Xiaogeng Xu

Xiaogeng Xu

Auto-generated profile, based on publicly available information

Xiaogeng Xu

School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 March 2020 in IEEE Access
Verified
Journal Article
Open access
XXXiaogeng Xu
Xiaogeng Xu
CFChunyan Feng
Chunyan Feng
SSSiyang Shan
Siyang Shan
TZTiankui Zhang
Tiankui Zhang
Jonathan LooJonathan Loo
Jonathan Loo
Edge computing is a promising infrastructure evolution to reduce traffic loads and support low-latency communications. Furthermore, content-centric networks provide a natural solution to cache contents at edge nodes. However, it is a challenge for edge nodes to handle massive and highly dynamic content requests by users, and if without an efficient content caching strategy, the edge nodes will encounter high traffic load and latency due to increasing retrieval from content providers. This paper formulates a proactive edge caching problem to minimize the content retrieval cost at edge nodes. We exploit the inherent content caching and request aggregation mechanism in the content-centric networks to jointly minimize traffic load and content retrieval delay cost generated by the massive and dynamic content requests. We develop a Q-learning algorithm, which is an online optimal caching strategy, as it is adaptable to dynamic content popularity and content request intensity, and derive the long-term minimization of the content retrieval cost. Simulation results illustrate that the proposed algorithm can achieve a lower content retrieval cost compared with several baseline caching schemes.

24 October 2016
Verified
Conference Paper
Closed access
YLYao Li
Yao Li
TZTiankui Zhang
Tiankui Zhang
XXXiaogeng Xu
Xiaogeng Xu
ZZZhimin Zeng
Zhimin Zeng
YLYinlong Liu
Yinlong Liu
Content Centric Networking (CCN) is one of the candidate future Internet architectures that give favorable promises in networks. In-network caching as one of its key functions, has been studied extensively to achieve less content access delay and to reduce traffic load. However, current caching schemes mostly suffer from a poor utilization of cache space; since many content replicas are replaced without being hit by coming requests. As the limited cache space in networks, less popular contents have much less replicas than the popular ones, and the requests for them will cause considerable delay. In this paper, a content popularity and node level matched based probability caching strategy (MPC) is proposed to maximize the cache utilization and to improve the content diversity in networks simultaneously. We first evaluate the caching property of nodes along the delivery path by utilizing multi-parameters, and classify nodes into levels according to their caching property. Then, we assign contents to the nodes with their matched level, which balances the proportion of contents with different popularities in the network. Simulation results demonstrate that the proposed strategy can achieve less content access delay, higher cache hit ratio, and richer content diversity.

1 May 2018
Verified
Conference Paper
Closed access
XXXiaogeng Xu
Xiaogeng Xu
CFChunyan Feng
Chunyan Feng
TZTiankui Zhang
Tiankui Zhang
Jonathan LooJonathan Loo
Jonathan Loo
GLGeoffrey Ye Li
Geoffrey Ye Li
In information-centric networking (ICN), content request aggregation can reduce the traffic load and impact the statistics of caching. Existing caching performance analysis in ICN has assumed zero content request aggregation and analyzed the cache hit and miss probabilities only. In this paper, the caching performance of ICN with content request aggregation is analyzed. The content request arrival is modeled by a random process with three states namely cache hit, forwarded, and aggregated. The state transition probabilities are derived. To analyze the proposed model, we transform the random process to a three-state Markov chain by approximating the shortest sojourn time and finding the average transition probabilities. The steady-state probabilities of the three states are obtained by the limit distribution of the Markov chain. The simulation results verify the accuracy of the analytical results and demonstrate the performance gain of in-network caching.