware Mobile Edge Computation Offloading for IoT Over Heterogenous Networks","volume":"7","author":"Li","year":"2019","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1397","DOI":"10.1109\/TWC.2016.2633522","article-title":"Energy-Efficient Resource Allocation for Mobile-Edge Computation Offloading","volume":"16","author":"You","year":"2017","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1109\/TPDS.2013.67","article-title":"A stochastic model to investigate data center performance and QoS in IaaS cloud computing systems","volume":"25","author":"Bruneo","year":"2014","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_35","unstructured":"Miettinen, A.P., and Nurminen, J.K. (2010, January 22\u201325). Energy efficiency of mobile clients in cloud computing. Proceedings of the 2nd USENIX Conference HotCloud, Boston, MA, USA."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.future.2018.02.042","article-title":"Power-aware performance analysis of self-adaptive resource management in IaaS clouds","volume":"86","author":"Ataie","year":"2018","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_37","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, MIT Press."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3990","DOI":"10.1109\/TCOMM.2013.071813.130105","article-title":"Wireless Information and Power Transfer: A Dynamic Power Splitting Approach","volume":"61","author":"Liu","year":"2013","journal-title":"IEEE Trans. Commun."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/6\/1446\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:40:20Z","timestamp":1760186420000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/6\/1446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,24]]},"references-count":38,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2019,3]]}},"alternative-id":["s19061446"],"URL":"https:\/\/doi.org\/10.3390\/s19061446","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,24]]}}}