Energy-Efficient Processing and Robust Wireless Cooperative Transmission for Edge Inference
Open accessThe DOI matches its Crossref record; 38 of the 39 references it cites were found in a registry or an index.
Abstract
Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge. This article presents an energy-efficient edge processing framework to execute deep learning inference tasks at the edge computing nodes whose wireless connections to mobile devices are prone to channel uncertainties. Aimed at minimizing the sum of computation and transmission power consumption with probabilistic Quality-of-Service (QoS) constraints, we formulate the joint inference tasking and the downlink beamforming problem that is characterized by a group sparse objective function. We provide a statistical learning-based robust optimization approach to approximate the highly intractable probabilistic-QoS constraints by nonconvex quadratic constraints, which are further reformulated as matrix inequalities with a rank-one constraint via matrix lifting. We design a reweighted power minimization approach by iteratively reweighted ℓ1minimization with difference-of-convex-functions (DC) regularization and updating weights, where the reweighted approach is adopted for enhancing group sparsity whereas the DC regularization is designed for inducing rank-one solutions. The numerical results demonstrate that the proposed approach outperforms other state-of-the-art approaches.
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 horizontal edge inference via wireless cooperative transmission at multiple edge servers, the sum of the computation and transmission power consumption for generating and delivering the inference results were minimized via downlink coordinated beamforming [53].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [53]
In the citing paper
“For edge inference via collaboration among edge servers, task selection, coordinated downlink beamforming among edge servers, as well as passive beamforming at RISs were jointly optimized to achieve green edge inference [53], [54].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [53]
In the citing paper
“For instance, the group sparsity can represent the combinatorial variables for edge devices selection in FL [31], edge devices activity detection [76], and inference tasks selection [53].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [53]
In the citing paper
“In particular, a statistical learning approach was presented in [53] to learn a tractable uncertainty set to approximate the chance constrained programming for achieving high computation efficiency and system performance in the energy-efficient edge inference systems.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [53]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 2×
“Energy consumption breakdown of the AlexNet [24].”
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215 · cited 1×
“In addition to the low-latency, improving the energy efficiency [5] is also critical due to the high computational complexity of processing DNNs, for which a number of works focusing on model compression methods [6], [7].”
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455 · cited 1×
“With the explosion of mobile data and the increasing edge computing capability, there is an emerging trend of edge intelligence [2], [3].”
BackgroundThe Roadmap to 6G: AI Empowered Wireless Networks
Letaief, K. B., Chen, W., Shi, Y., Zhang, J., & Zhang, Y.-J. A. (2019) · IEEE Communications Magazine · doi:10.1109/mcom.2019.1900271 · Cited by 2,207
Self-citationConvex Approximations of Chance Constrained Programs
Nemirovski, A., & Shapiro, A. (2007) · SIAM Journal on Optimization · doi:10.1137/050622328 · Cited by 1,160 · cited 4×
“A recognized scenario generation (SG) approach [15] is proposed to use a collection of sampled constraints to approximate the original chance constraints.”
InfluentialKang, J., Xiong, Z., Niyato, D., Xie, S., & Zhang, J. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2940820 · Cited by 953 · cited 1×
“Instead of uploading all data collected by mobile devices to the remote cloud data center, edge intelligence emphasizes the use of the computation and storage resources at network edges to provide low-latency and reliable artificial intelligent (AI) services [6], [7] for privacy/security sensitive devices, such as wea…”
BackgroundEdge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing
Li, E., Zeng, L., Zhou, Z., & Chen, X. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2946140 · Cited by 929
Distributed Deep Neural Networks Over the Cloud, the Edge and End Devices
Teerapittayanon, S., McDanel, B., & Kung, H. T. (2017) · 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2017.226 · Cited by 843
Cheng, Y., Wang, D., Zhou, P., & Zhang, T. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2765695 · Cited by 817 · cited 1×
“In addition to the low-latency, improving the energy efficiency [5] is also critical due to the high computational complexity of processing DNNs, for which a number of works focusing on model compression methods [6], [7].”
Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning
Yang, T.-J., Chen, Y.-H., & Sze, V. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.643 · Cited by 732 · cited 2×
“The energy consumption of performing an inference task consists of the computation part and the data movement part [8].”
Optimization with Sparsity-Inducing Penalties
Bach, F., Jenatton, R., Mairal, J., & Obozinski, G. (2025) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000015 · Cited by 730 · cited 1×
“The mixed `1/`2norm [18] is a well-known convex group sparsity inducing norm, which has been successfully applied in green cloud radio access networks [9] and cooperative wireless cellular network [19].”
Reliable Federated Learning for Mobile Networks
Kang, J., Xiong, Z., Niyato, D., Zou, Y., Zhang, Y., & Guizani, M. (2020) · IEEE Wireless Communications · doi:10.1109/mwc.001.1900119 · Cited by 617 · cited 1×
“Instead of uploading all data collected by mobile devices to the remote cloud data center, edge intelligence emphasizes the use of the computation and storage resources at network edges to provide low-latency and reliable artificial intelligent (AI) services [6], [7] for privacy/security sensitive devices, such as wea…”
BackgroundOptimization with Sparsity-Inducing Penalties
Bach, F. (2011) · now publishers, Inc. eBooks · doi:10.1561/9781601985118 · Cited by 608
Convex analysis approach to d.c. programming: Theory, Algorithm and Applications
Dinh, T. P., & Thi, H. A. L. (1997) · HAL · Cited by 515
Communication-efficient edge ai: algorithms and systems
Shi, Y., Yang, K., Jiang, T., Zhang, J., & Letaief, K. B. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3007787 · Cited by 488 · cited 1×
“With the explosion of mobile data and the increasing edge computing capability, there is an emerging trend of edge intelligence [2]–[4], followed by the evolution of future mobile networks from “connected things” to “connected intelligence” [5].”
BackgroundSelf-citationGroup Sparse Beamforming for Green Cloud-RAN
(2014) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2014.040214.131770 · Cited by 468 · cited 2×
“The mixed `1/`2norm [18] is a well-known convex group sparsity inducing norm, which has been successfully applied in green cloud radio access networks [9] and cooperative wireless cellular network [19].”
Self-citationCompletely Stale Transmitter Channel State Information is Still Very Useful
Maddah-Ali, M. A., & Tse, D. (2012) · IEEE Transactions on Information Theory · doi:10.1109/tit.2012.2193116 · Cited by 467 · cited 2×
“inevitable in practice due to training based channel estimation [11], limited feedback [12], partial CSI acquisition [13] and CSI acquisition delays [14].”
Scaling for edge inference of deep neural networks
Xu, X., Ding, Y., Hu, S. X., Niemier, M., Cong, J., Hu, Y., & Shi, Y. (2018) · Nature Electronics · doi:10.1038/s41928-018-0059-3 · Cited by 462 · cited 2×
“A promising solution is to enable processing at the mobile network access points to facilitate deep learning inference, which is termed as edge inference [3].”
Self-citationContent-Centric Sparse Multicast Beamforming for Cache-Enabled Cloud RAN
Tao, M., Chen, E., Zhou, H., & Yu, W. (2016) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2016.2578922 · Cited by 423 · cited 1×
“We observe that there is an intrinsic connection between the group sparse structure [9], [10] of the downlink aggregative beamforming vector and the combinatorial variable, i.”
Self-citationFang, F., Zhang, H., Cheng, J., Roy, S., & Leung, V. C. M. (2017) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2017.2777672 · Cited by 292 · cited 1×
“In this work, we adopt the additive error model [25], [26] of the channel imperfection, i.”
Hong, M., Sun, R., Baligh, H., & Luo, Z.-Q. (2013) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2013.130211 · Cited by 271 · cited 1×
“The mixed `1/`2norm [18] is a well-known convex group sparsity inducing norm, which has been successfully applied in green cloud radio access networks [9] and cooperative wireless cellular network [19].”
Energy Efficiency of Downlink Transmission Strategies for Cloud Radio Access Networks
Dai, B., & Yu, W. (2016) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2016.2544459 · Cited by 244 · cited 6×
“under constraints (46) and (47) using an majorizationminimization (MM) technique as stated in [21].”
InfluentialSelf-citationApproximation Bounds for Quadratic Optimization with Homogeneous Quadratic Constraints
Luo, Z., Sidiropoulos, N. D., Tseng, P., & Zhang, S. (2007) · SIAM Journal on Optimization · doi:10.1137/050642691 · Cited by 225 · cited 15×
“• “CB+SDR”: We assume that all tasks are performed at each AP and conduct coordinated beamforming for minimizing the transmission power consumption under probabilistic-QoS constraints.”
InfluentialWireless Network Intelligence at the Edge
Park, J., Samarakoon, S., Bennis, M., & Debbah, M. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2941458 · Cited by 92 · cited 3×
“However, since mobile devices are usually equipped with limited computation power, storage and energy [2], it is usually infeasible to deploy deep learning models, i.”
InfluentialLearning-Based Robust Optimization: Procedures and Statistical Guarantees
Hong, L. J., Huang, Z., & Lam, H. (2020) · Management Science · doi:10.1287/mnsc.2020.3640 · Cited by 89 · cited 4×
“The high probability region is further determined by adopting a statistical learning [16] approach.”
InfluentialSmoothed -Minimization for Green Cloud-RAN With User Admission Control
Shi, Y., Cheng, J., Zhang, J., Bai, B., Chen, W., & Letaief, K. B. (2016) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2016.2544578 · Cited by 70 · cited 3×
“In this article, we will adopt an iteratively reweighted minimization approach which has demonstrated its effectiveness in cloud radio access network [27], [28] to further enhance the group sparsity of the aggregative beamforming vector.”
InfluentialSelf-citationRobust Group Sparse Beamforming for Multicast Green Cloud-RAN With Imperfect CSI
Shi, Y., Zhang, J., & Letaief, K. B. (2015) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2015.2442957 · Cited by 63 · cited 6×
“Note that [20] also considers a group sparse beamforming problem with nonconvex quadratic constraints.”
InfluentialSelf-citationOptimal Stochastic Coordinated Beamforming for Wireless Cooperative Networks With CSI Uncertainty
Shi, Y., Zhang, J., & Letaief, K. B. (2015) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2014.2385669 · Cited by 61 · cited 6×
“It may originate from training based channel estimation [11], limited precision of feedback [12], partial CSI acquisition [13] and delays in CSI acquicition [14].”
InfluentialSelf-citationEdgeSanitizer: Locally Differentially Private Deep Inference at the Edge for Mobile Data Analytics
Xu, C., Ren, J., She, L., Zhang, Y., Qin, Z., & Ren, K. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2897005 · Cited by 53
Hanif, M. F., Tran, L., Tölli, A., Juntti, M. J., & Glisic, S. (2013) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2013.2278815 · Cited by 47 · cited 1×
“In this article, we choose ellipsoidal uncertainty set to model the uncertainty of each group of channel coefficient vector hk for its wide use in modeling CSI uncertainties [26], [35], as well as its tractability as shown in Section III-C.”
MethodTwo-Timescale Hybrid Compression and Forward for Massive MIMO Aided C-RAN
Liu, A., Chen, X., Yu, W., Lau, V. K. N., & Zhao, M. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2905813 · Cited by 42 · cited 2×
“Integrating the Robust Optimization Approximation with a Cost-Effective Sampling Strategy Consider the block fading channel where the channel distribution is assumed invariant [27] within the coherence interval for channel statistics.”
Self-citationNonconvex and Nonsmooth Sparse Optimization via Adaptively Iterative Reweighted Methods
Wang, H., Zhang, F., Shi, Y., & Hu, Y. (2021) · Journal of Global Optimization · doi:10.1007/s10898-021-01093-0 · Cited by 32 · cited 1×
“• It is still an open problem to provide the theoretical guarantee of the proposed reweighted power minimization algorithm since the conditions for convergence guarantee of reweighted approach in [21], [31] are not met.”
Self-citationLimited Feedback in Single and Multi-User MIMO Systems With Finite-Bit ADCs
Mo, J., & Heath, R. W. (2018) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2018.2808955 · Cited by 32
Pilot Contamination in Massive MIMO Induced by Timing and Frequency Errors
Yang, F., Cai, P., Qian, H. L., & Luo, X. (2018) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2018.2825982 · Cited by 25 · cited 2×
“inevitable in practice due to training based channel estimation [11], limited feedback [12], partial CSI acquisition [13] and CSI acquisition delays [14].”
Energy Efficient and Robust Beamforming for MISO Cognitive Small Cell Networks
Liu, B., Zhou, F., Lu, G., & Hu, R. Q. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2855186 · Cited by 10 · cited 1×
“In this work, we adopt the additive error model [25], [26] of the channel imperfection, i.”
Research works printed but not linked: 3
- 2019, Stroke of Genius: GauGAN Turns Doodles Into Stunning, Photorealistic Landscapes
- 2017, CNN Energy Estimation Website
- Tao, 1997, Convex analysis approach to DC programming: Theory, algorithms and applications, Acta Math. Vietnamica, 22, 289
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“power consumption for generating and delivering the inference results were minimized via downlink coordinated beamforming [53].”
BackgroundMethodInfluentialSelf-citationXu, W., Yang, Z., Ng, D. W. K., Levorato, M., Eldar, Y. C., & Debbah, M. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3239189 · Cited by 660
“transmission in an MEC-based wireless network, a framework of edge processing was proposed in [149], where DL inference tasks can be effectively executed at the edge computing nodes.”
Communication-efficient edge ai: algorithms and systems
Shi, Y., Yang, K., Jiang, T., Zhang, J., & Letaief, K. B. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3007787 · Cited by 488
“Fortunately, offloading the task from edge devices to powerful edge servers emerges as an antidote [13], [130], [131], [133].”
BackgroundMethodInfluentialSelf-citationAI Models for Green Communications Towards 6G
Mao, B., Tang, F., Kawamoto, Y., & Kato, N. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3130901 · Cited by 300
“Currently, very limited research has analyzed how to conduct AI algorithms with low energy consumption [280], [281].”
BackgroundTask-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI
Wen, D., Liu, P., Zhu, G., Shi, Y., Xu, J., Eldar, Y. C., & Cui, S. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3303232 · Cited by 232
Self-citation
Metadata
- Authors
- Yang, K., Shi, Y., Yu, W., & Ding, Z.
- Affiliations
- Chinese Academy of Sciences (CN)
- ShanghaiTech University (CN)
- University of Toronto (CA)
- University of California, Davis (US)
- Venue
- IEEE Internet of Things Journal
- Published
- 2020-10
- Volume
- 7
- Issue
- 10
- Pages
- 9456-9470
- ISSN
- 2327-4662 (ISSN-L)
- 2372-2541
- OpenAlex
- W3011916804
- Cited by
- 65
- References
- 39
- Citations by year
- 2026: 11 · 2025: 9 · 2024: 11 · 2023: 12 · 2022: 7 · 2021: 10 · 2020: 5
- FWCI
- 3.99
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Internet of Things Journal (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Nature Science Foundation of China (61601290)
- Natural Sciences and Engineering Research Council of Canada
- National Science Foundation (ECCS-1711823)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced MIMO Systems Optimization
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed Sensor Networks and Detection Algorithms
- Keywords
- edge machine learning, deep learning inference, energy efficiency, downlink beamforming, channel uncertainty, rank-one constraint, reweighted l1 minimization, difference of convex functions, power 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.