Conventional messaging technologies have been designed for large transactional systems, making the prediction and calibration of their delay impractical. In this paper, we present a minimal messaging system, implement...
详细信息
Conventional messaging technologies have been designed for large transactional systems, making the prediction and calibration of their delay impractical. In this paper, we present a minimal messaging system, implemented in Java (TM), that is designed to enable the analysis, modeling, and calibration of the expected performance of these technologies. We describe the algorithms and protocols that underlie this messaging system, show how an analysis can be performed, and give the actual measured performance figures. We show that the system achieves a throughput of more than 100,000 messages per second with less than 120-millisecond maximum latency, in the test environment. At 10,000 messages per second, a maximum latency of 5 milliseconds is measured. The algorithms make use of lock-free data structures, which allow the throughput to scale on multi-core systems.
The problem of modal sampled-data control for continuous-time linear time-invariant plant with delay is considered. The characteristic matrix of the system is constructed. An algorithm is given for generating the set ...
详细信息
The problem of modal sampled-data control for continuous-time linear time-invariant plant with delay is considered. The characteristic matrix of the system is constructed. An algorithm is given for generating the set of causal discrete-time controllers that place eigenvalues of the characteristic matrix at specified points of the complex plane.
Recently, a variable step-size affine projection (VSS-AP) algorithm has been introduced. The algorithm provides faster convergence rate and lower misadjustment but has heavy computational complexity. Proposed is a new...
详细信息
Recently, a variable step-size affine projection (VSS-AP) algorithm has been introduced. The algorithm provides faster convergence rate and lower misadjustment but has heavy computational complexity. Proposed is a new variable step-size pseudo affine projection (VSS-PAP) algorithm, which not only has a much lower complexity than the VSS-AP algorithm but also provides performance comparable with the conventional algorithm. Simulation results confirm fast convergence rate and small misalignment of the proposed algorithm with less computational complexity.
Wireless mesh networking is an emerging technology for future broadband wireless access. Future wireless networking can benefit from a robust and reliable wire-less can less mesh backbone rendered by me routers, provi...
详细信息
Wireless mesh networking is an emerging technology for future broadband wireless access. Future wireless networking can benefit from a robust and reliable wire-less can less mesh backbone rendered by me routers, providing an all-wireless ambience. Due to the requisite multichannel communications for high-speed data transmissions, power allocation for opportunistically exploiting fading wireless channels, and packet scheduling for QoS provisioning, joint power-frequency-time resource allocation is indispensable. In this article we propose a low-complexity intracluster resource allocation algorithm, taking power allocation, subcarrier allocation, and packet scheduling into consideration. Numerical results demonstrate that our scheme is near optimal, and that our optimality-driven resource allocation approach outperforms a greedy algorithm, working out a better performance compromise among throughput, packet dropping rate, and packet delay.
Admissible multicast traffic can be efficiently handled in high-capacity Internet routers using packet circulation. Presented is a practical algorithm for the building and maintenance of the circulation tree, as well ...
详细信息
Admissible multicast traffic can be efficiently handled in high-capacity Internet routers using packet circulation. Presented is a practical algorithm for the building and maintenance of the circulation tree, as well as a report on its implementation. Its scalability and speed were assessed, and shown to be satisfactory.
In pattern matching with the pair correlation distance problem, the goal is to find all occurrences of a pattern P of length m, in a text T of length n, where the distance between them is less than a threshold k. For ...
详细信息
In pattern matching with the pair correlation distance problem, the goal is to find all occurrences of a pattern P of length m, in a text T of length n, where the distance between them is less than a threshold k. For each text location i, the distance is defined as the number of different kinds of mismatched pairs (alpha, beta), between P and T[i...i + m]. We present an algorithm with running time of O (min {vertical bar Sigma(P)vertical bar(2) n log m, n (m log m)2/3}) for this problem. Another interesting problem is the one-side pair correlation distance where it is desired to find all occurrences of P where the number of mismatched characters in P is less than k. For this problem, we present an algorithm with running time of O (min{vertical bar Sigma(p)vertical bar n log m, n root m log m}). (C) 2008 Elsevier B.V. All rights reserved.
A novel dual-min-sum decoding algorithm for low-density parity-check codes is proposed. The proposed algorithm simplifies the check-node updates and thus reduces the computational complexity of the belief propagation ...
详细信息
A novel dual-min-sum decoding algorithm for low-density parity-check codes is proposed. The proposed algorithm simplifies the check-node updates and thus reduces the computational complexity of the belief propagation (BP) algorithm significantly. Simulation results show that the proposed algorithm can achieve an error performance very close to that of the BP algorithm.
The aim is to achieve the highest possible speedup when distributing a program across a cluster of computational nodes. The speedup may be achieved by concurrent execution of the distributed modules. In order to maxim...
详细信息
The aim is to achieve the highest possible speedup when distributing a program across a cluster of computational nodes. The speedup may be achieved by concurrent execution of the distributed modules. In order to maximise the concurrency, a two-stage approach is proposed. In the first stage, a novel statement-reordering algorithm reorders the statements within a given program, to maximise the distance between each call instruction and the instructions, which are data-dependent on any value affected by the call. In the second stage, a clustering algorithm is applied to look for a modular structure of the program which results in the highest concurrency in its execution. The clustering algorithm applies a novel performance evaluation function which is derived from the program code, automatically.
Today, companies in the chemical process industries (CPI) are faced with increased operating expenses, reductions in the number of qualified workers, strong competition and the need to do more with less. To meet these...
详细信息
Today, companies in the chemical process industries (CPI) are faced with increased operating expenses, reductions in the number of qualified workers, strong competition and the need to do more with less. To meet these challenges, many companies are making use of advancements in instrumentation and control technologies to optimize plant performance. The process instrumentation line -- from tap to transmitter -- is a network of devices and components, each intended to perform a specific function. Technological advancements in the CPI have made each transmitter a more valuable component than ever. The basis of a well-functioning unit, and its positive influence on a facility's bottom line, is the proper selection of fluid-handling components. The process interface valve, the impulse lines and fittings, and the manifold must be chosen carefully, as they produce the input that the transmitter relies on to make its measurements. From tap to transmitter, the process instrumentation line directly affects a facility's profitability.
An algorithm for constructing checksums based on the Reed - Solomon code is proposed. It makes it possible to increase the efficiency of creating checkpoint files on local disk memory for parallel applications, as wel...
详细信息
An algorithm for constructing checksums based on the Reed - Solomon code is proposed. It makes it possible to increase the efficiency of creating checkpoint files on local disk memory for parallel applications, as well as provide a series of other capabilities. The paper also corrects a number of errors committed by other researchers of this domain.
暂无评论