Deep Learning for Intelligent Wireless Networks: A Comprehensive Survey
The DOI matches its Crossref record; 125 of the 125 references it cites were found in a registry or an index.
Abstract
As a promising machine learning tool to handle the accurate pattern recognition from complex raw data, deep learning (DL) is becoming a powerful method to add intelligence to wireless networks with large-scale topology and complex radio conditions. DL uses many neural network layers to achieve a brain-like acute feature extraction from high-dimensional raw data. It can be used to find the network dynamics (such as hotspots, interference distribution, congestion points, traffic bottlenecks, spectrum availability, etc.) based on the analysis of a large amount of network parameters (such as delay, loss rate, link signal-to-noise ratio, etc.). Therefore, DL can analyze extremely complex wireless networks with many nodes and dynamic link quality. This paper performs a comprehensive survey of the applications of DL algorithms for different network layers, including physical layer modulation/coding, data link layer access control/resource allocation, and routing layer path search, and traffic balancing. The use of DL to enhance other network functions, such as network security, sensing data compression, etc., is also discussed. Moreover, the challenging unsolved research issues in this field are discussed in detail, which represent the future research trends of DL-based wireless networks. This paper can help the readers to deeply understand the state-of-the-art of the DL-based wireless network designs, and select interesting unsolved issues to pursue in their research.
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
“Therefore, all smart devices will be converted to intelligent devices in the era of 6G [25].”
From 6G Communication Technology: A Vision on Intelligent Healthcare (2021) · cites this paper as [25]
In the citing paper
“Big data 2.0 require a supercomputer to compute and analyze massive scale of small-sized data produced by healthcare devices [25].”
From 6G Communication Technology: A Vision on Intelligent Healthcare (2021) · cites this paper as [25]
In the citing paper
“a recent new trend is to optimize wireless communication by Artificial Intelligence (AI) techniques [4] [5], include but not limited to the application of AI for Physical Layer (PHY), Data Link Layer, and traffic control [6].”
From In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning (2019) · cites this paper as [5]
In the citing paper
“With the development of machine learning techniques, especially deep learning, a BS equipped with graphics processing units (GPUs) or the control centre of core network could carry out relevant learning algorithms to allocate resources efficiently to achieve performance close to the optimum [68].”
From What should 6G be? (2020) · cites this paper as [68]
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×
“2 million images into 1000 classes [4], [43].”
BackgroundLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 3×
“A classical application of DQN is video game (Atari 2600) [27], as shown if Fig.”
BackgroundMethodReinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · cited 1×
“Currently, many DL systems are tied with Reinforcement Learning (RL) models [17], which comprises three parts: 1) an environment which can be described by some features, 2) an agent which takes actions to change the environment, and 3) an interpreter which announces the current state and the action the”
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853 · cited 1×
“Furthermore, in [34] and [35], a ChebNet is proposed, which uses Chebyshev polynomials of the Laplacian to learn the filter structures for the graph data.”
MethodReinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 1×
“for a new but related task in the target domain without using new data [37].”
BackgroundSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“This idea has shown great success in many real-world control scenarios, such as voice recognition [2], [3], image recognition [4]–[7], semantic analysis [8], [9], language interpretation [10], [11], game control [12], drug discovery [13], and biomedical sciences [14]–[16], etc.”
BackgroundSystem Identification: Theory for the User
Lennart Ljung, A. (1987) · Cited by 17,690
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 16×
“The input of the DBN is flow information, which is represented by a flow demand vector X = (x1, x2, . . . , xN ), where N is the total number of network nodes.”
BackgroundInfluential
Research works printed but not linked: 8
- wang, 2015, The applications of deep learning on traffic identification, Proc Black Hat USA, 1
- goodfellow, 2016, Deep Learning
- 2017, NSL-KDD Dataset
- chollet, 2018, Deep Learning for Humans
- al-rfou, 2016, Theano: A Python framework for fast computation of mathematical expressions, eprint arXiv 1605 02688
- tieleman, 2012, Lecture 6.5-Rmsprop: Divide the gradient by a running average of its recent magnitude, Neural Netw Mach Learning, 4, 26
- 2018, WILL API
- 2018, Comparison of deep learning software
Cited by
Items 301–400 of 926
An Effective Data‐Collection Scheme with AUV Path Planning in Underwater Wireless Sensor Networks
Khan, W., Wang, H., Anwar, M. S., Alharbi, A., Imran, M. A., & Khan, J. A. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/8154573 · Cited by 25
Cellular traffic prediction via deep state space models with attention mechanism
Ma, H., Yang, K., & Pun, M.-O. (2022) · Computer Communications · doi:10.1016/j.comcom.2022.10.023 · Cited by 25
Wang, D., Zhang, N., Tao, M., & Chen, X. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3223526 · Cited by 25
“After decades of growth, AI technology has now permeated several sectors, including computer science and technology,healthcare,andwirelesscommunication[2],[3],[4], [5], etc.”
BackgroundA novel method to identify influential nodes based on hybrid topology structure
Wan, D., Yang, J., Zhang, T., & Xiong, Y. (2023) · Physical Communication · doi:10.1016/j.phycom.2023.102046 · Cited by 25
A Learning Transition from Machine Learning to Deep Learning: A Survey
Dol, M., & Geetha, A. (2021) · International Conference on Emerging Techniques in Computational Intelligence (ICETCI) · doi:10.1109/icetci51973.2021.9574066 · Cited by 25
Ullah, S. A., Hassan, S. A., Abou-Zeid, H., Qureshi, H. K., Jung, H., Mahmood, A., Gidlund, M., Imran, M. A., & Hossain, E. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3576571 · Cited by 24
“The surveys conducted in [79], [80], [53], [81] are relevant to networking, however, they are targeting the applications of ML and DL in specific network areas.”
A Survey on Deep Learning for the Routing Layer of Computer Network
Jiang, F., Dashtipour, K. K., & Hussain, A. (2019) · International Conference on UK-China Emerging Technologies (UCET) · doi:10.1109/ucet.2019.8881852 · Cited by 24
“Comparing with other survey [3], [17], [31] about computer network via deep learning, we focus on the routing selection via deep learning.”
BackgroundNeural Networks for Signal Intelligence
Jagannath, J., Polosky, N., Jagannath, A., Restuccia, F., & Melodia, T. (2019) · Wiley eBooks · doi:10.1002/9781119562306.ch13 · Cited by 24
Automatic Modulation Recognition of Unknown Interference Signals Based on Graph Model
Zhang, Q., Ji, H., Li, L., & Zhu, Z. (2024) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2024.3401720 · Cited by 24
“Deep learning has been widely used in various fields in recent years due to its powerful feature learning capability and also has an excellent performance in the field of AMR [5], [6].”
Machine learning techniques for route optimizations and logistics management description
Reyana, A., & Kautish, S. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-18464-2.00010-8 · Cited by 24
AI-enabled routing in next generation networks: A survey
Aktas, F., Shayea, I. A. M., Ergen, M., Saoud, B., Yahya, A. E., & Aldasheva, L. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.01.095 · Cited by 24
Generative neural network based spectrum sharing using linear sum assignment problems
Zaky, A. B., Huang, J. Z., Wu, K., & ElHalawany, B. M. (2020) · China Communications · doi:10.23919/jcc.2020.02.002 · Cited by 24
“DL techniques could provide intelligent functions that adaptively exploit the wireless resources, optimize the network operation, and guarantee the QoS needs in real-time [6,7].”
BackgroundSoftware Defined Internet of Things using lightweight protocol
Raikar, M. M., Meena, S. M., & Mulla, M. M. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.04.151 · Cited by 24
Deep Learning Techniques for OFDM Systems
Meenalakshmi, M., Chaturvedi, S., & Dwivedi, V. K. (2021) · IETE Journal of Research · doi:10.1080/03772063.2021.1986154 · Cited by 24
“A detailed survey on the applications of DL techniques in wireless networks was presented in [33].”
BackgroundAn Efficient Reinforcement Learning based Charging Data Delivery Scheme in VANET-Enhanced Smart Grid
Li, G., Gong, C., Zhao, L., Wu, J., & Boukhatem, L. (2020) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp48618.2020.00-64 · Cited by 23
“As a classic reinforcement learning method, Q-learning scheme [16] consists of a reward function, a transfer function, and a group of agent actions as well as environment states, and it is an unsupervised self-learning algorithm, which is skillful in searching the best action-selection strategy by…”
MethodHui, H. (2021) · Journal of Sensors · doi:10.1155/2021/3965087 · Cited by 23
“For example, real-time information-related service navigation channels have higher requirements for reliability and transmission delays, while the Internet and video services will be more concerned about bandwidth [8].”
BackgroundZhang, B., Jin, C. Z., Tian, B., Cao, K., Wang, J., & Zhang, P. (2022) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2022.3214004 · Cited by 23
“Deep reinforcement learning (DRL) is an efficient method to solve such a decision-making issue [9], [10], [11], [12].”
MethodDistributed Learning in Intelligent Transportation Systems: A Survey
Li, Q., Zhou, W., & Zheng, X. (2024) · Information · doi:10.3390/info15090550 · Cited by 23
Hamedani, K., Liu, L., & Yi, Y. (2020) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2020.3046725 · Cited by 23
“Convolutional neural networks (CNN) [18], RNNs, deep Bayesian networks, stacked auto encoders (SAEs) [19]–[21] are among the most recent methods [22].”
BackgroundMethodMachine Learning Algorithms in WSNs and its Applications
Raut, A. R., & Khandait, S. P. (2021) · International Conference on Computational Intelligence and Computing Applications (ICCICA) · doi:10.1109/iccica52458.2021.9697319 · Cited by 22
Machine Learning-Empowered Beam Management for mmWave-NOMA in Multi-UAVs Networks
Gao, H., Jia, C., Xu, W., Yuen, C., Feng, Z., & Lu, Y. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3172443 · Cited by 22
A novel blockchain federated safety-as-a-service scheme for industrial IoT using machine learning
Hasan, N., Chaudhary, K., & Alam, M. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13503-w · Cited by 22
“(2018) investigated the use of Deep Learning methodologies across a variety of network layers, including routing layer route search, data link layer process control traffic balancing [26], allocation, and physical layer modulation.”
BackgroundAl-Abiad, M. S., & Hossain, M. J. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3217963 · Cited by 22
“The local parameters of the users and the local aggregated models of the drones are considered to have a fixed size [39], [40] and denoted as s .”
BackgroundPath Loss Prediction in Evaporation Ducts Based on Deep Neural Network
Shu, B., Zhang, W., Chen, Y., Sun, J. F., & Wang, C. (2023) · IEEE Antennas and Wireless Propagation Letters · doi:10.1109/lawp.2023.3336469 · Cited by 22
“Theimpactofreceiver heightandtransmissiondistanceonthepredictionaccuracyisnotsignificant.”
Pathak, V., Chethan, R., Pandya, R. J., Iyer, S., & Bhatia, V. (2024) · IEEE Access · doi:10.1109/access.2024.3404473 · Cited by 22
“On the other hand, the 6G wireless networks aspire for a complete ML/Deep Learning (DL) integration [2], [3], [4], [5], [6].”
BackgroundTurhan, M., Öztürk, E., & Çırpan, H. A. (2019) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc.2019.8904193 · Cited by 22
Far-End Crosstalk Mitigation for Future Wireline Networks Beyond G.mgfast: A Survey and an Outlook
Zhang, Y., Zhang, R., Zhang, J., Bai, T., Rawi, A. F. A., Moonen, M., & Hanzo, L. (2020) · IEEE Access · doi:10.1109/access.2019.2963571 · Cited by 22
Rout, S. P. (2020) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt49239.2020.9225680 · Cited by 22
RetractedWang, J., Wang, R., Zheng, Z., Lin, R., Wu, L., & Shu, F. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3486015 · Cited by 21
“DRL has been widely applied in various complex communication systems, providing high-quality performances [24].”
Tseng, S., Tsai, C.-S., & Yu, C.-Y. (2020) · IEEE Access · doi:10.1109/access.2020.3004865 · Cited by 21
Multi-Agent Deep Reinforcement Learning Based User Association for Dense mmWave Networks
Sana, M., Domenico, A. D., & Strinati, E. C. (2019) · Globecom · doi:10.1109/globecom38437.2019.9013751 · Cited by 21
“Recently, the use of machine learning and reinforcement learning has attracted the interest of both academia and industry to handle the network management complexity [5], [6].”
BackgroundDeep Learning Network Based Spectrum Sensing Methods for OFDM SystemsPreprint
Cheng, Q., Shi, Z., Nguyen, D., & Dutkiewicz, E. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.09414 · Cited by 21
“possibly hidden features of the input signals. There are various deep learning network architectures, e.g., recurrent neural network (RNN), convolutionalneural network (CNN), stacked autoencoder, etc [31]. Amongthese, inthiswork we adopt the stacked autoencoder (SAE) [32] for the following reasons. First, RNN is a gen…”
BackgroundTransformer Neural Network for Throughput Improvement in Non-Terrestrial Networks
Giuliano, R., Innocenti, E., Mazzenga, F., Vizzarri, A., Nunzio, L. D., Parameshachari, B. D., & Habib, I. (2023) · International Conference on Networks, Multimedia and Information Technology (NMITCON) · doi:10.1109/nmitcon58196.2023.10276347 · Cited by 20
“In the last years, ML has been used to largely support communications [7] [8].”
MethodMinimizing AoI in High-Speed Railway Mobile Networks: DQN-Based Methods
Zhang, X., Xiong, K., Chen, W., Fan, P., Ai, B., & Letaief, K. B. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3472033 · Cited by 20
“To overcome this issue, DQN is employed to approximate the value function end-to-end [47], [48], [49], replacing the Q-learning.”
An Adaptive Service Function Chains Mapping With Multi-Task Deep Reinforcement Learning
Wei, W., Wang, Q., Gu, H., Zheng, D., Zhang, N., & Wu, C. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3556390 · Cited by 20
Cao, Y., Zhang, H., Choi, Y.-B., Wang, H., & Xiao, S. (2020) · IEEE Access · doi:10.1109/access.2020.2995442 · Cited by 20
“Health monitoring allows early disease diagnosis and prompt medical attention in emer-gencies, which can result in a reduction in injury and medical costs [11].”
BackgroundPolymoRF: polymorphic wireless receivers through physical-layer deep learning
Restuccia, F., & Melodia, T. (2020) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3397166.3409132 · Cited by 20
“been proposed as a viable alternative to traditional learning techniques [31].”
MethodPotential of Deep Learning Algorithms in Mitigating the Spread of COVID-19
Sarumi, O. A., Aouedi, O., & Muhammad, L. J. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-74761-9_10 · Cited by 20
Generative adversarial networks for generating synthetic features for Wi-Fi signal quality
Castelli, M., Manzoni, L., Espindola, T., Popovič, A., & Lorenzo, A. D. (2021) · PLoS ONE · doi:10.1371/journal.pone.0260308 · Cited by 20
“Altough the vast majority of the existing DL-based models are focused on the optimization of the functions related to the wireless network layers [3], DL models can be employed in other important areas.”
BackgroundInfluentialSelection of Waveform Parameters Using Machine Learning for 5G and Beyond
Yazar, A., & Arslan, H. (2019) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc.2019.8904153 · Cited by 20
“In [9], deep learning (DL) and wireless networks are discussed together in depth.”
BackgroundMachine Learning for Spectrum Access and Sharing
Cohen, K. (2019) · Wiley eBooks · doi:10.1002/9781119562306.ch1 · Cited by 19
Future Factories With 6G: Agentic AI and Cyber–Physical Digital Twins
Li, H., Madhukumar, H., Methley, N., Chen, X., Wu, Y., Parra-Ullauri, J. M., Sharma, V., Lee, J., Koblitz, A. R., Andrews, M., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3623075 · Cited by 19
A Deep Learning-Based Indoor Radio Estimation Method Driven by 2.4 GHz Ray-Tracing Data
Pyo, C., Sawada, H., & Matsumura, T. (2023) · IEEE Access · doi:10.1109/access.2023.3340204 · Cited by 19
“Deep learning has been successfully applied in wireless communication systems, including physical layer components and wireless network management [11].”
MethodNimi, T., & Babu, A. V. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3427331 · Cited by 19
“In the recent past, deep learning (DL) has garnered considerable attention as an effective data-driven technique for solving complex problems in wireless networks and IoT systems [38], [39], [40].”
BackgroundLi, H., He, Z., Wang, Y., Ding, X., & Cui, Y. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110686 · Cited by 19
D’Oro, S., Restuccia, F., & Melodia, T. (2021) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom42981.2021.9488865 · Cited by 19
“For this reason, DL systems are among the most promising tools to develop and deploy the nextgeneration of intelligent and adaptive wireless networks [21].”
BackgroundElectromagnetic Modulation Signal Classification Using Dual-Modal Feature Fusion CNN
Bai, J., Yao, J., Qi, J., & Wang, L. (2022) · Entropy · doi:10.3390/e24050700 · Cited by 19
“Many researchers have studied various features for extraction, including high-order cumulant (HOC) [5], cyclic spectrum [6], approximate entropy [7], Kullback–Leibler divergence (KLD) [8], etc. Classification networks include the artificial neural network (ANN) [9], decision tree, support vector machine (SVM) [10] and k…”
Deep Reinforcement Learning for QoS-Constrained Resource Allocation in Multiservice Networks
Saraiva, J. V., Braga, I. M., Monteiro, V. F., Lima, F. R. M., Maciel, T. F., Freitas, W. C., & Cavalcanti, F. R. P. (2020) · Journal of Communication and Information Systems · doi:10.14209/jcis.2020.7 · Cited by 19
Du, C., Zhang, H., Zhang, X., Zhao, Z., Yang, J., Zhang, X., Xing, Z., Feng, Z., Zuo, S., Xu, C., et al. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3582948 · Cited by 18
“Furthermore, AI has demonstrated significant potential for PLS performance of next generation wireless communication systems [207], [208].”
Efficient Automatic Modulation Classification in Nonterrestrial Networks With SNN-Based Transformer
Zeng, D., Xiao, Y., Liu, W., Du, H., Zhang, E., Zhang, D., Wang, Y., Zhang, M., & Chen, W. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3467284 · Cited by 18
“T ERRESTRIAL networks [1] have been extensively researched and applied in the past, providing network access services to a wide range of end users and institutional entities.”
Deep Soft Interference Cancellation for MIMO Detection
Shlezinger, N., Fu, R., & Eldar, Y. C. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054732 · Cited by 18
Scalable Approximate Computing Techniques for Latency and Bandwidth Constrained IoT Edge
George, A., & Ravindran, A. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-76063-2_20 · Cited by 18
AI4Mobile: Use Cases and Challenges of AI-based QoS Prediction for High-Mobility Scenarios
Kulzer, D. F., Kasparick, M., Palaios, A., Sattiraju, R., Ramos-Cantor, O. D., Wieruch, D., Tchouankem, H., Göttsch, F., Geuer, P., Schwardmann, J., et al. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-spring51267.2021.9449059 · Cited by 18
Feature-Based Deep Neural Networks for Short-Term Prediction of WiFi Channel Occupancy Rate
Al-Tahmeesschi, A., Umebayashi, K., Iwata, H., Lehtomäki, J. J., & López‐Benítez, M. (2021) · IEEE Access · doi:10.1109/access.2021.3088423 · Cited by 18
“A comprehensive survey on deep neural network (DNN) utilisation in smart wireless networks is presented in [13].”
BackgroundHossain, M. S., & Bečvář, Z. (2021) · IEEE Access · doi:10.1109/access.2021.3099535 · Cited by 18
Kaleci, B., Turgut, K., & Dutağacı, H. (2021) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2021.06.007 · Cited by 18
Wireless Network Abnormal Traffic Detection Method Based on Deep Transfer Reinforcement Learning
Xia, Y., Dong, S., Peng, T., & Wang, T. (2021) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn53354.2021.00083 · Cited by 18
An Interference-Oriented 5G Radio Resource Allocation Framework for Ultradense Networks
Peng, T., Guo, Y., Wang, Y., Chen, G., Feng, Y., & Chen, W. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3183930 · Cited by 18
“Two kinds of AI algorithms are commonly used: 1) deep learning (DL) and 2) reinforcement learning (RL) [14].”
MethodA low-complexity AMP detection algorithm with deep neural network for massive mimo systems
Zhang, Z., Li, Y., Yan, X., & Ouyang, Z. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2022.11.011 · Cited by 18
John, A. A., Thakur, P., & Singh, G. K. (2022) · International Journal of Communication Systems · doi:10.1002/dac.5410 · Cited by 18
Deep learning-driven MIMO: Data encoding and processing mechanism
Song, Z., & Ma, J. (2022) · Physical Communication · doi:10.1016/j.phycom.2022.101976 · Cited by 17
Bai, J., Yao, J., Guo, Y., Yang, Z., & Wang, L. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3375510 · Cited by 17
“…recognition methods include artificial neural networks (ANN) [9], decision trees, support vector machines (SVM) [10], K-nearest neighbors (KNN) [11], etc. Recently, deep learning(DL) has been introduced to solve AMC problems with powerful feature extraction capabilities and classification…”
MethodTransformer-Based Power Optimization for Max-Min Fairness in Cell-Free Massive MIMO
Chafaa, I., Bacci, G., & Sanguinetti, L. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3568336 · Cited by 17
“Unlike previous works [4], [6], [7], we eliminate the dependence on large-scale fading and channel statistics while maintaining near-optimal performance, by using only spatial coordinates of UEs and APs as inputs.”
Wireless Robotic Communication for Collaborative Multi-Agent Systems
Chen, K., & Hung, H.-M. (2019) · International Conference on Communications · doi:10.1109/icc.2019.8761140 · Cited by 17
Intelligent mining algorithm for complex medical data based on deep learning
Li, X., Li, D., Deng, Y., & Xing, J. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02239-w · Cited by 17
Spatiotemporal graph convolutional recurrent networks for traffic matrix prediction
Zhao, J., Qu, H., Zhao, J., Dai, H., & Jiang, D. (2020) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4056 · Cited by 17
“6,16,17 16-26 The deep architecture based on deep belief networks (DBN) has been successfully applied to solve TM prediction in large-scale IP backbone networks.”
BackgroundMethodShort-Packet Communications in Multi-Hop WPINs: Performance Analysis and Deep Learning Design
Nguyen, T.-V., Nguyen, V., da Costa, D. B., & An, B. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685765 · Cited by 17
“The related system variables with their ranges, which comprise of the number of hops with K ∈ [1, 6], the number of antennas at S with NS ∈ [1, 5], the number of PBs with L ∈ [1, 4], the number of relays in each cluster with Nk ∈ [1, 5], the positions of PBs with xPB ∈ [6, 9] and yPB ∈ [6, 9], the average SNR with γ ∈…”
BackgroundMethodDeep Learning at the Physical Layer for Adaptive Terahertz Communications
Hall, J., Jornet, J. M., Thawdar, N., Melodia, T., & Restuccia, F. (2023) · IEEE Transactions on Terahertz Science and Technology · doi:10.1109/tthz.2023.3237697 · Cited by 17
“For an exhaustive survey on the topic, we refer the reader to the excellent survey [44].”
BackgroundVariational autoencoder-enhanced deep neural network-based detection for MIMO systems
Omondi, G., & Olwal, T. O. (2023) · e-Prime - Advances in Electrical Engineering Electronics and Energy · doi:10.1016/j.prime.2023.100335 · Cited by 17
Machine Learning Based Dynamic Cooperative Transmission Framework for IoUT Networks
El-Banna, A. A. A., Zaky, A. B., ElHalawany, B. M., Huang, J. Z., & Wu, K. (2019) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/sahcn.2019.8824858 · Cited by 16
“ML techniques could provide intelligent functions that adaptively exploit the wireless resources, optimize the network operation, and guarantee the QoS needs in real-time applications [38], [39].”
BackgroundZheng, J., Liu, X., Ling, Z., & Hu, F. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3399404 · Cited by 16
“Especially, deep learning (DL) can extract information from complex communication networks with massive data to provide intelligent decision making for different protocol layers [7].”
BackgroundSelf-citationSemi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems
Sifaou, H., & Simeone, O. (2024) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2024.3503543 · Cited by 16
“N EXT-GENERATION wireless systems are expected to rely extensively on machine learning (ML) and data-driven decision-making [1], [2], [3].”
Bushehrian, O., & Moazeni, A. (2024) · Computing · doi:10.1007/s00607-024-01353-3 · Cited by 16
“…a combination of Rein-forcement Learning (RL) and Deep Neural Networks (DNN), provided promising solutions to the problem and are preferred to the heuristics-based approximation methods due to their ability to adapt perfectly in the stochastic and changing fog computing environments [16] [17] [18].”
Zhang, Q., Xin, C., & Wu, H. (2020) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2020.3040704 · Cited by 16
AI-Managed Cognitive Radio Digitizers
de la Rosa, J. M. (2022) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2022.3142669 · Cited by 16
Application of Machine Learning Methods to Solving Problems of Queuing Theory
Vishnevsky, V. M., & Gorbunova, A. V. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-09331-9_24 · Cited by 16
Extending Machine Learning Based RF Coverage Predictions to 3D
Chen, M., Châteauvert, M., & Ethier, J. (2022) · Digest - IEEE Antennas and Propagation Society. International Symposium · doi:10.1109/ap-s/usnc-ursi47032.2022.9887000 · Cited by 16
“It is well established that deep learning techniques, including machine learning, can enhance the tools that operators and regulators use to analyze these deployments, via faster predictions or deeper insights into trends in existing data [1].”
BackgroundJin, H., Seo, J., Park, J., & Kim, S. C. (2023) · IEEE Access · doi:10.1109/access.2023.3298953 · Cited by 16
“These attributes make RL perform well for complex problems [20], [21].”
BackgroundDistributed Machine Learning and Native AI Enablers for End-to-End Resources Management in 6G
Karachalios, O. A., Zafeiropoulos, A., Kontovasilis, K. P., & Papavassiliou, S. (2023) · Electronics · doi:10.3390/electronics12183761 · Cited by 15
Asynchronous Online Adaptation via Modular Drift Detection for Deep Receivers
Uzlaner, N., Raviv, T., Shlezinger, N., & Todros, K. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3533959 · Cited by 15
“A key aspect in which DNNs are expected to contribute is receiver processing, where their abstractness can be leveraged to learn from data to reliably operate in complex and unknown channel models [3], [4], [5].”
Nidagundi, P., Darvekar, A., Amber, M., & Ramesh, R. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.105409 · Cited by 15
Reinforcement Learning Based Congestion Control Technique for Wireless Mesh Networks
Mahajan, S. R., Srideviponmalar, P., Harikrishnan, R., & Kotecha, K. V. (2025) · The International journal of networked and distributed computing · doi:10.1007/s44227-025-00061-4 · Cited by 15
“When congestion is detected, TCP congestion management levies measures to control the packet flow rate in end-to-end systems [33].”
RL-Based Resource Allocation in SDN-Enabled 6G Networks
Radosavljević, I., Bojović, P. D., & Bojović, Ž. (2025) · Future Internet · doi:10.3390/fi17110497 · Cited by 15
Research on the Key Technologies of Network Security-Oriented Situation Prediction
Zhu, Y., & Du, Z. (2021) · Scientific Programming · doi:10.1155/2021/5527746 · Cited by 15
Deep learning trends and future perspectives of web security and vulnerabilities
Chughtai, M. S., Bibi, I., Karim, S., Shah, S. W. A., Laghari, A. A., & Khan, A. A. (2023) · Journal of High Speed Networks · doi:10.3233/jhs-230037 · Cited by 15
“The application of DL algorithm in different network layers should be introduced, and discussed to enhance other network functions, such as network security, data sensing and compression, etc. [77,97].”
Modular Model-Based Bayesian Learning for Uncertainty-Aware and Reliable Deep MIMO Receivers
Raviv, T., Park, S., Simeone, O., & Shlezinger, N. (2023) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops57953.2023.10283687 · Cited by 15
“The capacity of deep neural networks (DNNs) to learn complex tasks from data has led to a burgeoning interest in their utilization for communications receiver design [1]– [5].”
BackgroundIntelligent Wireless Networks: Challenges and Future Research Topics
Abusubaih, M. A. (2021) · Journal of Network and Systems Management · doi:10.1007/s10922-021-09625-5 · Cited by 15
Tefera, M. K., Jin, Z., & Zhang, S. (2022) · Sensors · doi:10.3390/s22093589 · Cited by 15
Ghoshal, S. C., Hossain, M. M., Das, B. C., Roy, P., Razzaque, M. A., Azad, S., Hassan, M. M., Savaglio, C., & Fortino, G. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.07.034 · Cited by 14
Mobility-Aware Federated Learning-Based Proactive UAVs Placement in Emerging Cellular Networks
Manzoor, S., Shakir, M. Z., Hasna, M. O., & Qaraqe, K. A. (2024) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2024.3439289 · Cited by 14
“Deep recurrent neural networks (RNN) such has long short-term memory (LSTM) has been known to capture long-term sequences and predict the next state [29], [30], [31].”
BackgroundJiang, J., Dong, Y., Han, G., & Su, G. (2025) · Drones · doi:10.3390/drones9020123 · Cited by 14
“In recent years, existing RL and DRL strategies have been applied to the MAC design of terrestrial wireless networks [15–17], and have gradually been extended to underwater acoustic networks (UANs) [7–11].”
A predictive energy‐efficient adaptive routing methodology for Mobile Ad hoc Networks
Malyadri, N., Ramakrishna, M., Nandalike, R., Chavan, P., Supreeth, S., Dayananda, P., & Rohith, S. (2025) · IET Networks · doi:10.1049/ntw2.70001 · Cited by 14
Intelligent Flexible Position Antenna Systems for Networking: A Survey
Yu, X., Wang, J., Hu, R. Q., Kim, D. I., Al‐Dhahir, N., Wymeersch, H., & Zhao, N. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3626312 · Cited by 14
“3, DL realizes various kinds of functionalities through neural network, which consists of three parts: input layer, hidden layers and output layer [26].”
Learning-Based Query Scheduling and Resource Allocation for Low-Latency Mobile-Edge Video Analytics
Lin, J., Yang, P., Wu, W. R., Zhang, N., Han, T., & Yu, L. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3300696 · Cited by 14
“Considering the fact that there is more than one end camera connecting to an edge node via the shared uplink channel, the bandwidth resources may become insufficient, especially in the case of the network fluctuation, which necessitates adaptive bandwidth allocation [20], [21].”
BackgroundElHalawany, B. M., Wu, K., & Zaky, A. B. (2020) · Mobile Networks and Applications · doi:10.1007/s11036-020-01566-8 · Cited by 14
Yu, P., Xiao, Y., Zhou, F., Li, H., Feng, L., Li, W., & Qiu, X. (2020) · Mobile Networks and Applications · doi:10.1007/s11036-020-01574-8 · Cited by 14
“The emerging Deep Reinforcement Learning (DRL) can be considered as an enhanced version of traditional RL, which provides a better solution to handle complicated problems [14].”
BackgroundShi, J., Ma, A., Cheng, X., Sha, M., & Peng, X. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2023.3335346 · Cited by 13
“Deep learning has been used to handle a large number of network parameters and automatically uncover correlations that would otherwise have been too complex to extract by human experts [21], [22] and reinforcement learning has been employed to enable network self-configurations [23].”
Pramitarini, Y., Perdana, R. H. Y., Shim, K., & An, B. (2024) · IEEE Access · doi:10.1109/access.2024.3392255 · Cited by 13
“The deep neural network (DNN) has emerged as a powerful paradigm in deep learning for addressing a variety of challenges in wireless networks and IoT systems [11], [12].”
BackgroundPCA-Featured Transformer for Jamming Detection in 5G UAV Networks
Viana, J., Farkhari, H., Sebastião, P. J. A., & Jiménez, V. P. G. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3619817 · Cited by 13
Hybrid GNN-Centric Architectures for AI-Native 6G Wireless Networks: A Comprehensive Survey
Ghourtani, M. R., Norouzi, S., Chen, J. Y., Ahmadi, H., Braun, T. I., Chowdhury, K. R., & Burr, A. G. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3681198 · Cited by 13
“Broad surveys such as [20] and [21] present AI applications across the protocol stack, from signal processing to network control.”
Metadata
- Authors
- Mao, Q., Hu, F., & Hao, Q.
- Affiliations
- University of Alabama (US)
- Southern University of Science and Technology (CN)
- Venue
- IEEE Communications Surveys & Tutorials
- Published
- 2018
- Volume
- 20
- Issue
- 4
- Pages
- 2595-2621
- ISSN
- 1553-877X (ISSN-L)
- 2373-745X
- OpenAlex
- W2807731816
- Cited by
- 789
- References
- 123
- Citations by year
- 2026: 42 · 2025: 83 · 2024: 88 · 2023: 115 · 2022: 113 · 2021: 129 · 2020: 139 · 2019: 73 · 2018: 7
- FWCI
- 33.25
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Communications Surveys & Tutorials (publishedVersion)
- Funders
- Science and Technology Innovation Commission of Shenzhen (CKFW2016041415372174)
- National Natural Science Foundation of China (61773197)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Computer Science › Computer Networks and Communications › Wireless Networks and Protocols
- Keywords
- deep learning, intelligent wireless networks, artificial neural networks, network dynamics, hotspot detection, interference distribution, traffic bottlenecks, spectrum availability, access control, resource allocation, routing, traffic load balancing, network security
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.