The performance of parallel computers grows rapidly. However, application software is lagging behind due to two bottlenecks: "performance wall" and "programmability wall". These bottlenecks have pr...
详细信息
ISBN:
(纸本)9781509024032
The performance of parallel computers grows rapidly. However, application software is lagging behind due to two bottlenecks: "performance wall" and "programmability wall". These bottlenecks have prevented a lot of application software from achieving good performance and fast development. programming framework is considered an effective approach to overcome the above bottlenecks. In this paper, we give a prototype of JAUMIN, which is a programming framework for large scale application software based on unstructured mesh. Some important technologies of JAUMIN will be presented, including distributed data structures, data communication patterns and application programming interfaces. Finally, some applications based on JAUMIN will be demonstrated to show that JAUMIN can accelerate the development of application software greatly and support effective simulation on petascale supercomputer.
The purpose of this paper is threefold;(1) Offer a synopsis of algorithmic review and to make a comparison between two branch-and-bound approaches for solving the sum-of-ratios problem;(2) Modify an promising algorith...
详细信息
ISBN:
(纸本)9783642135767
The purpose of this paper is threefold;(1) Offer a synopsis of algorithmic review and to make a comparison between two branch-and-bound approaches for solving the sum-of-ratios problem;(2) Modify an promising algorithm for nonlinear sum-of-ratios problem;(3) Study the efficiency of the algorithms via numerical experiments.
The evolution of energy infrastructures towards a more distributed, adaptive, predictive and market-based paradigm implies an effort on combining communication protocols and energy transmission and distribution system...
详细信息
ISBN:
(纸本)9781627484251
The evolution of energy infrastructures towards a more distributed, adaptive, predictive and market-based paradigm implies an effort on combining communication protocols and energy transmission and distribution systems in a common architecture. This architecture should allow decentralized control in order to be able to manage efficiently distributed generation, storage and exchange of energy between sources and sinks. Dynamic energy management models are a part of this "systems thinking" vision that aims to create a new field of applications that is at the intersection of computing science and energy technology. The broader implications associated with them are related with the possibility of creating communities that integrate energy supply and demand within a given region, in order to limit their impact. In order to push intelligence to the energy networks' edges, up to individual sources and sinks, scalable and flexible distributed systems will have to be build. In this sense, data mining techniques and multi-commodity network flow models can be combined for pattern detection, forecasting and optimization, which are essential features of dynamic energy management. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the organizing committee of 2ndinternationalconference on Advances in Energy Engineering (ICAEE).
Wireless sensor networks consist of small, inexpensive devices which interact with the environment, communicate with each other, and perform distributed computations in order to monitor spatio-temporal phenomena. Thes...
详细信息
ISBN:
(纸本)9781424406135
Wireless sensor networks consist of small, inexpensive devices which interact with the environment, communicate with each other, and perform distributed computations in order to monitor spatio-temporal phenomena. These devices are ideally suited for a variety of applications including object tracking, environmental monitoring, and homeland security. At present, sensor network technologies do not provide off-the-shelf solutions to users who lack low-level network programming experience. Because of limited resources, ad hoc deployments, and volatile wireless communication links, the development of distributed applications require the combination of both application and system-level logic. programming frameworks and middleware for traditional distributed computing are not suitable for many of these problems due to the resource constraints and interactions with the physical world. To address these challenges we have developed OASiS, a programming framework that provides abstractions for object-centric, ambient-aware, service-oriented sensor network applications. OASiS uses a well-defined model of computation based on globally asynchronous locally synchronous dataflow, and is complemented by a user-friendly modeling environment. applications are realized as graphs of modular services and executed in response to the detection of physical phenomena. We have also implemented a suite of middleware services that support OASiS to provide a layer of abstraction shielding the low-level system complexities. A tracking application is used to illustrate the features of OASiS. Our results demonstrate the feasibility and the benefits of a service-oriented programming framework for composing and deploying applications in resource-constrained sensor networks.
This paper studies the problem of computing an input vector for a given pair of Artificial Neural Network (ANN) and output vector, which is a kind of inverse problem. This problem has potential applications in design ...
详细信息
ISBN:
(纸本)9781450361033
This paper studies the problem of computing an input vector for a given pair of Artificial Neural Network (ANN) and output vector, which is a kind of inverse problem. This problem has potential applications in design of new objects, especially in design of new chemical compounds. This paper focuses on ANNs in which activation functions are represented as continuous piece-wise linear functions, which can exactly represent ReLU functions and well approximate sigmoid functions. It is shown that this inverse problem can be formulated as a Mixed Integer Linear programming Problem (MILP) with O(vertical bar V vertical bar + n(b) variables and constraints, where V is a set of neurons in a given ANN and nb denotes the total number of break points over all activation functions f(nu), nu is an element of V .
This paper presents a triangular lattice photonic crystal fiber (PCF) with very high nonlinear coefficient. Finite element method is used to scrutinize different optical characteristics of proposed highly nonlinear PC...
详细信息
ISBN:
(纸本)9781538633748
This paper presents a triangular lattice photonic crystal fiber (PCF) with very high nonlinear coefficient. Finite element method is used to scrutinize different optical characteristics of proposed highly nonlinear PCF (HNL-PCF). The HNL-PCF exhibits a high nonlinearity up to 10 x 10(4) W(-1)km(-1) over the wavelength band of 1500 nm to 1700 nm. Moreover, proposed fiber shows a very low confinement loss of 10(-3) dB/km and chromatic dispersion of -9000 ps/(nm-km) at 1550 nm wavelength. Furthermore, dispersion slope, effective area are also analyzed thoroughly. The proposed fiber will be a suitable candidate for sensing applications, dispersion compensation, nonlinear signal processing and supercontinuum generation.
Many heat conduction problems encountered in engineering applications are time intensive they are dependent on unsteady state variables. In many situations, temperature varies with respect to time function, for which ...
详细信息
Many heat conduction problems encountered in engineering applications are time intensive they are dependent on unsteady state variables. In many situations, temperature varies with respect to time function, for which a solution needs to be found. In this research paper, a 2D transient Qausi-harmonic equation is solved using Finite element method. In engineering applications, many engineering problems are governed by this Qausi-harmonic equation. The main aim of this analysis is to determine the variation of the temperature as a function of time by finding element conductivity matrix using standard Gauss quadrature numerical integration method as it is both accurate and efficient. The obtained results of MATLAB coding are verified with ANSYS with examples. Toolbox is created in MATLAB using Object Oriented programming language for this analysis. The template of this toolbox is also added in this paper.
This work suggests a design approach building on past results in the area of adaptive Neural Network (NN) based reconfigurable flight control which has been successfully utilized for a variety of aerospace application...
详细信息
ISBN:
(纸本)9781479928552
This work suggests a design approach building on past results in the area of adaptive Neural Network (NN) based reconfigurable flight control which has been successfully utilized for a variety of aerospace applications, while incorporating recent advances in the areas of output feedback and NN adaptation algorithms. The paradigm is based on feedback linearization and synthesis of a fixed-gain dynamic compensator, whilst incorporating a neural network by using concurrent update information to compensate for model uncertainties, system faults and external disturbances. The concurrent learning networks update law is simplified and restructured for better and easy use during applications. The stability and reconfigurable ability of the improved control system based on the concurrent learning algorithm is validated with simulation performances of the nonlinear Machan UAV.
The aim of the paper is to give the basic information about methods and approach to teaching programming for mobile applications. In the introductory part of the article we try to set out the objectives of teaching an...
详细信息
The aim of the paper is to give the basic information about methods and approach to teaching programming for mobile applications. In the introductory part of the article we try to set out the objectives of teaching and student entry requirements. Main stress is focused on clarifying the specifics that we have to consider during development process for the most used mobile platforms. At the end of article we try to explain current possible use of mobile devices in military area.
In this paper, the class of semi E h-b-preinvex and pseudo E h-b-preinvex functions are defined as an extension of E-B-preinvex and h-preinvex functions. In this extension the functions E:Rn → Rn, h: [0,1] → , and b...
详细信息
暂无评论