Online Energy-Efficient Power Control in Wireless Networks by Deep Neural Networks
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
The work describes how deep learning by artificial neural networks (ANNs) enables online power allocation for energy efficiency maximization in wireless interference networks. A deep ANN architecture is proposed and trained to take as input the network communication channels and to output suitable power allocations. It is shown that this approach requires a much lower computational complexity compared to traditional optimization-oriented approaches, dispensing with the need of solving the optimization problem anew in each channel coherence time. Despite the lower complexity, numerical results show that a properly trained ANN achieves similar performance as more traditional optimization-oriented methods.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728 · cited 1×
“F : d = {dk, , Pmin,k, Pmax,k}k, ∈ R → p∗ ∈ R (4) Then, leveraging the result that ANNs are universal function approximators [20], we propose to train an ANN to learn the unknown map (4).”
MethodMultilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,081
An Introduction to Deep Learning for the Physical Layer
O'Shea, T., & Hoydis, J. (2017) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2017.2758370 · Cited by 2,980 · cited 1×
“Overviews on deep learning applications to wireless communications have recently appeared in [12, 13].”
BackgroundMassive MIMO Networks: Spectral, Energy, and Hardware Efficiency
Björnson, E., Hoydis, J., & Sanguinetti, L. (2017) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000093 · Cited by 2,137 · cited 1×
“Moreover, μk = 10 for all k, whereas the circuit power Pc follows the model from [22].”
BackgroundA Survey of Energy-Efficient Techniques for 5G Networks and Challenges Ahead
Buzzi, S., I, C.-L., Klein, T. E., Poor, H. V., Yang, C., & Zappone, A. (2016) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2016.2550338 · Cited by 721 · cited 1×
“This means that the bitper-Joule energy efficiency of future wireless networks will have to increase by a factor 2000x [1, 2].”
BackgroundSelf-citationEnergy Efficiency in Wireless Networks via Fractional Programming Theory
Zappone, A., & Jorswieck, E. (2015) · Foundations and Trends in Communications and Information Theory · doi:10.1561/0100000088 · Cited by 513 · cited 2×
“In [3] a tutorial on optimization methods for energy efficiency is provided, describing the fundamental tool of fractional programming theory, and pointing out that energy efficiency maximization requires in general exponential complexity in realistic interference-limited network scenarios.”
BackgroundMethodSelf-citationEnergy-Efficient Resource Allocation in Multi-Cell OFDMA Systems with Limited Backhaul Capacity
Ng, D. W. K., Lo, E. S., & Schober, R. (2012) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2012.083112.111951 · Cited by 360 · cited 1×
“To circumvent this issue, a simple approach is to resort to interference cancelation techniques or to orthogonal transmission schemes, thus falling back into the noise-limited regime [4–6].”
MethodEnergy Efficiency in Wireless Networks via Fractional Programming Theory
Zappone, A., & Jorswieck, E. (2015) · now publishers, Inc. eBooks · doi:10.1561/9781680830439 · Cited by 326
Self-citationLearning to optimize: Training deep neural networks for wireless resource management
Sun, H., Chen, X., Shi, Q., Hong, M., Fu, X., & Sidiropoulos, N. D. (2017) · 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc.2017.8227766 · Cited by 308 · cited 5×
“• while [19] uses a neural network to separately emulate each iteration of an iterative algorithm, this work takes an end-to-end perspective, proposing to use a deep network to learn the overall input-output map of a generic resource allocation problem.”
BackgroundMethodInfluentialLearning the MMSE Channel Estimator
Neumann, D., Wiese, T., & Utschick, W. (2018) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2018.2799164 · Cited by 306 · cited 1×
“In [14] and [15] deep learning is used for MMSE channel estimation and positioning, respectively, while data detection algorithms based on deep learning have been proposed in [16].”
Method
Research works printed but not linked: 2
- goodfellow, 2016, Deep Learning MIT Press
- 2015, NGMN Alliance 5G White Paper
Cited by
Applications of Deep Reinforcement Learning in Communications and Networking: A Survey
Luong, N. C., Hoang, D. T., Gong, S., Niyato, D., Wang, P., Liang, Y.-C., & Kim, D. I. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2916583 · Cited by 2,060
“To address the problem, the authors in [167] propose to use the deep learn-”
BackgroundWireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both?
Zappone, A., Di Renzo, M., & Debbah, M. (2019) · IEEE Transactions on Communications · doi:10.1109/tcomm.2019.2924010 · Cited by 684
“In [153], [190], the problem of energy efficiency maximization in wireless interference networks by a fully connected FNN is tackled.”
BackgroundMethodSelf-citationWireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both?
Zappone, A., Di Renzo, M., & Debbah, M. (2019) · arXiv · doi:10.48550/arxiv.1902.02647 · Cited by 685
“In [153], [190], the problem of energy efficiency maximization in wireless interference networks by a fully connected FNN is tackled.”
BackgroundMethodSelf-citationQuantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future
Nawaz, S. J., Sharma, S. K., Wyne, S., Patwary, M. N., & Asaduzzaman, M. (2019) · IEEE Access · doi:10.1109/access.2019.2909490 · Cited by 658
“ical layer of communication networks is power control and optimization [102].”
BackgroundA Gentle Introduction to Reinforcement Learning and its Application in Different Fields
Naeem, M., Rizvi, S. T. H., & Coronato, A. (2020) · IEEE Access · doi:10.1109/access.2020.3038605 · Cited by 257
Metadata
- Authors
- Zappone, A., Debbah, M., & Altman, Z.
- Affiliations
- Université Paris-Saclay (FR)
- Orange (France) (FR)
- Venue
- 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 1-5
- OpenAlex
- W2803132538
- Cited by
- 48
- References
- 22
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 4 · 2023: 5 · 2022: 6 · 2021: 8 · 2020: 9 · 2019: 11 · 2018: 1
- FWCI
- 11.57
- Type
- conference paper
- Language
- en
- Open access
- Licence
- other-oa
- Locations
- IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) (publishedVersion)
- HAL (submittedVersion, other-oa)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced MIMO Systems Optimization
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Physical Sciences › Computer Science › Computer Networks and Communications › Wireless Communication Networks Research
- Keywords
- energy efficiency, deep neural network, artificial neural networks, power allocation, channel state information, computational complexity, channel coherence time
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Online Energy-Efficient Power Control in Wireless Networks by Deep Neural Networks. https://app.cochat.ai/papers/10.1109/spawc.2018.8445857
- The paper
- Zappone, A., Debbah, M., & Altman, Z. (2018). Online Energy-Efficient Power Control in Wireless Networks by Deep Neural Networks. 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). https://doi.org/10.1109/spawc.2018.8445857
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.