Xiuquan Qiao

A Low-Delay, Lightweight Publish/Subscribe Architecture for Delay-Sensitive IOT Services

In order to build a low-latency lightweight publish/subscribe (pub/sub) system for IOT services, we propose an efficient and scalable broker architecture, called Grid Quorum-based pub/sub system (GQPS). As a core component in the event-driven SOA framework for IOT services, this architecture organizes multiple pub/sub brokers into a quorum-based peer-to-peer topology for efficient topic searching. It also leverages a topic searching algorithm and a caching strategy to achieve a small and constant search latency. Lightweight RESTful interfaces make our GQPS more suitable for IOT services. Cost analysis and experiment study demonstrate that GQPS achieves a significant performance gain in search satisfaction without compromising search cost. We applied GQPS in the District Heating Control and Information Service System in Beijing, China, which validates the feasibility and availability of our architecture.

NDNBrowser: An extended web browser for named data networking

Web applications have become one of the fundamental Internet services. How to effectively support the popular browser-based web applications is a key to success for Named Data Networking (NDN). However, since NDN has a totally different running mechanism from the traditional IP network, the existing web browsers mainly designed for the HTTP protocol and the TCP/IP-based Internet rather than named data networking, cannot communicate with NDN routers directly and do not inherently support the NDN-based web applications. Instead of providing a browser add-on or HTTP–NDN proxy/gateway, we designed and developed a complete NDNBrowser based on open source WebKit to natively support NDN-based web applications in the web browser kernel. Some inherent NDN features are seamlessly integrated into the browser to support the direct interactions between web browser and NDN network. Considering backwards compatibility and smooth network evolution, the NDNBrowser enables content fetching and rendering by both ‘ccnx:/’ and ‘http:/’ schemes URI in HTML, CSS and JavaScript simultaneously. Experimental results show that the NDNBrowser outperforms existing NDN.JS and HTTP–NDN proxy/gateway implementations by 19× and 5× respectively in terms of throughput. Finally, a real NDN-based web application is deployed on a NDN experimental network in our campus environment for network innovations to verify the practicability of NDNBrowser.

Robust bandwidth aggregation for real-time video delivery in integrated heterogeneous wireless networks

Bandwidth aggregation is the process of integrating the limited channel resources available in heterogeneous wireless networks. Optimizing this process is an important step towards improving the throughput and reliability for the bandwidth-demanding video applications. In this paper, we investigate the bandwidth aggregation for real-time video delivery in heterogeneous wireless networks from a video server to a multihomed client. Forward Error Correction (FEC) coding is commonly adopted for data protection in implementing loss-resilient wireless video transmission systems. However, the inherent channel unreliability, along with the video traffic variability, can significantly degrade the FEC performance. To address the critical issues, we propose a ROBust BandwIdth Aggregation (ROBBIA) scheme that includes three phases: (1) FEC redundancy adaption, (2) transmission rate assignment, and (3) path interleaving. We present a mathematical formulation of the transmission scheduling to minimize end-to-end video distortion and provide comprehensive analysis for the channel distortion. We conduct the performance evaluation in the Exata and simulation results show that ROBBIA outperforms existing bandwidth aggregation approaches in improving video quality in terms of PSNR (Peak Signal-to-Noise Ratio).

A low-latency scheduling approach for high-definition video streaming in a heterogeneous wireless network with multihomed clients

We consider the problem of high-definition (HD) video transmission in a heterogeneous wireless network from a video server to a multihomed client. On the one hand, a single wireless network is limited in the transmission performance (e.g., available bandwidth and link delay); On the other hand, the HD video streaming is characterized by the high transmission rate and large-size video frames. Thus, the end-to-end video frame delay becomes a severely challenging problem which is critical for the real-time video applications. In this paper, we propose a novel scheduling approach named sub-frame-level (SFL), which deliberately splits the large-size video frames into sub-frames and dispatches each of them onto a different wireless network to the multihomed client. This approach is able to improve the frame-level delay for enhancing video quality. We formulate the optimization problem of video streaming allocation for minimizing the end-to-end delay based on the network calculus and derive its solution with the water filling algorithm. We evaluate the performance of the proposed SFL through the Exata emulations using real-time H.264 video streaming. Emulation results show that SFL outperforms the existing frame-level scheduling approaches in improving the frame-level delay as well as in enhancing video quality in terms of peak signal-to-noise ratio.

CCNxTomcat: An extended web server for Content-Centric Networking

Abstract TCP/IP networks are the backbone of the Internet today, and browser/server is the mainstream web architecture on it. Recently, Content-Centric Networking (CCN) has emerged as a clean-slate future network architecture, with totally different protocols than a host-based TCP/IP network. However, current web servers are mainly designed for HTTP over a TCP/IP network and can not directly support CCN-based web applications. Therefore, how to effectively support the dominant browser-based web applications is a key to the success of CCN. Instead of providing a transitional HTTP/CCN transforming gateway or proxy, we design and develop the first practical CCN-enabled web server (called CCNxTomcat) based on open source Apache Tomcat and the CCNx library to natively support CCN-based web applications. The CCN functions are integrated into the web server for content distribution by seamlessly coordinating with the underlying CCN network. To support legacy applications and a smooth evolution from an IP network to CCN, CCNxTomcat also supports the HTTP protocol besides the CCN. Experimental results show that CCNxTomcat outperforms the existing HTTP/CCN proxy implementations by 58% in a single request, and by a factor of three in 1000 concurrent requests, in terms of throughput. Furthermore, we design and implement a novel cache (called ccncache) for the Servlet response, performing name lookups for Content Packets with a high efficiency. The results indicate that ccncache is 2.5 times faster than the existing CCNx Content Store, with only 30% additional memory consumption. In addition, a real CCN-based web application is deployed on a CCN experimental network, which validates the applicability of CCNxTomcat.

Service Provisioning in Content-Centric Networking: Challenges, Opportunities, and Promising Directions

Contemporary IP-based Internet architecture increasingly is unable to meet the demands of current network usage patterns. Content-centric networking (CCN), as a clean-slate future network architecture, is different from existing IP networks and has some salient features, such as in-network caching, name-based routing, friendly mobility, and built-in security. This architecture has a profound impact on how Internet applications are provisioned. Here, from the perspective of upper-layer applications, the authors discuss challenges and opportunities regarding service provisioning in CCN. They also describe the Service Innovation Environment for Future Internet, their approach that addresses challenges while exploiting opportunities for the future of CCN.

Telecommunications Service Domain Ontology: Semantic Interoperation Foundation of Intelligent Integrated Services

Network is the bearer of services and services are the soul of network. The convergent network extends the original communications service type and gradually forms new convergent services which integrate the traditional telecommunication services and a large number of value-added services or contents on Internet (Kolberg et al., 2010). The integrated service is essentially to handle the data and services across heterogeneous networks and service platforms. Facing the heterogeneity and diversity of service resources, integrated services need to run in a multi-terminal, multi-access network and multi-platform heterogeneous environment. These tremendous changes of service environment present a significant interoperability challenge for traditional service provisioning theory. Nowadays, the provision of context-awareness, adaptive personalized services is the development goal of future ubiquitous network (Park et al., 2009). It can enable seamless information exchange between humans, with humans and with entities (e.g., mobile devices), as well as entities and entities at any time, any place and in any way. To meet the development needs of adaptive personalized convergent services, dynamic service discovery and composition technologies are explored widely in the telecommunication service field (Bashah et al., 2010; Niazi & Mahmoud, 2009).

Three Categories Customer Churn Prediction Based on the Adjusted Real Adaboost

It is necessary for enterprises to establish a customer churn management system. In this article, we take the heterogeneity into consideration and divide the churn people into two classes according to the data characteristics. Moreover, we try to modify the bias of multi-class unbalanced data classification. Then we propose a new method based on Real Adaboost for the problem. The proposed method takes the within-group error into consideration and creates another view of reweighing the cases. Empirical study on our sample data shows that the new method performs better than the other method.

Applying semantics to Parlay-based services for telecommunication and Internet networks

Ubiquitous convergent telecommunication and Internet networks need to deliver services and content to users in a way that is tailored to the users’ context information and preferences. Thus, there is a new challenge in the areas of accurate service description, linking dynamic service discovery and invocation, which involves the services of telecom networks and the Internet. Semantic annotation can provide advantages for precise service description, discovery and composition. However, open service interface specifications of telecommunication networks are currently still in the syntactic level. By applying semantics to Parlay-based services for telecommunication networks and the Internet, we present an OWL-S-based semantic description approach for telecommunication network services, enabled by the telecommunication service domain ontologies to address the semantic interoperability that exists. Using this approach, we have implemented the semantic telecommunication services gateway and proposed the unified service integration architecture of telecommunication and Internet networks within the semantic-web service environment. Proof-of-concept prototype and case studies demonstrate the practical feasibility of the suggested solution.

A Priority-Based Dynamic Web Requests Scheduling for Web Servers over Content-Centric Networking

Content-Centric Networking (CCN) facilitates the content distribution for static Web applications due to its in-network caching. However, when it comes to dynamic Web request, the original fair scheduling of Interest packets on the CCN Web server (i.e. without differentiating a new service request and the service requests being processed) increases the mean response time, resulting in a decrease of service performance. To address this problem, we present a Priority-based Dynamic Web Requests Scheduling (called PBDRS) for CCN Web server. We first increase the priority of the subsequent Interest packet requests belonging to dynamic Web requests being processed, based on the first-come-first-served strategy. Then, services with small-size response data are also scheduled to a higher priority, leveraging the shortest remaining processing time (SRPT) scheduling policy. To validate the proposed approach, we implemented the proposed PBDRS mechanism in our existing CCN Web server and conducted the performance evaluation experiments based on a real dataset crawled from three popular dynamic Web sites of China in a trace-driven way. Experimental results indicate that PBDRS outperforms existing fair scheduling approach of Interest packets in terms of the mean response time.