Zhonghong Ou

Performance evaluation of a Kademlia-based communication-oriented P2P system under churn

The phenomenon of churn has a significant effect on the performance of Peer-to-Peer (P2P) networks, especially in mobile environments that are characterized by intermittent connections and unguaranteed network bandwidths. A number of proposals have been put forward to deal with this problem; however, we have so far not seen any thorough analysis to guide the optimal design choices and parameter configurations for structured P2P networks. In this article, we present a performance evaluation of a structured communication-oriented P2P system in the presence of churn. The evaluation is conducted using both simulation models and a real-life prototype implementation. In both evaluation environments, we utilize Kademlia with some modifications as the underlying distributed hash table (DHT) algorithm, and Peer-to-Peer Protocol (P2PP) as the signaling protocol. The results from the simulation models created using Nethawk EAST (a telecommunication simulator software) suggest that, in most situations, a lookup parallelism degree of 3 and resource replication degree of 3 are enough for guaranteeing a high resource lookup success ratio. We also notice that, with the parallel lookup mechanism, a good success ratio is achieved even without the KeepAlive traffic that is used for detecting the aliveness of nodes. A prototype system that works in mobile environment is implemented to evaluate the feasibility of mobile nodes acting as full-fledged peers. The measurements made using the prototype show that, from the viewpoints of CPU load and network traffic load, it is feasible for the mobile nodes to take part in the overlay. Through energy consumption measurements, we draw the conclusion that in general the UMTS access mode consumes slightly more power than the WLAN access mode. Protocol packets with sizes of 200bytes or less are observed to be the most energy efficient in the UMTS access mode.

Digital Television for Mobile Devices

A survey of mobile television technologies analyzes technical characteristics for each mobile TV solution, discusses specifications and standards, and presents possible future developments.

Distributed resource directory architecture in Machine-to-Machine communications

Machine-to-Machine (M2M) communications emerge to achieve ubiquitous communications among all the networked devices. One challenging problem in M2M applications is to discover the resources provided by the devices efficiently. This challenge arises from two perspectives: (1) a large number of heterogeneous devices co-exist and most of them are constrained devices (e.g., limited processing capability), (2) different communication protocols are utilized to get access to different types of resources provided by the devices (e.g., humidity information provided by a sensor). This paper proposes distributed resource directory architecture for M2M applications, referred to as DRD4M. The DRD4M supports heterogeneous devices using HTTP and CoAP protocols for resource registration and lookup. This enables the interoperability among heterogeneous devices and resource access to constrained devices from disparate network including the Internet. The DRD4M introduces two components: a resource registration component for registering resources and a resource lookup component with caching functionality for handling resource lookup with filtering. A peer-to-peer (P2P) overlay is introduced in DRD4M to connect resource peers to avoid single point of failure. A real-world prototype is implemented and is verified with a demo application. Preliminary performance evaluation in terms of response time of resource lookup is provided.

Effects of different churn models on the performance of structured peer-to-peer networks

We present the effects of different churn models on the performance of structured peer-to-peer (P2P) networks in this paper. Specifically, Exponential distribution (ED), Pareto distribution (PD), and Weibull distribution (WD) are evaluated to provide a comparative analysis. Kademlia-based Peer-to-Peer Protocol (P2PP) is utilized as the underlying signaling protocol. Through simulations, we conclude that the simulated different churn models do not have a significant effect on the performance of the simulated structured P2P network. Quantitatively, ED and PD result in better performance compared to WD from the viewpoints of lookup success rate, mean network traffic load, and mean number of messages.

Feasibility evaluation of a communication-oriented P2P system in mobile environments

We present the feasibility evaluation of a structured communication-oriented Peer-to-Peer (P2P) system being used in mobile environments in this paper. The different levels of churn are modeled by the exponential distribution with varied value of mean online time. Our system utilizes Kademlia with some modifications as the underlying Distributed Hash Table (DHT) algorithm, and Peer-to-Peer Protocol (P2PP), one of the former candidates of Peer-to-Peer Session Initiation Protocol (P2PSIP) working group, as the signaling protocol. A prototype is implemented to evaluate the feasibility of mobile nodes acting as fully fledged peers. The prototype measurements show it is feasible for the mobile nodes to take part in the overlay from the viewpoints of CPU load and network traffic load. Through battery measurements, we draw the conclusion that the UMTS access mode consumes slightly more power than the WLAN access mode in general. Protocol packets with sizes of 200 bytes or less are observed to be the most energy efficient in the UMTS access mode.

GTPP: General Truncated Pyramid Peer-to-Peer Architecture over Structured DHT Networks

Hierarchical Distributed Hash Table (DHT) architectures have been among the most interesting research topics since the birth of flat DHT architecture. However, most of the previous work has merely focused on the two-tier hierarchy. In this paper, we study and analyze General Truncated Pyramid Peer-to-Peer (GTPP) architecture, the generalized version of Partially Vertical Hierarchical Architecture (PV-HA). The idea is to study whether added tiers of hierarchy can provide added value in performance and functionality. Through mathematical analysis, we demonstrate performance results in comparison to flat architecture, which helps understanding the typical characteristics of hierarchical architectures. Firstly, GTPP has slightly higher expected lookup hop count, although it can be decreased with optimizing the sub-overlay setup. However, GTPP significantly decreases the expected lookup routing latency. Secondly, GTPP has clearer and more reasonable traffic distribution among all the peers from different tiers of sub-overlays, and can work with slightly lower maintenance traffic. Thirdly, our studies indicate that two to three tiers are most suitable in most cases for GTPP, considering all the parameters.

Improving Community Management Performance with Two-Level Hierarchical DHT Overlays

In this paper, we evaluate a P2P community management system that works on top of a DHT-based P2PSIP protocol implementation. The key idea in our system is to establish a separate DHT overlay network for each community, resulting in multiple small overlays that are subsets of the main overlay. The main DHT overlay is largely used for community and membership information discovery. The feasibility of our two-level hierarchical system is evaluated with a prototype implementation. We compare our system against the flat structure where all the community related activities are performed in a single DHT overlay. The nodes average network traffic load is evaluated with varying parameters. In addition, the energy consumption of mobile nodes is measured. Our test results show that our P2P community management system performs especially well when there is a great deal of community-related activity of the nodes.

Peer-to-peer community management using structured overlay networks

In this paper, we present a system for the distributed management of user communities. The system utilizes multiple DHT overlay networks where nodes communicate in a peer-to-peer manner. Our system works on top of a P2PSIP protocol implementation that carries out the DHT signaling. The key idea behind our system is to use one overlay network per community; this results in multiple small overlays that are subsets of the main overlay. We evaluate how the usage of small community-overlays affects the nodes load, as opposed to doing all activities in the main overlay. We also evaluate how the maintenance of community-overlays affects the nodes load. Finally, we observe the tradeoff between these two quantities; while multiple small overlays decrease DHT-related network traffic in community activities, the management of multiple overlays also introduces some additional load to the nodes.

Distributed Resource Discovery in the Machine-to-Machine Applications

One challenging problem in Machine-to-Machine (M2M) applications is to efficiently discover the resources provided by a huge number of heterogeneous devices. This paper proposes distributed resource discovery architecture (DRD) for M2M applications. The DRD supports heterogeneous devices in resource description registration and discovery of resource value. It achieves interoperability among heterogeneous devices in disparate networks and enables resource access from the Internet. In the DRD, a resource registration component is designed for storing resource descriptions, a resource discovery component is designed to retrieve resource values on behalf of clients after getting address information by looking up resource descriptions. The DRD utilizes a peer-to-peer overlay to distribute workload and avoid single point of failure. A real-world prototype is implemented and verified with a simple demo. Preliminary evaluation on response time of resource discovery is provided.

Super-peer-based coordinated service provision

Leveraging P2P technologies for Web service provision attracts considerable research interests. One of the challenges is how to enable the service providers to adapt themselves in response to dynamic service demand. More specifically, one interesting research issue is coordinating the service groups in order to enable inter-group collaboration and resource sharing. In this paper, we propose a super-peer-based coordinated service provision framework (SCSP), consisting of an S-labor-market model (super-peer-based labor-market model), a recruiting protocol based on a weighting mechanism, and an optimal dispatch algorithm. In the SCSP, the S-labor-market model is designed to build the coordination among service groups by employing the proposed recruiting protocol. The optimal dispatch algorithm is designed to select the optimal service peers within a service group to process service requests. Finally, we perform simulations to evaluate the SCSP with four application scenarios. The experimental results show that our SCSP is efficient in coordinating the service groups, and possess good scalability and robustness.