Abstract
Semi-supervised learning self-training (SSST) is a promising approach to solving classification problems with unlabeled data. Our paper proposes a multi-objective cache content strategy that aims at maximizing small base stations’ cache hit rates in mobile edge networks (MENs). The cache placement algorithm is formulated as a classification problem. The logistic regression (LR) learning technique is used to create a classifier based on a limited amount of labeled data. The classifier then uses a self-training technique to classify unlabeled samples. To expand the number of samples in the dataset, the cases with the highest prediction probability are added to the training set. The proposed technique was developed and tested on samples with a variety of input characteristics, including file popularity, user location, user to SBS contact probability, communication range, contact duration, and others. Experiments on real user request sequences reveal that the proposed method increases prediction accuracy considerably. It also saves a lot of time when it comes to identifying the unlabeled data, making it an efficient solution to the cache location problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zeydan, E., et al.: Big data caching for networking: moving from cloud to edge. IEEE Commun. Mag. 54(9), 36–42 (2016)
Ahn, J., Jeon, S.H., Park, H.-S.: A novel proactive caching strategy with community-aware learning in CoMP-enabled small-cell networks. IEEE Commun. Lett. 22(9), 1918–1921 (2018)
Zhang, S., Yao, L., Sun, A., Tay, Y.: Deep learning based recommender system: a survey and new perspectives. ACM Comput. Surv. 1(1), 1–35 (2018)
Yao, Z., et al.: Mobility-aware pre-caching based on unsupervised deep generative model for small cell networks. In: 2019 13th IEEE International Conference on Signal Processing and Communication Systems (ICSPCS), pp. 1–7 (2019)
Zhou, Y., et al.: Content placement with unknown popularity in fog radio access networks. In: 2019 IEEE International Conference on Industrial Internet (ICII), pp. 361–367 (2019)
Zhu, X., Goldberg, A.B.: Introduction to semi-supervised learning. Synth. Lect. Artif. Intell. Mach. Learn. 3(1), 1–130 (2009)
Chai, H., Liang, Y., Wang, S., Shen, H.W.: A novel logistic regression model combining semi-supervised learning and active learning for disease classification. Sci. Rep. 8(1), 1–10 (2018)
Zhu, X., Ghahramani, Z.: Learning from labeled and unlabeled data with label propagation, CMU Tech report, CMU-CALD-02-107 (2002)
Tan, Y., Yuan, Y., Yang, T., Xu, Y., Hu, B.: Femtocaching in wireless video networks: Distributed framework based on exact potential game. In: 2016 IEEE/CIC International Conference on Communications in China (ICCC), pp. 1–6. IEEE, Piscataway (2016)
Chen, M., Hao, Y., Hu, L., Huang, K., Lau, K.V.: Green and mobility-aware caching in 5G networks. IEEE Trans. Wirel. Commun. 16(12), 8347–61 (2017)
Wang, R., Peng, X., Zhang, J., Letaief, K.B.: Mobility-aware caching for content-centric wireless networks: modeling and methodology. IEEE Commun. Mag. 54(8), 77–83 (2016)
Mohammed, L.B., Anpalagan, A., Khwaja, A.S., Jaseemuddin, M.: Mobility-aware latency-efficient cache placement in mobile edge networks. In: 22nd IEEE International Conference on High Performance Computing and Communications; HPCC 2020, Fiji (2020)
Quinn, A., Stranieri, A., Yearwood, J.: Classification for accuracy and insight: A weighted sum approach. In: Proceedings of the Sixth Australasian Conference on Data Mining and Analytics, vol. 70, pp. 203–208 (2007)
Theodoridis, S.: Machine Learning : A Bayesian and Optimization Perspective, Elsevier Science and Technology. Academic, New York (2020)
Kolosova, T., Berestizhevsky, S.: Supervised Machine Learning: Optimization Framework and Applications with SAS and R. Chapman and Hall/CRC, London (2020)
McNett, M., Voelker, G.M.: Access and mobility of wireless PDA users. ACM Sigmobile Mobile Comput. Commun. Rev. 9(2), 40–55 (2005)
Pedregosa, F., et al.: Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825–30 (2011)
Acknowledgement
This work is funded in part by a research grant from the National Science and Engineering Research Council of Canada.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mohammed, L.B., Anpalagan, A., Khwaja, A.S., Jaseemuddin, M. (2022). Semi-supervised Learning with Self-training Classifier for Cache Placement in Mobile Edge Networks. In: Nguyen, H., Le, L., Yahampath, P., Mohamed, E.B. (eds) 30th Biennial Symposium on Communications 2021. Signals and Communication Technology. Springer, Cham. https://doi.org/10.1007/978-3-031-06947-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-06947-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06946-8
Online ISBN: 978-3-031-06947-5
eBook Packages: Computer ScienceComputer Science (R0)