Abstract：Since the wireless edge node has a small cache size, the performance of proactive caching is much better than passive caching when file popularity is known. Recent studies in the scenario where file popularity is unknown and need to be predicted found that proactive caching is still better than passive caching. However, most of the work is based on synthesized data sets or open source datasets collected in areas such as recommendation systems, which can barely reflect the request behavior of wireless users. In this paper, a dataset recording the number of requests for videos measured in a local area is used, based on which a neural network is employed to predict the short-term behaviors of individual and group user. The predicted user behavior information is then applied for proactive caching at macro or micro base stations. The research results show that when the measured dataset is adopted, the false alarm, missing alarm and additive errors, which are caused by strong temporal locality or even burstiness of user request behavior, make passive caching outperform proactive caching, especially for caching at macro base station. Once a synthesized static dataset is used, proactive caching performs significantly better than passive caching. This means that it is not sufficient to use only additive errors to characterize the uncertainty of popularity prediction, while reducing false and missing alarms is more important in order to achieve the performance gain of proactive edge caching.
戚凯强,杨晨阳,韩圣千. 基于实测数据集预测用户请求行为对主动边缘缓存的影响[J]. 信号处理, 2019, 35(4): 531-541.
Qi Kaiqiang,Yang Chenyang,Han Shengqian. Impacts of Learning User Request Behavior with a Real Dataset on Proactive Wireless-edge Caching. Journal of Signal Processing, 2019, 35(4): 531-541.
E. Zeydan, E. Bastug, M. Bennis, et al. Big data caching for networking: Moving from cloud to edge[J]. IEEE Commun. Mag., 2016, 54(9): 36-42.
[2]
E. Bastug, J. Guenego, M. Debbah, et al. Proactive small cell networks[C]// IEEE ICT, 2013.
[3]
C. Zhong, M. C. Gursoy, S. Velipasalar, et al. A deep reinforcement learning-based framework for content caching[C]// IEEE CISS, 2018.
[4]
T. Hou, G. Feng, S. Qin, et al. Proactive content caching by exploiting transfer learning for mobile edge computing[C]// IEEE GLOBECOM, 2017.
[5]
Y. Tan, Y. Yuan, T. Yang, et al. Learning-based caching with unknown popularity in wireless video networks[C]// IEEE VTC, 2017.
[6]
D. Liu and C. Yang. Energy efficiency of downlink networks with caching at base station[J]. IEEE J. Sel. Areas Commun., 2016, 34(4): 907-922.
[7]
F. D. Calabrese, L. Wang, E. Ghadimi, G. Peters, L. Hanzo, and P. Soldati, Learning radio resource management in RANs: Framework, opportunities, and challenges[J]. IEEE Commun. Mag., 2018, 56(9): 138-145.
[8]
B. Chen, C. Yang, Caching policy for cache-enabled D2D communications by learning user preference[J]. IEEE Trans. Commun., 2018, 66(12): 6586-6601.
[9]
D. Liu and C. Yang, Caching at base stations with heterogeneous user demands and spatial locality[J], early access, IEEE Trans. Commun., 2018.
[10]
A. Sadeghi, F. Sheikholeslami, G. B. Giannakis, et al. Optimal and scalable caching for 5G using reinforcement learning of space-time popularities[J]. IEEE J. Sel. Top. Signal Process., 2018, 12(1): 180-190.
[11]
N. Zhang, K. Zheng, M. Tao, et al. Using grouped linear prediction and accelerated reinforcement learning for online content caching[C]// IEEE ICC, 2018.
[12]
S. Muller, O. Atan, M. V. Der Schaar, et al. Context-aware proactive content caching with service differentiation in wireless networks[J]. IEEE Trans. Wireless Commun., 2017, 16(2): 1024-1036.
[13]
F. M. Harper and J. A. Konstan.The movielens datasets: History and context[J]. ACM Trans. Interactive Intell. Syst., 2016, 5(4): 19.
[14]
S. Traverso, M. Ahmed, M. Garetto, et al. Unravelling the impact of temporal and geographical locality in content caching systems[J]. IEEE Trans. Multimedia, 2015, 17(10): 1839-1854.
[15]
I. Goodfellow, Y. Bengio, and A. Courville. Deep learning[M]. MIT press Cambridge, 2016, vol. 1.
[16]
D. Kingma and J. Ba, Adam: A method for stochastic optimization[J], Computer Science, 2014.
[17]
A. Tatar, M. D. De Amorim, S. Fdida, et al. A survey on predicting the popularity of web content[J]. Journal of Internet Services and Applications, 2014, 5(1).
[18]
W. Liu, S. Han, C. Yang, et al. Energy efficiency comparison of massive MIMO and small cell network[C]// IEEE GSIP, 2014.
[19]
3rd Generation Partnership Project (3GPP). Further advancements for E-UTRA physical layer aspects [R]. 3GPP TR36.814, Tech. Rep., 2010.
[20]
W. Liu, J. Zhang, Z. Liang, et al. Content popularity prediction and caching for ICN: A deep learning approach with SDN[J]. IEEE Access, 2018, 6: 5075-5089.
[21]
R. Crane, D. Sornette. Robust dynamic classes revealed by measuring the response function of a social system[J]. Proc. Natl. Acad. Sci. U. S. A., 2008, 105(41): 15649-15653.
2019, Vol. 35 
