Learning Radio Resource Management in RANs: Framework, Opportunities, and Challenges
The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
In the fifth generation (5G) of mobile broadband systems, radio resource management (RRM) will reach unprecedented levels of complexity. To cope with the ever more sophisticated RRM functionalities and the growing variety of scenarios, while carrying out the prompt decisions required in 5G, this manuscript presents a lean RRM architecture that capitalizes on recent advances in the field of machine learning in combination with the large amount of data readily available in the network from measurements and system observations. The architecture consists of a learner (or a few), which learns RRM policies directly from the data gathered in the network using a single general-purpose learning framework, and a set of distributed actors, which execute RRM policies issued by the learner and repeatedly generate samples of experience. Thus, the complexity of RRM is shifted to the design of the learning framework, while the RRM algorithms derived from this framework are executed in a computationally efficient distributed manner at the radio access nodes. The potential of this approach is verified in a pair of pertinent scenarios, and future directions on applications of machine learning to RRM are discussed. Although we focus on a mobile broadband context, the concepts proposed hereafter extend to any radio access network technology where one can conceive the idea of a central learning unit gathering data from distributed actors.
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
“In addition, DL for radio resource management in 5G networks is also suggested in [94], and a users location-aware DL method for run-time optimal users association for the maximization of sum-rate in M-MIMO based land mobile radio cellular networks is proposed in [95].”
From Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019) · cites this paper as [95]
Citations
Cites
Reinforcement 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 15×
“, using the same ANN weights) across different actors, 1 We follow the notation in [8] and note the difference between random variables and their instantiations with capital letters and lower letters, respectively.”
BackgroundMethodInfluentialReinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Andrews, J. G., Buzzi, S., Choi, W., Hanly, S. V., Lozano, A., Soong, A. C. K., & Zhang, J. C. (2014) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2014.2328098 · Cited by 8,106 · cited 1×
“Careful load balancing and efficient inter-cell interference mitigation will be crucial in ultra-dense small cell deployments [1].”
BackgroundAsynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 1×
“, [10] or the A3C framework [11]), the intention of this work is to exemplify how one such framework would be deployed in the proposed architecture to produce control policies specialized to individual RRM functionalities.”
BackgroundFive disruptive technology directions for 5G
Boccardi, F., Heath, R. W., Lozano, A., Marzetta, T. L., & Popovski, P. (2014) · IEEE Communications Magazine · doi:10.1109/mcom.2014.6736746 · Cited by 3,709
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Espeholt, L., Soyer, H., Munos, R., Simonyan, K., Mnih, V., Ward, T., Doron, Y., Firoiu, V., Harley, T., Dunning, I., et al. (2018) · arXiv · doi:10.48550/arxiv.1802.01561 · Cited by 1,708 · cited 2×
“, [10] or the A3C framework [11]), the intention of this work is to exemplify how one such framework would be deployed in the proposed architecture to produce control policies specialized to individual RRM functionalities.”
Background(1998) · Springer eBooks · doi:10.1007/978-1-4615-5529-2 · Cited by 1,235
User Association for Load Balancing in Heterogeneous Cellular Networks
Ye, Q., Rong, B., Chen, Y., Al-Shalash, M., Caramanis, C., & Andrews, J. G. (2013) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2013.040413.120676 · Cited by 1,228 · cited 1×
“Removing cell edges requires to address two problems: first, associating users to multiple TRPs for coordinate multipoint (CoMP) operation - a NP-hard task even for single TRP case [13]; second, dynamically forming joint transmission areas between TRPs by optimizing multiple SIR-thresholds per TRP to adjust to changes…”
MethodDesign considerations for a 5G network architecture
Agyapong, P., Iwamura, M., Staehle, D., Kiess, W., & Benjebbour, A. (2014) · IEEE Communications Magazine · doi:10.1109/mcom.2014.6957145 · Cited by 611 · cited 2×
“…which shall integrate new technology components (e.g. massive MIMO, mm-Wave communication, network slicing, vehicular networks, more and broader frequency bands, etc.) with larger optimization domains and tighter latency requirements, RRM is expected to reach unprecedented complexity [1]-[3].”
BackgroundA Q-learning based approach to interference avoidance in self-organized femtocell networks
Bennis, M., & Niyato, D. (2010) · 2010 IEEE Globecom Workshops · doi:10.1109/glocomw.2010.5700414 · Cited by 161 · cited 1×
“IEEE Communications Magazine • September 2018 145 [5] M.”
Background
Research works printed but not linked: 1
- goodfellow, 2016, Deep Learning
Cited by
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
Massive MIMO is a reality—What is next?
Björnson, E., Sanguinetti, L., Wymeersch, H., Hoydis, J., & Marzetta, T. L. (2019) · Digital Signal Processing · doi:10.1016/j.dsp.2019.06.007 · Cited by 797
Noor-A-Rahim, M., Liu, Z., Lee, H., Khyam, M. O., He, J., Pesch, D., Moessner, K., Saad, W., & Poor, H. V. (2022) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3173031 · Cited by 737
Wireless 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
Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networks
Nasir, Y. S., & Guo, D. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2933973 · Cited by 660
“Classical Q-learning techniques have been applied to the power allocation problem in [17]–[21].”
BackgroundMethodResultXu, 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
“Considering the distributedimplementationofMARL,afrequentlyadopted solutioniscentralizedtraininganddistributedexecution (CTDE).”
InfluentialQuantum 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
“In addition, DL for radio resource management in 5G networks is also suggested in [94], and a users location-aware DL method for run-time optimal users association for the maximization of sum-rate in M-MIMO based land mobile radio cellular networks is proposed in [95].”
MethodBlockchain for 5G and beyond networks: A state of the art survey
Nguyen, D. C., Pathirana, P. N., Ding, M., & Seneviratne, A. (2020) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2020.102693 · Cited by 412
“to unprecedented levels of complexity in mobile resource management [175].”
BackgroundAI-Assisted Network-Slicing Based Next-Generation Wireless Networks
Shen, X., Gao, J., Wu, W., Lyu, K., Li, M., Zhuang, W., Li, X., & Rao, J. (2020) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2020.2965100 · Cited by 342
“AI, paves the path for applying AI in NGWNs [27].”
MethodBenzaid, C., & Taleb, T. (2020) · IEEE Network · doi:10.1109/mnet.001.1900252 · Cited by 314
“[5] leveraged ML techniques to design a general-purpose learning framework, having the ability to autonomously generate algorithms specialized for Radio Resource Management (RRM) functionalities in 5G RANs.”
MethodPower Allocation in Multi-User Cellular Networks: Deep Reinforcement Learning Approaches
Meng, F., Chen, P., Wu, L., & Cheng, J. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3001736 · Cited by 288
“A framework of centralized training and distributed execution [36] was proposed to address these challenges.”
BackgroundDeep-Learning-Based Wireless Resource Allocation With Application to Vehicular Networks
Liang, L., Ye, H., Yu, G., & Li, G. Y. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2957798 · Cited by 282
“The power allocation problem has also been studied in [23], [65], which consider a cellular network with several cells and the base station in each cell serves multiple users.”
BackgroundLacava, A., Polese, M., Sivaraj, R., Soundrarajan, R., Bhati, B. S., Singh, T., Zugno, T., Cuomo, F., & Melodia, T. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3266642 · Cited by 207
“More examples can be found in [30], which discusses the state of the art and the challenges of intelligent RRM.”
BackgroundA survey on Zero touch network and Service Management (ZSM) for 5G and beyond networks
Liyanage, M., Pham, Q.-V., Dev, K., Bhattacharya, S., Maddikunta, P. K. R., Gadekallu, T. R., & Yenduri, G. (2022) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2022.103362 · Cited by 151
Cell-Free Massive MIMO for Wireless Federated Learning
Vu, T. T., Ngo, D. T., Tran, N. H., Ngo, H. Q., Dao, M. N., & Middleton, R. H. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3002988 · Cited by 194
“THE use of machine learning (ML) techniques in telecommunications industry has been growing dramatically in recent years [1], [2].”
BackgroundAI-Enabled Future Wireless Networks: Challenges, Opportunities, and Open Issues
Elsayed, M., & Erol-Kantarci, M. (2019) · IEEE Vehicular Technology Magazine · doi:10.1109/mvt.2019.2919236 · Cited by 156
“The research in [8] provides a radio resource-allocation learner architecture as well as a learning-algorithm framework based on reinforcement learning.”
BackgroundA review of wireless communication using high-altitude platforms for extended coverage and capacity
Arum, S. C., Grace, D., & Mitchell, P. (2020) · Computer Communications · doi:10.1016/j.comcom.2020.04.020 · Cited by 167
“8 – Machine learning based architecture for RAN [154].”
BackgroundInfluentialTowards artificial intelligence enabled 6G: State of the art, challenges, and opportunities
Zhang, S., & Zhu, D. (2020) · Computer Networks · doi:10.1016/j.comnet.2020.107556 · Cited by 162
Machine Learning Meets Communication Networks: Current Trends and Future Challenges
Ahmad, I., Shahabuddin, S., Malik, H. H., Harjula, E., Leppänen, T., Lovén, L., Anttonen, A., Sodhro, A. H., Alam, M. M., Juntti, M. J., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3041765 · Cited by 160
“However, the current MAC protocols derive little insight from such data as it considered to be short-lived and localized commodity due to aging and user mobility [127].”
BackgroundDRL-Based Energy-Efficient Resource Allocation Frameworks for Uplink NOMA Systems
Wang, X., Zhang, Y., Shen, R., Xu, Y., & Zheng, F. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2982699 · Cited by 152
“To solve these problems, we propose a multi-DQN structure inspired by [47].”
MethodRisk-Aware Resource Allocation for URLLC: Challenges and Strategies with Machine Learning
Azari, A., Özger, M., & Çavdar, Ç. (2019) · IEEE Communications Magazine · doi:10.1109/mcom.2019.1800610 · Cited by 143
Alhayani, B., Kwekha-Rashid, A. S., Mahajan, H. B., İlhan, H., Uke, N., Alkhayyat, A. H., & Mohammed, H. J. (2022) · Applied Nanoscience · doi:10.1007/s13204-021-02152-4 · Cited by 138
RetractedFederated Learning Empowered Computation Offloading and Resource Management in 6G-V2X
Prathiba, S. B., Raja, G., Anbalagan, S., Dev, K., Gurumoorthy, S., & Sankaran, A. P. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2021.3103124 · Cited by 130
“The Q-function is the estimated amount of incentives for a program p , state a , time t , and behaviour c [35].”
BackgroundApplications and Techniques for Fast Machine Learning in Science
Deiana, A. M., Tran, N. V., Agar, J., Blott, M., Guglielmo, G. D., Duarte, J. M., Harris, P. C., Hauck, S., Liu, M., Neubauer, M. S., et al. (2022) · Frontiers in Big Data · doi:10.3389/fdata.2022.787421 · Cited by 125
An AI-Assisted Smart Healthcare System Using 5G Communication
Pradhan, B., Das, S., Roy, D. S., Routray, S., Benedetto, F., & Jhaveri, R. H. (2023) · IEEE Access · doi:10.1109/access.2023.3317174 · Cited by 117
“cell network will be examined in a new study by [11].”
BackgroundML-Based Radio Resource Management in 5G and Beyond Networks: A Survey
Bartsiokas, I. A., Gkonis, P. K., Kaklamani, D. I., & Venieris, I. S. (2022) · IEEE Access · doi:10.1109/access.2022.3196657 · Cited by 116
“However, the coexistence of these technologies can significantly increase network complexity, due to the insertion of multiple computational levels and hardware needs, thus necessitating the importance of optimal radio resource management (RRM) strategies [21].”
A reinforcement learning approach to power control and rate adaptation in cellular networks
Ghadimi, E., Davide Calabrese, F., Peters, G., & Soldati, P. (2017) · 2017 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2017.7997440 · Cited by 100
Self-citationIntelligent User Association for Symbiotic Radio Networks Using Deep Reinforcement Learning
Zhang, Q., Liang, Y., & Poor, H. V. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.2984758 · Cited by 109
“In this subsection, we provide a distributed DRL-based user association algorithm, in which the BS serves as the agent and uses a centralized training and distributed execution framework [31].”
MethodLei, L., Lagunas, E., Yuan, Y., Kibria, M. G., Chatzinotas, S., & Ottersten, B. (2020) · IEEE Access · doi:10.1109/access.2020.3011746 · Cited by 107
“, greedy or round-robin algorithms [13], whereas adopting sophisticated heuristics to achieve satisfactory performance would require long computing time [21].”
BackgroundPower Allocation in Multi-User Cellular Networks with Deep Q Learning Approach
Meng, F., Chen, P., & Wu, L. (2019) · ICC 2019 - 2019 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2019.8761431 · Cited by 87
“of interacting with an unknown environment by exploration and exploitation. The Q learning method is the most well-studied RL algorithm, and it is exploited to cope with power allocation (PA) in [11]–[13], and some others [14]. The DNN trained with Q learning is called deep Q network (DQN), and it is proposed to addre…”
MethodExtreme Communication in 6G: Vision and Challenges for ‘in-X’ Subnetworks
Berardinelli, G., Baracca, P., Adeogun, R., Khosravirad, S. R., Schaich, F., Upadhya, K., Li, D., Tao, T., Viswanathan, H., & Mogensen, P. (2021) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2021.3121530 · Cited by 96
Matthiesen, B., Zappone, A., Besser, K.-L., Jorswieck, E. A., & Debbah, M. A. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3000328 · Cited by 90
Survey of Radio Resource Management in 5G Heterogeneous Networks
Manap, S. A., Dimyati, K., Hindia, M. N., Talip, M. S. A., & Tafazolli, R. (2020) · IEEE Access · doi:10.1109/access.2020.3002252 · Cited by 89
“Another interesting approach was presented by Calabrese et al. [97], where the RRM learning technique was split between the actors and learners.”
MethodExplainable and Robust Artificial Intelligence for Trustworthy Resource Management in 6G Networks
Khan, N., Coleri, S., Abdallah, A., Celik, A., & Eltawil, A. M. (2024) · IEEE Communications Magazine · doi:10.1109/mcom.001.2300172 · Cited by 74
Annu, & Rajalakshmi, P. (2024) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2024.3368240 · Cited by 73
Bayesian Optimization for Radio Resource Management: Open Loop Power Control
Maggi, L., Valcarce, A., & Hoydis, J. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3078490 · Cited by 67
“…learning (RL) has shown a great potential to solve RRM problems in simulations by running algorithms for thousands of iterations (e.g., [6]), it often suffers from poor convergence speed which renders its use questionable for many real-world applications, where one is often limited to…”
BackgroundSong, Y., & Wu, R. (2021) · Knowledge Management Research & Practice · doi:10.1080/14778238.2021.1955630 · Cited by 64
Intent-Aware Radio Resource Scheduling in a RAN Slicing Scenario Using Reinforcement Learning
Nahum, C., Lopes, V. H. L., Dreifuerst, R. M., Batista, P., Correa, I., Cardoso, K. V., Klautau, A., & Heath, R. W. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3297014 · Cited by 64
“In this context, machine learning is a key enabler in handling large data sets, presenting an opportunity to give data a central role in wireless networking [4].”
BackgroundJoint Resource Allocation to Minimize Execution Time of Federated Learning in Cell-Free Massive MIMO
Vu, T. T., Ngo, D. T., Ngo, H. Q., Dao, M. N., Tran, N. H. K., & Middleton, R. H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3183295 · Cited by 63
Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning
Liu, D., Sun, C., Yang, C., & Hanzo, L. (2020) · IEEE Network · doi:10.1109/mnet.001.1900517 · Cited by 56
“, distributed resource optimization [10], rather than the variable optimization problems formulated as P1 of Fig.”
BackgroundSelf-citationResource management in UAV-assisted wireless networks: An optimization perspective
Masroor, R., Naeem, M., & Ejaz, W. (2021) · Ad Hoc Networks · doi:10.1016/j.adhoc.2021.102596 · Cited by 54
Lavdas, S., Gkonis, P. K., Zinonos, Z., Trakadas, P. T., Sarakis, L., & Papadopoulos, K. A. (2022) · IEEE Access · doi:10.1109/access.2022.3202640 · Cited by 52
“Finally, in the last case, the best policies are defined dynamically via mobile agents that interact with the wireless environment [10].”
BackgroundTestbed for 5G Connected Artificial Intelligence on Virtualized Networks
Nahum, C., Pinto, L. D. N. M., Tavares, V., Batista, P., Lins, S., Linder, N., & Klautau, A. (2020) · IEEE Access · doi:10.1109/access.2020.3043876 · Cited by 51
“But CAI is also a convenient testbed to explore RAN slicing and RRM problems tackled with reinforcement learning (RL) methods [44].”
BackgroundLiu, D., & Yang, C. (2019) · IEEE Access · doi:10.1109/access.2019.2925019 · Cited by 50
Nagib, A. M., Abou-Zeid, H., & Hassanein, H. S. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3336191 · Cited by 49
“This will make solving dynamic RRM problems even more complex [4].”
BackgroundOnline Energy-Efficient Power Control in Wireless Networks by Deep Neural Networks
Zappone, A., Debbah, M., & Altman, Z. (2018) · 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc.2018.8445857 · Cited by 48
Reinforcement 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
Pala, S., Singh, K. K., Li, C., & Dobre, O. A. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3502394 · Cited by 46
“This setup is implemented for both DDPG and DQN methods, denoted as C-DDPG and C-DQN, respectively, in the figures [60].”
The case for blockchain in IoT identity management
Sousa, P. R., Resende, J. S., Martins, R., & Antunes, L. F. (2020) · Journal of Enterprise Information Management · doi:10.1108/jeim-07-2018-0148 · Cited by 46
A Tutorial on Radio System-Level Simulations With Emphasis on 3GPP 5G-Advanced and Beyond
Pedersen, K. I., Maldonado, R., Pocovi, G., Juan, E., Lauridsen, M., Kovács, I. Z., Brix, M., & Wigard, J. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3381669 · Cited by 45
“ML techniques can improve air-interface performance [155], [156], beamforming [152], radio resource management [149], power control optimization [150], network energy efficiency and load balancing [151], handovers [153], and many other network functionalities.”
Deep Learning for Beam Hopping in Multibeam Satellite Systems
Lei, L., Lagunas, E., Yuan, Y., Kibria, M. G., Chatzinotas, S., & Ottersten, B. (2020) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2020-spring48590.2020.9128905 · Cited by 45
“DL has received considerable research attention over the past few years in wireless communications [6]–[8].”
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
Distributed RRM for 5G Multi-RAT Multiconnectivity Networks
Monteiro, V. F., Sousa, D. A., Maciel, T. F., Cavalcanti, F. R. P., Silva, C. E. F. D. F., & Rodrigues, E. B. (2018) · IEEE Systems Journal · doi:10.1109/jsyst.2018.2838335 · Cited by 43
On Energy Efficient Resource Allocation in Shared RANs: Survey and Qualitative Analysis
Marzouk, F., Barraca, J. P., & Radwan, A. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3003261 · Cited by 42
“Reinforcement Learning for self-healing SON has been studied in [77] and [78], and further enhancements of RRM, in SON with ML, have been also been studied [79].”
BackgroundAsheralieva, A., & Niyato, D. T. (2020) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2020.2994366 · Cited by 40
“…and control protocols to support various mobile/IoT applications, e.g., spectrum sharing [15]–[19], network virtualization [20]–[22], or data and resource management [14], [23]–[27], by taking advantage of such useful blockchain features as traceability, decentralization, immutability and privacy.”
BackgroundDeep Reinforcement Learning Based Resource Management in UAV-Assisted IoT Networks
Munaye, Y. Y., Juang, R., Lin, H., Tarekegn, G. B., & Lin, D. (2021) · Applied Sciences · doi:10.3390/app11052163 · Cited by 38
“In Reference [26], the initial users and secondary users based on a constant control were considered.”
BackgroundInfluentialLearning-Assisted Optimization for Energy-Efficient Scheduling in Deadline-Aware NOMA Systems
Lei, L., You, L., He, Q., Vu, T. X., Chatzinotas, S., Yuan, D., & Ottersten, B. (2019) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2019.2902838 · Cited by 37
Ahmed, I., & Khammari, H. (2018) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/glocomw.2018.8644454 · Cited by 33
Liu, J., Lin, C. R., Hu, Y., & Donta, P. K. (2022) · Sensors · doi:10.3390/s22062328 · Cited by 33
“In addition, the previous works [29,38,39] introduced different deep Q-learning-based power control methods to maximize their objectives.”
MethodA Novel Machine Learning-Based Scheme for Spectrum Sharing in Virtualized 5G Networks
Morgado, A. J., Saghezchi, F. B., Mumtaz, S., Frascolla, V., Rodríguez, J., & Otung, I. E. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3173153 · Cited by 32
“Authors in [49] apply RL for RRM, proposing an architecture where every BS has an independent actor that takes actions and shares its experience with a central learner module in the core network (CN), sharing the learner among the actors.”
BackgroundA Machine Learning Approach for 5G SINR Prediction
Ullah, R., Marwat, S. N. K., Ahmad, A. M., Ahmed, S., Hafeez, A. B., Kamal, T., & Tufail, M. (2020) · Electronics · doi:10.3390/electronics9101660 · Cited by 32
Quality of Experience in 6G Networks: Outlook and Challenges
Taha, A. M. (2021) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan10010011 · Cited by 31
“, in [17,18]), whereby a hierarchical structure of intelligence that can address different operational tasks is introduced.”
BackgroundPala, S., Singh, K. K., Li, C., Dobre, O. A., & Duong, T. Q. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3526781 · Cited by 30
“This setup is implemented for DDPG, denoted as C-DDPG in the simulation [63].”
5G Heterogeneous Networks: An Overview on Radio Resource Management Scheduling Schemes
Mamane, A., Ghazi, M. E., Barb, G.-R., & Oteşteanu, M. (2019) · Mediterranean Congress of Telecommunications (CMT) · doi:10.1109/cmt.2019.8931369 · Cited by 27
“KPIs like reliability, battery latency and lifetime are as essential as standard methods such as data rates.[4] Efficient use of Radio Resource (RRM) is necessary to reach the 5G KPI targets.”
MethodA Survey on Requirements of Future Intelligent Networks: Solutions and Future Research Directions
Husen, A., Chaudary, M. H., & Ahmad, F. (2022) · ACM Computing Surveys · doi:10.1145/3524106 · Cited by 26
Toward Safe and Accelerated Deep Reinforcement Learning for Next-Generation Wireless Networks
Nagib, A. M., Abou-Zeid, H., & Hassanein, H. S. (2022) · IEEE Network · doi:10.1109/mnet.106.2100578 · Cited by 26
“The complexity of RRM problems is expected to continue growing in NGNs as optimization domains become larger and network requirements become tighter [1].”
BackgroundEsswie, A. A., Pedersen, K. I., & Mogensen, P. (2020) · IEEE Access · doi:10.1109/access.2020.3011026 · Cited by 26
Advancements in 5G New Radio TDD Cross Link Interference Mitigation
Pedersen, K. I., Esswie, A. A., Lei, D., Harrebek, J., Yuk, Y., Selvaganapathy, S., & Helmers, H. (2021) · IEEE Wireless Communications · doi:10.1109/mwc.001.2000376 · Cited by 25
Energy-Efficient Rate-Splitting Multiple Access: A Deep Reinforcement Learning-Based Framework
Diamanti, M., Kapsalis, G., Tsiropoulou, E. E., & Papavassiliou, S. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3322047 · Cited by 25
“Based on the proposed multi-agent DRL problem modeling described above, the centralized training and distributed execution architectural paradigm can be adopted [15], [25].”
MethodIntelligent User Association for Symbiotic Radio Networks Using Deep Reinforcement Learning
Zhang, Q., Liang, Y., & Poor, H. V. (2019) · Globecom · doi:10.1109/globecom38437.2019.9014223 · Cited by 24
“on Algorithm In this subsection, we provide a distributed DRL-based user association algorithm, in which the BS serves as the agent and uses a centralized training and distributed execution framework [31]. In this algorithm, the BS allocates Ncomputing units to make decision for IoT devices individually. In other word…”
MethodSecurity Orchestration in 5G and Beyond Smart Network Technologies
Batewela, S., Liyanage, M., Zeydan, E., Ylianttila, M., & Ranaweera, P. S. (2025) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2025.3563619 · Cited by 23
“Some of the listed work, such as [124], [125], [126], [127], [128], could be helpful in realizing a unified SCO framework for ZSM.”
A Comparison of Reinforcement Learning Algorithms in Fairness-Oriented OFDMA Schedulers
Comşa, I.-S., Zhang, S., Aydın, M. E., Kuonen, P., Trestian, R., & Ghinea, G. (2019) · Information · doi:10.3390/info10100315 · Cited by 23
“, massive Multiple-In, Multiple-Out (MIMO), mm-Wave communications) are envisioned to be incorporated into the next generation wireless networks to cope with these challenges, the complexity of the Radio Resource Management (RRM) will reach a substantial proportion [2].”
BackgroundSAMUS: Slice-Aware Machine Learning-based Ultra-Reliable Scheduling
Bektas, C., Overbeck, D., & Wietfeld, C. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500837 · Cited by 23
“[7] concentrates on handovers between base stations for changing channel qualities and provides an overview of different ML concepts.”
BackgroundExploiting Future Radio Resources With End-to-End Prediction by Deep Learning
Guo, J., Yang, C., & Chih‐Lin, I. (2018) · IEEE Access · doi:10.1109/access.2018.2882815 · Cited by 22
Distributed and Multi-Task Learning at the Edge for Energy Efficient Radio Access Networks
Miozzo, M., Ali, Z., Giupponi, L., & Dini, P. (2021) · IEEE Access · doi:10.1109/access.2021.3050841 · Cited by 22
“This type of framework, when based on DL applied to the raw network data, can be able to improve the feature-engineered solutions based on standard ML designed to solve specific tasks in a restricted environment and, possibly, solve multiple tasks [27].”
MethodPower Control in 5G Heterogeneous Cells Considering User Demands Using Deep Reinforcement Learning
Giannopoulos, A., Spantideas, S., Tsinos, C. G., & Trakadas, P. T. (2021) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-79157-5_9 · Cited by 22
“In order to cope with these demanding specifications, the design requirements of 5G networks inherently involve self-configuration and optimization capabilities of the network parameters [4], enabling autonomous decision-making processes.”
BackgroundWIP: Demand-Driven Power Allocation in Wireless Networks with Deep Q-Learning
Giannopoulos, A., Spantideas, S., Capsalis, N., Gkonis, P. K., Karkazis, P., Sarakis, L., Trakadas, P. T., & Capsalis, C. N. (2021) · IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) · doi:10.1109/wowmom51794.2021.00045 · Cited by 22
“Such networks are provisioned to present self-organizing capabilities, including selfconfiguration of radio resources and self-optimization of network parameters [2].”
BackgroundCoordinated Reinforcement Learning for Optimizing Mobile NetworksPreprint
Bouton, M., Farooq, H., Forgeat, J., Bothe, S., Shirazipour, M., & Karlsson, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.15175 · Cited by 22
“Learning algorithms leveraging coordination can use a centralized controller [7], [13] which does not scale to a large number of agents.”
BackgroundExplainable Artificial Intelligence for Energy-Efficient Radio Resource Management
Marcu, A.-D., Peesapati, S. K. G., Moysen, J., Imtiaz, S., & Gross, J. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10119130 · Cited by 21
“Thus, experts started using advanced AI methods such as deep learning (DL) and RL to solve this problem [4].”
DRL-Based Multidimensional Resource Management in SWIPT-NOMA-Enabled MEC
Shi, Z., Xie, X., Lu, H., Yang, H., Xiong, Z., Cai, J., & Ding, Z. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3306880 · Cited by 21
“As pointed out in [43], this mechanism has the following ratio-nales.”
BackgroundMethodDownlink Power Control in Dense 5G Radio Access Networks Through Deep Reinforcement Learning
Saeidian, S., Tayamon, S., & Ghadimi, E. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9149157 · Cited by 21
Self-citationΝομικός, Ν., Talebi, M. S., Charalambous, T., & Wichman, R. (2022) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2022.3154292 · Cited by 19
Softwarization and Optimization for Sustainable Future Mobile Networks: A Survey
Temesgene, D. A., Núñez‐Martínez, J., & Dini, P. (2017) · IEEE Access · doi:10.1109/access.2017.2771938 · Cited by 19
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
Reducing Latency: Improving Handover Procedure Using Machine Learning
Zhohov, R., Palaios, A., Rydén, H., Moosavi, R., & Berglund, J. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-spring51267.2021.9448875 · Cited by 18
“In the fifth-generation (5G) of mobile communication systems, new Radio Resource Management (RRM) mechanisms are needed in order to cope with a growing variety of scenarios and use-cases [4].”
BackgroundGeneralization in Reinforcement Learning for Radio Access Networks
Demirel, B., Wang, Y., Tatino, C., & Soldati, P. (2026) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2026.3655335 · Cited by 16
“…(AI) has shown strong potential in addressing these challenges for the next generation of RANs by replacing rule-based designs with AI-native solutions for various RAN functionalities [1], such as tra ffi c prediction, mobility optimization, interference management, and more [2], [3], [4].”
Self-citationDeep Deterministic Policy Gradient With Prioritized Sampling for Power Control
Zhou, S., Cheng, Y., Lei, X., & Duan, H. (2020) · IEEE Access · doi:10.1109/access.2020.3033333 · Cited by 16
“Then, we study the experience sharing approach to centrally train [29], [30] the network.”
MethodKoudouridis, G. P., He, Q., & Dán, G. (2022) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-022-02164-w · Cited by 17
“To address RRM problems with reduced complexity and cope with the growing variety of scenarios, in [67], the authors propose a lean RRM architecture that consists of one or a few learner(s) that learn RRM policies directly from the data gathered in the network using a single general-purpose…”
Design Principles for Model Generalization and Scalable AI Integration in Radio Access Networks
Soldati, P., Ghadimi, E., Demirel, B., Wang, Y., Gaigalas, R., & Sintorn, M. (2024) · IEEE Communications Magazine · doi:10.1109/mcom.001.2300812 · Cited by 15
“An architecture advocating actor-learner decoupling for RAN applications was independently proposed in [19].”
MethodSelf-citationDeep Reinforcement Learning Framework for Joint Resource Allocation in Heterogeneous Networks
Zhang, Y., Kang, C., Teng, Y., Li, S., Zheng, W., & Fang, J. (2019) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2019.8891448 · Cited by 15
6G and V2X Communications: Applications, Features, and Challenges
Ouamna, H., Madini, Z., & Zouine, Y. (2022) · 2022 8th International Conference on Optimization and Applications (ICOA) · doi:10.1109/icoa55659.2022.9934407 · Cited by 14
“The base stations (BS) usually take the main responsibility for RRM in the current cellular V2X networks, which has been widely studied in the research works [13].”
BackgroundSoltani, S., Ghafourian, E., Salehi, R., Martín, D. R., & Vahidi, M. (2024) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2024.042693 · Cited by 14
Lei, L., Vu, T. X., You, L., Fowler, S. A., & Yuan, D. (2018) · International Conference on Communications · doi:10.1109/icc.2018.8422520 · Cited by 14
Resource Allocation for Multi-UAV Assisted IoT Networks: A Deep Reinforcement Learning Approach
Munaye, Y. Y., Juang, R., Lin, H., & Tarekegn, G. B. (2020) · International Conference on Pervasive Artificial Intelligence (ICPAI) · doi:10.1109/icpai51961.2020.00011 · Cited by 14
“Two studies [8,9] explored an RL-based approach to improving the power control and network rate adaptation strategy for regulating the HetNets RA in terrestrial communication.”
BackgroundA compendium of radio resource management in UAV-assisted next generation computing paradigms
Shah, Z., Naeem, M., Javed, U., Ejaz, W., & Altaf, M. (2022) · Ad Hoc Networks · doi:10.1016/j.adhoc.2022.102844 · Cited by 13
Kaur, A., & Kumar, K. (2020) · Physical Communication · doi:10.1016/j.phycom.2020.101226 · Cited by 13
Vu, T. T., Ngo, D. T., Ngo, H. Q., Dao, M. N., Tran, N. H. K., & Middleton, R. H. (2020) · arXiv (Cornell University) · Cited by 13
Saghezchi, F. B., Rodríguez, J., Vujičić, Z., Nascimento, A., Huq, K. M. S., & Gil‐Castiñeira, F. (2021) · Springer eBooks · doi:10.1007/978-3-030-74648-3_1 · Cited by 12
Deep Learning in Network-Level Performance Prediction Using Cross-Layer Information
Cao, Q., Pun, M.-O., & Yi, C. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3163274 · Cited by 12
“There were early studies exploiting machine learning in radio resource management (RRM) for wireless networks [1], [2].”
BackgroundFerrús, R., Sallent, O., & Pérez-Romero, J. (2020) · IEEE Communications Magazine · doi:10.1109/mcom.001.1900475 · Cited by 12
“…control, mobility control, scheduling, inter-cell interference coordination, etc.), with only a few works starting to appear in this area (e.g., [9, 10]). contribute to filling this gap, and consistent with recent initiatives arising from the standardization novel functional framework for the…”
Result
Metadata
- Authors
- Calabrese, F. D., Wang, L., Ghadimi, E., Peters, G., Hanzo, L., & Soldati, P.
- Affiliations
- Huawei Technologies (Sweden) (SE)
- University of Southampton (GB)
- Venue
- IEEE Communications Magazine
- Published
- 2018-09
- Volume
- 56
- Issue
- 9
- Pages
- 138-145
- ISSN
- 0163-6804 (ISSN-L)
- 1558-1896
- OpenAlex
- W2891171329
- Cited by
- 154
- References
- 15
- Citations by year
- 2026: 6 · 2025: 13 · 2024: 10 · 2023: 17 · 2022: 29 · 2021: 23 · 2020: 39 · 2019: 16 · 2018: 1
- FWCI
- 7.56
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Communications Magazine (publishedVersion)
- ePrints Soton (University of Southampton) (submittedVersion)
- Funders
- Engineering and Physical Sciences Research Council (EP/N004558/1)
- 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 Communication Networks Research
- Keywords
- radio resource management, 5G, machine learning, radio access network, distributed learning, network measurement data, mobile broadband, reinforcement learning
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.