Energy Efficient Federated Learning Over Wireless Communication Networks
Open accessThe DOI matches its Crossref record; 44 of the 45 references it cites were found in a registry or an index.
Abstract
In this paper, the problem of energy efficient transmission and computation resource allocation for federated learning (FL) over wireless communication networks is investigated. In the considered model, each user exploits limited local computational resources to train a local FL model with its collected data and, then, sends the trained FL model to a base station (BS) which aggregates the local FL model and broadcasts it back to all of the users. Since FL involves an exchange of a learning model between users and the BS, both computation and communication latencies are determined by the learning accuracy level. Meanwhile, due to the limited energy budget of the wireless users, both local computation energy and transmission energy must be considered during the FL process. This joint learning and communication problem is formulated as an optimization problem whose goal is to minimize the total energy consumption of the system under a latency constraint. To solve this problem, an iterative algorithm is proposed where, at every step, closed-form solutions for time allocation, bandwidth allocation, power control, computation frequency, and learning accuracy are derived. Since the iterative algorithm requires an initial feasible solution, we construct the completion time minimization problem and a bisection-based algorithm is proposed to obtain the optimal solution, which is a feasible solution to the original energy minimization problem. Numerical results show that the proposed al…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“For example, FL has facilitated smart health services by enabling machine learning (ML) modeling without sharing patient data across multiple medical institutions [9].”
From Federated Learning for Internet of Things: A Comprehensive Survey (2021) · cites this paper as [9]
In the citing paper
“Both computation energy consumption for local model updates and communication energy consumption for uploading local updates are simultaneously minimized in [92] by considering the learning latency and accuracy constraints for wireless FL.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [92]
In the citing paper
“The constraint of power in IoT devices is a major issue for the deployment of federated learning.”
From Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis (2021) · cites this paper as [17]
Citations
Cites
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 1×
“federated learning (FL) framework that will be adopted in future Internet of Things (IoT) systems [16]–[24].”
BackgroundA Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems
Saad, W., Bennis, M., & Chen, M. (2020) · IEEE Network · doi:10.1109/mnet.001.1900287 · Cited by 4,985 · cited 1×
“To this end, distributed learning frameworks are needed, to enable the wireless devices to collaboratively build a shared learning model with training their collected data locally [6]–[15].”
BackgroundSelf-citationOn Nonlinear Fractional Programming
Dinkelbach, W. (1967) · Management Science · doi:10.1287/mnsc.13.7.492 · Cited by 3,139
Towards Federated Learning at Scale: System Design
Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Konečný, J., Mazzocchi, S., McMahan, H. B., et al. (2019) · arXiv · doi:10.48550/arxiv.1902.01046 · Cited by 2,334 · cited 1×
“INTRODUCTION In future wireless systems, due to privacy constraints and limited communication resources for data transmission, it is impractical for all wireless devices to transmit all of their collected data to a data center that can use the collected data to implement centralized machine learning algorithms for dat…”
BackgroundAdaptive Federated Learning in Resource Constrained Edge Computing Systems
Wang, S., Tuor, T., Salonidis, T., Leung, K. K., Makaya, C., He, T., & Chan, K. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2904348 · Cited by 2,232 · cited 1×
“The FL training problem can be formulated as [2], [19], [25]:”
BackgroundClient Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2019) · ICC 2019 - 2019 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2019.8761315 · Cited by 1,875
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2018) · arXiv · doi:10.48550/arxiv.1804.08333 · Cited by 1,875
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S. J., Stich, S. U., & Suresh, A. T. (2019) · arXiv · doi:10.48550/arxiv.1910.06378 · Cited by 1,734 · cited 1×
“To this end, distributed learning frameworks are needed, to enable the wireless devices to collaboratively build a shared learning model with training their collected data locally [6]–[15].”
BackgroundDynamic computation offloading for mobile-edge computing with energy harvesting devices
Mao, Y., Zhang, J., & Letaief, K. B. (2016) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2016.2611964 · Cited by 1,705 · cited 2×
“The effective switched capacitance in local computation is κ = 10−28 [35].”
BackgroundFederated Optimization: Distributed Machine Learning for On-Device Intelligence
Konečný, J., McMahan, H. B., Ramage, D., & Richtárik, P. (2016) · arXiv · doi:10.48550/arxiv.1610.02527 · Cited by 1,563 · cited 5×
“In FL, wireless devices can cooperatively execute a learning task by only uploading local learning model to the base station (BS) instead of sharing the entirety of their training data [25].”
BackgroundMethodInfluential
Research works printed but not linked: 1
- lin, 2018, Don’t use large mini-batches, use local SGD, arXiv 1808 07217
Cited by
Items 401–500 of 1,002
Tang, Q., Yang, Y. D., Yang, H., Cao, D., & Yang, K. (2024) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2024.3422658 · Cited by 23
Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client
Xia, J., Zhang, Y., & Shi, Y. (2024) · doi:10.1145/3676536.3676815 · Cited by 23
“In [20], Sun et al. presented an online energy-aware dynamic worker scheduling policy, which can maximize the average number of workers scheduled for gradient update under a long-term energy constraint.”
oneVFC—A Vehicular Fog Computation Platform for Artificial Intelligence in Internet of Vehicles
Phung, K.-H., Tran, H., Nguyen, T. T., Dao, H., Tran-Quang, V., Truong, T.-H., Braeken, A., & Steenhaut, K. (2021) · IEEE Access · doi:10.1109/access.2021.3106284 · Cited by 22
“model, and the server updates the global model to the local devices [28], [37], [38].”
MethodZhou, X., Feng, J., Wang, J., & Pan, J. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.1049 · Cited by 22
“Each family participant can conduct model training locally, and finally, just upload the updated model parameters to the cloud server (Yang et al., 2020).”
MethodLatency-Efficient Wireless Federated Learning With Quantization and Scheduling
Yan, Z., Li, D., Yu, X., & Zhang, Z. (2022) · IEEE Communications Letters · doi:10.1109/lcomm.2022.3199490 · Cited by 22
“According to [14], [15], [16], if the frequency of the aggregation (e.”
BackgroundAl-Abiad, M. S., & Hossain, M. J. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3217963 · Cited by 22
“In [21], the authors formulated an optimization problem to study the trade-off between the FL time and the consumed energy for local computations and transmission in wireless communication networks.”
BackgroundLe, M., Hoang, D. T., Nguyen, D. N., Pham, Q., & Hwang, W. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3324151 · Cited by 22
“For example, the work in [7] considered optimizing the total energy consumption and the total completion time in FDMA-based FL networks and showed that FDMA is mostly superior to time-division multiple access (TDMA), which may outperform FDMA in terms of the computation energy consumption in case of the high power bud…”
BackgroundMethodResultInfluentialYan, Z., & Li, D. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3362143 · Cited by 22
“To address this issue, several resource allocation strategies [8], [9], [10], [11], user scheduling strategies [12], [13], [14], parameter quantization algorithms [15], [16], [17], and advanced aggregation algorithms [18], [19], [20] have been proposed.”
BackgroundLi, C., Wu, J., Zhang, Y., & Wan, S. (2024) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2024.3433457 · Cited by 22
Adaptive Model Pruning and Personalization for Federated Learning Over Wireless Networks
Liu, X., Ratnarajah, T., Sellathurai, M., & Eldar, Y. C. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3459808 · Cited by 22
“Index Terms —Adaptive partial model pruning and personalization, communication and computation latency, federated learning, wireless networks.”
BackgroundLiu, J., Liu, J., Xu, H., Liao, Y., Yao, Z., Chen, M., & Qian, C. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3492140 · Cited by 22
Self-citationLi, Z., Chen, M., Wang, K., Pan, C., Huang, N., & Hu, Y. (2020) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops49005.2020.9145209 · Cited by 22
Self-citationRen, J., Sun, J., Tian, H., Ni, W., Nie, G., & Wang, Y. (2021) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops50388.2021.9473734 · Cited by 22
“al [11] minimized the total energy consumption of all edge devices with latency constraints.”
BackgroundWireless Network Optimization for Federated Learning with Model Compression in Hybrid VLC/RF Systems
Huang, W., Yang, Y., Chen, M., Liu, C., Feng, C., & Poor, H. V. (2021) · Entropy · doi:10.3390/e23111413 · Cited by 22
“Meanwhile, the authors of [15] optimized a joint computation and transmission problem, whose goal is to minimize the total energy consumption with communication constraints such as limited computational resources and transmission energy.”
BackgroundSelf-citationMachine Learning for Predictive Deployment of UAVs With Multiple Access
Guo, F., Lu, L.-Y., Zang, Z., & Shikh‐Bahaei, M. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3264465 · Cited by 22
“Machine learning (ML) techniques are useful tools that have the ability to efficiently predict the distribution of future traffic data [9], [10], [11], [12], [13], [14], [15].”
BackgroundSelf-citationPfeiffer, K., Rapp, M., Khalili, R., & Henkel, J. (2023) · Transactions on machine learning research · doi:10.48550/arxiv.2203.05468 · Cited by 22
“The communication channel between devices and servers is commonly asymmetric, where the download link from the server to the devices can be neglected due to the commonly high transmit power of base stations [35], but the upload link from devices to the server is subject to heterogeneous channel quality as discussed in”
BackgroundAlahmari, S., & Alghamdi, I. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.107849 · Cited by 21
Hier-FUN: Hierarchical Federated Learning and Unlearning in Heterogeneous Edge Computing
Ma, Z.-G., Tu, H.-Q., Zhou, L., Pengli, Ji, Yan, X., Xu, H.-L., Wang, Z., & Chen, S. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3502666 · Cited by 16
Nguyen, T., Ho, N. D., HOANG, T. H., Do, C., & Wong, K. (2022) · IEEE Access · doi:10.1109/access.2022.3215758 · Cited by 21
“The majority of these studies have focused on optimization of FL in a single aspect such as device selection and scheduling [14], [15], FL model parameter updates and transmission [11], [16], or network resource management [17], [18].”
BackgroundMulti-Objective Optimization for Bandwidth-Limited Federated Learning in Wireless Edge Systems
Zhou, Y. F., Liu, X., & Lei, L. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3266389 · Cited by 21
“Yang et al. [14] jointly considered the CPU frequency, communication power, and bandwidth allocation to minimize the total energy consumption and learning time.”
BackgroundZhang, H., Wu, J., Lin, X., Bashir, A. K., & Al‐Otaibi, Y. D. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3280069 · Cited by 21
Qian, L., Liu, C., & Zhao, J. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3401184 · Cited by 21
“Energy used for user n processing data locally can be calculated as follows based on [33]: , where κ n denotes the effective switched capacitance that depends on the chip architecture of user n .”
Adaptive Clustering-Based Straggler-Aware Federated Learning in Wireless Edge Networks
Liu, Y.-J., Feng, G., Du, H., Qin, Z., Sun, Y., Kang, J., Li, X., & Niyato, D. T. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3412763 · Cited by 21
“…model aggregation according to where Specifically, the local model updating time is determined by the amount of the used data samples and available local computing resources, while local model transmission time is affected by the wireless channel quality and wireless bandwidth [3], [32], [33].”
InfluentialJoint Participant and Learning Topology Selection for Federated Learning in Edge Clouds
Wei, X., Ye, K., Shi, X. M., Xu, C., & Wang, Y. (2024) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2024.3413751 · Cited by 21
Device Sampling and Resource Optimization for Federated Learning in Cooperative Edge Networks
Wang, S., Morabito, R., Hosseinalipour, S., Chiang, M., & Brinton, C. G. (2024) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2024.3423673 · Cited by 21
“In this regard, most works have assumed a static or uniform device selection strategy, e.g., [9], [23], [25], [28], [29], [30], and [31], where the main server chooses a subset of devices either uniformly at random or according to a pre-determined sampling distribution.”
Incentive Mechanism Design for Cross-Device Federated Learning: A Reinforcement Auction Approach
Li, G., Cai, J., Lu, J., & Chen, H. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3508260 · Cited by 21
Laidi, R., Merabtine, N., Djenouri, D., Latif, S., Qadir, H. A., Djenouri, Y., & Balasingham, I. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3557475 · Cited by 24
Simultaneous Wireless Information and Power Transfer for Federated Learning
da Silva, J. M. B., Ntougias, K., Krikidis, I., Fodor, G., & Fischione, C. (2021) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51858.2021.9593160 · Cited by 21
Federated learning for distributed spectrum sensing in NextG communication networks
Shi, Y., Sagduyu, Y. E., & Erpek, T. (2022) · Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications · doi:10.1117/12.2622935 · Cited by 21
FedRelay: Federated Relay Learning for 6G Mobile Edge Intelligence
Li, P., Zhong, Y., Zhang, C., Wu, Y., & Yu, R. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3225087 · Cited by 21
“sumption by arranging the computation and communication resources, such as computing frequency scheduling [17], [18], [19], bandwidth allocation [12], [20], device selection [21], [22], etc.”
How to Launch Jamming Attacks on Federated Learning in NextG Wireless Networks
Shi, Y., & Sagduyu, Y. E. (2022) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps56602.2022.10008669 · Cited by 21
A Transistor Operations Model for Deep Learning Energy Consumption Scaling Law
Li, C., Tsourdos, A., & Guo, W. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3229280 · Cited by 20
“now widespread efforts to reduce the size of neural network architectures both post-training [7], federated to the edge [8], and more recently during training [9].”
BackgroundKuang, Z., & Chen, C. (2023) · Egyptian Informatics Journal · doi:10.1016/j.eij.2023.02.005 · Cited by 20
Dong, Y., Wang, L., Wang, J., Hu, X., Zhang, H., Yu, F. R., & Leung, V. C. M. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3329375 · Cited by 20
“…were designed to optimize the training loss [15], [16], training efficiency [17], [18], training duration [19], [20], [21], consumed energy [22], the number of correctly received model parameters per unit duration [23] as well as the tradeoff between training duration and consumed energy…”
BackgroundZhai, Z., Yuan, X., & Wang, X. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3385443 · Cited by 20
“• Digital communication without mixing matrix optimization (DC w/o MMO) [40] : In this benchmark, each model parameter is quantized to 16 bits and transmitted reliably with a channel capacity-achieving rate [40].”
2P3FL: A Novel Approach for Privacy Preserving in Financial Sectors Using Flower Federated Learning
Dasari, S., & Kaluri, R. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.049152 · Cited by 20
Luo, K., Zhao, K., Ouyang, T., Zhang, X., Zhou, Z., Wang, H., & Chen, X. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3466844 · Cited by 20
Liang, Y., Chen, Q., & Jiang, H. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3486121 · Cited by 20
Zhang, Z., Gao, Z., Guo, Y., & Gong, Y. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3492916 · Cited by 21
“When nocompressionandupdateprobabilityisapplied(i.e., θ tn = 1 and ρ tn = 1 ), the error corresponds to the Fully synchronous SGD error in [35].”
Ni, W., Liu, Y., Yang, Z., & Tian, H. (2021) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps51825.2021.9484466 · Cited by 20
Self-citationEfficiency-Boosting Federated Learning in Wireless Networks: A Long-Term Perspective
Ji, Y., Zhong, X., Kou, Z., Zhang, S., Li, H., & Yang, Y. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3250273 · Cited by 20
“More recent research aims to reduce the time consumption or improve the FL accuracy within the resource or energy constraint via client selecting, bandwidth allocation, or joint both [7], [8], [9].”
BackgroundTF-Net: Deep Learning Empowered Tiny Feature Network for Night-Time UAV Detection
Misbah, M., Khan, M. U., Yang, Z., & Kaleem, Z. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-34851-8_1 · Cited by 20
Self-citationResource Allocation of Federated Learning Assisted Mobile Augmented Reality System in the Metaverse
Zhou, X., Li, Y., & Zhao, J. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279550 · Cited by 20
“Following [19], [20], the energy consumed at the base station is not considered.”
BackgroundAdaptive Task Allocation for Asynchronous Federated and Parallelized Mobile Edge LearningPreprint
Mohammad, U., & Sorour, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.01656 · Cited by 20
Semi-asynchronous Hierarchical Federated Learning for Cooperative Intelligent Transportation SystemsPreprint
Chen, Q., You, Z., & Jiang, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.09073 · Cited by 20
“The existing federated learning methods mainly utilize the synchronous model aggregation mechanism, where the central server needs to wait for the slowest device to complete the training in each communication round [14], [22].”
MethodLarge-Small Model Collaboration in Mobile Edge Networks With Heterogeneous Computational Resources
Cheng, L., Zhang, S., Zhang, H., Liu, Q., Di, B., Niyato, D., & Song, L. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3644295 · Cited by 19
Robust Design of Federated Learning for Edge-Intelligent Networks
Qi, Q., & Chen, X. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3175921 · Cited by 19
Ahn, J.-H., Bennis, M., & Kang, J. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2022.3186538 · Cited by 19
A Reinforcement Learning Approach for Minimizing Job Completion Time in Clustered Federated Learning
Zhou, R., Yu, J., Wang, R., Li, B., Jiang, J., & Wu, L. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10228925 · Cited by 19
“For the local computation model, the parameter Ui is uniformly distributed in [1, 3] ⇥ 10(4) cycles/sample, and CPU cycle frequency fi is uniformly distributed in [1, 2] GHz [39].”
Group-based Hierarchical Federated Learning: Convergence, Group Formation, and Sampling
Liu, J., Wei, X., Liu, X., Gao, H., & Wang, Y. (2023) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3605573.3605584 · Cited by 19
“[25] study the energy consumption optimization problem for battery-sensitive devices and the proposed method can save up to 59.”
MethodXu, Z., Wang, L., Liang, W., Xia, Q., Xu, W., Zhou, P., & RANA, O. F. (2023) · IEEE Transactions on Computers · doi:10.1109/tc.2023.3333213 · Cited by 19
“For clarity, the symbols used in this paper are summarized in Table I.”
MethodDelay Minimization of Federated Learning Over Wireless Powered Communication Networks
Poposka, M., Pejoski, S., Rakovic, V., Denkovski, D., Gjoreski, H., & Hadži-Velkov, Z. (2023) · IEEE Communications Letters · doi:10.1109/lcomm.2023.3337320 · Cited by 19
“For example, for the FL model considered in [12], ν 1 = 2 / ((2 − Lδ 1 ) µδ 1 ) and ν 2 ( ϵ 0 ) = (2 L 2 / ( µ 2 δ 2 ))log(1 /ϵ 0 ) , where L and µ are the smoothness parameter and the convexity-strongness parameter of the EHCs’ loss functions, δ 1 is the learning rate of the EHCs’ local models ( 0…”
BackgroundInfluentialSelective Updates and Adaptive Masking for Communication-Efficient Federated Learning
Herzog, A., Southam, R., Belarbi, O., Anwar, S., Bullo, M., Carnelli, P., & Khan, A. (2024) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2024.3349697 · Cited by 20
Electrical Load Forecasting Over Multihop Smart Metering Networks With Federated Learning
Rahman, R., Moriano, P., Khan, S. U., & Nguyen, D. C. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3586115 · Cited by 19
“…hold, the expected upper bound of the variance of the stochastic gradient on local model training is given as Proof: See Appendix C. Theorem 1: Let Assumptions 1–3 hold, then the upper bound of the convergence rate of the federated model training at each cluster after K global rounds satisfies where”
Image Semantic Communications: An Extended Rate-Distortion Theory Based Scheme
Tong, W., Liu, F., Sun, Z., Yang, Y., & Guo, C. (2022) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps56602.2022.10008733 · Cited by 19
Wen, D., Jeon, K. J., Bennis, M., & Huang, K. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3092075 · Cited by 19
“Moreover, researchers have designed energy efficient RRM techniques to tackle the challenge of executing a complex learning task at energy constrained devices in a FEEL system[18]–[20].”
MethodEnergy-Aware Deep Learning on Resource-Constrained HardwarePreprint
Millar, J., Haddadi, H., & Madhavapeddy, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.12523 · Cited by 19
“Yang et. al [177] derive energy consumption models of different FL approaches based on their convergence rates, utilizing these to form a novel joint-optimization problem.”
CF4FL: A Communication Framework for Federated Learning in Transportation Systems
Sangdeh, P. K., Li, C., Pirayesh, H., Zhang, S., Zeng, H., & Hou, Y. T. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3221770 · Cited by 18
“Several research efforts have been made to study participant scheduling and resource allocation toward different objectives, such as minimizing FL loss [10]–[12], minimizing latency [13], improving energy efficiency [14]–[16], and enhancing learning efficiency [28].”
BackgroundThe Node Selection Strategy for Federated Learning in UAV-Assisted Edge Computing Environment
Bai, J., & Chen, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3263359 · Cited by 18
“Some widely used loss functions, for example, logistic regression, mean-squared error, and cross entropy, satisfy these assumptions [20], [21].”
MethodResource Allocation of NOMA Communication Systems for Federated Learning
Poposka, M., Jovanovski, B., Rakovic, V., Denkovski, D., & Hadži-Velkov, Z. (2023) · IEEE Communications Letters · doi:10.1109/lcomm.2023.3286909 · Cited by 18
“For widely used FL loss functions, such as linear or logistic loss functions, due to the exponentially decaying dependence between the accuracy of the global WFL model and the number of TRs [17, Eq.”
BackgroundMethodInfluentialLiu, S., Guan, P., Yu, J., & Taherkordi, A. (2023) · Computer Networks · doi:10.1016/j.comnet.2023.110100 · Cited by 18
Charatsaris, P., Diamanti, M., & Papavassiliou, S. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3347354 · Cited by 18
“1 Kbits, ∀ n ∈ N [14], [40].”
A Carbon Tracking Model for Federated Learning: Impact of Quantization and Sparsification
Barbieri, L., Savazzi, S., Kianoush, S., Nicoli, M., & Serio, L. (2023) · IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD) · doi:10.1109/camad59638.2023.10478391 · Cited by 18
“Quantitative and qualitative evaluation of energy-efficient FL strategies has been also carried out by comparing different implementations [10], [5].”
MethodFolino, F., Folino, G., Pisani, F. S., Pontieri, L., & Sabatino, P. (2024) · Journal Of Big Data · doi:10.1186/s40537-024-00933-6 · Cited by 18
“From a methodological viewpoint, key research topics include optimally balancing energy consumption with training time [14] and developing methods to control total energy usage by adjusting accuracy targets during local training [15].”
BackgroundTask-Oriented Communication Design at Scale
Mostaani, A., Vu, T. X., Habibi, H., Chatzinotas, S., & Ottersten, B. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3416898 · Cited by 18
“In [8], [9], the authors investigate the effect of quantization channels for the transmission of signals from one neuron to another, inside different types of NNs.”
BackgroundFederated Split Learning for Edge Intelligence in Resource-Constrained Wireless Networks
Ao, H., Tian, H., & Ni, W. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3464731 · Cited by 18
Jamming Attacks on Federated Learning in Wireless NetworksPreprint
Shi, Y., & Sagduyu, Y. E. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.05172 · Cited by 18
A Federated Learning Framework for Multi-Parameter Optimization in Edge Computing
Soma, R., Sahoo, S. K., Amin, F., & Mishra, S. K. (2025) · International Conference on Intelligent Systems and Embedded Design (ISED) · doi:10.1109/ised67359.2025.11405143 · Cited by 17
“Energy-aware FL over wireless settings is extensively studied in recent works [11], [12], [13].”
FLSTRA: Federated Learning in Stratosphere
Farajzadeh, A., Yadav, A., Abbasi, O., Jaafar, W., & Yanıkömeroğlu, H. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3285435 · Cited by 17
“In [10], the authors investigate energy-efficient transmission and computation resource allocation for FL over wireless communication networks.”
BackgroundMethodResultInfluentialQuantum Assisted Scheduling Algorithm for Federated Learning in Distributed Networks
Wei, X., Fan, L., Guo, Y., Gong, Y., Han, Z., & Wang, Y. (2023) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn58024.2023.10230094 · Cited by 17
Asynchronous Online Federated Learning With Reduced Communication Requirements
Gauthier, F., Gogineni, V. C., Werner, S., Huang, Y.-F., & Kuh, A. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3314923 · Cited by 17
Resource Management for MEC Assisted Multi-Layer Federated Learning Framework
Li, H., Pan, Y., Zhu, H., Gong, P., & Wang, J. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3327809 · Cited by 18
“Loss function f d ( ω j , x d , y d ) is introduced to evaluate the prediction performance for data sample d , which is determined by learning tasks [25].”
BackgroundStable Matching Based Revenue Maximization for Federated Learning in UAV-Assisted WBANs
Singh, M. B., Singh, H. K., & Pratap, A. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3360692 · Cited by 17
Naseh, D., Abdollahpour, M., & Tarchi, D. (2024) · Information · doi:10.3390/info15040190 · Cited by 17
Energy-Efficient Hierarchical Collaborative Learning Over LEO Satellite Constellations
Luo, L., Zhang, C., Yu, H., Li, Z., Sun, G., & Luo, S. (2024) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2024.3459021 · Cited by 17
“Restrictions apply. a mini-batch of size S ( E ) can be calculated by where κ denotes the effective switched capacitance of the calculation chip [33].”
Unified Analysis of Decentralized Gradient Descent: A Contraction Mapping Framework
Larsson, E. G., & Michelusi, N. (2025) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2025.3557332 · Cited by 17
Zhao, H., Xia, T., Xia, Y., Yang, J., Liu, M., & Zhu, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3557906 · Cited by 17
Ke, J., Zhou, J., Meng, D., Zeng, Y. W., Shi, Y., Qu, X., & Guo, S. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3605765 · Cited by 17
Age-aware Communication Strategy in Federated Learning with Energy Harvesting Devices
Liu, X., Qin, X., Chen, H., Liu, Y., Liu, B., & Zhang, P. (2021) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc52777.2021.9580240 · Cited by 17
Completion Time Minimization of Fog-RAN-Assisted Federated Learning With Rate-Splitting Transmission
Park, S.-H., & Lee, H. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3180747 · Cited by 17
“Following [4], [6], we set α = 2, β = 4, δ = 1/4, and ξ = 1/10, but the optimization algorithm proposed in this work can be applied for arbitrary values.”
BackgroundMethodInfluentialJoint SIC-Based Precoding and Sub-Connected Architecture Design for MIMO VLC Systems
Wang, C., Yang, Y., Yang, Z., Feng, C., Cheng, J., & Guo, C. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3231635 · Cited by 17
“The data transmission for VLC is achieved through intensity modulation and direction detection (IM/DD) [4], [5].”
MethodSelf-citationFederated Learning over LEO Satellite
Wang, Y., Zou, C., Wen, D., & Shi, Y. (2022) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps56602.2022.10008719 · Cited by 17
Joint Edge Aggregation and Association for Cost-Efficient Multi-Cell Federated Learning
Wu, T., Qu, Y., Liu, C., Jing, Y., Wu, F., Dai, H., Dong, C., & Cao, J. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10229060 · Cited by 17
“The parameters setting of FL task is based on the work in [19].”
On differential privacy for federated learning in wireless systems with multiple base stations
Tavangaran, N., Chen, M., Yang, Z., da Silva, J. M. B., & Poor, H. V. (2024) · IET Communications · doi:10.1049/cmu2.12722 · Cited by 17
Self-citationFedCau: A Proactive Stop Policy for Communication and Computation Efficient Federated Learning
Mahmoudi, A., Ghadikolaei, H. S., Barros Da Silva, J. M., & Fischione, C. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3378351 · Cited by 16
“…k is the energy needed for performing a global iteration to receive w k at a worker and send { w } j ∈ [ M ] to the master node over the wireless channel; • Latency : c k is the overall delay to compute and send parameters from and to the workers and the master node over the wireless channel [11].”
BackgroundMethodInfluentialTask Allocation for Mobile Federated and Offloaded Learning with Energy and Delay Constraints
Mohammad, U., Sorour, S., & Hefeida, M. (2020) · 2020 IEEE International Conference on Communications Workshops (ICC Workshops) · doi:10.1109/iccworkshops49005.2020.9145450 · Cited by 16
“The impact of energy on the validation accuracy has only recently been studied [13], [14].”
BackgroundLong-Term Energy Management Empowered Hierarchical Federated Learning for Smart Consumer Electronics
Xu, B., Zhao, H., Cao, H., Garg, S., & Alrashoud, M. R. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3355058 · Cited by 16
Towards Energy-efficient Federated Learning via INT8-based Training on Mobile DSPs
Yuan, J., Wang, S., Li, H., Xu, D., Li, Y., Xu, M., & Liu, X. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3645341 · Cited by 16
“Several studies have focused on energy optimization through resource scheduling [9, 16, 26, 44], primarily emphasizing communication-level energy consumption.”
BackgroundFedCarbon: Carbon-Efficient Federated Learning with Double Flexible Controls for Green Edge AI
Li, Y., Ouyang, T., Chen, X., & Cao, X. (2024) · International Workshop on Quality of Service · doi:10.1109/iwqos61813.2024.10682880 · Cited by 16
“For VGG-16, the maximal latency is fixed at T max = 30 seconds and parameter µ n is uniformly distributed in [4 .”
BackgroundMethodInfluentialSRFL: A Swarm-Reputation-Based Autonomic Federated Learning Framework for AIoT
Zhang, W., Du, M., Guo, X., & Xiong, N. N. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3509264 · Cited by 16
Semi-Asynchronous Hierarchical Federated Learning Over Mobile Edge Networks
Chen, Q., You, Z., Wu, J., Liu, Y., & Jiang, H. (2022) · IEEE Access · doi:10.1109/access.2022.3227561 · Cited by 16
“The existing federated learning methods mainly utilize the synchronous model aggregation mechanism, where the central server needs to wait for the slowest device to complete the training in each communication round [15], [16].”
MethodXie, R., Li, C., Zhou, X., & Dong, Z. Y. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10097251 · Cited by 16
“Neverthe-less, communication is still a challenge issue, requiring efficient techniques such as compression, resource allocation, and semantic communication [10, 11, 12, 13].”
Topology identification for stochastic multi-layer networks via graph-theoretic method
Zhang, C., Li, R., Zhu, Q., & Xu, Q. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.05.036 · Cited by 16
Energy-Efficient Federated Learning in Internet of Drones Networks
Yao, J., & Sun, X. (2023) · IEEE International Conference on High Performance Switching and Routing (HPSR) · doi:10.1109/hpsr57248.2023.10147956 · Cited by 16
“The above parameters for FL training are consistent with the ones in [13].”
BackgroundResultImportance-aware data selection and resource allocation for hierarchical federated edge learning
Qiang, X., Hu, Y., Chang, Z., & Hämäläinen, T. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.12.014 · Cited by 16
Clients Eligibility-Based Lightweight Protocol in Federated Learning: An IDS Use Case
Asad, M., Otoum, S., & Shaukat, S. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3398213 · Cited by 16
Data Partition and Rate Control for Learning and Energy Efficient Edge Intelligence
Li, X., Wang, S., Zhu, G., Zhou, Z., Huang, K., & Gong, Y. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3173262 · Cited by 16
“the energy consumption in EI, the computation and communication resource allocations were jointly optimized in [22] and [23].”
Özfatura, E., Zhao, J., & Gündüz, D. (2021) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51858.2021.9593130 · Cited by 16
Yu, Y., Chen, D., Tang, X., Song, T., Hong, C. S., & Han, Z. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3190377 · Cited by 16
“distributed setting [32], [33], the general upper bound on the”
BackgroundInfluentialSelf-citationBandwidth Allocation for Federated Learning With Wireless Providers and Cost Constraints
Xue, J., Qu, Z., Xu, J., Liu, Y., & Lu, Z. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3335258 · Cited by 15
Metadata
- Authors
- Yang, Z., Chen, M., Saad, W., Hong, C. S., & Shikh-Bahaei, M.
- Affiliations
- King's College London (GB)
- Princeton University (US)
- Virginia Tech (US)
- Kyung Hee University (KR)
- Venue
- IEEE Transactions on Wireless Communications
- Published
- 2021-03
- Volume
- 20
- Issue
- 3
- Pages
- 1935-1949
- ISSN
- 1536-1276 (ISSN-L)
- 1558-2248
- OpenAlex
- W3109847748
- Cited by
- 1,153
- References
- 45
- Citations by year
- 2026: 116 · 2025: 198 · 2024: 241 · 2023: 237 · 2022: 195 · 2021: 115
- FWCI
- 58.63
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Wireless Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Engineering and Physical Sciences Research Council (EPSRC) through the Scalable Full Duplex Dense Wireless Networks (EP/P003486/1)
- U.S. National Science Foundation (CNS-1814477)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Keywords
- federated learning, energy efficiency, wireless networks, resource allocation, time allocation, bandwidth allocation, power control, learning accuracy, iterative methods, completion time minimization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.