Xirong Que

BalanceFlow: Controller load balancing for OpenFlow networks

In the discussion about Future Internet, Software-Defined Networking (SDN), enabled by OpenFlow, is currently seen as one of the most promising paradigm. While the availability and scalability concerns rises as a single controller could be alleviated by using replicate or distributed controllers, there lacks a flexible mechanism to allow controller load balancing. This paper proposes BalanceFlow, a controller load balancing architecture for OpenFlow networks. By utilizing CONTROLLER X action extension for OpenFlow switches and cross-controller communication, one of the controllers, called “super controller”, can flexibly tune the flow-requests handled by each controller, without introducing unacceptable propagation latencies. Experiments based on real topology show that BalanceFlow can adjust the load of each controller dynamically.

An enhanced personal photo recommendation system by fusing contextual and textual features on mobile device

As a main means to record scene in personal daily life, personal photos convey high-level semantic information (e.g., who, what, when, where) of an activity user engaged in. Different from other information retrieval tasks, personal photo recommendation depends on the measure of activity relevancy which is implicitly embedded in photos. Spurred by this observation, an enhanced recommendation approach by fusing both contextual and textual features is proposed. First, contextual relevancy is incrementally refined with an enhanced temporal and spatial clustering method respectively. Second, textual similarity of photo annotations is calculated using WordNet to augment the activity relevancy. Third, a fuzzy decision based multi-criteria ranking algorithm i.e., Preference Ranking Organization Method of Enrichment Evaluation (PROMETHEE) is adopted to make recommendations when giving an entry photo. A prototype has been developed on mobile device to illustrate this concept. Experiment results on a real dataset which contains 10,827 photos collected from 50 volunteers during 12 months demonstrate that our approach is more accurate than traditional schemes.

Maximizing Network Utilization in Hybrid Software-Defined Networks

By separating the control and forwarding planes, Software-Defined networking (SDN) enables the forwarding paths to be flexibly controlled by the logically centralized controllers using the global network view. To introduce SDN into existing networks, it is necessary to upgrade traditional devices to SDN- enabled ones. However, due to the business, economic and management limitations, it is difficult to realize full SDN deployment. As a result, how to migrate existing devices to SDN-compliant ones becomes the obvious dilemma for every network operator. In this paper, we address this question from the network performance perspective, and study how to leverage the capability of SDN to maximize traffic flow that can be achieved in hybrid SDNs. We formulate the maximum flow problem in networks with partial SDN deployment, and develop a fast Fully Polynomial Time Approximation Scheme (FPTAS) for solving it. Simulation results using real topologies show that hybrid SDNs outperform traditional networks, and we can obtain a near optimal network performance when 50% of SDN nodes are deployed.

Empirical analysis of different hierarchical addressing deployments

Currently the increasing prevalence of multi-homing and traffic engineering leads to an explosive growth of the global routing table. It is well known that hierarchical addressing could improve the routing scalability. Hence, some proposals exploring the routing architecture for future Internet reuse the hierarchical addressing for the locator assignment. However, this may result in some ASes assigned too many prefixes which would consequently make hosts, routers, Internet Service Providers and Domain Name System faced with big challenges. By modeling the Internet AS-level topology using a hierarchical graph, we define the processes of prefix assignment and routing advertisement in different hierarchical addressing deployment ways. Then, we quantify the impact of these deployments on the prefix assignment and the routing scalability based on the real routing data. we find that when the deploying position gets lower, the prefix amount of arbitrary AS is getting smaller, while the size of the global Forwarding Information Base is monotonically increasing. Comparing with the actual Internets data, suitable deployment ways for hierarchical addressing are obtained. With these deployment ways, the excessive prefix problem is solved and the size of the global Forwarding Information Base could be reduced into 56% or even 32% of the one in current Internet.

A hybrid social search model based on the user's online social networks

Online social networks (OSNs) have become a new networking platform for connecting people through a variety of mutual relationships. Owing to its widespread use of applications such as email, online shopping, online business networking and instant messaging, OSNs play an indispensable part in peoples work and life. People tend to seek information through their OSNs rather than the traditional search engine. This paper presents a hybrid social search model, which harnesses the users social relation to generate the satisfying results. Upon receiving a users query, the social search model aims to return a list of ranked answerers who might give the correct answers to that query. Two novel algorithms are proposed to calculate the result ranking: 1) Topic Relevance Rank (TRR) evaluates users professional score on the relevant topics; 2) Social Relation Rank (SRR) captures the social relation strength between users. In addition, a topic classification label is defined to control the weight of these two algorithms. We describe the architecture of the social search model and give details of the ranking algorithms. A use-case is described to illustrate the potential applications of the proposed model. 3G RenRen Network, mobile edition of the biggest student social networking site in China is studied and the experiment results show that the two ranking algorithms under control of topic classification label can benefit the social search model evidently.

VNMC for network virtualization in OpenFlow network

Network virtualization provides an efficient way to share physical network infrastructure so that multiple virtual slices can run concurrently. OpenFlow is a promising and successful future networking technology which enables network innovation efficiently. However, the existing network virtualization methods in OpenFlow network usually have limitations such as introducing a proxy, flow entry conflicts, lacking of extensibility. In this paper, we present VNMC, a Virtual Network Management Component for rapidly creating, configuring and managing virtual networks in OpenFlow network. It has the following features: VNMC is implemented in a single controller without a middle layer. VNMC provides bandwidth guarantee, topology isolation, flow isolation and control isolation. It resolves flow entry conflicts from different controllers using the multiple flow tables mechanism defined in the latest OpenFlow standard. It manages the virtual networks in a modular way, which brings great extensibility to add new functionalities to virtual networks.

A hybrid model based on Kalman Filter and neutral network for traffic prediction

In this paper, a hybrid model based on Kalman Filter and Neural Network is introduced for traffic prediction to make our travel more convenient. The proposed model, taking both the real-time data and the historical data, can predict the link travel time in near future more accurately and thus increase the user service quality of APTS. The performance of evaluation is demonstrated on the real link travel time from Wenhui Bridge to Mingguang Bridge collected by mobile phone supporting GPS. Finally MAPE is used to calculate the prediction error and the result shows that the hybrid model performs well than both the two separate models. Based on our proposed model for traffic prediction, the APTS, which is one of the most important applications of ITS, would attract much more people to use the public transportation system and greatly reliever the burden of the urban traffic pressure.

Phone-Radar: Infrastructure-Free Device-to-Device Localization

In some practical scenarios such as tour guiding and children babysitting, one mobile device held by tour guides or parents need to know the distance and direction of another nearby mobile device held by tourist or children. However, to date, most existing pedestrian localization methods rely on a fixed external infrastructure, such as a global positioning system(GPS) or pre-deployed wifi access points to provide Localization service for mobile devices. Such methods are constrained either by limited GPS coverage or by complicated set-up procedures. We observe that, when two devices are moving, the change of their positions leads to the change of distance between them. Given the same movements, different relative locations between devices lead to different distance changes. Besides, the distance between and relative movement of devices can be measured by two phone-embedded sensors respectively. This motivates us to exploit the relative localization method by merely two mobile devices. In this work, we present Phone-Radar, which is an infrastructure-free device-to-device localization system. According to the propagation model of wireless signals, the change of distance between devices are modeled by the change of wireless signal strength between them. The movements of devices are recorded by the inertial sensors using step-counting method. We further study the relationship among the initial relative locations between the two devices, their relative movements and the change of received signal strength measurements. Moreover, we implement the proposed method and measure its performance under real world conditions. The testbed experiments show the efficiency of our proposed method.

A rate adaptive algorithm for HTTP streaming

Recently, the traffic volume of HTTP streaming application is rapidly growing on the Internet. As an adaptive streaming technology, the most challenge of HTTP streaming technology is when and how to switch bitrates so that the user can get satisfactory experience. In this paper, we propose a novel Bitrates Adaptive HTTP Streaming (BAHS) algorithm. This algorithm uses application layer information, not needs to require information from transport layer, detecting network congestion and client buffer state to determine next media quality level. Simulation results show that the flexible BAHS algorithm can effectively combine real-time network state with client player buffer as well as control the frequency and total time of buffer overflow and underflow, prompting user experience.

An Autonomic Active Queue Management Mechanism to Improve Multimedia Flow Delivery Quality

With the rapid development of network technology and network services, the users’ requirements of network QoS are also improved. The traditional Active Queue Management(AQM) mechanisms are not adequate to provide QoS guarantee to multimedia video traffics effectively. To provide better quality of service to the multimedia applications in Mobile Ad Hoc Network(MANETs), whose resource is limited and changed dynamically, in this paper, we propose an Active Queue Management mechanism with autonomic features, named Autonomic Active Queue Management (AAQM). AAQM tries to adjust its behavior according to service and network condition information. Simulation under NS2 in MANETs has shown that AAQM is capable of improving the quality of multimedia video streams.