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
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498
“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.”
BackgroundSelf-citationYao, J., Han, T., & Ansari, N. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2908280 · Cited by 248
A deep reinforcement learning-based framework for content caching
Zhong, C., Gursoy, M. C., & Velipasalar, S. (2018) · 2018 52nd Annual Conference on Information Sciences and Systems (CISS) · doi:10.1109/ciss.2018.8362276 · Cited by 231
Learn to Cache: Machine Learning for Network Edge Caching in the Big Data Era
Chang, Z., Lei, L., Zhou, Z., Mao, S., & Ristaniemi, T. (2018) · IEEE Wireless Communications · doi:10.1109/mwc.2018.1700317 · Cited by 212
“The multi-armed bandit learning scheme [10] has also been applied to edge caching design by properly designing the reward of caching.”
BackgroundMethodDeep Reinforcement Learning for Mobile Edge Caching: Review, New Features, and Open Issues
Zhu, H., Cao, Y., Wang, W., Jiang, T., & Jin, S. (2018) · IEEE Network · doi:10.1109/mnet.2018.1800109 · Cited by 153
“The problem of content caching and sharing among multiple cooperative SBSs was solved through the MAB approach in [10].”
MethodDeep Reinforcement Learning-Based Edge Caching in Wireless Networks
Zhong, C., Gursoy, M. C., & Velipasalar, S. (2020) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2020.2968326 · Cited by 159
“a multi-agent Q-learning solution was proposed in [25], and authors in [26] and [27] presented two different multi-armed bandit based caching schemes.”
BackgroundCaching Transient Data for Internet of Things: A Deep Reinforcement Learning Approach
Zhu, H., Cao, Y., Wei, X., Wang, W., Jiang, T., & Jin, S. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2882583 · Cited by 159
“In [8], the estimation of the file popularity was incorporated with the file caching process through the multiarmed bandit approach.”
MethodZhang, D., Wang, W., Zhang, J., Zhang, T., Du, J., & Yang, C. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3264553 · Cited by 117
“Song and Sheng [44] proposed a DRL-based framework designed to maximize click-through rates.”
BackgroundA Mobility-Aware Vehicular Caching Scheme in Content Centric Networks: Model and Optimization
Zhang, Y., Li, C., Luan, T. H., Fu, Y., Shi, W., & Zhu, L. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2899923 · Cited by 98
Cooperative Caching Strategy With Content Request Prediction in Internet of Vehicles
Wang, R., Kan, Z., Cui, Y., Wu, D., & Zhen, Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3056084 · Cited by 100
“In [15]–[17], multiarmed bandit learning was employed to estimate the content popularity, which was then used to optimize the”
MethodMulti-Agent Reinforcement Learning Based Cooperative Content Caching for Mobile Edge Networks
Jiang, W. P., Feng, G., Qin, S., & Liu, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2916314 · Cited by 83
“In this case, learning methods could be used to predict content popularity from traffic and content access pattern [16]–[20].”
BackgroundMethodInfluentialLiu, X., & Deng, Y. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3073623 · Cited by 94
A Secure Content Caching Scheme for Disaster Backup in Fog Computing Enabled Mobile Social Networks
Su, Z., Xu, Q., Luo, J., Pu, H., Peng, Y., & Lu, R. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2849984 · Cited by 78
“[34] explored the content caching problem with a multiarmed bandit learning algorithm to jointly optimize content popularity distributions and the cost of content retrieving.”
BackgroundWu, Q., Wang, W., Fan, P., Fan, Q., Zhu, H., & Letaief, K. B. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3403842 · Cited by 88
“In [37], Song et al. addressed the content caching and sharing problem in cooperative base stations while considering unknown content popularity distribution and content retrieval costs.”
BackgroundContent-Aware Proactive Caching for Backhaul Offloading in Cellular Network
Doan, K. N., Nguyen, T. V., Quek, T. Q. S., & Shin, H. (2018) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2018.2806971 · Cited by 73
“For example, works in [3]–[8] optimize the cache content at the BS to increase the user’s quality-ofservice (QoS), while the optimal cache placement is studied in [9]–[11] to improve the energy efficiency.”
BackgroundSelf-citationAsheralieva, A., & Niyato, D. T. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2934027 · Cited by 69
“, [7], [36]), the content popularity distribution is stationary over a relatively long period T 1 slots.”
BackgroundTang, J., Tang, H., Zhang, X. Y., Cumanan, K., Chen, G., Wong, K., & Chambers, J. A. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2954127 · Cited by 70
“and the learning-based centralized caching scheme [4].”
Chen, S., Yao, Z., Jiang, X., Yang, J., & Hanzo, L. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.3044298 · Cited by 66
“Additionally, in order to find the optimal caching strategy, the algorithm in [26] had to iterate over all feasible actions which might lead to a high computation complexity.”
MethodInfluentialA Realization of Fog-RAN Slicing via Deep Reinforcement Learning
Xiang, H., Yan, S., & Peng, M. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.2965927 · Cited by 67
“Particularly, the content popularity distribution may change with spatio-temporal variation [21] and the channel is variant in the real wireless environment.”
BackgroundCollaborative Multi-Agent Multi-Armed Bandit Learning for Small-Cell Caching
Xu, X., Tao, M., & Shen, C. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.2966599 · Cited by 64
“The work [18] also utilizes MAB to estimate local popularity of each SBS and then optimize the cache strategies to minimize the total cost of multiple SBSs with centralized and distributed algorithms.”
MethodEdge Intelligence for Adaptive Multimedia Streaming in Heterogeneous Internet of Vehicles
Dai, P., Song, F. B., Liu, K., Dai, Y., Zhou, P., & Guo, S. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3106147 · Cited by 64
“The edge cache schemes, such as cooperative caching [5], vehicle-assisted caching [6] and learning-based caching [7], are proposed to prefetch the file for accelerating user access.”
D2D-Assisted Caching on Truncated Zipf Distribution
Li, Q., Zhang, Y., Pandharipande, A., Ge, X., & Zhang, J. (2019) · IEEE Access · doi:10.1109/access.2019.2894837 · Cited by 58
“Then the popularity distribution of contents can be learnt periodically or whenever necessary and known to the system by using learning techniques or big data analytics [37], [38].”
BackgroundAsheralieva, A., & Niyato, D. T. (2020) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2020.2978117 · Cited by 53
“In heterogeneous and small-cell CDNs (e.g., [7], [8], [17], [20], [26], [27], [35]–[40]), in addition to the macro-cell BSs, the content can be placed at densely deployed small-cell BSs (SBSs) to improve spectral efficiency.”
BackgroundResultInfluentialDeep Multi-Agent Reinforcement Learning Based Cooperative Edge Caching in Wireless Networks
Zhong, C., Gursoy, M. C., & Velipasalar, S. (2019) · International Conference on Communications · doi:10.1109/icc.2019.8762084 · Cited by 53
“And to seek for the optimal cooperative caching policy in a decentralized caching network, the authors in [11] presented a multi-armed bandit based solution, while the authors in [12] adopted a multi-agent Q-learning scheme.”
MethodA Game-Theoretic Approach to Cache and Radio Resource Management in Fog Radio Access Networks
Sun, Y., Peng, M., & Mao, S. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2935098 · Cited by 51
“In [14], learning content popularity is incorporated in multi-armed bandit learning [15], and content caching and sharing are optimized under the current popularity estimation.”
BackgroundCocktail Edge Caching: Ride Dynamic Trends of Content Popularity With Ensemble Learning
Zong, T., Li, C., Lei, Y., Li, G., Cao, H., & Liu, Y. (2022) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2022.3193680 · Cited by 55
“Recent measurement studies have demonstrated that IRM cannot model the intrinsic non-stationarity in online traffic [19], [20].”
BackgroundXiao, H., Zhuang, Y., Xu, C., Wang, W., Zhang, H., Ding, R., Cao, T., Zhong, L., & Muntean, G. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3312916 · Cited by 46
“Time-Varying Information: It includes the video popularity, user requests, and network conditions [18], [19].”
BackgroundSelf-citationCaching With Time-Varying Popularity Profiles: A Learning-Theoretic Perspective
Bharath, B. N., Nagananda, K. G., Gündüz, D., & Poor, H. V. (2018) · IEEE Transactions on Communications · doi:10.1109/tcomm.2018.2835479 · Cited by 51
Popularity-Aware Caching Increases the Capacity of Wireless Networks
Qiu, L., & Cao, G. (2019) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2019.2892419 · Cited by 44
“Furthermore, these works [14], [15], [16], [17] only proposed caching schemes, and the effect of caching on network capacity was not investigated.”
BackgroundGame Theoretical Secure Caching Scheme in Multihoming Edge Computing-Enabled Heterogeneous Networks
Xu, Q., Su, Z., Zheng, Q., Luo, M., Dong, B., & Zhang, K. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2876417 · Cited by 44
“Although some existing methods make efforts to improve the content caching performance in wireless networks [28]–[30], it is still a challenge to provide secure caching services in heterogeneous networks due to the following reasons.”
MethodWu, H., Fan, Y., Wang, Y., Ma, H., & Xing, L. (2021) · Sensors · doi:10.3390/s21155033 · Cited by 53
“When the nodes in the wireless network model move, the average user throughput will increase significantly [107].”
BackgroundMethodDQN-enabled content caching and quantum ant colony-based computation offloading in MEC
Li, C., Zhang, Y., & Luo, Y. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109900 · Cited by 44
Learning-Based Cooperative Content Caching Policy for Mobile Edge Computing
Jiang, W. P., Feng, G., Qin, S., & Liang, Y. (2019) · International Conference on Communications · doi:10.1109/icc.2019.8761121 · Cited by 37
“In [7], [8], a multi-armed bandit (MAB) method is used to online learn the content popularity distribution.”
MethodA Personalized Preference Learning Framework for Caching in Mobile Networks
Malik, A. M., Kim, J., Kim, K. S., & Shin, W.-Y. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.2975786 · Cited by 32
“eir approximate solutions. On the one hand, studies on integrating machine learning-based or data-driven algorithms into caching frameworks in wireless networks have recently received attention [12], [13], [14], [15], [16]. In [12], [13], [14], the optimal caching problems were studied when the file popularity profile i…”
BackgroundHan, Y., Ai, L., Wang, R., Wu, J. H., Liu, D., & Ren, H. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3090440 · Cited by 30
“Reference [13] applies the semidefinite relaxation approach in the centralized cache placement situation, where the cache placement strategy of all base stations is jointly derived.”
BackgroundMethodInfluentialSomesula, M. K., Rout, R. R., & Somayajulu, D. V. L. N. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.108876 · Cited by 34
Recommendation-Driven Multi-Cell Cooperative Caching: A Multi-Agent Reinforcement Learning Approach
Zhou, X., Ke, Z., & Qiu, T. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3297213 · Cited by 31
Proactive Content Caching Based on Actor–Critic Reinforcement Learning for Mobile Edge Networks
Jiang, W. P., Feng, D., Sun, Y., Feng, G., Wang, Z., & Xia, X. (2021) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2021.3130995 · Cited by 32
Deep Reinforcement Learning for Edge Caching and Content Delivery in Internet of Vehicles
Dai, Y., Xu, D., Lu, Y., Maharjan, S., & Zhang, Y. (2019) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccchina.2019.8855951 · Cited by 26
“In [11], the authors estimated the unknown popularity of cached contents by using multi-armed bandit learning, and then proposed a content caching policy based on the learned content popularity distribution in wireless networks.”
BackgroundContent Caching in HAP-Assisted Multi-UAV Networks Using Hierarchical Federated Learning
Masood, A., Nguyen, T. V., Truong, T. P., & Cho, S. (2021) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc52510.2021.9621115 · Cited by 28
Joint Long-Term Cache Updating and Short-Term Content Delivery in Cloud-Based Small Cell Networks
Wu, X., Li, Q., Li, X., Leung, V. C. M., & Ching, P. C. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.2970986 · Cited by 25
“For instance, cache updating schemes were studied in some learning-based research [21]–[24].”
BackgroundA Game-Theoretic Analysis of Joint Mobile Edge Caching and Peer Content Sharing
Jiang, C., Gao, L. X., Luo, J., Zhou, P., & Li, J. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3225021 · Cited by 24
“Some recent works focused on cooperative caching and sharing in wireless networks [22], [23], [24], [25], [26].”
BackgroundTeng, Z., Fang, J., & Liu, Y. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3361796 · Cited by 24
“To mitigate the limitations of storage capacity and duplication in edge devices, collaborative caching has been recognized as an effective solution [2].”
BackgroundMobility-Aware Content Preference Learning in Decentralized Caching Networks
Ye, Y., Xiao, M., & Skoglund, M. (2019) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2019.2937519 · Cited by 23
“transfer learning-based approach is proposed, where extra source domain samples are provided for estimation. The authors in [20] construct an extreme learning machine (ELM) to estimate popularity. In [24], content preference is learned by multiarmed bandit method incorporated with the content caching and sharing proce…”
MethodMachine-Learning Approach for User Association and Content Placement in Fog Radio Access Networks
Yan, S., Jiao, M., Zhou, Y., Peng, M., & Daneshmand, M. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2973339 · Cited by 22
“In [19], Q -learning is used for the efficient caching strategy design where the proposal outperforms traditional caching strategies.”
MethodIntelligent Cache Pollution Attacks Detection for Edge Computing Enabled Mobile Social Networks
Xu, Q., Su, Z., Zhang, K., & Li, P. (2019) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2019.2918573 · Cited by 21
“According to the existing caching schemes based on Zipf-like distribution [14], [15], the edge devices close to mobile users proactively cache popular contents that are frequently requested by mobile users [16].”
Downlink Coordinated Multi-Point Transmission in Ultra-Dense Networks with Mobile Edge Computing
Chen, S., Zhao, T., Chen, H., & Meng, W. (2018) · IEEE Network · doi:10.1109/mnet.2018.1700421 · Cited by 20
“The collaboration between different caches is not a new topic, as an effective way to enlarge storage capacity in computers [9].”
BackgroundDecentralized Multi-Agent Multi-Armed Bandit Learning With Calibration for Multi-Cell Caching
Xu, X., & Tao, M. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.3045050 · Cited by 21
“In [33], MAB is applied for local popularity prediction and then an alternating direction method of multipliers algorithm is utilized for decentralized cache decision making.”
MethodYan, S., Qi, L., Zhou, Y., Peng, M., & Rahman, G. (2019) · IEEE Transactions on Communications · doi:10.1109/tcomm.2019.2950215 · Cited by 19
“Considering the calculation complexity of the specific popularity numerical probability, the final popularity result is expressed by the popularity level [30].”
BackgroundYe, C., Cui, Y., Yang, Y., & Wang, R. (2019) · IEEE Transactions on Communications · doi:10.1109/tcomm.2019.2919724 · Cited by 20
“In [21] and [22], the authors formulate the optimal caching design problem for a single-cell wireless network [21] and the optimal cooperative caching design problem for a multi-cell wireless network [22], and develop low-complexity algorithms to obtain approximate solutions using results for multi-armed bandit proble…”
BackgroundMethodLearning to Cache: Federated Caching in a Cellular Network With Correlated Demands
Tharakan, K. S., Bharath, B. N., Garg, N., Bhatia, V., & Ratnarajah, T. (2021) · IEEE Transactions on Communications · doi:10.1109/tcomm.2021.3132048 · Cited by 24
Gao, X., Huang, X., Tang, Y., Shao, Z., & Yang, Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3072115 · Cited by 18
“[18] proposed a joint cache placement and content sharing scheme among cooperative caching units to maximize the content caching revenue and minimize the content sharing expense.”
BackgroundZhou, P., Gong, S., Xu, Z., Chen, L., Xie, Y., Jiang, C., & Ding, X. (2021) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2021.3075770 · Cited by 18
Multi-Agent Reinforcement Learning-Based Joint Caching and Routing in Heterogeneous Networks
Yang, M., Gao, D., Foh, C. H., Quan, W., & Leung, V. C. M. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3391322 · Cited by 19
“Song et al. [8] and Yan et al. [9] all study online joint caching and fetching algorithms in a single-hop setting, while the multi-armed bandit (MAB) method is used in [8] to estimate content popularity.”
BackgroundMethodDeep Reinforcement Learning-Based Joint Caching and Routing in AI-Driven Networks
Yang, M., Gao, D., Zhang, W., Yang, D., Niyato, D. T., Zhang, H., & Leung, V. C. M. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3481276 · Cited by 21
A Bayesian Poisson–Gaussian Process Model for Popularity Learning in Edge-Caching Networks
Mehrizi, S., Tsakmalis, A., Chatzinotas, S., & Ottersten, B. (2019) · IEEE Access · doi:10.1109/access.2019.2927494 · Cited by 17
Cocktail Edge Caching: Ride Dynamic Trends of Content Popularity with Ensemble Learning
Zong, T., Li, C., Lei, Y., Li, G., Cao, H., & Liu, Y. (2021) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom42981.2021.9488910 · Cited by 19
“Recent measurement studies have demonstrated that IRM cannot model the intrinsic non-stationarity in online traffic [18], [19].”
BackgroundTransient content caching and updating with modified harmony search for Internet of Things
Xu, C., & Wang, X. (2018) · Digital Communications and Networks · doi:10.1016/j.dcan.2018.10.002 · Cited by 18
Self-citationYi, B., Lv, J., Wang, X., Ma, L., & Huang, M. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2022.09.014 · Cited by 17
Self-citationProactive Caching Strategy With Content-Aware Weighted Feature Matrix Learning in Small Cell Network
Teng, L., Xiang, Y., Tang, J., & Liao, M. (2019) · IEEE Communications Letters · doi:10.1109/lcomm.2019.2896028 · Cited by 16
“methodology, the multi player multi-armed bandit (MPMAB) scheme studied in [7] set tradeoff between exploitation and”
MethodInfluentialA Feature-Based Bayesian Method for Content Popularity Prediction in Edge-Caching Networks
Mehrizi, S., Tsakmalis, A., Chatzinotas, S., & Ottersten, B. (2019) · Open Repository and Bibliography (University of Luxembourg) · Cited by 15
Cooperation Based Proactive Caching in Multi-Tier Cellular Networks
Ahmad, F., Ahmad, A., Hussain, I., Uthansakul, P., & Khan, S. (2020) · Applied Sciences · doi:10.3390/app10186145 · Cited by 16
“In [14], the author suggested the multi-armed bandit algorithm to estimate content popularity and the authors in [15] proposed an extreme-learning machine algorithm for estimation of the future content popularity.”
BackgroundUser Preference Learning-Aided Collaborative Edge Caching for Small Cell Networks
Pervej, M. F., Tan, L. T., & Hu, R. Q. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322208 · Cited by 18
“[13] proposed a dynamic approach for the scenarios of the single player and the multiple players.”
BackgroundZhang, X., Zheng, G., Lambotharan, S., Nakhai, M. R., & Wong, K. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.2977895 · Cited by 14
“Solving problem in (10) via either the branching algorithms such as the branch and bound (B&B) algorithm, or the semidefinite relaxation (SDR) approach [3] will generally require high computational complexity.”
BackgroundMethodInfluentialDistributed Caching in Converged Networks: A Deep Reinforcement Learning Approach
Xiong, J., Fang, Y., Cheng, P., Shi, Z., & Zhang, W. (2020) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2020.2996087 · Cited by 14
“In [19], learning-based content caching and sharing scheme is proposed.”
BackgroundCollaborative Multi-Agent Reinforcement Learning of Caching Optimization in Small-Cell Networks
Xu, X., & Tao, M. (2018) · Globecom · doi:10.1109/glocom.2018.8647341 · Cited by 12
“In [7], the coordination among SBSs only exists in the cache”
BackgroundInfluentialEdge Caching for D2D Enabled Hierarchical Wireless Networks with Deep Reinforcement Learning
Li, W., Wang, C., Ding, L., Hu, B., Wang, X., & Ren, J. (2019) · Wireless Communications and Mobile Computing · doi:10.1155/2019/2561069 · Cited by 14
“Recently, a learning-based method is proposed to jointly optimize the mobile content sharing and caching [4, 5].”
Self-citationStochastic Design and Analysis of User-Centric Wireless Cloud Caching Networks
Azimi‐Abarghouyi, S. M., Nasiri‐Kenari, M., & Debbah, M. A. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.2988559 · Cited by 13
“In general, the content popularity distribution can be characterized by machine learning tools [37], [38].”
BackgroundIncreasing network throughput based on dynamic caching policy at wireless access points
Ren, J., Hou, T., Wang, H., Ren, H., & Zhang, X. (2019) · Wireless Networks · doi:10.1007/s11276-019-02125-0 · Cited by 12
“There are some attempts to apply reinforcement learning (RL) in caching design [16, 17].”
BackgroundA Proactive On-Demand Content Placement Strategy in Edge Intelligent Gateways
Sun, H., Chen, Y., Sha, K., Huang, S., Wang, X., & Shi, W. (2023) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2023.3249797 · Cited by 14
“The authors of [30] propose a multi-armed bandit-based caching strategy to estimate”
BackgroundSelf-citationEnabling Content-Centric Device-to-Device Communication in the Millimeter-Wave Band
Bahadori, N., Nabil, M., Kelley, B., & Homaifar, A. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3071468 · Cited by 12
“In the second scenario, to consider content popularity distribution, network can use data from DTs’ social media to identify the popular contents and evaluate the desire of DTs in sharing contents [35], [36].”
BackgroundMethodWu, H., Wang, B., Ma, H., & Xing, L. (2023) · Ad Hoc Networks · doi:10.1016/j.adhoc.2023.103313 · Cited by 14
Predictive Caching via Learning Temporal Distribution of Content Requests
Song, H.-G., Chae, S. H., Shin, W.-Y., & Jeon, S.-W. (2019) · IEEE Communications Letters · doi:10.1109/lcomm.2019.2941202 · Cited by 12
“The content caching and sharing optimization problem was addressed by incorporating a multi-armed bandit framework into learning-based content popularity estimation [7]–[9].”
MethodReal-Time Algorithms for the Detection of Changes in the Variance of Video Content Popularity
Skaperas, S., Mamatas, L., & Chorti, A. (2020) · IEEE Access · doi:10.1109/access.2020.2972640 · Cited by 12
“, deep learning) need effective feature mining and a huge mass of labeled examples to provide successful performance [8], [9].”
BackgroundProactive Cache Placement with Bandit Learning in Fog-Assisted IoT Systems
Gao, X., Huang, X., Tang, Y., Shao, Z., & Yang, Y. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9149047 · Cited by 12
“Faced with such challenges, existing works [6]–[9] have proposed various solutions based on bandit learning methods to optimize cache placement with unknown file popularities.”
BackgroundExploiting Caching for Millimeter-Wave TCP Networks: Gain Analysis and Practical Design
Kim, M., Ko, S., Kim, H., Kim, S., & Kim, S. (2018) · IEEE Access · doi:10.1109/access.2018.2880774 · Cited by 11
“, stochastic geometry [9], mean-field theory [10], cross-entropy optimization [11] and machine learning [12].”
BackgroundIntelligent Edge-Based Service Provisioning Using Smart Cloudlets, Fog and Mobile Edges
Guan, S., & Boukerche, A. (2022) · IEEE Network · doi:10.1109/mnet.012.1900434 · Cited by 11
Joint Content Placement and Storage Allocation Based on Federated Learning in F-RANs
Xiao, T., Cui, T., Islam, S. M. R., & Chen, Q. (2020) · Sensors · doi:10.3390/s21010215 · Cited by 10
Content Placement with Unknown Popularity in Fog Radio Access Networks
Zhou, Y., Yan, S., & Peng, M. (2019) · IEEE International Conference on Industrial Internet (ICII) · doi:10.1109/icii.2019.00068 · Cited by 9
A Learning-Based Caching Mechanism for Edge Content Delivery
Torabi, H., Khazaei, H., & Litoiu, M. (2024) · ACM/SPEC International Conference on Performance Engineering (ICPE) · doi:10.1145/3629526.3645037 · Cited by 14
Content Popularity Estimation in Edge-Caching Networks from Bayesian Inference Perspective
Mehrizi, S., Tsakmalis, A., Chatzinotas, S., & Ottersten, B. (2019) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc.2019.8651737 · Cited by 9
“In [9], [10], the authors designed a multi-armed-bandit (MAB) algorithm to estimate the popularities.”
BackgroundCooperative Edge-Cloud Caching for Real-time Sensing Big Data Search in Vehicular Networks
Liu, M., Li, D., Wu, H., Lyu, F., & Shen, X. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500777 · Cited by 9
“To facilitate content deployment, prediction of the varying popularity of sensing data is indispensable yet laborious [17].”
BackgroundIntelli-AR Preloading: A Learning Approach to Proactive Hologram Transmissions in Mobile AR
Han, Y., Chen, Y., Wang, R., Wu, J. H., & Gorlatova, M. A. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3159554 · Cited by 9
“The multiarmed bandit (MAB) model is used in [25]–[27] to optimize the caching policy without a predefined model of user devices’ preference of requesting contents.”
BackgroundMethodCaching and resource allocation in small cell networks
Hou, R., Huang, K., Xie, H., Lui, K., & Li, H. (2020) · Computer Networks · doi:10.1016/j.comnet.2020.107100 · Cited by 10
A Reinforcement Learning Approach for D2D-Assisted Cache-Enabled HetNets
Tang, J., Tang, H., Zhao, N., Cumanan, K., Zhang, S., & Zhou, Y. J. (2019) · Globecom · doi:10.1109/globecom38437.2019.9014027 · Cited by 9
“Given the fact that caching enabled HetNets serve users from either local cache or core net [3], different caching policies have been investigated recently, including the coded caching and delivery scheme [4], the learning based caching scheme [5] and so on.”
BackgroundDeep Multi‐Agent Reinforcement Learning for Cooperative Edge Caching
Gursoy, M. C., Chen, Z., & Velipasalar, S. (2019) · Machine Learning for Future Wireless Communications · doi:10.1002/9781119562306.ch21 · Cited by 6
Content Caching Policy for 5G Network Based on Asynchronous Advantage Actor-Critic Method
Shi, Z., Li, L., Xu, Y., Li, X., Chen, W., & Han, Z. (2019) · Globecom · doi:10.1109/globecom38437.2019.9014268 · Cited by 8
“The authors employed two reinforcement learning algorithms to design a cooperative BSs’ caching strategy, aiming at improving cache hit ratio [5], [6].”
MethodLiu, X., Derakhshani, M., & Lambotharan, S. (2021) · IEEE Transactions on Communications · doi:10.1109/tcomm.2021.3059305 · Cited by 8
“In [26], a MAB problem was formulated to learn the file popularities and to maximize the caching reward.”
BackgroundReal-Time Search-Driven Caching for Sensing Data in Vehicular Networks
Liu, M.-L., Li, D.-S., Wu, H.-Q., Lyu, F., & Shen, X. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3134964 · Cited by 7
“However, as the popularity is predefined or needs to be predicted with sufficient historical requests [20], [21], the popularity of SD that have various types and application cases can hardly be practically achieved.”
BackgroundEconomic Analysis of Joint Mobile Edge Caching and Peer Content Sharing
Jiang, C. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10229068 · Cited by 7
Learning based Content Caching for Wireless Networks
Masood, A., Lakew, D. S., & Cho, S. (2020) · International Conference on Information Networking · doi:10.1109/icoin48656.2020.9016489 · Cited by 7
A Learning-Based Cooperative Caching Strategy in D2D Assisted Cellular Networks
Niu, Y., Qin, X., & Zhang, Z. (2018) · Asia-Pacific Conference on Communications (APCC) · doi:10.1109/apcc.2018.8633483 · Cited by 7
“The popularity of content f in BS b can be modeled as a Zipf like distribution [8]–[10] as follows”
BackgroundLearning-Aided Content Placement in Caching-Enabled fog Computing Systems Using Thompson Sampling
Zhu, J., Huang, X., & Shao, Z. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053162 · Cited by 9
“A more promising alternative is to integrate online learning into the online decision-making procedure, i.e. , having each EFN update its content placement through continuous learning from hit-or-miss feedback information in real-time [8–10].”
BackgroundDynamic Content Updates in Heterogeneous Wireless Networks
Abad, M. S. H., Özfatura, E., Erçetin, Ö., & Gündüz, D. (2019) · Annual Conference on Wireless On-demand Network Systems and Services (WONS) · doi:10.23919/wons.2019.8795490 · Cited by 9
“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.”
MethodDeep Learning Empowered Real-Time Haptic Communications for IoT
Zhang, X., & Chen, M. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3502402 · Cited by 7
“Scheduling the network resources properly is always an effective way to improve users’ QoE, especially in resource-limited networks [35], [36], [37].”
Popularity based content caching of YouTube data in cellular networks
Raja, K., Abilash, B., Anbalagan, S., Dev, K., & Ganapathisubramaniyan, A. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13528-1 · Cited by 6
“Caching at both EPC and RAN [18, 20] can reduce the overall content download delay and in turn reduces the data traffic at the server.”
BackgroundMethodInfluentialSparse Bandit Learning Based Location Management for Space-Ground Integrated Networks
He, H., Qin, C., Chen, S., Jiang, X., Yang, J., & Hanzo, L. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3258140 · Cited by 6
“By letting X̄n = ∑n i=1 Xi n , for all a ≥ 0, we have P{X̄n − μ ≥ a} ≤ e−2na(2) and P{X̄n − μ ≤ −a} ≤ e−2na 2 [32].”
Learning-Based Joint User Association and Cache Replacement for Cache-Enabled Cloud RAN
Jeon, S.-E., Jung, J.-W., Lee, K., & Hong, J. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3397054 · Cited by 7
“In situations where the content popularity information is initially unknown, an algorithm for MAB problem has been adopted for the decentralized content placement and sharing among BSs [21].”
MethodA Q-Learning Based Scheme to Securely Cache Content in Edge-Enabled Heterogeneous Networks
Dai, M., Su, Z., Xu, Q., & Chen, W. (2019) · IEEE Access · doi:10.1109/access.2019.2946319 · Cited by 6
“Recently, researches on the Q-learning approach focus on caching content over the conventional network [19]–[21].”
BackgroundMinimizing Edge Caching Service Costs Through Regret-Optimal Online Learning
Quan, G., Eryılmaz, A., & Shroff, N. B. (2024) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2024.3420758 · Cited by 5
“However, most of the existing works in this area focus on learning unknown data popularities or user preference [13], [14], [15], [16], [17], [18].”
Background
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.