Zongming Fei

A novel server selection technique for improving the response time of a replicated service

Server replication is an approach often used to improve the ability of a service to handle a large number of clients. One of the important factors in the efficient utilization of replicated servers is the ability to direct client requests to the best server, according to some optimality criteria. In this paper we target an environment in which servers are distributed across the Internet, and clients identify servers using our application-layer any-casting service. Our goal is to allocate servers to clients in a way that minimizes a clients response time. To that end, we develop an approach for estimating the performance that a client would experience when accessing particular servers. Such information is maintained in a resolver that clients can query to obtain the identity of the server with the best response time. Our performance collection technique combines server push with client probes to estimate the expected response time. A set of experiments is used to demonstrate the properties of our performance determination approach and to show its advantages when used within the application-layer anycasting architecture.

Scalable delivery of Web pages using cyclic best-effort multicast

The World Wide Web (WWW) has gained tremendously in popularity. In this work we explore the use of UDP, best-effort multicast as a delivery option. Reliability is achieved through repetitive, cyclic transmission of a requested page. This solution is expected to be most efficient when used for highly requested pages. We view this cyclic multicast technique as a delivery option that can be integrated with the traditional reliable unicast and reliable multicast options. We first describe the architecture of an integrated Web server employing all three delivery options. We then describe the cyclic multicast technique and consider the various procedures needed for its successful operation. We characterize the gains in performance achieved by our proposal through an extensive performance analysis and simulation of our technique by itself, and when integrated with the other delivery options. We also describe our experience with an implementation of a prototype cyclic multicast server and its performance over the multicast backbone (MBone).

A proactive approach to reconstructing overlay multicast trees

Overlay multicast constructs a multicast delivery tree among end hosts. Unlike traditional IP multicast, the non-leaf nodes in the tree are normal end hosts, which are potentially more susceptible to failures than routers and may leave the multicast group voluntarily. In these cases, all downstream nodes are affected. Thus an important problem in overlay multicast is how to recover from node departures in order to minimize the disruption of service to those affected nodes. In this paper, we propose a proactive approach to restore overlay multicast trees. Rather than letting downstream nodes try to find a new parent after a node departure, each non-leaf node pre-calculates a parent-to-be for each of its children. When this non-leaf node is gone, all its children can find their respective new parents immediately. The salient feature of the approach is that each non-leaf node can compute a rescue plan for its children independently, and in most cases, rescue plans from multiple non-leaf nodes can work together for their children when they fail or leave at the same time. We develop a protocol for nodes to communicate with new parents so that the delivery tree can be quickly restored. Extensive simulations demonstrate that our proactive approach can recover from node departures 5 times faster than reactive methods in some cases, and 2 times faster on average.

Distributed caching with centralized control

The benefits of using caches for reducing traffic in backbone trunk links and for improving web access times are well-known. However, there are some known problems with traditional web caching, namely, maintaining freshness of web objects, balancing load among a number of caches and providing protection against cache failure. This paper investigates in detail the advantages and disadvantages of a distributed architecture of caches which are coordinated through a central controller. In particular, the performance of a set of independent caches is compared against the performance of a set of coordinated distributed caches using extensive simulation. The conclusion is that a distributed architecture of coordinated caches consistently provides a better hit ratio, improves response time, provides better freshness, achieves load balancing, and increases the overall traffic handling capacity of a network while paying a small price in terms of additional control traffic. In particular, we have observed up to 40% improvement in hit ratio, 70% improvement in response time, 60% improvement in freshness and 25% improvement in traffic handling capacity of a network with caches.

A model for replica placement in content distribution networks for multimedia applications

The distribution of multimedia files brings new challenges to the problem of replica placement in content distribution networks (CDN) and invalidates several assumptions underlying the existing solutions. In this paper we formulate a new model for the problem of replica placement to accommodate these new characteristics. We perform a theoretical analysis of the cost of distributing multimedia files over CDNs and find out that, contrary to the intuition, deploying as many replicas as possible is not always a good strategy. We then propose several replica placement algorithms that can determine the optimal number of replicas we should select from a given set of potential sites. By simulation we demonstrate that the performance of clients may degrade if we choose too many sites for replica placement.

A proactive tree recovery mechanism for resilient overlay multicast

Overlay multicast constructs a multicast delivery tree among end hosts. Unlike traditional IP multicast, the non-leaf nodes in the tree are normal end hosts, which are potentially more susceptible to failures than routers and may leave the multicast group voluntarily. In these cases, all downstream nodes are affected. Thus, an important problem for making overlay multicast more dependable is how to recover from node departures in order to minimize the disruption of service to those affected nodes. In this paper, we propose a proactive tree recovery mechanism to make the overlay multicast resilient to these failures and unexpected events. Rather than letting downstream nodes try to find a new parent after a node departure, each non-leaf node precalculates a parent-to-be for each of its children. When this non-leaf node is gone, all its children can find their respective new parents immediately. The salient feature of the approach is that rescue plans for multiple non-leaf nodes can work together for their respective children when they fail or leave at the same time. Extensive simulations demonstrate that our proactive approach can recover from node departures much faster than reactive methods, while the quality of trees restored and the cost of recovery are reasonable

Multicast server selection: problems, complexity, and solutions

We formulate and investigate fundamental problems that arise when multicast servers, that deliver content to multiple clients simultaneously, are replicated to enhance scalability and performance. Our study consists of two parts. First, we consider the problem under the assumption that the multicast clients are static for the duration of the multicast content distribution session. In this context, we examine two models for server behavior: fixed-rate servers, which transmit at a constant rate, and rate-adaptive servers, which adapt their transmission rate based on network conditions and/or feedback from clients. In both cases, we show that general versions of the client assignment problems are NP-hard. We then develop and evaluate efficient algorithms for interesting special cases, as well as heuristics for general cases. Second, we consider the case in which the set of clients changes dynamically during the multicast content distribution session. We again consider both fixed-rate and rate-adaptive servers. We formulate the problem as a Markov decision process, capturing the costs associated with trees, as well as the transition costs to dynamically change the trees. We use the properties of optimal solutions for small examples to develop a set of dynamic server selection heuristics.

A Novel Energy-Aware Fault Tolerance Mechanism for Wireless Sensor Networks

Sensors in a Wireless Sensor Network (WSN) are prone to failure, due to energy depletion, hardware failures, etc. Fault tolerance is one of the critical issues in WSNs. The existing fault tolerant mechanisms either consume significant extra energy to detect and recover from the failures or need to use additional hardware and software resource. In this paper, we propose a novel energy-aware fault tolerance mechanism for WSN, called Informer Homed Routing (IHR). In our IHR, the non cluster head nodes limit and select the target of their data transmission. Therefore, it consumes less energy. Our experiments show that our proposed protocol can dramatically reduce energy consumption, compared to two existing protocols, LEACH and DHR.

Bipartite Graph Based Dynamic Spectrum Allocation for Wireless Mesh Networks

The capacity of a wireless mesh network can be improved by equipping mesh nodes with multi-radios tuned to non-overlapping channels. By letting these nodes utilize the available spectrum opportunistically, we can increase the utilization of the available bandwidth in the spectrum space. The key problem is how to allocate the spectrum to these multi-radio nodes, especially when they are heterogeneous with diverse transmission types and bandwidth. Most of current work has been based on the conflict-graph model and given solutions that focused on either increasing bandwidth utilization or minimizing starvation. In this paper, we propose a new bipartite-graph based model and design an channel allocation algorithm that considers both bandwidth utilization and starvation problems. Our solution is based on using augmenting path to find a matching in the bipartite-graph and can minimize starvation and then maximize the bandwidth utilization. The simulations demonstrate that our algorithm can reduce the starvation ratio and improve the bandwidth utilization, compared with previous conflict-graph based algorithms.

The Metaverse: a networked collection of inexpensive, self-configuring, immersive environments

Immersive projection-based display environments have been growing steadily in popularity. However, these systems have, for the most part, been confined to laboratories or other special-purpose uses and have had relatively little impact on human-computer interaction or user-to-user communication/collaboration models. Before large-scale deployment and adoption of these technologies can occur, some key technical issues must be resolved. We address these issues in the design of the Metaverse. In particular, the Metaverse system supports automatic self-calibration of an arbitrary number of projectors, thereby simplifying systems setup and maintenance. The Metaverse also supports novel communication models that enhance the scalability of the system and facilitate collaboration between Metaverse portals. Finally, we describe a prototype implementation of the Metaverse.