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 201–300 of 926
Deep Reinforcement Learning Based End-to-End Multiuser Channel Prediction and Beamforming
Chu, M., Liu, A., Lau, V. K. N., Jiang, C., & Yang, T. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3183255 · Cited by 50
Saleem, R., Ni, W., Ikram, M., & Jamalipour, A. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3232360 · Cited by 49
“DL exploits multiple neural network layers to intelligently extract useful information from high dimensional data [40].”
BackgroundNeural network based instant parameter prediction for wireless sensor network optimization models
Akbaş, A., Yıldız, H. U., Özbayoğlu, A. M., & Tavlı, B. (2018) · Wireless Networks · doi:10.1007/s11276-018-1808-y · Cited by 49
“It is shown that DL provides much improvements in wireless network applications when compared to classical ML algorithms due to its high prediction accuracy and no pre-processing complexity of the input data [38].”
BackgroundMethodInfluentialCao, J., Peng, T., Liu, X., Dong, W., Duan, R., Yuan, Y., Wang, W., & Cui, S. R. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2959232 · Cited by 49
“In addition, the machine learning method could tolerate the incomplete or even erroneous input raw data [22].”
MethodDistributed Intelligence in Wireless Networks
Liu, X., Yu, J., Liu, Y., Gao, Y., Mahmoodi, T., Lambotharan, S., & Tsang, D. H. K. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3265425 · Cited by 48
“In conventional chain-shape block-based communication systems, DL has been deployed in different independent modules for multiple purposes with significantly improved performance [19], such as interference alignment [20], jamming resistance, modulation classification [21], physical coding [22] and so on.”
MethodReinforcement Learning Meets Wireless Networks: A Layering Perspective
Chen, Y., Liu, Y., Zeng, M., Saleem, U., Lu, Z., Wen, X., Jin, D., Han, Z., Jiang, T., & Li, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3025365 · Cited by 47
“On the other hand, the focus of [12]–[15], and [17] was on the applications of advanced ML methods, such as DL and DRL, while the applications of traditional RL methods were not touched.”
BackgroundInfluentialAI/ML for beyond 5G systems: Concepts, technology enablers & solutions
Taleb, T., Benzaïd, C., Addad, R. A., & Samdanis, K. (2023) · Computer Networks · doi:10.1016/j.comnet.2023.110044 · Cited by 46
Reliability enhancement in multi-numerology-based 5G new radio using INI-aware scheduling
Yazar, A., & Arslan, H. (2019) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-019-1435-z · Cited by 46
A Novel SVM Based IDS for Distributed Denial of Sleep Strike in Wireless Sensor Networks
Mohd, N., Singh, A., & Bhadauria, H. S. (2019) · Wireless Personal Communications · doi:10.1007/s11277-019-06969-9 · Cited by 46
“In recent scenario the availability of data is too much, so deep learning methods were also applicable in IDS development [47–49].”
MethodLOS and NLOS identification in real indoor environment using deep learning approach
Olejniczak, A., Błaszkiewicz, O., Cwalina, K. K., Rajchowski, P., & Sadowski, J. (2023) · Digital Communications and Networks · doi:10.1016/j.dcan.2023.05.009 · Cited by 45
Elsayed, M. I., El-Banna, A. A. A., Dobre, O. A., Shiu, W., & Wang, P. (2023) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2023.3331185 · Cited by 45
“…area of computer science, has currently made a profound technological revolution in all disciplines of communications [58], [59], [60], [61], [62], [63], [64], [65], [66], [67], [68], [69], [70], [71], [72], [73], [74], [75], [76], [77], [78], [79], [80], [81], [82], [83], [84], [85], [86], [87].”
Respati, M. A. K., & Lee, B. M. (2024) · IEEE Access · doi:10.1109/access.2024.3501363 · Cited by 45
“Machine learning has been utilized in wireless communication technology, both in 5G and 6G. ML can be used to solve existing problems [19], [21] and optimize wireless networks [11], [20], [22], [95].”
Autoencoder-Based Error Correction Coding for One-Bit Quantization
Balevi, E., & Andrews, J. G. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.2977280 · Cited by 45
“, see [3]–[5] for learning transmit constellations, [6], [7] for channel estimation, or [8] for several other problems.”
BackgroundArtificial Intelligence-Based Security Authentication: Applications in Wireless Multimedia Networks
Qiu, X., Du, Z., & Sun, X. (2019) · IEEE Access · doi:10.1109/access.2019.2956480 · Cited by 45
“In addition, with the help of artificial intelligence algorithms, intelligent authentication provisioning can be designed by utilizing channel reciprocity, specific communication link characteristics, and device characteristics [27]–[29].”
BackgroundKoufos, K., Haloui, K. E., Dianati, M., Higgins, M. D., Elmirghani, J. M. H., Imran, M. A., & Tafazolli, R. (2021) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan10040060 · Cited by 45
Deep Reinforcement Learning for Scheduling in Cellular Networks
Wang, J., Chen, X., Huangfu, Y., Li, R., Ge, Y., & Wang, J. (2019) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2019.8927868 · Cited by 44
“Some have explored its applications into the wireless communication domain, as summarized in [1] and [2].”
BackgroundGong, J., Xu, X., Qin, Y., & Dong, W. (2019) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2019.8927888 · Cited by 44
Lee, Y. L., & Qin, D. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023331 · Cited by 44
“The survey in [9] emphasizes on machine learning for massive machine type communications in HetNets.”
BackgroundA Deep Learning Method for Predictive Channel Assignment in Beyond 5G Networks
Sakib, S., Tazrin, T., Fouda, M. M., Fadlullah, Z. M., & Nasser, N. (2020) · IEEE Network · doi:10.1109/mnet.011.2000301 · Cited by 44
“In each layer, a 1-D (one-dimensional) CNN is considered with zi number of fi lters and Rectified Linear Unit (ReLU) as activation function, [6].”
BackgroundDeep Reinforcement Learning for QoS provisioning at the MAC layer: A Survey
Abbasi, M., Shahraki, A., Piran, M. J., & Taherkordi, A. (2021) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104234 · Cited by 44
Sadia, H., Hassan, A. K., Abbas, Z. H., Abbas, G., Waqas, M. M., & Han, Z. (2023) · Digital Communications and Networks · doi:10.1016/j.dcan.2023.09.002 · Cited by 44
A Waveform Parameter Assignment Framework for 6G With the Role of Machine Learning
Yazar, A., & Arslan, H. (2020) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2020.2992502 · Cited by 43
“An overview of the emerging studies on DL-based solutions for different network layers are provided in [47]–[49].”
BackgroundCost-Effective Resource Allocation for Multitier Mobile Edge Computing in 5G Mobile Networks
Šlapak, E., Gazda, J., Guo, W., Maksymyuk, T., & Döhler, M. (2021) · IEEE Access · doi:10.1109/access.2021.3059029 · Cited by 43
“To date, many research works have pursued the goal of optimal MEC deployment through the proposal of various implementations of game theory, convex optimization and deep learning [7], [19], [20].”
BackgroundConstellation Design for Future Communication Systems: A Comprehensive Survey
Barrueco, J., Montalbán, J., Iradier, E., & Angueira, P. (2021) · IEEE Access · doi:10.1109/access.2021.3090774 · Cited by 43
Latency-Energy Tradeoff in Connected Autonomous Vehicles: A Deep Reinforcement Learning Scheme
Budhiraja, I., Kumar, N., Sharma, H., Elhoseny, M., Lakys, Y., & Rodrigues, J. J. P. C. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3215523 · Cited by 43
“To overcome these issues, researchers from both academia and industry proposed a technology known as the connected autonomous vehicle (CAVs) [4].”
BackgroundYuan, Y., Liu, M., Zhuo, X., Wei, Y. D., Tu, X., & Qu, F. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3232614 · Cited by 43
“…of artificial intelligence (AI) in adapting to the harsh underwater environment and decision-making, there have emerged a few works on incorporating intelligent algorithms into the design of routing protocols to increase transmission efficiency and transmission reliability recently [15], [16].”
Background6G System architecture: A service of services vision
Taleb, T., Benzaïd, C., López, M. B., Mikhaylov, K., Tarkoma, S., Kostakos, P., Mahmood, N. H., Pirinen, P., Matinmikko‐Blue, M., Latva‐aho, M., et al. (2022) · ITU Journal on Future and Evolving Technologies · doi:10.52953/dgko1067 · Cited by 42
“Ubiquitous intelligence pertains to the convergence of communications, sensing and localization [43] combined with decentralized learning and inference over the end-to-end environment [44] and [45] .”
BackgroundA comprehensive survey of artificial intelligence applications in UAV-enabled wireless networks
Zhou, L., Yin, H., Zhao, H., Wei, J., Hu, D., & Leung, V. C. M. (2024) · Digital Communications and Networks · doi:10.1016/j.dcan.2024.11.005 · Cited by 42
Adaptive Routing in Wireless Mesh Networks Using Hybrid Reinforcement Learning Algorithm
Mahajan, S. R., Harikrishnan, R., & Kotecha, K. V. (2022) · IEEE Access · doi:10.1109/access.2022.3210993 · Cited by 42
“As a result, such networks are developed by connecting wireless access points at each network client’s location [5], [6].”
BackgroundRadio Frequency Fingerprinting Improved by Statistical Noise Reduction
Wang, W., & Gan, L. (2022) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3171792 · Cited by 41
Tefera, M. K., Zhang, S., & Jin, Z. (2023) · Entropy · doi:10.3390/e25030413 · Cited by 42
“The development of machine learning (ML) techniques, especially the deep learning (DL) method, improve the quality of resource allocation by learning efficient representations of data from unstructured sources rather than pre-established massive data sets [11].”
BackgroundUdayakumar, R., Pansambal, S., Gajmal, Y., Dr.V.R., V., & Sugumar, R. (2023) · Journal of Wireless Mobile Networks Ubiquitous Computing and Dependable Applications · doi:10.58346/jowua.2023.i2.006 · Cited by 41
“In network layers (Liu, L., 2018) (Mao, Q., 2018) (Zhang, C., 2019), routing establishments, optimizations (Zhao, L., 2019), and network securities (Guo, Y., 2021) (Xia, J., 2019) have been enhanced by DLTs. Numerous studies on data link layers (Sun, H., 2017), channel resource allocations (Li, Y.,…”
BackgroundAugmented Reality Dynamic Image Recognition Technology Based on Deep Learning Algorithm
Cheng, Q., Zhang, S., Bo, S., Chen, D., & Zhang, H. (2020) · IEEE Access · doi:10.1109/access.2020.3012130 · Cited by 41
“In addition to the Scale Invariant Feature Transform (SIFT) algorithm for feature description, the local feature descriptor Spin Image is also used to count the characteristics of the two-dimensional coordinate distribution histogram around the feature points [39], [40].”
MethodFederated Learning Over Wireless Channels: Dynamic Resource Allocation and Task Scheduling
Chu, S., Li, J., Wang, J., Wang, Z., Ding, M., Zhang, Y., Qian, Y., & Chen, W. (2022) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3196009 · Cited by 41
“3196009 also one of the current hot research directions [2].”
BackgroundStratification of 5G evolution and Beyond 5G
Ziegler, V., Wild, T., Uusitalo, M. A., Flinck, H., Räisänen, V., & Hätönen, K. (2019) · IEEE 5G World Forum (5GWF) · doi:10.1109/5gwf.2019.8911739 · Cited by 40
“More and more usage of artificial intelligence [7] within our wireless systems will expand the range of usage possibilities.”
BackgroundAI Inspired Intelligent Resource Management in Future Wireless Network
Fu, S., Yang, F., & Xiao, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2968554 · Cited by 40
“• Deep Learning (DL): DL is usually used for classification or regression [11], [18].”
BackgroundMethodAoI-minimizing Scheduling in UAV-relayed IoT Networks
Choudhury, B., Shah, V. K., Ferdowsi, A., Reed, J. H., & Hou, Y. T. (2021) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass52906.2021.00023 · Cited by 40
Lu, Y., Zhang, S., Liu, C., Zhang, R., Ai, B., Niyato, D. T., Ni, W., Wang, X., & Jamalipour, A. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3651990 · Cited by 39
“Currently, the core focus of GNN-enabled wireless designs lies in infusing intelligence across diverse protocol layers (including the physical, media access control (MAC), and network layers) to enhance system performance [124], [125].”
A Vision on Intelligent Medical Service for Emergency on 5G and 6G Communication Era
Nayak, S., & Patgiri, R. (2020) · EAI Endorsed Transactions on Internet of Things · doi:10.4108/eai.17-8-2020.166293 · Cited by 39
“Moreover, it shows high accuracy while computing a large number of network parameters [18].”
BackgroundDeep Learning-Based LOS and NLOS Identification in Wireless Body Area Networks
Cwalina, K. K., Rajchowski, P., Błaszkiewicz, O., Olejniczak, A., & Sadowski, J. (2019) · Sensors · doi:10.3390/s19194229 · Cited by 39
“The dynamic development of an AI (Artificial Intelligence), including ML (Machine Learning) and DL (Deep Learning), mainly in the field of informatics, automation and robotics also increases interest in the usage of DL methods in the radiocommunication and NGNs (Next Generation Networks) [7,8].”
MethodAdversarial denoising of EEG signals: a comparative analysis of standard GAN and WGAN-GP approaches
Tibermacine, I. E., Russo, S., Citeroni, F., Mancini, G., Rabehi, A., Alharbi, A. H., El‐kenawy, E. M., & Napoli, C. (2025) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2025.1583342 · Cited by 38
“Deep neural networks (DNNs) (Sze et al., 2017) extend beyond traditional filtering by learning complex patterns of noise and interference (Sun et al., 2018), making them suitable for environments with substantial interference and dynamic behavior (Mao et al., 2018; Russo et al., 2024b).”
Zhou, T. Y., Wang, Y., Wang, C., Salous, S., Liu, L., & Tao, C. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2999313 · Cited by 38
“representations for classification or regression purpose [42].”
Sakib, S., Tazrin, T., Fouda, M. M., Fadlullah, Z. M., & Nasser, N. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3032516 · Cited by 37
“The 1-D convolution layers have an initial filter size of SF in the first layer and Sigmoid as activation function, [17].”
BackgroundMethodEfficient Channel Estimation in OFDM Systems Using a Fast Super-Resolution CNN Model
Khichar, S., Santipach, W., Wuttisittikulkij, L., Parnianifard, A., & Chaudhary, S. (2024) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan13050055 · Cited by 36
Knowledge-Powered Explainable Artificial Intelligence for Network Automation toward 6G
Wu, Y., Lin, G., & Ge, J. (2022) · IEEE Network · doi:10.1109/mnet.005.2100541 · Cited by 36
A Machine Learning based Mission Critical Data Transmission Protocol in Wireless Sensor Networks
Raut, A. R., Khandait, S. P., & Dongre, S. (2021) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces51350.2021.9489013 · Cited by 35
“Extensive review of machine learning and deep learning algorithms for improving the real time data transmissions in WSNs is done in [31].”
BackgroundDAR-DRL: A dynamic adaptive routing method based on deep reinforcement learning
Rao, Z., Xu, Y., Yao, Y., & Meng, W. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.107983 · Cited by 35
From Nodes to Roads: Surveying DRL Applications in MEC-Enhanced Terrestrial Wireless Networks
Ullah, S. A., Bibi, M., Hassan, S. A., Abou-Zeid, H., Qureshi, H. K., Jung, H., Mahmood, A., Gidlund, M., & Hossain, E. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3568035 · Cited by 35
“Similarly, the surveys conducted in [21], [48], [49], [50] are relevant to networking.”
Load-Aware Distributed Resource Allocation for MF-TDMA Ad Hoc Networks: A Multi-Agent DRL Approach
Zhang, S., Ni, Z., Kuang, L., Jiang, C., & Zhao, X. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3201121 · Cited by 35
“Recently, motivated by the development of artificial intelligence, reinforcement learning (RL) as an efficient method for time-varying dynamic system has been gradually used in resource allocation for wireless networks [28], [29], [30].”
BackgroundA Deep Learning Model for Wireless Channel Quality Prediction
Herath, J. D., Seetharam, A., & Ramesh, A. (2019) · International Conference on Communications · doi:10.1109/icc.2019.8761934 · Cited by 35
“Additionally, the rapid increase in computational power over the last decade and the availability of large amounts of data, coupled with advances in the field of machine learning provide us the opportunity to design models that provide superior prediction performance of wireless channel quality variations [10].”
BackgroundKhan, W. U., Javed, M. A., Zeadally, S., Lagunas, E., & Chatzinotas, S. (2023) · IEEE Communications Standards Magazine · doi:10.1109/mcomstd.0007.2200065 · Cited by 34
“…consider many aspects from modulation and coding for timely scheduling of data, and optimal spectrum access. are many variants of deep reinforcement learning and some of the commonly used are deep Contextual Bandit (CB) [10], distributed proximal policy optimization, and deep policy gradient [8].”
BackgroundPhysical Layer Security in the Age of Artificial Intelligence and Edge Computing
Zhao, L., Zhang, X., Chen, J., & Zhou, L. (2020) · IEEE Wireless Communications · doi:10.1109/mwc.001.2000044 · Cited by 34
“Fortunately, the recent success of artificial intelligence (AI) and edge computing (EC) provides novel and powerful tools to solve issues in this space [11].”
BackgroundArtificial intelligence and wireless communications
Wang, J., Li, R., Wang, J., Ge, Y., Zhang, Q., & Shi, W. (2020) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1900527 · Cited by 33
Machine Learning Methods for UAV Flocks Management-A Survey
Azoulay, R., Haddad, Y., & Reches, S. (2021) · IEEE Access · doi:10.1109/access.2021.3117451 · Cited by 33
DeepSeek-Inspired Exploration of RL-Based LLMs and Synergy with Wireless Networks: A Survey
Qiao, Y., Tran, P.-N., Yoon, J. S., Nguyen, L. X., Huh, E., Niyato, D. T., & Hong, C. S. (2025) · ACM Computing Surveys · doi:10.1145/3776745 · Cited by 32
Shi, J., Sha, M., & Peng, X. (2021) · Networked Systems Design and Implementation · Cited by 32
Deep learning in physical layer communications: Evolution and prospects in 5G and 6G networks
Mao, C., Mu, Z., Liang, Q., Schizas, I. D., & Pan, C. (2023) · IET Communications · doi:10.1049/cmu2.12669 · Cited by 32
Deep Learning Meets Swarm Intelligence for UAV-Assisted IoT Coverage in Massive MIMO
Mahmood, M., Ghadaksaz, M., Koç, A., & Le‐Ngoc, T. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3318529 · Cited by 32
“The remarkable success of DL in these fields has motivated researchers to explore its potential applications in wireless communications systems [35], [36], [37], [38].”
BackgroundGuest editorial: 6G mobile networks: Emerging technologies and applications
Liang, Y., Niyato, D. T., Larsson, E. G., & Popovski, P. (2020) · China Communications · doi:10.23919/jcc.2020.9205979 · Cited by 32
Wong, L. J., Clark, W. H., Flowers, B., Buehrer, R. M., Michaels, A. J., & Headley, W. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00432 · Cited by 32
Lightweight privacy-preserving predictive maintenance in 6G enabled IIoT
Li, S., Li, S., & Min, G. (2024) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2023.100548 · Cited by 30
Deep-Learning-Aided Cross-Layer Resource Allocation of OFDMA/NOMA Video Communication Systems
Tseng, S., Chen, Y., Tsai, C.-S., & Tsai, W. (2019) · IEEE Access · doi:10.1109/access.2019.2950127 · Cited by 30
“), the focus of this paper is on a comparison of the existing works in this area using deep learning, as summarized in detail in Table 1 [40]–[42].”
BackgroundInfluentialMobility Trace Analysis for Intelligent Vehicular Networks: Methods, Models, and Applications
Celes, C. S. F. D. S., Boukerche, A., & Loureiro, A. A. F. (2021) · ACM Computing Surveys · doi:10.1145/3446679 · Cited by 30
“In addition, there are some studies on data analysis in wireless networks [Mao et al. 2018; Nguyen et al. 2020; Zhang et al. 2019].”
BackgroundChen, G., Shao, R., Shen, F., & Zeng, Q. (2023) · Sensors · doi:10.3390/s23052518 · Cited by 30
“As deep reinforcement learning (DRL) has evolved, many research works based on DRL approaches have also been achieved [13,14].”
BackgroundMultilayer extreme learning machine: a systematic review
Kaur, R., Roul, R. K., & Batra, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14634-4 · Cited by 30
“…known DL architectures such as Recurrent Neural Network (RNN), Convolution Neural Network (CNN), Long-short Term Memory (LSTM), etc. [42, 84, 86, 88, 114, 135, 164], suffer from time-consuming training process due to their complicated hierarchical structure and need to fine-tune a large number…”
MethodMintoo, A. A., Saimon, A. S. M., Bakhsh, M. M., & Akter, M. (2022) · American Journal of Scholarly Research and Innovation · doi:10.63125/sdz8km60 · Cited by 30
DeepFIR: Channel-Robust Physical-Layer Deep Learning Through Adaptive Waveform Filtering
Restuccia, F., D’Oro, S., Al-Shawabka, A., Rendon, B. C., Ioannidis, S., & Melodia, T. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3089878 · Cited by 30
“Recently, deep learning [2] has been proposed as a viable solution [28] to perform complex signal classification without incurring in manual feature extraction.”
MethodAn ultra lightweight neural network for automatic modulation classification in drone communications
Wang, M., Fang, S., Fan, Y., Li, J., Zhao, Y., & Wang, Y. (2024) · Scientific Reports · doi:10.1038/s41598-024-72867-1 · Cited by 29
Systematic Literature Review of AI-enabled Spectrum Management in 6G and Future Networks
Sabir, B., Yang, S., Nguyen, D. D., Wu, N., Abuadbba, A., Suzuki, H., Lai, S., Ni, W., Ding, M., & Nepal, . (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.10981 · Cited by 29
Wong, L. J., Clark, W. H., Flowers, B., Buehrer, R. M., Headley, W. C., & Michaels, A. J. (2021) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2021.3112939 · Cited by 29
Deep Learning-Assisted Secure UAV-Relaying Networks With Channel Uncertainties
Tang, X., Liu, N., Zhang, R., & Han, Z. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3151471 · Cited by 29
“Inrecentyears,asanimportant branchofmachinelearningtheory,deeplearninghasbeen widelyappliedinvariousresearchfields,suchastransmitpower control,channelestimation,informationsecurity,andsoon[19].”
Wireless Signal Representation Techniques for Automatic Modulation Classification
Liu, X., Li, C. J., Jin, C. T., & Leong, P. H. W. (2022) · IEEE Access · doi:10.1109/access.2022.3197224 · Cited by 29
Machine Learning: A Catalyst for THz Wireless Networks
Boulogeorgos, A. A., Yaqub, E., Renzo, M. D., Alexiou, A., Desai, R., & Klinkenberg, R. (2021) · Frontiers in Communications and Networks · doi:10.3389/frcmn.2021.704546 · Cited by 29
Stitching the Spectrum: Semantic Spectrum Segmentation with Wideband Signal Stitching
Uvaydov, D., Zhang, M., Robinson, C. P., D’Oro, S., Melodia, T., & Restuccia, F. (2024) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom52122.2024.10621332 · Cited by 29
“For this reason, a much more relevant – though significantly more challenging – problem is determining which wireless technology is utilizing a given portion of the spectrum over time and frequency, also known as spectrum classification [13].”
BackgroundLarge Language Model as a Catalyst: A Paradigm Shift in Base Station Siting Optimization
Wang, Y., Afzal, M., Li, Z., Zhou, J., Feng, C., Guo, S., & Quek, T. Q. S. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3548615 · Cited by 28
“The rapid pace of advancements in telecommunications technology [19], [20] and shifting user behavior patterns [21] require engineers to continuously learn and adapt.”
Data-Rate Driven Transmission Strategies for Deep Learning-Based Communication Systems
Chen, X., Cheng, J., Zhang, Z., Wu, L., Dang, J., & Wang, J. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.2968314 · Cited by 28
“For these reasons, with the significant development of deep learning (DL) [11]–[13], researchers have applied the machine learning (ML), especially DL technologies, to design communication systems for benefits that cannot be obtained using the conventional approaches [14]–[18].”
BackgroundHuang, S., Lin, C., Zhou, K., Yao, Y., Lu, H., & Zhu, F. (2020) · Physical Communication · doi:10.1016/j.phycom.2020.101180 · Cited by 28
Towards a Learning-Based Framework for Self-Driving Design of Networking Protocols
Pasandi, H. B., & Nadeem, T. (2021) · IEEE Access · doi:10.1109/access.2021.3061729 · Cited by 28
“RL has been utilized in tuning and optimizing many network sub-fields [37] such as Wi-Fi [21], [28] in PHY [20], [41],”
MethodQoS Aware Machine Learning Algorithms for Real-Time Applications in Wireless Sensor Networks
Raut, A. R., Khandait, S. P., & Chavhan, N. A. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-8221-9_249 · Cited by 28
Online Service Provisioning in NFV-Enabled Networks Using Deep Reinforcement Learning
Nouruzi, A., Zakeri, A., Javan, M. R., Mokari, N., Hussain, R., & Kazmi, S. M. A. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3159670 · Cited by 28
“At the same time, DRL-based methods to solve various RA problems have attracted much attention [4], [16], [17].”
MethodDeep Learning Empowered MAC Protocol Identification With Squeeze-and-Excitation Networks
Zhang, X., Ding, G., Li, J., Wang, W., & Wu, Q. (2021) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2021.3126306 · Cited by 28
Xu, C., Luong, T. V., Xiang, L., Sugiura, S., Maunder, R. G., Yang, L., & Hanzo, L. (2022) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3168725 · Cited by 28
“…processing architecture of GPUs is generally considered to be capable of excuting the V-BLAST MC-AE decoder operations faster than the conventional CPU slowed down by the exponential complexity escalation of the ML detectors of V-BLAST OFDM and V-BLAST OFDM-IM [7], [8], [10], [11], [13], [49].”
MethodHan, H., Yi, Z., Zhu, Z., Li, L., Gong, S., Li, B., & Wang, M. (2023) · Electronics · doi:10.3390/electronics12030552 · Cited by 29
“Automatic modulation recognition (AMR) is a critical step in signal detection and subsequent demodulation tasks [1], which aim to utilize prior information of signals to identify the modulation type in cognitive radio, electronic countermeasures, electromagnetic spectrum monitoring and other fields,…”
BackgroundLi, D., Liu, X., Yin, Z., Cheng, N., & Liu, J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3425470 · Cited by 28
“…understand the exact physical impact of different wireless channels on the transmission of radio signals, which is the key knowledge that enables us to design and deploy effective and feasible communication technologies for different propagation channels in practical application environments [30].”
BackgroundAnsari, S., Alnajjar, K. A., Majzoub, S., Almajali, E. R., Jarndal, A., Bonny, T., Hussain, A. J., & Mahmoud, S. A. (2025) · IEEE Access · doi:10.1109/access.2025.3580574 · Cited by 27
Adam, A. B. M., Wang, Z., Wan, X., Xu, Y., & Duo, B. (2022) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3198652 · Cited by 27
“As a powerful techniques, deep learning approaches have become useful tools in tackling communication problems [16] and proven to be more suitable to the real-time applications and solving different problems such as user association [17], [18], power allocation [19], [20], [21], subchannel…”
MethodMultiband Delay Estimation for Localization Using a Two-Stage Global Estimation Scheme
Wan, Y., Liu, A., Hu, Q., Zhang, M., & Cai, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3269624 · Cited by 27
“It has been widely employed in multisensory extended reality (XR) [6], smart transportation [7], and connected robotics and autonomous systems (CRAS) [8].”
BackgroundRau, F., Soto, I., Zabala‐Blanco, D., Azurdia-Meza, C. A., Ijaz, M., Ekpo, S., & Gutiérrez, S. (2023) · Sensors · doi:10.3390/s23114997 · Cited by 27
“Neural networks are being widely used to predict time series [24].”
Semisupervised RF Fingerprinting With Consistency-Based Regularization
Wang, W., Luo, C., An, J., Gan, L., Liao, H., & Yuen, C. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3320975 · Cited by 27
“Refer to [8], [9], and [10] for more comprehensive reviews.”
BackgroundLearning Energy-Efficient Transmitter Configurations for Massive MIMO Beamforming
Hojatian, H., Mlika, Z., Nadal, J., Frigon, J., & Leduc-Primeau, F. (2024) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2024.3419728 · Cited by 27
“Thanks to the enormous success of deep learning (DL), in a wide variety of engineering fields, deep neural networks (DNNs) have received significant attention in recent years and have been widely applied to wireless communication systems [10], [11].”
BackgroundRevenue-Optimal Auction For Resource Allocation in Wireless Virtualization: A Deep Learning Approach
Zhu, K., Xu, Y., Jun, Q., & Niyato, D. T. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3021416 · Cited by 27
Fedrec: Federated Learning of Universal Receivers Over Fading Channels
Mashhadi, M. B., Shlezinger, N., Eldar, Y. C., & Gündüz, D. (2021) · IEEE Statistical Signal Processing Workshop (SSP) · doi:10.1109/ssp49050.2021.9513736 · Cited by 27
Domingo, M. C. (2021) · Applied Sciences · doi:10.3390/app112210735 · Cited by 27
“The DNN takes the input data and extracts automatically appropriate representations for detection or classification purposes [28].”
MethodA Survey of 6G Wireless Communications: Emerging TechnologiesPreprint
Zhao, Y., Zhao, J., Zhai, W., Sun, S., Niyato, D. T., & Lam, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.08549 · Cited by 27
“1) An overview of AI and related techniques: Deep learning, considered as the vital ingredient of AI technology, has been widely used in the wireless networks in the last decade [23].”
Machine Learning in Intelligent Networks: Architectures, Techniques, and Use Cases
Dritsas, E., & Τρίγκα, Μ. (2025) · IEEE Access · doi:10.1109/access.2025.3577968 · Cited by 26
“Similarly, references [58] and [199] investigate DL for wireless and mobile networks, yet they lack a broader perspective that spans multi-layered IN designs.”
AI Reasoning for Wireless Communications and Networking: A Survey and Perspectives
Luo, H., Yan, Y., Bian, Y., Feng, W., Zhang, R., Liu, Y., Wang, J., Sun, G., Niyato, D. T., Yu, H., et al. (2026) · ACM Computing Surveys · doi:10.1145/3811822 · Cited by 26
“Over the past decades, numerous successes have been reported in applying deep learning to wireless problems, for example, neural networks for channel decoding, traffic prediction, resource allocation, and routing [3].”
AI Model Selection and Monitoring for Beam Management in 5G-Advanced
Sun, C., Zhao, L., Cui, T., Li, H., Bai, Y., Wu, S., & Tong, Q. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3337850 · Cited by 26
“Multiple studies have explored the application of AI technologies across various layers of communication protocols, as evidenced by [8].”
Background6G Wireless Communication Networks: Challenges and Potential Solution
Haque, M. A., Ahmad, S., Abboud, A. J., Hossain, M. A., Kumar, K., Haque, S., Sonal, D., Rahman, M., & Senapathy, M. (2024) · International Journal of Business Data Communications and Networking · doi:10.4018/ijbdcn.339889 · Cited by 26
Deep Neural Network Symbol Detection for Millimeter Wave Communications
Liao, Y., Farsad, N., Shlezinger, N., Eldar, Y. C., & Goldsmith, A. J. (2019) · Globecom · doi:10.1109/globecom38437.2019.9013468 · Cited by 26
Deep learning for load balancing of SDN‐based data center networks
Babayiğit, B., & Ulu, B. (2021) · International Journal of Communication Systems · doi:10.1002/dac.4760 · Cited by 25
“Equation 2 is numerically obtained by maximizing the log-likelihood estimator, which is simply an expression for SVM 31,32 is based on the LR method and appoints training examples to one of two categories with a bisecting hyperplane separating the data points.”
BackgroundMethod
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.