Learning Based Content Caching and Sharing for Wireless Networks
The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Abstract
Content caching at base stations (BSs) is a promising technique for future wireless networks by reducing network traffic and alleviating server bottleneck. However, in practice, the content popularity distribution may change with spatio-temporal variation but be unknown for BSs, which is an intractable obstacle for efficient caching strategy design. In this paper, considering unknown popularity distribution, we explore the content caching problem by jointly optimizing the content caching in cooperative BSs, content sharing among BSs, and cost of content retrieving. We tackle the problem from a multi-armed bandit learning perspective, where the learning of the popularity distribution is incorporated with the content caching and sharing process. Specifically, we first propose a centralized algorithm by employing a semidefinite relaxation approach, and we prove that this centralized algorithm learns efficient caching by deriving a sub-linear learning regret bound. To further reduce computational complexity, we propose a distributed algorithm based on alternating direction method of multipliers, where each BS only solves their own problems by exchanging local information with neighbor BSs. Extensive simulation results show the effectiveness of the proposed algorithms in terms of learning content popularity distributions of individual BSs, offloading traffic from the content server, and reducing cost of content retrieving.
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
“Compared to traditional RL irrelevant to DL, such as Q-learning [240] and Multi-Armed Bandit (MAB) learning [230], the advantage of DRL lies in that DNNs can learn key features from the raw observation data.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [230]
Citations
Cites
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
Boyd, S. (2010) · now publishers, Inc. eBooks · doi:10.1561/9781601984616 · Cited by 12,677
Finite-time Analysis of the Multiarmed Bandit Problem
Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002) · Machine Learning · doi:10.1023/a:1013689704352 · Cited by 6,033
Semidefinite Relaxation of Quadratic Optimization Problems
Luo, Z.-Q., Ma, W.-K., So, A., Ye, Y., & Zhang, S. (2010) · IEEE Signal Processing Magazine · doi:10.1109/msp.2010.936019 · Cited by 3,715
Five 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
Web caching and Zipf-like distributions: evidence and implications
Breslau, L., Cao, P., Fan, L., Phillips, G., & Shenker, S. (1999) · IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320) · doi:10.1109/infcom.1999.749260 · Cited by 3,467
FemtoCaching: Wireless Content Delivery Through Distributed Caching Helpers
Shanmugam, K., Golrezaei, N., Dimakis, A. G., Molisch, A. F., & Caire, G. (2013) · IEEE Transactions on Information Theory · doi:10.1109/tit.2013.2281606 · Cited by 1,246
Living on the edge: The role of proactive caching in 5G wireless networks
Bastug, E., Bennis, M., & Debbah, M. (2014) · IEEE Communications Magazine · doi:10.1109/mcom.2014.6871674 · Cited by 1,146
Cache in the air: exploiting content caching and delivery techniques for 5G systems
Wang, X., Chen, M., Taleb, T., Ksentini, A., & Leung, V. (2014) · IEEE Communications Magazine · doi:10.1109/mcom.2014.6736753 · Cited by 1,063 · cited 1×
“With this technique, content can be cached in base stations1 (BSs) [6]–[10] rather than CDN so that the content can be directly delivered to users by BSs, which can significantly offloading the traffic flowing to the network.”
MethodSelf-citation
Research works printed but not linked: 2
- grant, 2013, CVX Matlab Software for Disciplined Convex Programming Version 2 0
- 2016, Cisco Visual Networking Index Forecast and Methodology 2015–2020
Cited by
Items 101–143 of 143
Learning-based cooperative content caching and sharing for multi-layer vehicular networks
Shi, J., Ni, Y., Cai, L., & Du, Z. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100277 · Cited by 5
A Learning Approach to Edge Caching with Dynamic Content Library in Wireless Networks
Zhang, X., Zheng, G., Lambotharan, S., Nakhai, M. R., & Wong, K. (2019) · Globecom · doi:10.1109/globecom38437.2019.9013584 · Cited by 5
“3 presents the comparison of the average reward, i.e., the weighted content delivery rate, of the proposed caching design against the benchmark designs in [5], [6], the random caching design and the popularity-known caching design at the individual time slots.”
BackgroundMethodInfluentialMa, T., Chen, X., Ma, Z., & Jiao, L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86137-7_27 · Cited by 5
TPA based content popularity prediction for caching and routing in edge-cloud cooperative network
Yi, B., Li, F., Zhang, Y., & Wang, X. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685955 · Cited by 5
“Similarly, reference [11] adopted another learning model to estimate the popularity of contents dynamically, which was then used to guide the process of caching.”
MethodSelf-citationMultiple contents offloading mechanism in AI-enabled opportunistic networks
Chien, W.-C., Huang, S.-Y., Lai, C., Chao, H., Hossain, M. S., & Muhammad, G. (2020) · Computer Communications · doi:10.1016/j.comcom.2020.02.084 · Cited by 5
Joint Minimization of Wired and Wireless Traffic for Content Delivery by Multicast Pushing
Chen, Z., Tao, X., Jiang, C., & Leung, V. C. M. (2019) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2908398 · Cited by 5
Liu, X., & Deng, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.08332 · Cited by 5
Stateless Q-learning algorithm for service caching in resource constrained edge environment
Huang, B., Ran, Z., Yu, D., Xiang, Y., Shi, X., Li, Z., & Xu, Z. (2023) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-023-00506-7 · Cited by 4
“Song et al. [19] proposed a distributed algorithm based on alternating direction method of multipliers to jointly optimize the content caching in cooperative base stations, aiming at reducing cost of content retrieving.”
MethodJoint Service Scheduling and Content Caching Over Unreliable Channels
Nie, T., Luo, J., Gao, L. X., Zheng, F., & Yu, L. C. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322536 · Cited by 4
“[1] learns content popularity first and then proposes the centralized and distributed algorithms to maximize the cache reward.”
BackgroundSa’ad, U., Lakew, D. S., & Cho, S. (2021) · International Conference on Information Networking · doi:10.1109/icoin50884.2021.9333855 · Cited by 4
“For example, a study in [7] considered the joint problems of caching in cooperative BSs, content sharing among BSs, and cost of content retrieval between BSs.”
BackgroundA Novel Predictive Approach to Content Popularity-Aware Edge Caching in VEC
Zuo, Y., Xia, Y., Yang, R., Wang, X., Zhong, X., Xia, Q., Sun, X., & Feng, J. (2024) · IEEE International Conference on Software Services Engineering (SSE) · doi:10.1109/sse62657.2024.00014 · Cited by 4
Self-citationCost Efficient Intelligent Sensing Big Data Caching in ICN-IoT Networks
Yang, M., Deyun Gao, A., Hu, X., & Qin, Y. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278641 · Cited by 3
“The authors in [5] and [6] use multi-armed bandit (MAB) to estimate content popularity.”
BackgroundMethodEvolutionary Adaptation Mechanism for Edge Caching Under Propagation Dynamics
Fan, S., Gao, H., Tian, H., & Yang, S. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3347415 · Cited by 3
“Although, machine learning has received extensive attention to track the dynamics of popularity distribution [11], [12], [13], the learning-based edge caching algorithms rely on vast historical data which are not applicable to new hot contents, and the trial-and-error process of online learning…”
BackgroundCaching Salon: From Classical to Learning-Based Approaches
Zhao, Y., Zhang, X., Yang, K., Fan, Q., Guo, D., Lyu, Y., Yin, H., & Ma, Z. (2019) · IEEE International Symposium on Service-Oriented System Engineering (SOSE) · doi:10.1109/sose.2019.00046 · Cited by 3
“[8] 2017 Wireless Network MAB ADMM [30] synthetic data sets: 20 unique objects LFU LRU Reference algorithm [31] Yes”
BackgroundRen, J., Li, D., Zhang, L., & Zhang, G. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/8880015 · Cited by 3
“In addition, there are several technics to improve the performance of wireless networks, such as directional antennas [10–12], infrastructure support [13–15], secrecy analysis [16, 17], and reinforcement learning [18, 19].”
BackgroundOutage and delay performance of content caching in two‐tier cooperative cellular networks
Ghadi, F. R., & Javan, M. R. (2019) · IET Communications · doi:10.1049/iet-com.2018.5496 · Cited by 3
Filho, E. R. L., Savva, G., Yang, L., Fu, K., Shen, J., & Herodotou, H. (2025) · Future Internet · doi:10.3390/fi17040170 · Cited by 2
A Fault-Tolerant Mobility-Aware Caching Method in Edge Computing
Ma, Y., Zhao, H., Guo, K., Xia, Y., Wang, X., Niu, X., Zhu, D., & Dong, Y. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.048759 · Cited by 3
Self-citationA Latency Aware and Dynamic Caching Model for Heterogeneous Datalake Environments
Saxena, D., Singh, A. K., & Lindenstruth, V. (2024) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac61105.2024.00370 · Cited by 2
“Jelenkovic et al. [12] proposed a caching strategy using the Independent Reference Model (IRM) for content requests, but recent research [11], [13] suggests IRM is not suitable for dynamic web page requests.”
BackgroundMethodCooperative Caching Based on Popularity-Aware Block Partitioning in Space-Ground Integrated Networks
Wan, Y., Hou, Y., He, H., Chen, S., Jiang, X., & Yang, J. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3592597 · Cited by 2
“The problem can be solved through optimization methods [43], however, it’s still extremely challenging to solve the problem for the BSs which are located in remote areas and have poor resources, especially when the number of nodes increases.”
Caching Strategy Based on Deep Q-Learning in Device-to-device Scenario
Zeng, S., Ren, Y., Wang, Y., Zhao, T., & Qian, Z. (2019) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2019.00047 · Cited by 2
“In [16], the multi-arm bandit learning is used to jointly optimize the content caching method in the cooperative base stations, wherein the popularity distribution learning is incorporated with the content caching and sharing process.”
Method[Retracted] Data Processing Method of Distributed Parallel Database System Based on Wireless Network
Guo, Z., Jiang, G., & Zhao, J. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/2366262 · Cited by 2
“Therefore, it is necessary to use the distributed database synchronization technology to reasonably plan and layout the data in different places, so that the data can be shared [15].”
BackgroundRetractedA Distributed Caching Scheme in Dense Small Cell Network with Cooperative Transmission
Hou, R., Sun, S., Lui, K., & Li, H. (2018) · IEEE Vehicular Technology Conference · doi:10.1109/vtcspring.2018.8417555 · Cited by 2
“Some works study the file popularity estimation and cache update policy [10], [11], which is outside scope of this paper.”
BackgroundA Spectral Efficiency Guaranteed Caching Scheme in Small Cell Networks
Xie, H., Hou, R., Lui, K., & Li, H. (2018) · IEEE Vehicular Technology Conference · doi:10.1109/vtcspring.2018.8417485 · Cited by 3
“[4]–[8] focus on file popularity estimation.”
On the Exploration and Exploitation Trade-off in Cooperative Caching-enabled Networks
Bommaraveni, S., Gautam, S., Vu, T. X., & Chatzinotas, S. (2021) · IEEE Wireless Communications and Networking Conference Workshops (WCNCW) · doi:10.1109/wcncw49093.2021.9419984 · Cited by 2
QuAd-caching management model for heterogeneous data lake environments
Saxena, D., Singh, A. K., & Lindenstruth, V. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129133 · Cited by 1
Smart Helper-Aided F-RANs: Improving Delay and Reducing Fronthaul Load
Mokhtarzadeh, H., Saif, M., Hossain, M. J., & Cheng, J. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3523961 · Cited by 1
“Consequently, caching capability helps to reduce the load on the fronthaul link by reducing the amount of data that needs to be retrieved from the MBS [9], [10].”
BackgroundA Feature-Based Bayesian Method for Content Popularity Prediction in Edge-Caching Networks
Mehrizi, S., Tsakmalis, A., Chatzinotas, S., & Ottersten, B. (2019) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc.2019.8885590 · Cited by 16
Artificial Intelligence for Optimizing Edge
Wang, X., Han, Y., Leung, V. C. M., Niyato, D. T., Yan, X., & Chen, X. (2020) · Springer eBooks · doi:10.1007/978-981-15-6186-3_8 · Cited by 1
Self-citationMulti-agent Deep Reinforcement Learning-Based Content Caching in Cache-Enabled Networks
Liu, S., Chen, J., Gao, D., Yang, M., & Ma, J. (2023) · Communications in computer and information science · doi:10.1007/978-981-19-9697-9_12 · Cited by 1
Learning to Cache: Distributed Coded Caching in a Cellular Network With Correlated DemandsPreprint
Krishnendu, S., Bharath, B. N., Garg, N., Bhatia, V., & Ratnarajah, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.06195 · Cited by 1
Yousefi, H. (2018) · Scholarship@Western (Western University)
Stochastic Design and Analysis of Wireless Cloud Caching NetworksPreprint
Azimi‐Abarghouyi, S. M., Nasiri‐Kenari, M., & Debbah, M. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.01708
“In general, the content popularity distribution can be characterized by machine learning tools [33]-[34].”
Dynamic Content Updates in Heterogeneous Wireless NetworksPreprint
Abad, M. S. H., Özfatura, E., Erçetin, Ö., & Gündüz, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.09445
“In [6], this approach has been extended to a cooperative caching framework, where the SBSs fetch a requested content from neighboring SBSs if it is cached there.”
MethodEdge Caching for Small Cell Networks
Pervej, M. F. (2020) · Digital Commons - USU (Utah State University) · doi:10.26076/6805-42b7
“However, in comparison to the proposed system model of [24], this thesis considers a device to device (D2D) based CDN platform.”
BackgroundMethodBase Station Selection for Cache-enabled Wireless Networks
Liao, Y.-C., Gan, R., Xiao, Y., Yang, P., & Fu, B. (2019) · International Symposium on Networks, Computers and Communications (ISNCC) · doi:10.1109/isncc.2019.8909184
“In addition, the cost related to content retrieving has been widely combined in content caching and sharing over perfect content popularity distribution [8] and unknown content popularity distribution [9], respectively.”
BackgroundCooperative Caching based on Small Base Station Selection for Wireless Networks
Gan, R., Liao, Y.-C., Xiao, Y., Yang, P., & Fu, B. (2019) · International Symposium on Networks, Computers and Communications (ISNCC) · doi:10.1109/isncc.2019.8909138
“Moreover, an alternative scenario was considered in [7], where the SBSs are endowed with the ability to help each other accomplish the file transmission with the objective of maximize the expected total caching reward.”
BackgroundContent-Aware Proactive Caching and Energy-Efficient Design in Clustered Small Cell Networks
Xiang, Y., Luo, H., Teng, L., & Liu, T. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-67720-6_20
Learning Distributed Coded Caching Strategy in a Cellular Network
Doshi, Y., Bharath, B. N., Garg, N., Bhatia, V., & Ratnarajah, T. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-spring51267.2021.9449047
A Future-Oriented Cache Management for Mobile Games
Hu, Y. H., Wang, M., Chen, Y., & Fan, C. (2021) · IEEE Conference on Games (CoG) · doi:10.1109/cog52621.2021.9619023
Gupta, D., Rani, S., & Ahmed, S. H. (2022) · AIP conference proceedings · doi:10.1063/5.0080968
CacheMoE: Task-Aware Expert Model Caching for Multitask Inference in Distributed Edge IoT Networks
Sinthia, A. K., Mahbub, N. I., Sultan, M. N., & Huh, E. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3625275
“Song et al. [51] addressed cooperative caching and sharing among base stations under uncertain content popularity.”
Li, J., Xia, Y., & Feng, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3725916
“To address these limitations, learning-based approaches have recently been proposed [10], [11], [12].”
Metadata
- Authors
- Song, J., Sheng, M., Quek, T. Q. S., Xu, C., & Wang, X.
- Affiliations
- Xidian University (CN)
- Singapore University of Technology and Design (SG)
- Venue
- IEEE Transactions on Communications
- Published
- 2017
- Pages
- 1-1
- ISSN
- 0090-6778 (ISSN-L)
- OpenAlex
- W2624186268
- Cited by
- 144
- References
- 37
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 13 · 2023: 11 · 2022: 10 · 2021: 23 · 2020: 27 · 2019: 39 · 2018: 16
- FWCI
- 14.92
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Communications (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Caching and Content Delivery
- Physical Sciences › Computer Science › Computer Networks and Communications › Age of Information Optimization
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- content caching, content sharing, base station, multi-armed bandits, cooperative caching, semidefinite relaxation, distributed algorithms, alternating direction method of multipliers, traffic offloading, wireless networks
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.