Filter by type:

Sort by year:

AI-based Two-Stage Intrusion Detection for Software Defined IoT Networks

Journals and Magazines
Jiaqi Li, Zhifeng Zhao, Rongpeng Li, and Honggang Zhang
IEEE Internet of Things Journal

Software Defined Internet of Things (SD-IoT) Networks profit from centralized management and interactive resource sharing, which enhances the efficiency and scalability of IoT applications. But with the rapid growth in services and applications, they are vulnerable to possible attacks and face severe security challenges. Intrusion detection has been widely used to ensure network security, but classical detection methods are usually signature-based or explicit-behavior-based and fail to detect unknown attacks intelligently, which makes it hard to satisfy the requirements of SD-IoT Networks. In this paper, we propose an AI-based two-stage intrusion detection empowered by software defined technology. It flexibly captures network flows with a global view and detects attacks intelligently. We firstly leverage Bat Algorithm with Swarm Division and Binary Differential Mutation to select typical features. Then, we exploit Random Forest through adaptively altering the weights of samples using the weighted voting mechanism to classify flows. Evaluation results prove that the modified intelligent algorithms select more important features and achieve superior performance in flow classification. It is also verified that our solution shows better accuracy with lower overhead compared with existing solutions.

The Stochastic Geometry Analyses of Cellular Networks with ALPHA-Stable Self-Similarity

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Yi Zhong, Chen Qi, and Honggang Zhang
IEEE Trans. Commun.
To understand the spatial deployment of base stations (BSs) is the first step to analyze the performance of cellular networks and further design efficient networking protocols. Poisson point process (PPP), which has been widely adopted to characterize the deployment of BSs and established the reputation to give tractable results in the stochastic geometry analyses, usually assumes a static BS deployment density in homogeneous PPP (HPPP) models or delicately designed location-dependent density functions in in-homogeneous PPP (IPPP) models. However, the simultaneous existence of attractiveness and repulsiveness among BSs practically deployed in a large-scale area defies such an assumption, and the ALPHA-stable distribution, one kind of heavy-tailed distributions, has recently demonstrated superior accuracy to statistically model the varying BS density in different areas. In this paper, we start with these new findings and investigate the intrinsic feature (i.e., the spatial self-similarity) embedded in the BSs. Afterwards, we refer to a generalized PPP setup with ALPHA-stable distributed density and theoretically derive the related coverage probability. In particular, we give an upper bound of the derived coverage probability for high signal-to-interference-plus-noise ratio (SINR) thresholds and show the monotonically decreasing property of this bound with respect to the variance of BS density. Besides, we prove that our model could reduce to the single-tier HPPP for some special cases, and demonstrate the superior accuracy of the ALPHA-stable model to approach the real environment.

Deep Reinforcement Learning for Resource Management in Network Slicing

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Qi Sun, Chi-Lin I, Chenyang Yang, Xianfu Chen, Minjian Zhao, and Honggang Zhang
IEEE Access

Network slicing is born as an emerging business to operators, by allowing them to sell the customized slices to various tenants at different prices. In order to provide better-performing and cost-efficient services, network slicing involves challenging technical issues and urgently looks forward to intelligent innovations to make the resource management consistent with users’ activities per slice. In that regard, deep reinforcement learning (DRL), which focuses on how to interact with the environment by trying alternative actions and reinforcing the tendency actions producing more rewarding consequences, is assumed to be a promising solution. In this paper, after briefly reviewing the fundamental concepts of DRL, we investigate the application of DRL in solving some typical resource management for network slicing scenarios, which include radio resource slicing and priority-based core network slicing, and demonstrate the advantage of DRL over several competing schemes through extensive simulations. Finally, we also discuss the possible challenges to apply DRL in network slicing from a general perspective.

Traffic prediction based on random connectivity in deep learning with long short-term memory

International Conference Papers
Yuxiu Hua, Zhifeng Zhao, Rongpeng Li, Xianfu Chen, Zhiming Liu, Honggang Zhang
Proc. IEEE VTC 2018 Fall, Chicago, Illinois, USA, 2018

Traffic prediction plays an important role in evaluating the performance of telecommunication networks and attracts intense research interests. A significant number of algorithms and models have been put forward to analyse traffic data and make prediction. In the recent big data era, deep learning has been exploited to mine the profound information hidden in the data. In particular, Long Short-Term Memory (LSTM), one kind of Recurrent Neural Network (RNN) schemes, has attracted a lot of attentions due to its capability of processing the long-range dependency embedded in the sequential traffic data. However, LSTM has considerable computational cost, which can not be tolerated in tasks with stringent latency requirement. In this paper, we propose a deep learning model based on LSTM, called Random Connectivity LSTM (RCLSTM). Compared to the conventional LSTM, RCLSTM makes a notable breakthrough in the formation of neural network, which is that the neurons are connected in a stochastic manner rather than full connected. So, the RCLSTM, with certain intrinsic sparsity, have many neural connections absent (distinguished from the full connectivity) and which leads to the reduction of the parameters to be trained and the computational cost. We apply the RCLSTM to predict traffic and validate that the RCLSTM with even 35% neural connectivity still shows a satisfactory performance. When we gradually add training samples, the performance of RCLSTM becomes increasingly closer to the baseline LSTM. Moreover, for the input traffic sequences of enough length, the RCLSTM exhibits even superior prediction accuracy than the baseline LSTM.

Wireless Big Data in Cellular Networks: The Cornerstone of Smart Cities

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Chenyang Yang, Chunming Wu, and Honggang Zhang
IET Communications, vol. 12, no. 13, pp. 1517 - 1523, Aug 2018.

The rapid urbanization has transformed cities to the preferential human settlement and allowed cities to quietly witness all range of human activities. As the key enabler in the information and communications technology industry, cellular networks play a decisive role in delivering communication messages and entertainment content. In particular, cellular network operators respond to human initiated service requests by gradually deploying necessary infrastructure and calibrating transmission protocols. Hence, cellular network records encompass the interesting interaction between human-initiated messages and network-triggered responses. In this article, we collect the “big data” in urban cellular networks and try to dig out the human and urban planning properties. Specifically, we focus on the statistical modeling of three representative scenarios like spatial deployment density of base stations, packet length or traffic volume of mobile services, as well as inter-arrival time and dwell time of human mobility. Through extensive data mining, we validate the heavy-tailed feature universally existing in these scenarios. Afterwards, we discuss the implications of this heavy-tailed feature and talk about its fundamental contribution to intelligent resource adjustment, proactive content caching, and enhanced connection management in cellular networks. Finally, we highlight the applications of this feature towards smarter cellular networks and cities.

Robust Relative Fingerprinting-Based Passive Source Localization via Data Cleansing

Journals and Magazines
Changju Kan, Guoru Ding, Qihui Wu, Rongpeng Li, and Fei Song
IEEE Access, vol. 6, pp. 19255 - 19269, Mar. 2018.

Recently, source localization is becoming a major research focus. The majority of the existing studies focus on the design of received signal strength (RSS)-based localization methods. However, when in the face of complicated environments with severe fading, RSS-based localization methods achieve relatively inferior accuracy performance, compared with fingerprinting-based localization methods. Nevertheless, traditional fingerprinting-based localization methods are subject to the condition that the source transmit power is known, which cannot be directly used in passive localization cases where the sensing  nodes do not have the prior information on the source. In addition, the received sensing data may contain errors and then affect the location precision due to various abnormal conditions, such as device failure and
malicious cases. In this paper, we propose a novel robust relative fingerprinting-based passive localization algorithm via a data cleansing approach. First, we figure out the fingerprint correlations property and introduce a new relative fingerprint framework. The key idea is that by exploring the correlations between the source fingerprint and the reference fingerprint database, the correction factors can be achieved to apply the fingerprint idea into the passive localization case. Second, we formulate a generalized modeling of the abnormal data in localization problem and propose a data cleansing approach which utilizes the sparse property of the abnormal data. Based on this, the negative influence of abnormal data can be further
eliminated. Third, considering the sparse property of the source position, we use the sparse Bayesian learning
in the matching process for the purpose of achieving more precise estimated source position. Simulation results demonstrate that the proposed algorithm achieves higher accuracy performance in passive source
localization in terms of eliminating the abnormal data impairment.

On the Capacity of D2D Social Networks with Fractal Communications

International Conference Papers
Ying Chen, Zhifeng Zhao, Rongpeng Li, and Honggang Zhang
Proc. ICT 2018, St. Malo, France, Jun. 2018

The maximum capacity of a D2D (device-to-device) social network with fractal interactions is studied in this paper. Specifically, the self-similarity of a fractal network is mathematically formulated by a power-law degree distribution $ P(k) $, and the social connection feature between two users with degree $ k_{1} $ and $ k_{2} $ is captured by a joint probability distribution $ P(k_{1},k_{2}) $. It is proved that if the source user communicates with one of his contacts randomly, the maximum capacity is $ \Theta\left(\frac{1}{\sqrt{n\log n}}\right) $. On the other hand, if two users with distance $ d $ communicate according to the probability $ d^{-\beta} $, the maximum capacity can reach up to $ \Theta\left(\frac{1}{\log n}\right) $, where $ \beta $ is the frequency parameter.

Characterizing and Learning the Mobile Data Traffic in Cellular Network -- 5G Networks: Fundamental Requirements, Enabling Technologies, and Operations Management (Edited by Anwer Al-Dulaimi, Xianbin Wang, and Chih-Lin I)

Book ChaptersFirst Author
Rongpeng Li, Zhifeng Zhao, Chen Qi, and Honggang Zhang

A Machine Learning Based Intrusion Detection System for Software Defined 5G Network

Journals and Magazines
Jiaqi Li, Zhifeng Zhao, Rongpeng Li
IET Net., vol. 7, no. 2, pp. 53–60, Mar. 2018.

As an inevitable trend of future 5G networks, Software Defined architecture has many advantages in providing centralized control and flexible resource management. But it is also confronted with various security challenges and potential threats with emerging services and technologies. As the focus of network security, Intrusion Detection Systems (IDS) are usually deployed separately without collaboration. They are also unable to detect novel attacks with limited intelligent abilities, which are hard to meet the needs of software defined 5G. In this paper, we propose an intelligent intrusion detection system taking the advances of software defined technology and artificial intelligence based on Software Defined 5G architecture. It flexibly integrates security function modules which are adaptively invoked under centralized management and control with a globle view. It can also deal with unknown intrusions by using machine learning algorithms. Evaluation results prove that the intelligent intrusion detection system achieves better performance with lower overhead. It is also verified that the selected machine learning algorithms shows better accuracy and reduced false alarm rate in flow-based classification.

Predictability Analysis of Spectrum State Evolution: Performance Bounds and Real-World Data Analytics

Journals and Magazines
Jiachen Sun, Liang Shen, Guoru Ding, Rongpeng Li, and Qihui Wu
IEEE Access, vol. 5, pp. 22760–22774, 2017.

Predictability in spectrum prediction refers to the degree to which a correct prediction of the radio spectrum state (RSS) can be made quantitatively. It is obvious that the possibility that the future RSS is accurately predicted will be different when using different spectrum prediction algorithms. However, the fundamental limits on the accuracy of various spectrum prediction algorithms should exist and be worthwhile to be paid attention to. In this paper, we firstly transform large amount of spectrum data into symbol sequences by sampling and quantization, to calculate the entropy of the symbol sequence, which represents the randomness of the RSS evolution. Then we derive the upper bound and the lower bound of the predictability mainly from entropies of the symbol sequences. Further, we conduct the detailed analysis on the performance bounds of the predictability of the RSS. The key insights among others include: i) entropies almost have no relationship with selection of sampling intervals in the data preprocessing; ii) the upper bounds and the lower bounds of the predictability will both decrease as the quantization level rises and tend to be stable around a value at last; iii) two kinds of lower bounds of the predictability are proposed, and one of the lower bounds, the regularity R, can reveal the tidal effect of the evolution of the RSS.

SDN based VxLAN optimization in cloud computing networks

Corresponding AuthorJournals and Magazines
Zhifeng Zhao, Feng Hong, and Rongpeng Li
IEEE Access, vol. 5, pp. 23312–23319, Oct. 2017.
Nowadays, cloud computing networks significantly benefit the deployment of new services and have become one infrastructure provider in the digital society. Virtual extensible local area network (VxLAN), which belongs to the network schemes to overlay Layer 2 over Layer 3, is one of the most popular methods to realize cloud computing networks. Though VxLAN partially overcome the capacity limitation of its predecessor virtual local area network (VLAN), it still faces several challenges like annoying signaling overhead during the multicast period and interrupted communication with a migrating virtual machine (VM). In this paper, we propose a new software defined network (SDN) based VxLAN network architecture. Based on this architecture, we address how we can deploy an intelligent center to enhance the multicast capability and facilitate the VM migration. Besides, we discuss the means to update the global information and guarantee the communication continuum. Finally, we use Mininet to emulate this SDN based VxLAN architecture and demonstrate effective load balancing results. In a word, this proposed architecture could provide a blueprint for future cloud computing networks.

An intelligent honeynet architecture based on software defined security

International Conference Papers
Xiangjun Meng, Zhifeng Zhao, Rongpeng Li, and Honggang Zhang
Proc. WCSP 2017, Hangzhou, China, 2017

Honeynet is deployed to trap attackers and learn their behavior patterns and motivations. Conventional honeynet is implemented by dedicated hardware and software. It suffers from inflexibility, high CAPEX and OPEX. There have been several virtualized honeynet architectures to solve those problems. But they lack a standard operating environment and common architecture for dynamic scheduling and adaptive resource allocation. Software Defined Security (SDS) framework has a centralized control mechanism and intelligent decision making ability for different security functions. In this paper, we present a new intelligent honeynet architecture based on SDS framework. It implements security functions over Network Function Virtualization Infrastructure (NFVI). Under uniform and intelligent control, security functional modules can be dynamically deployed and collaborated to complete different tasks. It migrates resources according to the workloads of each honeypot and power off unused modules. Simulation results show that intelligent honeynet has a better performance in conserving resources and reducing energy consumption. The new architecture can fit the needs of future honeynet development and deployment.

Joint computation offloading and data caching with delay optimization in mobile-edge computing systems

International Conference Papers
Haixia Wang, Rongpeng Li, Lu Fan, and Honggang Zhang
Proc. WCSP 2017, Hangzhou, China, 2017

paper, we aim at designing a computation offloading and data caching model under the joint of MEC and DC. Then, by analyzing the execution delay and transmission delay of each task, we formulate a resource-constrained delay minimization problem, and put forward a heuristic algorithm based on Genetic Algorithm (GA) and Simulated Annealing (SA). Numerical simulation results show that our scheme outperforms the conventional schemes in different scenarios, and also verify that the proposed algorithm can converge to a better value than the other two classical algorithms.

A resource scheduling scheme based on utility function in CoMP environment

International Conference Papers
Xing Xu, Zhifeng Zhao, Rongpeng Li and Honggang Zhang
Proc. WCSP 2017, Hangzhou, China, 2017.

In the paper, we studied the solution of resource allocation problem with Coordinated Multi-Point(CoMP) in heterogeneous
wireless networks. The utilization of CoMP technology enhances channel quality of users at the edge of cells, but it also brings more complexity to resource management of the network. To reduce this pressure, we exploited a feedback-based method to determine the allocation of users in a multi-layer heterogeneous network. Traditional Proportional Fairness(PF) achieves a balance between system throughput and fairness. However, fairness among users should be reconsidered because applications become more diversified and have different requirements for the network. Therefore, we proposed an improved resource allocation scheme through the introduction of utility function, which can allocate resource according to the application type so as to improve fairness. Simulation results indicate that the scheme based on utility function can achieve a better balance between system throughput and fairness among users.

Temporal-Spatial Distribution Nature of Traffic and Base Stations in Cellular Networks

Corresponding AuthorJournals and Magazines
Zhifeng Zhao, Meng Li, Rongpeng Li, and Yifan Zhou
IET Commun.

Recent years have witnessed the unprecedented surge of mobile traffic and base stations (BSs) deployment, which poses severe requirement for future communications systems. Understanding the distribution dynamics of traffic and BSs in time-space domain is of vital importance for better network design and resource management in cellular networks. In this paper, a study on the statistical characteristics of cellular traffic series is carried out and ALPHA-Stable distribution is verified to be valid for modeling the traffic series of each BS. On the other hand, inspired by the fact that BSs traffic series are spatially correlated, we study the statistical relationship between the correlation coefficient and the distance between BSs. Moreover, ALPHA-Stable model is also suitable to describe the BSs deployment, thus conducing to prove the existence of self-similarity. In addition, both the traffic time series and the BSs spatial distribution are deeply associated with heterogeneity, so we come up with the density-based and distance-based methods to quantify their heterogeneous degree.

Cooperation Based Probabilistic Caching Strategy in Clustered Cellular Networks

Journals and Magazines
Yifan Zhou, Zhifeng Zhao, Rongpeng Li, Honggang Zhang, and Yves Louet
IEEE Commun. Lett., vol. 21, no. 9, pp. 2029–2032, Sep. 2017.

This paper will discuss the probabilistic caching strategies in spatially clustered cellular networks. Thanks to the content preference of mobile users, proactive caching can be adopted as a promising technic to diminish the backhaul traffic and to decrease the content delivery latency. However, basically there are two obstacles to accomplish the caching policy, i.e., the
limited storage capacity of small cells to cache large amount of multimedia contents, and the too small number of users under each base station to imply the content aggregation effect. Traditional caching strategies of the base station only concern its
local requests from the connected users through wireless links, but neglects the potential benefit from the cluster feature of the network infrastructure and user traffic demand. In this letter, we proposed a new policy called ‘Caching as a Cluster’, where small cells can exchange content with each other to fulfill every user request within the cluster of base stations. Intuitively, this cooperation between base stations makes a difference to decrease the content delivery latency of mobile users in clustered cellular networks as testified in our numerical simulation.

A Tomography of Full-Duplex Cellular Networks

First AuthorInternational Conference Papers
Rongpeng Li, Wei Quan, Yan Chen, and Yiqun Wu
IEEE VTC 2017-Spring, Sydney, Australia, Jun. 2017.

On the Emerging of Scaling Law , Fractality and Small-World in Cellular Networks

International Conference Papers
Chao Yuan, Zhifeng Zhao, Rongpeng Li, Meng Li, Honggang Zhang
IEEE VTC 2017- Spring, Sydney, Australia, Jun. 2017.

A Revisiting to Queueing Theory for Mobile Instant Messaging with Keep-Alive Mechanism in Cellular Networks,

International Conference Papers
Lu Fan, Zhifeng Zhao, Chen Qi, Rongpeng Li, Honggang Zhang
IEEE ICC 2017, Paris, France, May 2017.

Full Duplex Delay Diversity Relay Transmission Using Bit-Interleaved Coded OFDM

Journals and Magazines
Yuansheng Jin, Xiang-Gen Xia, Yan Chen, and Rongpeng Li
IEEE Trans. Commun., vol. 65, no. 8, pp. 3250–3258, Aug. 2017.

In this paper, a delay diversity OFDM (DD OFDM) transmission scheme in amplify-and-forward (AF) full-duplex relay systems is investigated. One direct source-to-destination link, one relay forwarding link and residual self-interference (RSI) are considered in the system. The necessary cyclic prefix (CP) length is investigated and a suitable AF relay protocol in the full-duplex relay OFDM system is proposed. This paper demonstrates that the AF relay link and the direct source-to-destination link can be combined to provide spatial diversity. The key is that the DD OFDM scheme is used to transform the spatial diversity into increased channel frequency diversity that is further exploited by using the bit-interleaved coding. The BER performance of the proposed system is verified by simulation results.

The Learning and Prediction of Application-level Traffic Data in Cellular Networks

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Jianchao Zheng, Chengli Mei, Yueming Cai, and Honggang Zhang
IEEE Trans. Wireless Commun, vol. 16, no. 6, pp. 3899–3912, Jun. 2017.

Traffic learning and prediction is at the heart of the evaluation of the performance of telecommunications networks and attracts a lot of attention in wired broadband networks. Now, benefiting from the big data in cellular networks, it becomes possible to make the analyses one step further into the application level. In this paper, we firstly collect a significant amount of application-level traffic data from cellular network operators. Afterwards, with the aid of the traffic “big data”, we make a comprehensive study over the modeling and prediction framework of cellular network traffic. Our results solidly demonstrate that there universally exist some traffic statistical modeling characteristics, including ALPHA-stable modeled property in the temporal domain and the sparsity in the spatial domain. Meanwhile, the results also demonstrate the distinctions originated from the uniqueness of different service types of applications. Furthermore, we propose a new traffic prediction framework to encompass and explore these aforementioned characteristics and then develop a dictionary learning-based alternating direction method to solve it. Besides, we validate the prediction accuracy improvement and the robustness of the proposed framework through extensive simulation results.

The Emergence of Scaling Law, Fractal Patterns and Small-World in Wireless Networks

Journals and Magazines
Chao Yuan, Zhifeng Zhao, Rongpeng Li, Meng Li, Honggang Zhang
IEEE Access, vol. 5, no. 1, pp. 3121–3130, Mar. 2017.

In conventional cellular networks, for base stations (BSs) that are deployed far away from each other, it is general to assume them to be mutually independent. Nevertheless, after long-term evolution of cellular networks in various generations, this assumption no longer holds. Instead, the BSs, which seem to be gradually deployed by operators in a service-oriented manner, have embedded many fundamentally distinctive features in their locations, coverage and traffic loading. These features can be leveraged to analyze the intrinstic pattern in BSs and even human community. In this paper, according to large-scale measurement datasets, we build up a correlation model of BSs by utilizing one of the most important features, i.e., spatial traffic. Coupling with the theory of complex networks, we make further analysis on the structure and characteristics of this traffic load correlation model. Numerical results show that the degree distribution follows scale-free property. Also the datasets unveil the characteristics of fractality and small-world. Furthermore, we apply collective influence (CI) algorithm to localize the influential base stations and demonstrate that some low-degree BSs may outrank BSs with larger degree.

Results on Energy- and Spectral- Efficiency Tradeoff in Cellular Networks with Full-Duplex Enabled Base Stations

Journals and Magazines
Dingzhu Wen, Guanding Yu, Rongpeng Li, Yan Chen, Geoffrey Ye Li
IEEE Trans. Wireless Commun., vol. 16, no. 3, pp. 1494-1507, Mar. 2017

In this paper, we address the tradeoff between energy-efficiency (EE) and spectral-efficiency (SE) for cellular
networks with full-duplex (FD) communications enabled base stations. To be backward compatible with legacy LTE systems, it is assumed that user devices still work in the conventional half-duplex (HD) mode. There usually exists residual self-interference (RSI) in FD communications after advanced interference suppression techniques are applied. In our work, we consider two different RSI models: constant RSI model and linear RSI model. First, the necessary conditions for a FD transceiver to achieve better EE-SE tradeoff than a HD one are derived for both RSI models. Then, for the constant RSI model, a closed-form EE-SE expression is obtained in the scenario of single pair of users. We further extend our result and prove that EE is a quasi-concave function of SE in the scenario of multiple user pairs. Accordingly, an optimal algorithm to achieve the maximum EE based on the Lagrange dual decomposition technique is developed. For the linear RSI model, the EE-SE relation is difficult to deal with and
we develop a heuristic algorithm by decoupling the problem into two sub-problems: power control and resource allocation. Our analysis and algorithms are finally verified by comprehensive numerical results.

Full-Duplex Cellular Networks

First AuthorJournals and Magazines
Rongpeng Li, Yan Chen, Ye Geoffery Li, Guangyi Liu
IEEE Communications Magazine, vol. 56, no. 4, pp. 184-191, Apr. 2017

Full-duplex (FD) communications with simultaneous transmission and reception on the same carrier have long been deemed a promising way to boost spectrum efficiency, but hindered by the techniques for self-interference cancellation (SIC). Recent breakthroughs in analog and digital signal processing yield the feasibility of over $100$ dB SIC capability and make it possible for FD communications to demonstrate nearly doubled spectrum efficiency for point-to-point links. Now it is time to shift at least partial of our focus to FD networking, such as in cellular networks. FD networking has more complicated interference environments. Therefore, its performance improvement is not that straightforward compared with half-duplex networking. Before putting FD networking into practice, we need to understand what scenarios FD communications should be applied in under the current technology maturity, how bad the performance will be if we do nothing to deal with the newly introduced interference, and most importantly, how much improvement could be achieved after applying advanced interference management solutions. We will discuss all these questions in this article. In particular, we will investigate some advanced interference management solutions including power control and user scheduling, and unveil that up to $91\%$ spectrum efficiency gain and $110\%$ energy efficiency gain of FD cellular networks over its HD counterpart can be benefited from applying these solutions.

Energy- and Spectral- Efficiency Tradeoff in Full-Duplex Communications

International Conference Papers
Dingzhu Wen, Guanding Yu, Rongpeng Li , Yan Chen, and Ye Geoffrey Li
IEEE Globecom 2016 (FD Workshop), Washington USA.

This paper investigates the tradeoff between energy efficiency (EE) and spectral-efficiency (SE) for full-duplex (FD) communication enabled cellular networks. We assume that small cell base stations are working in the FD mode while user devices still work in the conventional half-duplex (HD) mode. First, a necessary condition for a FD transceiver to achieve better EE-SE tradeoff than a HD one is derived. Then, we analyze the EE-SE relation of a FD transceiver in the scenario of single pair of users and obtain a closed-form expression of the EE-SE relation. Next, we extend our result to the multi-user scenario and prove that EE is a quasi-concave function of SE in general and develop an optimal algorithm to achieve the maximum EE based on the Lagrange dual method. Our analysis is finally verified by extensive numerical results.

Intelligent 5G: When Cellular Networks Meet Artificial Intelligence

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Xuan Zhou, Guoru Ding, Yan Chen, Zhongyao Wang, and Honggang Zhang
IEEE Wireless Communications, vol. 5, no. 24, pp. 175–183, Oct. 2017.

The fifth-generation (5G) cellular networks is assumed to be the key enabler and infrastructure provider in the information communication technology (ICT) industry, by catering various services with diverse requirements. Now, the standardization of 5G cellular networks is being expedited, which also implies more of the candidate technologies will be adopted. Therefore, it is worthwhile to give insight into the candidate techniques as a whole and examine the design philosophy behind them. In this paper, we try to highlight one of the most fundamental features among the revolutionary techniques in 5G era, that is, there emerges initial intelligence in nearly every important aspect of cellular networks, including radio resource management, mobility management, service provisioning management, etc. However, faced with ever-increasingly complicated configuration issues and blossoming new service requirements, it is still insufficient for 5G cellular networks if it lacks complete artificial intelligence (AI) functionalities. Hence, we further introduce some fundamental concepts in AI and discuss the relationship between AI and the candidate techniques in 5G cellular networks. Specifically, we discuss the opportunities and challenges to exploit AI for achieving intelligent 5G networks. Furthermore, we also demonstrate the effectiveness of AI to manage and orchestrate cellular network resources. We envision that AI empowered 5G cellular networks will make the acclaimed ICT enabler a reality.

Binary Power Control for Full-Duplex Networks

First AuthorInternational Conference Papers
Rongpeng Li, Yan Chen, and Yiqun Wu
Proc. IEEE PIMRC 2016, Valencia, Spain, Sep 2016.

Full-duplex (FD) communications benefit from recent breakthroughs in analog and digital signal processing and demonstrate nearly doubled spectrum efficiency for point-to-point links with beyond $100$ dB self-interference cancellation capability. However, FD cellular networks with base stations (BSs) in FD mode and user terminals (UEs) in half-duplex mode also introduce intra-cell inter-UE interference and other kinds of interference, which might even eat up the potential gain. In this paper, we propose to take advantage of power control and inter-UE interference cancellation (IC) techniques to cope with the bothersome intra-cell inter-UE interference. We verify that the power control solution for single-cell FD network with a given user pair exhibits an interesting binary feature, that is, either both the BS and the uplink UE transmit at the maximum power or one of them completely mutes to achieve the optimal sum rate. Moreover, the binary feature holds even when inter-UE IC is applied, thus showing appealing computational efficiency. We also demonstrate significant performance improvement by applying binary power control with inter-UE IC to both single-cell and multi-cell FD networks.

Characterizing and Modeling Social Mobile Data Traffic in Cellular Networks

International Conference Papers
Chen Qi, Zhifeng Zhao, Rongpeng Li, Honggang Zhang
Proc. IEEE VTC 2016-Spring, Najing, China, May 2016.

Understanding traffic characteristics in cellular networks is of great significance for better network design and performance optimization. The rapid development of various social networking applications for smart devices makes it an imperative to carry out cellular data traffic analysis further into the application level. In this paper, based on a plenty of practical mobile data traffic records, we focus on three typical application types and draw conclusions in terms of statistical characteristics and appropriate distribution model for social mobile data traffic. Firstly, the universal existence of burstiness and self-similarity is demonstrated by testing traffic series at different time scales. Afterwards, -stable distributions are used to model traffic series benefiting from their internal burstiness and self- similarity. The minor fitting errors verify the validity of -stable model and a preliminary traffic prediction shows the usefulness of -stable model for further traffic analysis.

Network Slicing as a Service: Enable Industries Own Software-defined Cellular Networks

Journals and Magazines
Xuan Zhou, Rongpeng Li, Tao Chen, and Honggang Zhang
IEEE Communications Magazine, vol. 54, no. 7, pp. 146 - 153, Jul. 2016.

With the blossom of network functions virtualization (NFV) and software-defined networks (SDN), networks are becoming more and more agile with the features like resilience, programmability and open interfaces, which help operators to launch a network or service with more flexibility and shorter time to market. Recently, the concept and solution of network slicing (NS) have been proposed to facilitate to build a dedicated and customized logical network with virtualized resources. In this article,
we introduce the concept of a hierarchical network slicing as a service (NSaaS), helping operators to offer customized end-to-end cellular network as a service. Moreover, the service orchestration and service-level agreement (SLA) mapping for quality assurance are introduced to illustrate the architecture of service management across different levels of service models. Finally, we illustrate the process of NSaaS within operators by typical examples. With NSaaS, we believe that the supporting system will transform itself to a production system by merging operation domain and business domain, and enable operators to build network slices for vertical industries more agilely.

Game-Theoretic Multi-Channel Multi-Access in Energy Harvesting Wireless Sensor Networks

Journals and Magazines
Jianchao Zheng, Honggang Zhang, Yueming Cai, Rongpeng Li, Alagan Anpalagan
IEEE Sensors J., Vol. 16, No. 11, pp. 4587 - 4594, Apr. 2016.
In this paper, we use game theory to investigate the distributed multichannel multiaccess in an energy harvesting wireless sensor network (EH-WSN). Sensors’ competition for channel access is formulated as a non-cooperative game, which is proved to be an ordinal potential game that has at least one Nash equilibrium (NE). Furthermore, all the NE of the game are proved to be Pareto-optimal, and the Jain’s fairness index bound of the NE is theoretically derived. Finally, we design a fully distributed, online learning algorithm for the multichannel multiaccess in the EH-WSN, which is proved to converge to the NE of the formulated game. Simulation results validate the effectiveness of the proposed algorithm.

Large-scale Spatial Distribution Identification of Base Stations in Cellular Networks

Journals and Magazines
Yifan Zhou, Zhifeng Zhou, Yves Louet, Qianlan Ying, Rongpeng Li, Xuan Zhou, Xianfu Chen, Honggang Zhang
IEEE Access, vol 3, pp. 2987 - 2999, Dec. 2015

The performance of cellular system significantly depends on its network topology while cellular networks are undergoing a heterogeneous evolution. This promising trend introduces unplanned deployment of smaller base stations (BSs), thus complicating the performance evaluation even further. In this paper, based on large amount of real BS locations data, we present a comprehensive analysis on the spatial modeling of cellular network structure. Unlike the related works, we divide the BSs into different subsets according to geographical factor (e.g. urban or rural) and functional type (e.g. macrocells or microcells), and perform detailed spatial analysis to each subset. After discovering the inaccuracy of the Poisson point process (PPP) in BS locations modeling, we take into account the Gibbs point processes as well as Neyman-Scott point processes and compare their performance in view of large-scale modeling test, and finally reveal the general clustering nature of BSs deployment. This paper carries out the first large-scale identification regarding available literature, and provides more realistic and general results to contribute to the performance analysis for the forthcoming heterogeneous cellular networks.

Energy Efficiency Analysis of Heterogeneous Cellular Networks with Downlink and Uplink Decoupling

International Conference Papers
Xianzhong Sui, Zhifeng Zhao, Rongpeng Li, and Honggang Zhang
Proc. IEEE Globecom 2015, San Diego, CA, USA, Dec. 2015.

As current cellular networks are becoming increasingly heterogeneous, traditional cell association rule based on the downlink reference signal receiving power (RSRP) no longer serves well. Under this circumstance, the concept of downlink (DL) and uplink (UL) decoupling (DUDe), in which user equipments choose the serving Base Station (BS) in DL and UL separately, has drawn great attention during the design of next generation cellular networks. In this paper, using the framework of stochastic geometry, we at first derive the theoretical energy efficiency (EE) distribution of a two-tier heterogeneous network both in DL and UL with DUDe. Then through numerical simulation, we verify that the DUDe rule can improve EE of a heterogeneous network comparing with the traditional RSRP rule. The improvement is shown to be significant through a further comparison with bias-based Cell Range Extension (CRE).

Understanding the Traffic Nature of Mobile Instantaneous Messaging in Cellular Networks: A Revisiting to ALPHA-Stable Models

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Chen Qi, Xuan Zhou, Yifan Zhou, and Honggang Zhang
IEEE Access, vol. 3, pp. 1416-1422, Sep. 2015

Mobile instantaneous messaging (MIM) services significantly facilitate personal and business communications, inevitably consume substantial network resources and potentially affect the network stability. In this paper, we aim to understand the traffic nature of MIM in cellular networks. Specifically, in order to reach credible conclusions, our research takes account of practical measurement records of MIM services from China Mobile at two different levels. Firstly, a dataset of \textit{individual message level (IML) traffic} is exploited and reveals power-law distributed message length and lognormal distributed inter-arrival time, the heavy-tailness of which completely diverts from the geometric model and exponential model recommended by 3GPP. Secondly, another dataset considers the statistical pattern of \textit{aggregated traffic} within one whole base station, and demonstrates the accuracy of $\alpha$-stable models for the aggregated traffic. Further, it verifies that $\alpha$-stable models are suitable for characterizing the traffic in both conventional fixed core networks and cellular access networks. At last, with the aid of the generalized central limit theorem, we build up a theoretical relationship between the distributions of IML traffic and aggregated traffic.

On the ALPHA-Stable Distribution of Base Stations in Cellular Networks

Journals and Magazines
Yifan Zhou, Rongpeng Li, Zhifeng Zhao, Xuan Zhou, and Honggang Zhang
IEEE Communications Letters, vol. 19, no. 10, pp. 1750-1753 , Aug. 2015

Cellular networks are now nearly universally deployed and are under ever-growing pressure to increase the volume of data deliverable to consumers. Understanding how base stations (BSs) are spatially deployed, could prominently facilitate the performance analyses of cellular networks, as well as the design of efficient networking protocols. In this letter, inspired by the clustering reality of BSs and the intrinsic heavy-tailed characteristics of human activities, we aim to re-examine the statistical pattern of BSs in cellular networks, and find the most appropriate spatial density distribution of BSs. Interestingly, by taking advantage of large amount of realistic deployment information of BSs from on-operating cellular networks, we find that the widely adopted Poisson distribution severely diverges from the practical density distribution of BSs. Instead, heavy-tailed distributions could more precisely match the practical distribution. In particular, $\alpha$-stable distribution, the distribution also found in traffic pattern of broadband networks and cellular networks, is most consistent with the practical one.

On the Limits of Predictability in Real-World Radio Spectrum State Dynamics: From Entropy Theory to 5G Spectrum Sharing

Journals and Magazines
Guoru Ding, Jinlong Wang, Qihui Wu, Yu-Dong Yao, Rongpeng Li, Honggang Zhang, and Yulong Zou
IEEE Communications Magazine, vol. 53, no. 7, pp. 178–183, Jul. 2015.

Abstract: A range of applications in cognitive radio networks, from adaptive spectrum sensing to predictive spectrum mobility and dynamic spectrum access, depend on our ability to foresee the state evolution of radio spectrum, raising a fundamental question: To what degree is radio spectrum state (RSS) predictable? In this paper, we explore the fundamental limits of predictability in RSS dynamics by studying the RSS evolution patterns in spectrum bands of several popular services, including TV bands, ISM bands, and Cellular bands, etc. From an information theory perspective, we introduce a methodology of using statistical entropy measures and Fano inequality to quantify the degree of predictability underlying real-world spectrum measurements. Despite the apparent randomness, we find a remarkable predictability, as large as 90%, in the real-world RSS dynamics over a number of spectrum bands for all popular services. Furthermore, we discuss the potential applications of prediction-based spectrum sharing in 5G wireless communications.

Optimal Base Station Sleeping in Green Cellular Networks: A Distributed Cooperative Framework Based on Game Theory

Journals and Magazines
Jianchao Zheng, Yueming Cai, Xianfu Chen, Rongpeng Li, and Honggang Zhang
IEEE Transactions Wireless Communications, vol. 14, no. 8, pp. 4391–4406, Aug. 2015.

Abstract: This paper proposes a distributed cooperative framework to improve the energy efficiency of green cellular networks. Based on the traffic load, neighboring base stations (BSs) cooperate to optimize the BS switching (sleeping) strategies so as to maximize the energy saving while guaranteeing users’ minimal service requirements. The inter-BS cooperation is formulated following the principle of ecological self-organization. An interaction graph is defined to capture the network impact of the BS switching operation. Then, we formulate the problem of energy saving as a constrained graphical game, where each BS acts as a game player with the constraint of traffic load. The constrained graphical game is proved to be an exact constrained potential game. Furthermore, we prove the existence of a generalized Nash equilibrium (GNE), and the best GNE coincides with the optimal solution of total energy consumption minimization. Accordingly, we design a decentralized iterative algorithm to find the best GNE (i.e., the global optimum), where only local information exchange among the neighboring BSs is needed. Theoretical analysis and simulation results finally illustrate the convergence and optimality of the proposed algorithm.

Towards 5G: When Explosive Bursts Meet Soft Cloud

Journals and Magazines
Xuan Zhou, Zhifeng Zhao, Rongpeng Li, Yifan Zhou, Tao Chen, Zhisheng Niu, and Honggang Zhang
IEEE Network, vol. 28, no. 6, pp. 12–17, Nov. 2014..

Abstract: Rapid growing demand for mobile data traffic challenges capacities and service provision of the next-generation (5G) cellular networks. The real measurement data from operating cellular networks indicates that the traffic models and scenarios disobey our traditional assumptions, i.e., expressing burst nature. As a result, the current network architectures and service management may cause experience deterioration of the subscribers in future networks. In this article, we propose three approaches to alleviate the influence caused by various traffic bursts: baseband resource pool on cloud platform as wireless infrastructure to enhance the capacity and flexibility of networks, cloud core networks to provide dynamic extension and service flow control abilities, and software-defined bearer networks to simplify service delivery instructed by core networks. Different from the conventional stovepipe-like cloud computing network architectures, our proposed architecture interconnects and shares information with each other, breaking through horizontal device barriers and vertical layers. These cloud based approaches not only avoid the potentially negative impact from bursts, but also provide a software-controlled end-to-end service management framework for future cellular networks. In addition, by taking advantage of open interfaces of cloud based network elements, service control algorithms and network APIs could also be implemented to realize a smart and soft 5G cellular networks.

Characterizing Spatial Patterns of Base Stations in Cellular Networks

International Conference Papers
Qianlan Ying, Zhifeng Zhao, Yifan Zhou, Rongpeng Li, Xuan Zhou and Honggang Zhang
Proc. IEEE ICCC, Shanghai, China, Oct. 2014.

A game-theoretic approach for optimal base station sleeping in green cellular networks

International Conference Papers
Jianchao Zheng, Yueming Cai, Xianfu Chen, Rongpeng Li, and Honggang Zhang
Proc. WCSP, Hefei, China, Oct. 2014.

Service-oriented cross-layer management for software-defined cellular networks

International Conference Papers
Xuan Zhou, Zhifeng Zhao, Rongpeng Li, Yifan Zhou, and Honggang Zhang
Proc. IEEE PIMRC, Washington, DC, USA, Sep. 2014.

Two-tier Spatial Modeling of Base Stations in Cellular Networks

International Conference Papers
Yifan Zhou, Zhifeng Zhao, Qianlan Ying, Rongpeng Li, Xuan Zhou and Honggang Zhang
Proc. IEEE PIMRC, Washington, DC, USA, Sep. 2014.

Abstract: Poisson Point Process (PPP) has been widely adopted as an efficient model for the spatial distribution of base stations (BSs) in cellular networks. However, real BSs deployment are rarely completely random, due to environmental impact on actual site planning. Particularly, for multi-tier heterogeneous cellular networks, operators have to place different BSs according to local coverage and capacity requirement, and the diversity of BSs’ functions may result in different spatial patterns on each networking tier. In this paper, we consider a two-tier scenario that consists of macrocell and microcell BSs in cellular networks. By analyzing these two tiers separately and applying both classical statistics and network performance as evaluation metrics, we obtain accurate spatial model of BSs deployment for each tier. Basically, we verify the inaccuracy of using PPP in BS locations modeling for either macrocells or microcells. Specifically, we find that the first tier with macrocell BSs is dispersed and can be precisely modelled by Strauss point process, while Matern cluster process captures the second tier’s aggregation nature very well. These statistical models coincide with the inherent properties of macrocell and microcell BSs respectively, thus providing a new perspective in understanding the relationship between spatial structure and operational functions of BSs.

An Approximate Algorithm of Configurating Controllers in Multi-domain SDN Architecture

International Conference Papers
Gang Wang, Zhifeng Zhao, Jialiang Peng, Rongpeng Li, and Honggang Zhang
Proc. Chinacom, Maoming, China, Aug. 2014.

Intelligent Base Station Management in Greener Traffic-aware Cellular Networks

First AuthorInternational Conference Papers
Rongpeng Li, Zhifeng Zhao, Xianfu Chen, Yves Louet, and Honggang Zhang
URSI General Assembly and Scientific Symposium (GASS), Beijing, China, Aug. 2014.

Adaptive Multi-Task Compressive Sensing for Localization in Wireless LANs

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Yuan Zhang, Jacques Palicot,and Honggang Zhang
IET Communications, vol. 8, no. 10, pp. 1736 – 1744, Jul. 2014.

Abstract: The spatially distributed sparsity of the mobile devices (MDs) in indoor wireless local area networks (WLANs) makes compressive sensing (CS) based localization algorithms feasible and desirable. In this paper, we exploit the most recent developments in CS to efficiently perform localization in WLANs and design an accurate indoor localization scheme by taking advantage of the theory of multi-task Bayesian compressive sensing (MBCS). The proposed scheme assembles the strength measurements of signals from the MDs to distinct access points (APs) and jointly utilizes them at a central unit or a specific AP to achieve localization, thus being able to alleviate the burden of MDs while simultaneously giving a precise estimation of the locations. Afterwards, we give a deeper insight into the localization problem in more practical scenarios with varying number of MDs and investigate two different adaptive algorithms to meet the satisfactory localization error requirement. Compared to the conventional MBCS algorithms, simulation results validate that both adaptive algorithms could provide superior localization accuracy and exhibit stronger resilience to the changes in the number of MDs.

The Prediction Analysis of Cellular Radio Access Network Traffic: From Entropy Theory to Networking Practice

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Xuan Zhou, Jacques Palicot,and Honggang Zhang
IEEE Communications Magazine, vol. 52, no. 6, pp. 234 – 240, Jun. 2014.

Abstract: Although the research on traffic prediction is an established field, most existing works have been carried out on traditional wired broadband networks and rarely shed light on cellular radio access networks (CRANs). However, with the explosively growing demand for radio access, there is an urgent need to design a traffic-aware energy-efficient network architecture. In order to realize such a design, it becomes increasingly important to model the traffic predictability theoretically and discuss the traffic-aware networking practice technically. In the light of that perspective, we firstly exploit entropy theory to analyze the traffic predictability in CRANs and demonstrate the practical prediction performance with the state-of-the-art methods. Then, we propose a blueprint for a traffic-based software-defined cellular radio access network (SDCRAN) architecture and address the potential applications of predicted traffic knowledge into this envisioned architecture.

Energy Savings Scheme in Radio Access Network via Compressed Sensing Based Traffic Load Prediction

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Xuan Zhou and Honggang Zhang
Transactions on Emerging Telecommunications Technologies (ETT), vol. 25, no. 4, pp. 468–478, Apr. 2014.

Abstract: In radio access networks, the base stations’ (BSs) power consumption does not merely depend on the traffic loads within its coverage. The auxiliary devices, especially the cooling system in BSs, contribute to significant energy exhaustion. As the traffic loads fluctuate spatially and temporally, the BSs consequently suffer from heavy energy wastage when the traffic loads of their coverage are low. In this paper, an energy saving scheme over predicted traffic loads is proposed to tackle this energy inefficiency problem in incumbent radio access networks induced by the fluctuations of traffic loads. The proposed scheme firstly takes advantage of the spatial-temporal pattern of traffic loads and employs the compressive sensing method to predict the future traffic loads. Then, a grid-based energy saving scheme is developed to improve the energy efficiency through turning some BSs into sleeping mode while ensuring the quality of experience. Results of the simulation with real traffic load statistics finally validate the accuracy of the traffic load prediction and large improvement of energy efficiency.

TACT: A Transfer Actor-Critic Learning Framework for Energy Saving in Cellular Radio Access Networks

First AuthorJournals and Magazines
Rongpeng Li, Zhifeng Zhao, Xianfu Chen, Jacques Palicot, and Honggang Zhang
IEEE Transactions on Wireless Communications, vol. 13, no. 4, pp. 2000–2011, Apr. 2014.

Abstract: Recent works have validated the possibility of improving energy efficiency in radio access networks (RANs), achieved by dynamically turning on/off some base stations (BSs). In this paper, we extend the research over BS switching operations, which should match up with traffic load variations. Instead of depending on the dynamic traffic loads which are still quite challenging to precisely forecast, we firstly formulate the traffic variations as a Markov decision process. Afterwards, in order to foresightedly minimize the energy consumption of RANs, we design a reinforcement learning framework based BS switching operation scheme. Furthermore, to speed up the ongoing learning process, a transfer actor-critic algorithm (TACT), which utilizes the transferred learning expertise in historical periods or neighboring regions, is proposed and provably converges. In the end, we evaluate our proposed scheme by extensive simulations under various practical configurations and show that the proposed TACT algorithm contributes to a performance jumpstart and demonstrates the feasibility of significant energy efficiency improvement at the expense of tolerable delay performance.

Here below is the Abstract in Chinese.
中文翻译:如何通过动态基站开关策略提高接入网的能量效率,是最近的研究热点之一。本文开展的正是匹配流量变化的基站开关策略研究,但与之前通过预测流量实现基站智能开关不同的是:本文中我们将流量变化建模成了马尔科夫决策过程,从而规避了流量在实际中较难预测的弊端。同时,我们考虑到接入网需要更具前瞻性的进行耗能优化,采用了基于强化学习的基站开关方案。此外,我们吸收借鉴了过去时间、相邻区域的学习结果,提出了转移学习算法(即transfer actor-critic algorithm),从而达到加快当下正在进行的学习过程的目的,并通过理论分析证明了相关算法的收敛特性。本文最后模拟实际场景进行了仿真实验,评估验证了所提的转移学习算法的性能——初始节能效率的跃升和可容忍延迟的能效提高。

Understanding the Nature of Social Mobile Instant Messaging in Cellular Networks

Journals and Magazines
Xuan Zhou, Zhifeng Zhao, Rongpeng Li, Yifan Zhou, Jacques Palicot,and Honggang Zhang
IEEE Communications Letters, vol. 18, no. 3, pp. 389 – 392, Mar. 2014.

Abstract: Social mobile instant messaging (MIM) applications, running on portable devices such as smartphones and tablets, have become increasingly popular around the world, and have generated significant traffic demands on cellular networks. Despite its huge user base and popularity, little work has been done to characterize the traffic patterns of MIM. Compared with traditional cellular network service, MIM traffic embodies several specific attributes such as non-Poisson arrivals, keepalive (KA) mechanism and heavy-tailed message length, which consumes even small amount of core network bandwidth but considerable radio resources of mobile access network. This letter investigates user behavior patterns and traffic characteristics of MIM applications, based on real traffic measurements within a large-scale cellular network covering 7 million subscribers. Moreover, we propose a joint ON/OFF model to describe the traffic characteristics of MIM, and evaluate the performance of cellular network running MIM service in various scenarios. Comparing with the MIM service models of 3GPP, our results are more realistic to estimate the networks performance.

Here below is the Chinese translation of the Abstract.
论文摘要:近年来,得益于日益普遍的智能手机、平板等便携式个人设备,移动即时通信(MIM)应用(例如“微信”)逐渐走进了千家万户,并在蜂窝移动通信网络上产生了巨大的流量。我们注意到,尽管“微信”等MIM应用已拥有庞大的用户基数和与日俱增的流行度,时下却鲜有MIM应用相关的流量模式及特性研究。而与传统互联网流量相比,MIM应用流量具有非泊松到达、常连接(keep-alive :“保持心跳”)机制和满足重尾统计分布的包长等诸多显著的不同特征。这些不同特性使得MIM应用虽然仅需要很少的核心网带宽,却往往消耗了大量的无线接入资源。本论文通过分析一个现有700多万用户的蜂窝移动通信网流量数据,探讨、归纳了MIM应用的用户行为特点和流量特征。此外,我们提出了一个联合开/关模型(JOOM)来更准确地描述“微信”等MIM应用的流量特征,并用于2G、3G、4G蜂窝网下“微信”等MIM应用对网络资源占用情况的分析、评估。分析结果表明,我们提出的JOOM模型能够更好地模拟实际网络中的流量情况、并估计网络资源的占用情况。

Compressive Sensing Based Overhead Reduction Scheme in Multi-antenna Downlink Management

International Conference Papers
Jianxiong Jin, Zhifeng Zhao, Rongpeng Li and Honggang Zhang
Proc. WCSP, Hangzhou, China, Oct. 2013.

Human Mobility Patterns in Cellular Networks

Journals and Magazines
Xuan Zhou, Zhifeng Zhao, Rongpeng Li, Yifan Zhou, Jacques Palicot,and Honggang Zhang
IEEE Communications Letters, vol. 17, no. 10, pp. 1877-1880, Sep. 2013.

Abstract: This letter investigates inter-arrival time, dwell time distributions and other mobility patterns in mobile cellular networks. It has been generally assumed and widely accepted that both inter-arrival time and dwell time distributions can be well approximated by exponential distribution. However, based on real cellular data measurements, we evaluate the fitness of various typical statistical distributions such as power-law, exponential, Weibull, lognormal and Rayleigh distributions, and find that a power-law distribution fits both inter-arrival time and dwell time most precisely. Besides, mobility patterns in daytime, night, rural and urban areas provide further demonstrations of the power-law model. Moreover, new models on the distributions of inter-departure time and the number of arrived subscribers are also proposed to characterize other mobility patterns, and the corresponding simulation results are well consistent with the empirical ones.

Downlink Interference Minimization in Cognitive LTE-Femtocell Networks

International Conference Papers
Xin Tao, Zhifeng Zhao, Rongpeng Li, Jacques Palicot and Honggang Zhang
Proc. IEEE ICCC , Xi’an, China, Aug. 2013.

Downlink interference minimization in cooperative cognitive LTE-femtocell networks

Journals and Magazines
Xin Tao, Zhifeng Zhao, Rongpeng Li, Jacques Palicot and Honggang Zhang
EURASIP Journal on Wireless Communications & Networking (Special Issue on Cooperative Cognitive Networks), vol. 2013, no. 1, p. 194, Jul. 2013.

Abstract: Femtocell is considered to be one of the most promising solutions for future indoor wireless communication. Due to the scarcity of spectrum resources, femtocells need to share the spectrum with other networks, which will inevitably bring in severe interference. Therefore, minimizing the cross-tier and co-tier interference while maintaining high system throughput or spectrum efficiency is one of main challenges before largely deploying femtocell networks. In order to effectively mitigate the interference, cognitive radio-enabled techniques can play a key role by providing more secondary spectrum access opportunities, especially in dense femtocells deployment scenarios. Supported by cognitive radio functionality, femtocell users can access and share these licensed spectra including the frequency bands of both macrocells and other licensed systems (e.g., TV white spaces) as long as not causing harmful interference to the coexisting licensed systems. In this paper, based on cognitive sensing, we propose a joint channel assignment and power allocation scheme, aiming to minimize the aggregate interference from multiple femtocells to the licensed users while satisfying the constraints of each femtocell’s capacity and power budget. It is believed that the cooperation among multiple femtocells is quite helpful in mitigating the interference considering the mobility of the licensed users. Specifically, Hungarian algorithm is involved in our scheme to address the co-tier femtocell interference issue. In order to illustrate our scheme more explicitly, we come up with the concepts of Physical Cluster and Virtual Cluster and synthetically apply the related algorithms to reduce the interference step by step. Finally, the performances of employed algorithms are evaluated and analyzed. Numerical results have validated that the proposed scheme is viable and effective in managing the femtocell interference.

Energy Saving through a Learning Framework in Greener Cellular Radio Access Networks

First AuthorInternational Conference Papers
Rongpeng Li, Zhifeng Zhao, Xianfu Chen and Honggang Zhang
Proc. IEEE Globecom 2012, Anaheim, California, USA, Dec. 2012.

Recent works have validated the possibility of energy efficiency improvement in radio access networks (RAN), depending on dynamically turn on/off some base stations (BSs). In this paper, we extend the research over BS switching operation, matching up with traffic load variations. However, instead of depending on the predicted traffic loads, which is still quite challenging to precisely forecast, we formulate the traffic variation as a Markov decision process (MDP). Afterwards, in order to foresightedly minimize the energy consumption of RAN, we adopt the actor-critic method and design a reinforcement learning framework based BS switching operation scheme. In the end, we evaluate our proposed scheme by extensive simulations under various practical configurations and prove the feasibility of significant energy efficiency improvement.

The Predictability of Cellular Networks Traffic

International Conference Papers
Xuan Zhou, Zhifeng Zhao, Rongpeng Li, Yifan Zhou and Honggang Zhang
Proc. IEEE ISCIT 2012, Gold Coast, Australia, Oct. 2012.

Abstract: In order to improve the energy efficiency and resource management of cellular networks, traffic modeling and prediction has been focused in recent years. In this paper, we take advantage of entropy theory to explore the limits of predictability of cellular network traffic based on large amount of traffic dataset gathered from real cellular network in China. By categorizing traffic according to voice, text and data group, we investigate random entropy of each type of traffic, as well as conditional entropy by temporal, spatial and service related information. Our key findings are that (1) traffic can be well predicted by preceding 15 hours traffic, (2) voice traffic has so close similarity to text traffic in the same cell that we can use one of them to predict the other, (3) knowledge of adjacent cells traffic can enhance the predictability of voice and text more than data. Considering the large amount traffic dataset which contains thousands of base stations and billions of records, the impact of dataset pre-processing, quantization and time resolution are also taken into account and are discussed. Moreover, macroscopic view of entropy distribution is presented by geo-location markers.

Spatial-Temporal Compressed Sensing Based Traffic Prediction in Cellular Networks

International Conference Papers
Qian Wen, Zhifeng Zhao, Rongpeng Li, and Honggang Zhang
Proc. IEEE ICCC 2012 (SGCNet wksp), Beijing, China, Aug. 2012.

Abstract: In conventional cellular networks, base stations (BSs) usually suffer from severe power consumption since they are working to guarantee the coverage and QoS (quality-of-service) requirement according to the peak traffic load generated by the mobile cellular users Accordingly, how to precisely forecast the future traffic load to promote network cooperation and adaptive energy resource allocation in complying with the variation of spatial-temporal traffic load has been an emerged issue due to the significant energy exhaustion of BSs. In this paper, we propose a spatial-temporal compressed sensing based network traffic prediction method to solve this problem. We first construct a traffic matrix (TM) by using previously measured data and setting the data to be predicted as zeros, corresponding to the volume of traffic load. Then, compressed sensing approach with large scale and small scale temporal constraints as well as spatial constraints is employed to factorize the traffic matrix. By reuniting the results of traffic matrix factorization, we obtain the estimation of predicted traffic data. Numerical results have showed that this method can restrict the prediction error under 10% when dealing with real traffic load data.

Filter Bank Techniques for Multi-Carrier Cognitive Radio Systems – Cognitive Communications – Distributed Artificial Intelligence (DAI), Regulatory Policy & Economics, Implementation (David Grace and Honggang Zhang)

Book Chapters
Yun Cui, Zhifeng Zhao, Rongpeng Li, Guangchao Zhang, and Honggang Zhang

GM-PAB: A Grid-based Energy Saving Scheme with Predicted Traffic Load Guidance for Cellular Networks

First AuthorInternational Conference Papers
Rongpeng Li, Zhifeng Zhao, Yan Wei, Xuan Zhou and Honggang Zhang
Proc. IEEE ICC 2012, Ottawa, Canada, June 2012.

Abstract: In cellular networks, the base station power consumption is not simply proportional to the traffic loads of its coverage. As the traffic load fluctuates spatially and temporally, the base stations consequently suffer from heavy energy wastage when the traffic loads of their coverage are low. In this paper, we propose a grid-based energy saving scheme over predicted traffic loads. We firstly take advantage of the spatial-temporal pattern of traffic loads and employ the compressed sensing method to predict the future traffic loads. Then, we propose a grid-based energy saving scheme to improve the energy efficiency through turning some base stations into sleeping mode while ensuring the quality of service. Results of the simulation with real traffic loads finally show the accuracy of the traffic load prediction and large energy efficiency improvement.