Distributed Weighted Data Aggregation Algorithm in End-to-Edge Communication Networks Based on Multi-armed Bandit

doi:10.11896/jsjkx.221100134

Abstract

Abstract: As a combination of edge computing and artificial intelligence,edge intelligence has become a promising technique and provided its users with a series of fast,precise,and customized services.In edge intelligence,when learning agents are deployed on the edge side,the data aggregation from the end side to the designated edge devices is an important research topic.Considering the various importance of end devices,this paper studies the weighted data aggregation problem in a single hop end-to-edge communication network.Firstly,to make sure all the end devices with various weights are fairly treated in data aggregation,a distributed end-to-edge cooperative scheme is proposed.Then,to handle the massive contention on the wireless channel caused by end devices,a multi-armed bandit (MAB) algorithm is designed to help the end devices find their most appropriate update rates.Diffe-rent from the traditional data aggregation works,combining the MAB enables our algorithm a higher efficiency in data aggregation.With a theoretical analysis,we show that the efficiency of our algorithm is asymptotically optimal.Comparative experiments with previous works are also conducted to show the strength of our algorithm.

Key words: Weighted data aggregation, End-to-edge communication, Multi-armed bandit, Edge intelligence

CLC Number:

TP393

Yifei ZOU, Senmao QI, Cong'an XU, Dongxiao YU. Distributed Weighted Data Aggregation Algorithm in End-to-Edge Communication Networks Based on Multi-armed Bandit[J].Computer Science, 2023, 50(2): 13-22.

References

[1]CAI Z,SHI T.Distributed Query Processing in the Edge Assisted IoT Data Monitoring System[J].IEEE Internet of Things Journal,2021,8(16):12679-12693.
[2]ZHU T,SHI T,LI J,et al.Task Scheduling in Deadline-Aware Mobile Edge Computing Systems[J].IEEE Internet of Things Journal,2019,6(3):4854-4866.
[3]YU L,SHEN H,CAI Z,et al.Towards Bandwidth Guaranteefor Virtual Clusters under Demand Uncertainty in Multi-tenant Clouds[J].IEEE Transactions on Parallel and Distributed Systems,2018,29(2):450-465.
[4]DENG S,ZHAO H,FANG W,et al.Edge intelligence:The confluence of edge computing and artificial intelligence[J].IEEE Internet of Things Journal,2020,7(8):7457-7469.
[5]KAUR M,MUNJAL A.Data aggregation algorithms for wireless sensor network:a review[J].Ad Hoc Networks,2020,100:102083.
[6]SUMALEE A,HO H W.Smarter and more connected:Futureintelligent transportation system[J].Iatss Research,2018,42(2):67-71.
[7]RANDHAWA S,JAIN S.Dahda:dynamic adaptive hierarchical data aggregation for clustered wireless sensor networks[J].Wireless Personal Communications,2017,97(4):6369-6399.
[8]GUPTA G P,MISRA M,GARG K.Towards scalable and load-balanced mobile agents-based data aggregation for wireless sensor networks[J].Computers & Electrical Engineering,2017,64:262-276.
[9]EL FISSAOUI M,BENI-HSSANE A,SAADI M.Mobile agent protocol-based energy aware data aggregation for wireless sensor networks[C]//Procedia computer science.2017:25-32.
[10][１０] LEI Y,QIN H,CHEN W,et al.Secure Data AggregationScheme Based on Dynamic Multi-cluster Key Management Mo-del[J].Computer Science,2011,38(9):36-40.
[11]YU D,ZOU Y,XU M,et al.Competitive age of information in dynamic iot networks[J].IEEE Internet of Things Journal,2020,8(20):15160-15169.
[12]YU D,ZOU Y,ZHANG Y,et al.An exact implementation of the abstract mac layer via carrier sensing in dynamic networks[J].IEEE/ACM Transactions on Networking,2021,29(3):994-1007.
[13]RICHA A,SCHEIDELER C,SCHMID S,et al.An efficient and fair mac protocol robust to reactive interference[J].IEEE/ACM Transactions on Networking,2012,21(3):760-771.
[14]XU H,HUANG L,ZHANG Y,et al.Energy-efficient cooperative data aggregation for wireless sensor networks[J].Journal of Parallel and Distributed Computing,2010,70(9):953-961.
[15]XIAO S,LI B,YUAN X.Maximizing precision for energy-efficient data aggregation in wireless sensor networks with lossy links[J].Ad Hoc Networks,2015,26:103-113.
[16]NIKNAM S,DHILLON H S,REED J H.Federated learning for wireless communications:Motivation,opportunities,and challenges[J].IEEE Communications Magazine,2020,58(6):46-51.
[17]LI F,YU D,YANG H,et al.Multi-armed-bandit-based spec-trum scheduling algorithms in wireless networks:A survey[J].IEEE Wireless Communications,2020,27(1):24-30.
[18]CHEN S,WANG X,ZHOU P,et al.Heterogeneous semi-asynchronous federated learning in internet of things:A multi-armed bandit approach[J].IEEE Transactions on Emerging Topics in Computational Intelligence,2022,6(5):1113-1124.
[19]XIA W,QUEK T Q,GUO K,et al.Multi-armed bandit-based client scheduling for federated learning[J].IEEE Transactions on Wireless Communications,2020,19(11):7108-7123.
[20]DHAND G,TYAGI S.Data aggregation techniques in wsn:Survey[J].Procedia Computer Science,2016,92:378-384.
[21]GHATE V V,VIJAYAKUMAR V.Machine learning for data aggregation in wsn:A survey[J].International Journal of Pure and Applied Mathematics,2018,118(24):1-12.
[22]DONG H,WEI S,LIU X,et al.A Survey of Routing Methods for Wireless Sensor Networks Oriented to Environment Awareness[J].Computer Science,2018,45(1):14-22.
[23]FENG H Y,ZHOU L,DING Q L.Data Aggregation Algorithm for Wireless Sensor Networks Based on Data Stream and Network Coding[J].Computer Science,2015,42(5):136-140.
[24]XU D,LI T,LI Y,et al.Edge intelligence:Architectures,challenges,and applications[J].arXiv:2003.12172,2020.
[25]ABBASI-DARESARI S,ABOUEI J.Toward cluster-basedweighted compressive data aggregation in wireless sensor networks[J].Ad Hoc Networks,2016,36:368-385.
[26]RAZZAQ M,KWON G R,SHIN S.Energy efficient dijkstra-based weighted sum minimization routing protocol for wsn[C]//2018 Third International Conference on Fog and Mobile Edge Computing(FMEC).IEEE,2018:246-251.
[27]ZHANG X,TAO L,YAN F,et al.Shortest-latency opportunistic routing in asynchronous wireless sensor networks with independent duty-cycling[J].IEEE Transactions on Mobile Computing,2019,19(3):711-723.
[28]YANG L,ZOU Y,XU M,et al.Distributedconsensus for blockchains in internet-of-things networks[J].Tsinghua Science and Technology,2022,27(5):817-831.
[29]ZOU Y,XU M,YU J,et al.A fast consensus forpermissioned wireless blockchains[J].IEEE Internet of Things Journal,2021.
[30]CHEN Y,SUN X,JIN Y.Communication-efficient federateddeeplearning with layerwise asynchronous model update and temporallyweighted aggregation[J].IEEE Transactions on Neural Networks Andlearning Systems,2019,31(10):4229-4238.
[31]MA Z,ZHAO M,CAI X,et al.Fast-convergent federated lear-ning with class-weighted aggregation[J].Journal of Systems Architecture,2021,117:102125-102131.
[32]ALEXANDRU A B,PAPPAS G J.Private weighted sum aggregationfor distributed control systems[J].IFAC-Papers OnLine,2020,53(2):11081-11088.
[33]ADACHI R,YAMASHITA Y,KOBAYASHI K.Distributedestimationbased on weighted data aggregation over delayed sensor networks[J].IFAC Journal of Systems and Control,2020,14:100109-100115.
[34]KULESHOV V,PRECUP D.Algorithms for multi-armed bandit problems[J].arXiv:1402.6028,2014.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!