Selected authored books

目前，科学计算在力学、电磁学、生物学、金融、航空航天等领域已经成为必不可少的工具，研究者借助电子计算机和高性能算法，可以对雪后屋顶的形变、音乐厅的声音效果、机翼附近的空气流动等实际问题进行仿真，无须实物模型参与。

本书主要针对偏微分方程离散化后得到的大规模问题，借助实例讲解和展示最新的科学计算技术，重点讨论大规模线性方程组的求解方法，如直接法、迭代法、区域分解法等。本书主要针对包含分布式存储和大量处理器的计算环境，因此也会介绍计算机基础知识以及基于消息传递接口的消息传递编程技术，但不会过多涉及计算机组成原理。此外，书中还将展示科学计算中的经典并行算法，相关示例来源于研究者关于有限元法等方法的实践经验。从教学角度看，本书循序渐进地介绍了数学与计算机的相关概念，包括机器的架构特性、并行管理的相关问题、矩阵计算的基础知识等，但仅面向科学计算工具的使用者，不会从计算机视角进行深入解读。

建筑的能源性能受很多因素的影响，《建筑能耗分析中的数据挖掘与机器学习》针对建筑的复杂特性，重点研究用新的数据挖掘和机器学习方法来对建筑能耗进行准确的预测、分析或者故障检测/诊断。《建筑能耗分析中的数据挖掘与机器学习》涉及建筑能耗分析的建模及用于模型降阶与并行计算的技术和相关算法，同时提出了新的算法用于能耗分析预测及建筑能耗故障检测/诊断，既有一定的理论深度，又有较好的应用宽度。我国建筑能耗占社会总能耗很大的比例，目前对建筑能耗分析的理论、技术和方法所做的研究工作与国际先进水平有相当大的差距，在实际建筑中实施建筑能耗管理与分析的水平也较低。因此，当前特别迫切需要学习并借鉴国外在建筑能耗管理、优化控制与评估上的先进理论、技术与实施经验。 《建筑能耗分析中的数据挖掘与机器学习》很好地填补了我国在建筑能耗相关领域的研究与应用的空白，对从事能源管理和能源效率的知识发现和数据挖掘研究领域的工程师有很大的吸引力，本书提出的算法对与建筑能耗分析相关的工程领域的研究生有很好的借鉴作用，对设计建筑的工程师也有很好的指导作用。后，对于建筑能耗的预测分析对我国的建筑能耗管理也有很好的促进作用。

Ez a könyv bevezetés a nagy-teljesítményű számítások (High Performance Computing, HPC) területére és fő célja olyan numerikus algoritmusok bemutatása, amelyek segítségével lehetővé válik hagyományos számítógéppel nem megoldható problémák megoldása és kezelése is.

A párhuzamos számítási módszerek aktuális kérdéseiből a következőket tárgyaljuk:

• adat párhuzamosság,
• vektorizáció,
• üzenet-küldés,
• mátrixok párhuzamos összeállítása,
• mátrixok párhuzamos szorzása,
• nagyméretű lineáris egyenletrendszerek direkt és iteratív megoldása párhuzamosan.

Le but de cet ouvrage est d'expliquer et d'illustrer par des exemples concrets les techniques recentes de calcul scientifique pour la simulation numerique de problemes de grandes tailles issus de systemes modelises par des equations aux derivees partielles. Les differentes methodes de formation et de resolution des grands systemes lineaires sont presentees. La conception des methodes recentes et les algorithmes associes sont etudies en detail.

Ce livre est destine aux etudiants en Masters de mathematiques appliquees ou de mecanique numerique ainsi qu'aux eleves ingenieurs.

The energy consumption of a building has, in recent years, become a determining factor during its design and construction. With carbon footprints being a growing issue, it is important that buildings be optimized for energy conservation and CO2 reduction. This book therefore presents AI models and optimization techniques related to this application. The authors start with a review of recent models for the prediction of building energy consumption: engineering methods, statistical methods, artificial intelligence methods, ANNs and SVMs in particular. The book then focuses on SVMs, by first applying them to building energy consumption, then presenting the principles and various extensions, and SVR. The authors then move on to RDP, which they use to determine building energy faults through simulation experiments before presenting SVR model reduction methods and the benefits of parallel computing. The book then closes off by presenting some of the current research and advancements in the field.

Scientific computing has become an indispensable tool in numerous fields, such as physics, biology, chemistry, finance and engineering. For example, it enables us, thanks to efficient algorithms adapted to current computers and supercomputers, to simulate complex phenomena, without the help of models or experimentations. Some examples are the structural behaviors of civil engineering structures, the sound level in a theater, a fluid flowing around an aircraft or a formula one car, and the hydrodynamics of a racing yacht. This book presents the scientific computing techniques applied to parallel computing for the numerical simulation of large-scale problems; these problems mainly result from systems modeled by partial differential equations. Computing concepts are tackled via examples. Implementation and programming techniques resulting from the finite element, finite volume and finite difference methods are presented for direct solvers, iterative solvers and domain decomposition methods, along with an introduction to MPI and OpenMP.

並列計算の数理とアルゴリズム

フレデリック・マグレス , フランソワ = グザヴィエ・ルー , 桑原 拓也

科学技術計算は、物理や機械工学、生物学、金融工学、産業などの多くの分野で今日欠かすことのできない道具となっている。例えば、高性能なアルゴリズムを現在のコンピュータに適用することにより、模型実験を行わなくても梁のたわみ、劇場での音響、航空機の翼周りの流れを知ることができる。 本書の目的は、 複雑なシステムの大規模な問題を解くための 数値シミュレーションに関する近年の科学技術計算手法を分かり易く説明することである。大規模な線型問題に関係するシステムの様々な組み立て方法や解法を紹介している。 メッセージ通信プログラミング手法やループ並列計算について、 を用いた例題により分かり易く説明している 。理解を深めるために章末には演習問題も設けている。 本書は主に応用数学および数値計算に携わる機械工学を専攻する修士課程の学生、さらにハイパフォーマンス計算に興味を抱くすべての理工学分野の学生を対象としている。

El calculo cientifico se ha convertido en una herramienta imprescindible en numerosos campos como la fisica, la quimica, la biologia, las finanzas o la industria. La simulacion de fenomenos cada vez mas complejos permite reducir el numero de experimentos o incluso prescindir de ellos, asi como explorar nuevas soluciones a los problemas propuestos. Nada de esto seria viable sin el desarrollo de algoritmos eficientes y adaptados a las nuevas arquitecturas computacionales paralelas de las que hoy disponemos.

El objetivo de este libro es explicar las tecnicas del calculo cientifico paralelo para la simulacion numerica de problemas de gran tamano, derivados de la resolucion de ecuaciones en derivadas parciales que rigen los fenomenos a resolver. Todo ello quedara ilustrado a traves de ejemplos concretos para facilitar su comprension.

Le calcul scientifique est devenu un outil indispensable dans de tres nombreux domaines de la physique, la mecanique, la biologie ou la finance. Il permet par exemple, grace a des algorithmes performants, de simuler l'ecoulement de l'air autour d'une aile d'avion, ou le comportement d'une structure en materiaux composites.

Le but de cet ouvrage est d'expliquer des techniques avancees de calcul scientifique, pour la resolution de problemes de grandes tailles issus de la modelisation numerique de phenomenes complexes. Les techniques de programmation par echanges de messages et de parallelisme de boucle sont illustrees par des exemples avec MPI et OpenMP. Des exercices corriges completent chaque chapitre.

Ce livre est destine aux etudiants en Masters de mathematiques appliquees ou de mecanique numerique ainsi qu'aux eleves ingenieurs.

As more and more data is generated at a faster-than-ever rate, processing large volumes of data is becoming a challenge for data analysis software. Addressing performance issues, Cloud Computing: Data-Intensive Computing and Scheduling explores the evolution of classical techniques and describes completely new methods and innovative algorithms. The book delineates many concepts, models, methods, algorithms, and software used in cloud computing.

After a general introduction to the field, the text covers resource management, including scheduling algorithms for real-time tasks and practical algorithms for user bidding and auctioneer pricing. It next explains approaches to data analytical query processing, including pre-computing, data indexing, and data partitioning. Applications of MapReduce, a new parallel programming model, are then presented. The authors also discuss how to optimize multiple group-by query processing and introduce a MapReduce real-time scheduling algorithm.

A useful reference for studying and using MapReduce and cloud computing platforms, this book presents various technologies that demonstrate how cloud computing can meet business requirements and serve as the infrastructure of multidimensional data analysis applications.

Poised to follow in the footsteps of the Internet, grid computing is on the verge of becoming more robust and accessible to the public in the near future. Focusing on this novel, yet already powerful, technology, Introduction to Grid Computing explores state-of-the-art grid projects, core grid technologies, and applications of the grid.

After comparing the grid with other distributed systems, the book covers two important aspects of a grid system: scheduling of jobs and resource discovery and monitoring in grid. It then discusses existing and emerging security technologies, such as WS-Security and OGSA security, as well as the functions of grid middleware at a conceptual level. The authors also describe famous grid projects, demonstrate the pricing of European options through the use of the Monte Carlo method on grids, and highlight different parallelization possibilities on the grid.

Taking a tutorial approach, this concise book provides a complete introduction to the components of the grid architecture and applications of grid computing. It expertly shows how grid computing can be used in various areas, from computational mechanics to risk management in financial institutions.

Grid technology offers the potential for providing secure access to remote services, thereby promoting scientific collaborations in an unprecedented scale. Grid Resource Management: Toward Virtual and Services Compliant Grid Computing presents a comprehensive account of the architectural issues of grid technology, such as security, data management, logging, and aggregation of services, as well as related technologies.

After covering grid usages, grid systems, and the evolution of grid computing, the book discusses operational issues associated with web services and service-oriented architecture. It also explores technical and business topics relevant to data management, the development and characteristics of P2P systems, and a grid-enabled virtual file system (GRAVY) that integrates underlying heterogeneous file systems into a unified location-transparent file system of the grid. The book covers scheduling algorithms, strategies, problems, and architectures as well as workflow management systems and semantic technologies. In addition, the authors describe how to deploy scientific applications into a grid environment. They also explain grid engineering and grid service programming.

Examining both data and execution management in grid computing, this book chronicles the current trend of grid developments toward a more service-oriented approach that exposes grid protocols using web services standards.