Learn to Cache: Machine Learning for Network Edge Caching in the Big Data Era
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
The unprecedented growth of wireless data traffic not only challenges the design and evolution of the wireless network architecture, but also brings about profound opportunities to drive and improve future networks. Meanwhile, the evolution of communications and computing technologies can make the network edge, such as BSs or UEs, become intelligent and rich in terms of computing and communications capabilities, which intuitively enables big data analytics at the network edge. In this article, we propose to explore big data analytics to advance edge caching capability, which is considered as a promising approach to improve network efficiency and alleviate the high demand for the radio resource in future networks. The learning-based approaches for network edge caching are discussed, where a vast amount of data can be harnessed for content popularity estimation and proactive caching strategy design. An outlook of research directions, challenges, and opportunities is provided and discussed in depth. To validate the proposed solution, a case study and a performance evaluation are presented. Numerical studies show that several gains are achieved by employing learning- based schemes for edge caching.
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
“As illustrated in [233] [234], the complexity of optimization algorithms can be transferred to the training of DNNs, and thus breaking the practical limitation of employing them.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [233]
In the citing paper
“For the second purpose, when using DNNs to optimize the strategy of edge caching, online heavy computation iterations can be avoided by offline training.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [233]
Citations
Cites
Machine Learning Paradigms for Next-Generation Wireless Networks
Jiang, C., Zhang, H., Ren, Y., Han, Z., Chen, K.-C., & Hanzo, L. (2017) · IEEE Wireless Communications · doi:10.1109/mwc.2016.1500356wc · Cited by 1,095
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 3×
“For infrastructureless caching, the authors of [1] discuss the importance of exploring where, what, and when to cache and share data.”
BackgroundInfluentialA Survey of Caching Mechanisms in Information-Centric Networking
Zhang, M., Luo, H., & Zhang, H. (2015) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2015.2420097 · Cited by 360
Big data caching for networking: moving from cloud to edge
Zeydan, E., Bastug, E., Bennis, M., Kader, M. A., Karatepe, I. A., Er, A. S., & Debbah, M. (2016) · IEEE Communications Magazine · doi:10.1109/mcom.2016.7565185 · Cited by 310
Wireless communications in the era of big data
Bi, S., Zhang, R., Ding, Z., & Cui, S. (2015) · IEEE Communications Magazine · doi:10.1109/mcom.2015.7295483 · Cited by 260
A Learning-Based Approach to Caching in Heterogenous Small Cell Networks
Bharath, B. N., Nagananda, K. G., & Poor, H. V. (2016) · IEEE Transactions on Communications · doi:10.1109/tcomm.2016.2536728 · Cited by 202
Bai, B., Wang, L., Han, Z., Chen, W., & Svensson, T. (2016) · IEEE Wireless Communications · doi:10.1109/mwc.2016.7553029 · Cited by 145
Learning Based Content Caching and Sharing for Wireless Networks
Song, J., Sheng, M., Quek, T. Q. S., Xu, C., & Wang, X. (2017) · IEEE Transactions on Communications · doi:10.1109/tcomm.2017.2713384 · Cited by 144 · cited 2×
“The multi-armed bandit learning scheme [10] has also been applied to edge caching design by properly designing the reward of caching.”
BackgroundMethodContent-aware user clustering and caching in wireless small cell networks
Elbamby, M. S., Bennis, M., Saad, W., & Latva‐aho, M. (2014) · International Symposium on Wireless Communication Systems · doi:10.1109/iswcs.2014.6933489 · Cited by 121
Joint Caching, Routing, and Channel Assignment for Collaborative Small-Cell Cellular Networks
Khreishah, A. A., Chakareski, J., & Gharaibeh, A. M. (2016) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2016.2577199 · Cited by 98
Cited by
Items 201–212 of 212
A Data Distribution and Caching Mechanism for Heterogeneous Edges and Devices
Li, J., Zheng, X., Yu, W., Wu, J., Liao, H., Zhou, G., Qian, C., Yan, Y., Hu, X., & Wang, J. (2023) · International Conference on Artificial Intelligence of Things and Systems (AIoTSys) · doi:10.1109/aiotsys58602.2023.00036
“[12] discuss learning-based approaches for network edge caching.”
BackgroundTarangga, B., & Trafika, E. (2024) · Information Technology International Journal · doi:10.33005/itij.v1i2.17
Model-Based and Model-Free Learning-Based Caching for Dynamic Content
Abolhassani, B., Eryılmaz, A., & Hou, Y. T. (2024) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom61039.2024.10773884
Darbanian, E., & Nickray, M. (2025) · TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES · doi:10.55730/1300-0632.4113
UniCache: A Unified Batch-Level Learning-Based Content Caching
Chen, Y., Zhang, X., Yang, Y., Huan, C., Ma, S., Ye, J., Wang, P., & Wu, J. (2025) · International Workshop on Quality of Service · doi:10.1109/iwqos65803.2025.11143380
“Object-level learning methods predict popularity [12], [13], [15] or reuse distance [14], [16]–[18], [21] based on object-specific features for caching decisions.”
Marwan, M., Afoudi, Y., Hmaidi, S., Temghart, A. A., & Lazaar, M. (2025) · Cluster Computing · doi:10.1007/s10586-025-05752-9
“This adaptive caching approach addresses critical challenges in resource-constrained edge environments, such as cache overflow, network congestion, and service-level agreement (SLA) violations, thereby enhancing system reliability and improving the overall quality of user experience [5 ].”
Online Learning for Edge Node Program Placement in Mobile Edge Computing Networks
Feng, M., & Krunz, M. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3658535
“Because the content popularity profile is often unknown, machine learning (ML) algorithms have been developed to predict the content request pattern and optimize caching strategies (e.g., [12], [13], [14]).”
PCICaching: Learning-Driven and Resilient UAV Caching with Cache-Aware User Association in SAGINs
Tie, L., Sun, C., Zhang, Y., & Sun, W. (2026) · Electronics · doi:10.3390/electronics15061170
Popularity-Aware Neural Network-based Caching
Park, C., & Kim, D. (2026) · ACM Symposium on Applied Computing · doi:10.1145/3748522.3779764
“Toaddress this issue, the concept of caching, referred to as NN-cache, has been applied to DNN services [6].”
Rashid, H. U., & Jeong, S.-H. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02596-0
Rethinking Cache Eviction: Low-Overhead and Precise Learning-based Design
Wang, Q., Xu, C., Zhou, W., Fang, J., Xiong, Y., & Niu, Z. (2026) · ACM Transactions on Computer Systems · doi:10.1145/3839232 · Cited by 1
“Multiple works have studied on making eviction decision by predicting objects’ popularity [26, 27, 31, 41, 47, 52, 53, 61, 64, 66, 81, 83], hit probability (e.g., HRO [55] and LHR [73]), or reuse distance (e.g., Raven [34], LRB [62], LFO [19], Hawkeye [36], Demand-MIN [37], Parrot [48], HALP [63],…”
Wang, W., Ji, Y., Zhang, C., Zhang, X., Qiao, M., & Zhou, X. (2026) · Frontiers in Communications and Networks · doi:10.3389/frcmn.2026.1914399
Metadata
- Authors
- Chang, Z., Lei, L., Zhou, Z., Mao, S., & Ristaniemi, T.
- Affiliations
- North China Electric Power University (CN)
- University of Luxembourg (LU)
- Venue
- IEEE Wireless Communications
- Published
- 2018-06
- Volume
- 25
- Issue
- 3
- Pages
- 28-35
- ISSN
- 1536-1284 (ISSN-L)
- 1558-0687
- OpenAlex
- W2833256931
- Cited by
- 212
- References
- 15
- Citations by year
- 2026: 9 · 2025: 11 · 2024: 10 · 2023: 18 · 2022: 30 · 2021: 41 · 2020: 52 · 2019: 34 · 2018: 7
- FWCI
- 20.75
- Type
- journal article
- Language
- en
- Open access
- green
- orbilu.uni.lu
- Locations
- IEEE Wireless Communications (publishedVersion)
- Open Repository and Bibliography (University of Luxembourg) (submittedVersion, cc-by-nc-sa)
- Funders
- National Science Foundation (1702957, 1736470)
- Auburn University
- National Natural Science Foundation of China (61601181, 4174104, 2016000020124G081)
- Fonds National de la Recherche Luxembourg (11632107)
- Fundamental Research Funds for the Central Universities (2017MS13, 2016000020124G081, 4174104, 61601181)
- H2020 European Research Council (742648)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Caching and Content Delivery
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Networks and Communications › Age of Information Optimization
- Keywords
- machine learning, big data analytics, proactive caching, radio resource efficiency, edge computing
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.