Full Text:
<1438>
Summary: 
<357>
CLC number: TN929.5
On-line Access: 2024-08-27
Received: 2023-10-17
Revision Accepted: 2024-05-08
Crosschecked: 2023-09-14
Cited: 0
Clicked: 2158
Citations: Bibtex RefMan EndNote GB/T7714
A survey of energy-efficient strategies for federated learning in mobile edge computing
| ||||||||||||||
Abstract: With the booming development of fifth-generation network technology and Internet of Things, the number of end-user devices (EDs) and diverse applications is surging, resulting in massive data generated at the edge of networks. To process these data efficiently, the innovative mobile edge computing (MEC) framework has emerged to guarantee low latency and enable efficient computing close to the user traffic. Recently, federated learning (FL) has demonstrated its empirical success in edge computing due to its privacy-preserving advantages. Thus, it becomes a promising solution for analyzing and processing distributed data on EDs in various machine learning tasks, which are the major workloads in MEC. Unfortunately, EDs are typically powered by batteries with limited capacity, which brings challenges when performing energy-intensive FL tasks. To address these challenges, many strategies have been proposed to save energy in FL. Considering the absence of a survey that thoroughly summarizes and classifies these strategies, in this paper, we provide a comprehensive survey of recent advances in energy-efficient strategies for FL in MEC. Specifically, we first introduce the system model and energy consumption models in FL, in terms of computation and communication. Then we analyze the challenges regarding improving energy efficiency and summarize the energy-efficient strategies from three perspectives: learning-based, resource allocation, and client selection. We conduct a detailed analysis of these strategies, comparing their advantages and disadvantages. Additionally, we visually illustrate the impact of these strategies on the performance of FL by showcasing experimental results. Finally, several potential future research directions for energy-efficient FL are discussed.
[1]Abdelmoniem AM, Canini M, 2021. Towards mitigating device heterogeneity in federated learning via adaptive model quantization. Proc 1st Workshop on Machine Learning and Systems, p.96-103.
[2]Abdelmoniem AM, Ho CY, Papageorgiou P, et al., 2023. A comprehensive empirical study of heterogeneity in federated learning. IEEE Int Things J, 10(16):14071-14083.
[3]Abe Y, Sasaki H, Kato S, et al., 2014. Power and performance characterization and modeling of GPU-accelerated systems. Proc 28th Int Parallel and Distributed Processing Symp, p.113-122.
[4]Al-Abiad MS, Obeed M, Hossain J, et al., 2022. Decentralized aggregation for energy-efficient federated learning via overlapped clustering and D2D communications. https://arxiv.org/abs/2206.02981
[5]Albaseer A, Abdallah M, Al-Fuqaha A, et al., 2021. Threshold-based data exclusion approach for energy-efficient federated edge learning. Proc IEEE Int Conf on Communications Workshops, p.1-6.
[6]Albelaihi R, Yu LK, Craft WD, et al., 2022. Green federated learning via energy-aware client selection. Proc IEEE Global Communications Conf, p.13-18.
[7]Arouj A, Abdelmoniem AM, 2022. Towards energy-aware federated learning on battery-powered clients. Proc 1st ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network, p.7-12.
[8]Battiloro C, di Lorenzo P, Merluzzi M, et al., 2023. Lyapunov-based optimization of edge resources for energy-efficient adaptive federated learning. IEEE Trans Green Commun Netw, 7(1):265-280.
[9]Capra M, Bussolino B, Marchisio A, et al., 2020. An updated survey of efficient hardware architectures for accelerating deep convolutional neural networks. Fut Int, 12(7):113.
[10]Chen MZ, Poor HV, Saad W, et al., 2020. Wireless communications for collaborative federated learning. IEEE Commun Mag, 58(12):48-54.
[11]Chen R, Li L, Xue KP, et al., 2023. Energy efficient federated learning over heterogeneous mobile devices via joint design of weight quantization and wireless transmission. IEEE Trans Mob Comput, 22(12):7451-7465.
[12]Cho YJ, Wang JY, Joshi G, 2020. Client selection in federated learning: convergence analysis and power-of-choice selection strategies. https://arxiv.org/abs/2010.01243
[13]da Silva JMB, Ntougias K, Krikidis I, et al., 2021. Simultaneous wireless information and power transfer for federated learning. Proc 22nd Int Workshop on Signal Processing Advances in Wireless Communications, p.296-300.
[14]Deng L, Li GQ, Han S, et al., 2020. Model compression and hardware acceleration for neural networks: a comprehensive survey. Proc IEEE, 108(4):485-532.
[15]Gaudette B, Wu CJ, Vrudhula S, 2016. Improving smartphone user experience by balancing performance and energy with probabilistic QoS guarantee. Proc IEEE Int Symp on High Performance Computer Architecture, p.52-63.
[16]Gaudette B, Wu CJ, Vrudhula S, 2019. Optimizing user satisfaction of mobile workloads subject to various sources of uncertainties. IEEE Trans Mob Comput, 18(12):2941-2953.
[17]Hong S, Kim H, 2010. An integrated GPU power and performance model. ACM SIGARCH Comput Archit News, 38(3):280-289.
[18]Hospedales T, Antoniou A, Micaelli P, et al., 2022. Meta-learning in neural networks: a survey. IEEE Trans Patt Anal Mach Intell, 44(9):5149-5169.
[19]Hosseini M, Mohsenin T, 2021. QS-NAS: optimally quantized scaled architecture search to enable efficient on-device micro-AI. IEEE J Emerg Sel Top Circ Syst, 11(4):597-610.
[20]Hu YQ, Huang HJ, Yu N, 2022. Device scheduling and channel allocation for energy-efficient federated edge learning. Comput Commun, 189:53-66.
[21]Imteaj A, Thakker U, Wang SQ, et al., 2022. A survey on federated learning for resource-constrained IoT devices. IEEE Int Things J, 9(1):1-24.
[22]Jararweh Y, Doulat A, AlQudah O, et al., 2016. The future of mobile cloud computing: integrating cloudlets and mobile edge computing. Proc 23rd Int Conf on Telecommunications, p.1-5.
[23]Khowaja SA, Dev K, Khowaja P, et al., 2021. Toward energy-efficient distributed federated learning for 6G networks. IEEE Wirel Commun, 28(6):34-40.
[24]Kim J, Kim D, Lee J, et al., 2022. A novel joint dataset and computation management scheme for energy-efficient federated learning in mobile edge computing. IEEE Wirel Commun Lett, 11(5):898-902.
[25]Kim YG, Wu CJ, 2020. AutoScale: energy efficiency optimization for stochastic edge inference using reinforcement learning. Proc 53rd Annual IEEE/ACM Int Symp on Microarchitecture, p.1082-1096.
[26]Kim YG, Wu CJ, 2021. AutoFL: enabling heterogeneity-aware energy efficient federated learning. Proc 54th Annual IEEE/ACM Int Symp on Microarchitecture, p.183-198.
[27]Li L, Xiong HY, Guo ZS, et al., 2019. SmartPC: hierarchical pace control in real-time federated learning system. Proc IEEE Real-Time Systems Symp, p.406-418.
[28]Li L, Wang J, Chen X, et al., 2020. Multi-layer coordination for high-performance energy-efficient federated learning. Proc 28th Int Symp on Quality of Service, p.1-10.
[29]Li L, Shi D, Hou RH, et al., 2021. To talk or to work: flexible communication compression for energy efficient federated learning over heterogeneous mobile edge devices. Proc IEEE Conf on Computer Communications, p.1-10.
[30]Lim WYB, Luong NC, Hoang DT, et al., 2020. Federated learning in mobile edge networks: a comprehensive survey. IEEE Commun Surv Tut, 22(3):2031-2063.
[31]Lin FPC, Hosseinalipour S, Azam SS, et al., 2021. Semi-decentralized federated learning with cooperative D2D local model aggregations. IEEE J Sel Areas Commun, 39(12):3851-3869.
[32]Luo B, Li X, Wang SQ, et al., 2021. Cost-effective federated learning design. Proc IEEE Conf on Computer Communications, p.1-10.
[33]Mao YY, You CS, Zhang J, et al., 2017. A survey on mobile edge computing: the communication perspective. IEEE Commun Surv Tut, 19(4):2322-2358.
[34]Mazumder AN, Meng J, Rashid HA, et al., 2021. A survey on the optimization of neural network accelerators for micro-AI on-device inference. IEEE J Emerg Sel Top Circ Syst, 11(4):532-547.
[35]McMahan HB, Moore E, Ramage D, et al., 2017. Communication-efficient learning of deep networks from decentralized data. Proc 20th Int Conf on Artificial Intelligence and Statistics, p.1273-1282.
[36]Mei XX, Chu XW, Liu H, et al., 2017a. Energy efficient real-time task scheduling on CPU-GPU hybrid clusters. Proc IEEE Conf on Computer Communications, p.1-9.
[37]Mei XX, Wang Q, Chu XW, 2017b. A survey and measurement study of GPU DVFS on energy conservation. Dig Commun Netw, 3(2):89-100.
[38]Mo XP, Xu J, 2021. Energy-efficient federated edge learning with joint communication and computation design. J Commun Inform Netw, 6(2):110-124.
[39]Nguyen VD, Sharma SK, Vu TX, et al., 2021. Efficient federated learning algorithm for resource allocation in wireless IoT networks. IEEE Int Things J, 8(5):3394-3409.
[40]Niknam S, Dhillon HS, Reed JH, 2020. Federated learning for wireless communications: motivation, opportunities, and challenges. IEEE Commun Mag, 58(6):46-51.
[41]Peng C, Hu Q, Wang ZL, et al., 2023. Online-learning-based fast-convergent and energy-efficient device selection in federated edge learning. IEEE Int Things J, 10(6):5571-5582.
[42]Perazzone J, Wang SQ, Ji MY, et al., 2022. Communication-efficient device scheduling for federated learning using stochastic optimization. Proc IEEE Conf on Computer Communications, p.1449-1458.
[43]Prakash P, Ding JH, Chen R, et al., 2022. IoT device friendly and communication-efficient federated learning via joint model pruning and quantization. IEEE Int Things J, 9(15):13638-13650.
[44]Shi D, Li L, Chen R, et al., 2022a. Toward energy-efficient federated learning over 5G+ mobile devices. IEEE Wirel Commun, 29(5):44-51.
[45]Shi D, Li L, Wu MQ, et al., 2022b. To talk or to work: dynamic batch sizes assisted time efficient federated learning over future mobile edge devices. IEEE Trans Wirel Commun, 21(12):11038-11050.
[46]Sun W, Lei SY, Wang L, et al., 2021. Adaptive federated learning and digital twin for Industrial Internet of Things. IEEE Trans Ind Inform, 17(8):5605-5614.
[47]Sun W, Zhao Y, Ma WQ, et al., 2024. Accelerating convergence of federated learning in MEC with dynamic community. IEEE Trans Mob Comput, 23(2):1769-1784.
[48]Tang MX, Ning XF, Wang YT, et al., 2022. FedCor: correlation-based active client selection strategy for heterogeneous federated learning. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.10092-10101.
[49]Tran HV, Kaddoum G, Elgala H, et al., 2020. Lightwave power transfer for federated learning-based wireless networks. IEEE Commun Lett, 24(7):1472-1476.
[50]Tran NH, Bao W, Zomaya A, et al., 2019. Federated learning over wireless networks: optimization model design and analysis. Proc IEEE Conf on Computer Communications, p.1387-1395.
[51]Vu TT, Ngo HQ, Dao MN, et al., 2022. Energy-efficient massive MIMO for federated learning: transmission designs and resource allocations. IEEE Open J Commun Soc, 3:2329-2346.
[52]Wang H, Kaplan Z, Niu D, et al., 2020. Optimizing federated learning on non-IID data with reinforcement learning. Proc IEEE Conf on Computer Communications, p.1698-1707.
[53]Wang SQ, Tuor T, Salonidis T, et al., 2018. When edge meets learning: adaptive control for resource-constrained distributed machine learning. Proc IEEE Conf on Computer Communications, p.63-71.
[54]Wheeldon A, Shafik R, Rahman T, et al., 2020. Learning automata based energy-efficient AI hardware design for IoT applications. Phil Trans R Soc A Math Phys Eng Sci, 378(2182):20190593
[55]Wu T, Qu YB, Liu CS, et al., 2023. Joint edge aggregation and association for cost-efficient multi-cell federated learning. Proc IEEE Conf on Computer Communications, p.1-10.
[56]Wu T, Fan XC, Wei H, et al., 2024. Predictive service provisioning with online learning in wireless edge networks. IEEE Trans Mob Comput, 23(5):4076-4091.
[57]Wu Y, Song YX, Wang TS, et al., 2022. Non-orthogonal multiple access assisted federated learning via wireless power transfer: a cost-efficient approach. IEEE Trans Commun, 70(4):2853-2869.
[58]Xu J, Wang HQ, 2021. Client selection and bandwidth allocation in wireless federated learning networks: a long-term perspective. IEEE Trans Wirel Commun, 20(2):1188-1200.
[59]Yang CX, Xu MW, Wang QP, et al., 2024. FLASH: heterogeneity-aware federated learning at scale. IEEE Trans Mob Comput, 23(1):483-500.
[60]Yang ZH, Chen MZ, Saad W, et al., 2021. Energy efficient federated learning over wireless communication networks. IEEE Trans Wirel Commun, 20(3):1935-1949.
[61]You XH, Wang CX, Huang J, et al., 2021. Towards 6G wireless communication networks: vision, enabling technologies, and new paradigm shifts. Sci China Inform Sci, 64(1):110301.
[62]Yu R, Li PC, 2021. Toward resource-efficient federated learning in mobile edge computing. IEEE Netw, 35(1):148-155.
[63]Yurtsever E, Lambert J, Carballo A, et al., 2020. A survey of autonomous driving: common practices and emerging technologies. IEEE Access, 8:58443-58469.
[64]Zaman KS, Reaz MBI, Ali SH Md, et al., 2022. Custom hardware architectures for deep learning on portable devices: a review. IEEE Trans Neur Netw Learn Syst, 33(11):6068-6088.
[65]Zeng QS, Du YQ, Huang KB, et al., 2020. Energy-efficient radio resource allocation for federated edge learning. Proc IEEE Int Conf on Communications Workshops, p.1-6.
[66]Zeng QS, Du YQ, Huang KB, et al., 2021a. Energy-efficient resource management for federated edge learning with CPU-GPU heterogeneous computing. IEEE Trans Wirel Commun, 20(12):7947-7962.
[67]Zeng QS, Du YQ, Huang KB, 2021b. Wirelessly powered federated edge learning. Proc 22nd Int Workshop on Signal Processing Advances in Wireless Communications, p.286-290.
[68]Zeng SG, Wu MH, 2019. Based on public health service in smart medical comprehensive service platform. Proc IEEE Int Conf on Computation, Communication and Engineering, p.48-51.
[69]Zhan YF, Li P, Guo S, 2020. Experience-driven computational resource allocation of federated learning by deep reinforcement learning. Proc IEEE Int Parallel and Distributed Processing Symp, p.234-243.
[70]Zhang TC, Mao SW, 2022. Energy-efficient federated learning with intelligent reflecting surface. IEEE Trans Green Commun Netw, 6(2):845-858.
[71]Zhao BR, Cui QM, Liang SY, et al., 2022. Green concerns in federated learning over 6G. China Commun, 19(3):50-69.
[72]Zhao JX, Feng YH, Chang XY, et al., 2022. Energy-efficient client selection in federated learning with heterogeneous data on edge. Peer-to-Peer Netw Appl, 15(2):1139-1151.
[73]Zheng JJ, Li K, Tovar E, et al., 2021. Federated learning for energy-balanced client selection in mobile edge computing. Proc Int Wireless Communications and Mobile Computing, p.1942-1947.
Kang YAN, Nina SHU, Tao WU, Chunsheng LIU, Panlong YANG. A survey of energy-efficient strategies for federated learning in mobile edge computing[J]. Frontiers of Information Technology & Electronic Engineering, 2024, 25(5): 645-663.
@article{title="A survey of energy-efficient strategies for federated learning in mobile edge computing",
author="Kang YAN, Nina SHU, Tao WU, Chunsheng LIU, Panlong YANG",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="25",
number="5",
pages="645-663",
year="2024",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2300181"
}
%0 Journal Article
%T A survey of energy-efficient strategies for federated learning in mobile edge computing
%A Kang YAN
%A Nina SHU
%A Tao WU
%A Chunsheng LIU
%A Panlong YANG
%J Frontiers of Information Technology & Electronic Engineering
%V 25
%N 5
%P 645-663
%@ 2095-9184
%D 2024
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2300181
TY - JOUR
T1 - A survey of energy-efficient strategies for federated learning in mobile edge computing
A1 - Kang YAN
A1 - Nina SHU
A1 - Tao WU
A1 - Chunsheng LIU
A1 - Panlong YANG
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 25
IS - 5
SP - 645
EP - 663
%@ 2095-9184
Y1 - 2024
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2300181
Click to get updates and verify authenticity.
ORCID: 
Open peer comments: Debate/Discuss/Question/Opinion
<1>