Much of the prior work in business process modeling is activity-centric. Recently, an information-centric approach has emerged, where a business process is modeled as the interacting lifecycles of business entities. The benefits of this approach are documented in a number of case studies. In this paper, the authors formalize the information-centric approach and derive the relationships between the two approaches. The authors formally define the notion of a business entity, provide an algorithm to transform an activity-centric model into an information-centric process model, and demonstrate the equivalence between these two models. Further, they show the value of transforming from the activity-centric paradigm to the information-centric paradigm in business process componentization and Service-Oriented Architecture design and also provide an empirical evaluation.

Model-driven architectures (MDA) separate the business or application logic from the underlying platform technology and represent this logic with precise semantic models. These models are supposed to span the entire life cycle of a software system and ease the software production and maintenance tasks. Consequently, tools will be needed that support these tasks. In this paper, we present a method that implements model-driven transformations between particular platform-independent (business view) and platform-specific (IT architectural) models. On the business level, we focus on business view models expressed in ADF or UML2, whereas on the IT architecture side we focus on service-oriented architectures with Web service interfaces and processes specified in business process protocol languages such as BPEL4WS.

With today's fast changing business environment and distributed global organizations, business processes of enterprises need to be able to quickly adapt to the new business requirements. BPI middlewares are thus developed to facilitate the integration of various types of enterprise applications that operate within or across enterprise boundaries. Due to the varying complexity and distributed nature of the business processes and the wide range of enterprise applications' characteristics, capacity planning and performance tuning of BPI middleware has been a challenge for engineers who develop and deploy BPI solutions. This poster presents a layered queueing network-based performance model for a BPI middleware to address this challenge.

Business process integration and automation (BPIA) has emerged as an important aspect of the enterprise computing landscape. Intra-enterprise application integration (EAI) as well as the inter enterprise integration (B2B) are increasingly being performed in the context of business processes. The integration scenarios typically involve distributed systems that are autonomous to some degree. From the BPIA perspective, the autonomy refers to the fact that the systems being integrated have their own process choreography engines and execute internal business processes that are private to them. In the case of B2B integration, the systems being integrated are fully autonomous, while various levels of autonomy exist in systems partaking in EAI. We present a new paradigm for business process integration. Our approach is based on a conversation model that enables autonomous, distributed BPM (Business Process Management) modules to integrate and collaborate. Our conversation model supports the exchange of multiple correlated messages with arbitrary sequencing constraints and covers the formatting of messages that are to be sent as well as the parsing of the messages that have been received. The crux of our conversation model is the notion of a conversation policy, which is a machine-readable specification of a pattern of message exchange in a conversation. Our model supports nesting and composition of conversation policies to provide a dynamic, adaptable, incremental, open-ended, and extensible mechanism for business process integration. We discuss the current implementation of this conversation model and early experience in applying the model to solve customer problems. The implementation utilizes distributed object technology.

Today's business applications and their underlying process models are becoming more and more complicated, making the implementation of these processes an increasingly challenging task. On the one hand, tools and methods exist to describe the business processes. On the other hand, different tools and method exist to describe the IT artifacts implementing them. But a significant gap exists between the two. To overcome this gap, new methodologies are sought. In this paper we discuss a pattern-based modeling and mapping process. Starting from a business process model, which emphasizes the underlying structural process pattern and its associated requirements, we map this model into a corresponding IT model based on nondeterministic automata with state variables. Model checking techniques are used to automatically verify elementary requirements on a process such as the termination and reachability of states. Using an example involving coupled, repetitive activities we discuss the advantages of an iterative process of correcting and refining a model based on insights gained in the interleaved verification steps.

Traditional capacity sizing of enterprise systems relies on benchmarking a system using benchmark clients that generate a workload pattern similar to real-world workload. When new functions are added to the system or when the workload pattern changes, benchmarking has to be performed again. This is a costly and time-consuming approach for capacity planning. Layered queueing models have been used to study the performance of software systems. The approach is able to identify major performance parameters of software systems. Given a workload pattern, the models can be solved analytically to predict the system performance quickly. This paper proposes a layered queueing model for predicting the performance of distributed enterprise applications built on Enterprise JavaBeans (EJB) technology. We show how such models can be applied for capacity sizing of distributed enterprise systems. We demonstrate this by using this methodology to predict the performance of a sample application built on an EJB-based business-to-business e-commerce platform. We compare deployment options and study the effect of different workload patterns on system capacity.

We describe a software environment for high performance distributed computing on a network of multiprocessor workstations. In designing this environment, we have used a problem oriented approach as opposed to the traditional algorithm oriented approach. This paradigm shift enables us to generate efficient programs automatically for a well defined class of problems. Thus, our system frees the users from the esoteric tasks of algorithm design and implementation. An important feature of our system is its ability to handle the large variation in granularity-we call this dual level parallelism-in a hybrid processing environment. This feature is the key to the superior efficiency delivered by the system. We give preliminary results from a case study in which our system is used to generate programs automatically for a scientific application, with a network of multiprocessors as the target platform.

We describe an architecture-adaptable methodology for the parallel implementation of finite element numerical models of physical systems. We use a model of time-dependent ocean currents as our working example. The heart of the computation is the solution of a banded linear system, and we describe an algorithm based on the domain decompositionmethod to solve the banded system. The algorithm is represented in a divide-and-conquer framework facilitates easy implementation of various algorithmic options. The process is straightforward and amenable to automation. We demonstrate the validity of this approach using two radically different target machine, a workstation network and a supercomputer. Our results show very good speedup on both platforms.