Xiaomin Zhu

Introducing multipath selection for concurrent multipath transfer in the future internet

It is essential for the Future Internet to fully support multihoming and select most appropriate paths for Concurrent Multipath Transfer (CMT). In real complex networks, different paths are likely to overlap each other and even share bottlenecks which can weaken the path diversity gained through CMT. Spurred by this observation, it is necessary to select multiple independent paths insofar as possible. However, the path correlation lurks behind the IP/network layer topology, so we have to fall back to end-to-end probes to estimate this correlation by analyzing path delay characteristics. In this paper, we present the first step towards a new topic of correlation-aware multipath selection, with formal and systematic problem definition, modeling and solution. Based on a well-designed delay probing, a Grouping-based Multipath Selection (GMS) mechanism is developed to avoid underlying shared bottlenecks between topologically joint paths. In addition, we further propose a practical functionality framework and define a novel multihoming sublayer for the exchange of the multipath capabilities. Extensive simulations demonstrate that the GMS under different network conditions performs much better than other selection schemes, even with burst background traffic.

A multi-path mechanism for reliable VoIP transmission over wireless networks

With the advances in audio encoding standards and wireless access networks, voice over IP (VoIP) is becoming quite popular. However, real-time voice data over lossy networks (such as WLAN and UMTS), still posses several challenging problems because of the adverse effects caused by complex network dynamics. One approach to provide QoS for VoIP applications over the wireless networks is to use multiple paths to deliver VoIP data destined for a particular receiver. This paper introduced cmpSCTP, a transport layer solution for concurrent multi-path transfer that modifies the standard stream control transmission protocol (SCTP). The cmpSCTP aims at exploiting SCTPs multi-homing capability by selecting several best paths among multiple available network interfaces to improve data transfer rate to the same multi-homed device. Through the use of path monitoring and packet allotment techniques, cmpSCTP tries to transmit an amount of packets corresponding to the paths ability. At the same time, cmpSCTP updates the transmission strategy based on the real-time information of all of paths. Using cmpSCTPs flexible path management capability, we may switch the flow between multiple paths automatically to realize seamless path handover. The theoretical analysis evaluated the model of cmpSCTP and formulated optimal traffic fragmentation of VoIP data. Extensive simulations under different scenarios using OPNET verified that cmpSCTP can effectively enhance VoIP transmission efficiency and highlighted the superiority of cmpSCTP against the other SCTPs extension implementations under performance indexes such as throughput, handover latency, packet delay, and packet loss.

A distributed end-to-end overload control mechanism for networks of SIP servers

The Session Initiation Protocol (SIP) is an application-layer control protocol standardized by the IETF for creating, modifying and terminating multimedia sessions. With the increasing use of SIP in large deployments, the current SIP design cannot handle overload effectively, which may cause SIP networks to suffer from congestion collapse under heavy offered load. This paper introduces a distributed end-to-end overload control (DEOC) mechanism, which is deployed at the edge servers of SIP networks and is easy to implement. By applying overload control closest to the source of traffic, DEOC can keep high throughput for SIP networks even when the offered load exceeds the capacity of the network. Besides, it responds quickly to the sudden variations of the offered load and achieves good fairness. Theoretic analysis and extensive simulations verify that DEOC is effective in controlling overload of SIP networks.

IIN model: modifications and case study

Abstract Referring to IN/Internet interworking models proposed by International Telecommunication Union and Telecommunication standardization sector (ITU-T) and the Internet Engineering Task Force (IETF), a new model is proposed based on the China Mobile Intelligent Network version 02 (CMIN02) system from Beijing University of Posts and Telecommunications (BUPT). This model adds modifications and refinements to the former two reference models. This model can be divided into three layers horizontally and three sections vertically. Emphasis is put on the gateways due to their importance. Moreover, a novel notion called information flow trail is proposed, which is helpful in designing complex gateways. So far, most work on gateways focuses on studying simple cases where gateways have only two interfaces towards the outside. However, Management Gateway Function (MGF), Service Control Gateway Function (SCGF) and Call/Bearer Gateway Function (C/BGF) have more than two interfaces. In this case, the novel notion is quite helpful. During the implementation of Project 863 the modified model has been tested and proved viable.

An optimized QoS scheme for IMS-NEMO in heterogeneous networks

The network mobility (NEMO) is proposed to support the mobility management when users move as a whole. In IP Multimedia Subsystem (IMS), the individual Quality of Service (QoS) control for NEMO results in excessive signaling cost. On the other hand, current QoS schemes have two drawbacks: unawareness of the heterogeneous wireless environment and inefficient utilization of the reserved bandwidth. To solve these problems, we present a novel heterogeneous bandwidth sharing (HBS) scheme for QoS provision under IMS-based NEMO (IMS-NEMO). The HBS scheme selects the most suitable access network for each session and enables the new coming non-real-time sessions to share bandwidth with the Variable Bit Rate (VBR) coded media flows. The modeling and simulation results demonstrate that the HBS can satisfy users QoS requirement and obtain a more efficient use of the scarce wireless bandwidth. Copyright

A scalable approach for content based image retrieval in cloud datacenter

The emergence of cloud datacenters enhances the capability of online data storage. Since massive data is stored in datacenters, it is necessary to effectively locate and access interest data in such a distributed system. However, traditional search techniques only allow users to search images over exact-match keywords through a centralized index. These techniques cannot satisfy the requirements of content based image retrieval (CBIR). In this paper, we propose a scalable image retrieval framework which can efficiently support content similarity search and semantic search in the distributed environment. Its key idea is to integrate image feature vectors into distributed hash tables (DHTs) by exploiting the property of locality sensitive hashing (LSH). Thus, images with similar content are most likely gathered into the same node without the knowledge of any global information. For searching semantically close images, the relevance feedback is adopted in our system to overcome the gap between low-level features and high-level features. We show that our approach yields high recall rate with good load balance and only requires a few number of hops.

Hybrid virtual network embedding with K-core decomposition and time-oriented priority

Network virtualization provides a powerful tool to allow multiple networks, each customized to a specific purpose, to run on a shared substrate. However, a big challenge is how to map multiple virtual networks onto specific nodes and links in the shared substrate network, known as virtual network embedding problem. Previous works in virtual network embedding can be decomposed to two classes: two-stage virtual network embedding and one-stage virtual network embedding. In this paper, by pruning the topology of virtual network using k-core decomposition, a hybrid virtual network embedding algorithm is proposed to leverage the respective advantage of the two kinds of algorithm simultaneously in the mapping process. In addition, a time-oriented scheduling policy is introduced to improve the mapping performance. We conduct extensive simulations and the results show that the proposed algorithm obtains more revenue in the long-term run.

Latent Handover: A flow-oriented progressive handover mechanism

The next generation network may be regarded as an IP (Internet Protocol) converged network, combining various access technologies. In this environment, ubiquitous computing and seamless networking are required for the mobile host. The growing availability of multiple network interfaces on mobile devices makes Concurrent Multi-path Transfer (CMT) an appealing candidate to realize the seamless handover. In this paper, we proposed a novel Latent Handover mechanism, which is flow-oriented and switches the traffic to the new path progressively to make the handover process unconscious to users or upper layer applications, especially real-time services. In addition, to support the proposed Latent Handover, the transport layer introduces our proposed cmpSCTP (concurrent multi-path Stream Control Transmission Protocol), which adds concurrent multi-path transfer and dynamic Multi-Path Management support to the standard SCTP for realizing seamless handover. The theoretical analysis verified that the proposed Latent Handover can efficiently optimize the handover process and enhance transmission efficiency during handover. Extensive simulations under different scenarios using OPNET highlighted the superiority of the proposed Latent Handover solution against other existing handover schemes under performance indexes such as throughput, handover latency, packet delay, and packet loss.

A token-bucket based notification traffic control mechanism for IMS presence service

Presence is a service that allows a user to be informed about the specified state of another user. Presence service has become a key enabler for next-generation applications such as instant messaging, push-to-talk and web2.0. However, recent studies show that the notification traffic of presence service causes heavy signaling load on IP multimedia subsystem (IMS) network. This paper introduced a token-bucket based notification traffic control (TNTC) mechanism, which is an application layer solution deployed at the presence server. The TNTC aims at upgrading valid access probability while controlling the notification traffic. A mathematical model of a queuing system is proposed to describe TNTC. We analyzed its main probability features and investigated the effects of different parameters on the performance of TNTC. Extensive simulations verified that TNTC can effectively control notification traffic and perform better than the existing schemes in terms of valid access probability and update arrival rate.

A Group Based Service Triggering Algorithm for IMS Network

To determine the potential signaling traffic reductions, the session establishment procedures are investigated. The investigation shows that, the S-CSCF (Serving Call Session Control Function) is the major bottleneck in IMS (IP Multimedia Subsystem) and the existing 3GPP (the 3rd Generation Partnership Project) Service Triggering Algorithm (3GPP STA) increases largely the end to end session setup delay. To reduce the session setup delay and improve the system performance, a new Group based Service Triggering Algorithm (GSTA) is proposed. And then the modeling of 3GPP STA and GSTA are presented. Theoretical analysis and simulation results show that, GSTA can efficiently reduce the signaling traffic load of the S-CSCF, increase the throughput of the system and considerably reduce the session setup delay, improve IMS network quality of service.