Distributed algorithm

About: Distributed algorithm is a research topic. Over the lifetime, 20416 publications have been published within this topic receiving 548109 citations.

A Mutual Exclusion Algorithm for Ad Hoc Mobile Networks

Abstract: A fault-tolerant distributed mutual exclusion algorithm that adjusts to node mobility is presented, along with proof of correctness and simulation results. The algorithm requires nodes to communicate with only their current neighbors, making it well-suited to the ad hoc environment. Experimental results indicate that adaptation to mobility can improve performance over that of similar non-adaptive algorithms when nodes are mobile.

An overlay MAC layer for 802.11 networks

Abstract: The widespread availability of 802.11-based hardware has made it the premier choice of both researchers and practitioners for developing new wireless networks and applications. However, the ever increasing set of demands posed by these applications is stretching the 802.11 MAC protocol beyond its intended capabilities. For example, 802.11 provides no control over allocation of resources, and the default allocation policy is ill-suited for heterogeneous environments and multi-hop networks. Fairness problems are further exacerbated in multi-hop networks due to link asymmetry and hidden terminals. In this paper, we take a first step towards addressing these problems without replacing the MAC layer by presenting the design and the implementation of an Overlay MAC Layer (OML), that works on top of the 802.11 MAC layer. OML uses loosely-synchronized clocks to divide the time in to equal size slots, and employs a distributed algorithm to allocate these slots among competing nodes. We have implemented OML in both a simulator and on a wireless testbed using the Click modular router. Our evaluation shows that OML can not only provide better flexibility but also improve the fairness, throughput and predictability of 802.11 networks.

A framework for event composition in distributed systems

Abstract: For large-scale distributed applications such as internet-wide or ubiquitous systems, event-based communication is an effective messaging mechanism between components. In order to handle the large volume of events in such systems, composite event detection enables application components to express interest in the occurrence of complex patterns of events. In this paper, we introduce a general composite event detection framework that can be added on top of existing middleware architectures -- as demonstrated in our implementation over JMS. We argue that the framework is flexible, expressive, and easy to implement. Based on finite state automata extended with a rich time model and support for parameterisation, it provides a decomposable core language for composite event specification, so that composite event detection can be distributed throughout the system. We discuss the issues associated with automatic distribution of composite event expressions. Finally, tests of our composite event system over JMS show reduced bandwidth consumption and a low notification delay for composite events.

NOMAD: non-locking, stochastic multi-machine algorithm for asynchronous and decentralized matrix completion

Abstract: We develop an efficient parallel distributed algorithm for matrix completion, named NOMAD (Non-locking, stOchastic Multi-machine algorithm for Asynchronous and Decentralized matrix completion). NOMAD is a decentralized algorithm with non-blocking communication between processors. One of the key features of NOMAD is that the ownership of a variable is asynchronously transferred between processors in a decentralized fashion. As a consequence it is a lock-free parallel algorithm. In spite of being asynchronous, the variable updates of NOMAD are serializable, that is, there is an equivalent update ordering in a serial implementation. NOMAD outperforms synchronous algorithms which require explicit bulk synchronization after every iteration: our extensive empirical evaluation shows that not only does our algorithm perform well in distributed setting on commodity hardware, but also outperforms state-of-the-art algorithms on a HPC cluster both in multi-core and distributed memory settings.

Computation and communication in R*: a distributed database manager

Abstract: This article presents and discusses the computation and communication model used by R*, a prototype distributed database management system. An R* computation consists of a tree of processes connected by virtual circuit communication paths. The process management and communication protocols used by R* enable the system to provide reliable, distributed transactions while maintaining adequate levels of performance. Of particular interest is the use of processes in R* to retain user context from one transaction to another, in order to improve the system performance and recovery characteristics.