André Höing’s research while affiliated with Technische Universität Berlin and other places

The need for information system integration is typical for many companies including small and medium-sized enterprises (SMEs). But especially for SMEs, the costs to run a full-fledged integration platform in-house are beyond the available IT budget. This article describes the concept of Orchestration as a Service (OaaS), a specialization of the Platform as a Service (PaaS) paradigm in the Cloud (computing) world. The goal of this paradigm is to provide a workflow-based integration platform as a (Cloud) service focusing on so-called service orchestrations. We present the BIS-Grid Engine as a core middleware for an OaaS infrastructure including a discussion about how our solution addresses security requirements that are a key issue in Cloud technologies.

Within the BIS-Grid project, a BMBF-funded project in the context of the German D-Grid initiative, we developed the BIS-Grid workflow engine that is based upon service extensions to UNICORE 6 to use an arbitrary WS-BPEL workflow engine and standard WS-BPEL to orchestrate stateful, WSRF-based Grid services. Although aimed at proving the feasibility of applying Grid technologies for business information systems integration, we illustrate that this engine is also well-suited for scientific workflow execution, making standard WS-BPEL-based tooling accessible for scientific workflows. In this paper, we describe using the BIS-Grid engine for the execution of scientific workflows. This includes a differentiation of scientific and business workflows in general and an analysis of the suitability of the BIS-Grid infrastructure to execute scientific workflows. We propose reusable WS-BPEL patterns for typical scientific workflow activities whereas job submission is focused. Finally, we prospect our future work.

The BIS-Grid project, a BMBF-funded project in the context of the German D-Grid initiative, focusses on realising Enterprise Application Integration using Grid technologies to proof that Grid technologies are feasible for information systems integration. Small and medium enterprises shall be enabled to integrate heterogeneous business information systems and to use external Grid resources and services with affordable effort. In this paper, we describe service extensions to UNICORE6 to use an arbitrary WS-BPEL workflow engine and standard WS-BPEL to orchestrate stateful, WSRF-based Web Services, also called Grid Services. Thereby, we focus on how to combine the arbitrary workflow engine with UNICORE6, and on how to access workflows and workflow instances. The workflows itself are also provided as Grid Services, realised by a Workflow Management Service that deploys Workflow Services within UNICORE6, each wrapping a WS-BPEL workflow that is deployed in the arbitrary workflow engine.

The BIS-Grid project, as part of the German D-Grid initiative, investigates service orchestration using Grid service technologies to show how such technologies can be employed for information systems integration, especially when crossing enterprise boundaries. Small and medium enterprises will be enabled to integrate heterogeneous business information systems and to use external resources and services with affordable effort. In this paper, we discuss our Orchestration as a Service (OaaS) paradigm and present the BIS-Grid OaaS infrastructure. This infrastructure is based upon service extensions to the Grid middleware UNICORE 6 to use an arbitrary WS-BPEL workflow engine and standard WS-BPEL to orchestrate both plain Web services and stateful, WSRF-based Grid services. We report on the evaluation scenarios at our industrial application partners and on the applied service modeling methodology.

Many load balancing strategies have been proposed for distributed hash tables, like Pastry. These strategies assume that hash functions spread even skewed key distributions almost evenly over the ID space. They neglect the problem that many applications produce data with common keys (multi-sets) that entail hash collisions and therewith load imbalance concerning query and storage load. A second drawback of using hash functions in DHTs is the lack of range queries needed in many scenarios. This paper presents a solution for how to use the routing structure of the P2P network Pastry to create a new alphanumerical overlay with very little additional costs. This overlay is capable of storing data in a totally ordered manner instead of using hashed keys. Therewith, it enables range queries and sophisticated load balancing. We discuss the impact on Pastry that arises when nodes are relocated during load balancing. This possibly causes a skewed distribution of nodes in the circular id space. We demonstrate the feasibility of our idea including advantages and problems through an evaluation of simulations.

Many structured Peer-to-Peer-Systems (P2P) have been developed over the past years. However, most of them rely on hash-functions and thus put major restrictions on applications being implemented on top of them. In this paper we present a very detailed description of Papnet, a hash-free P2P overlay-network that supports range-queries and realizes an infinite alphanumeric address space that can be used to store arbitrarily skewed data. We show how Papnet is able to distribute load amongst its nodes using the Ganesan On-Line Load Balancing providing a constant imbalance ratio while still being able to perform proximity routing, reaching each participating node with a latency being only roughly twice the direct latency. Further, we introduce a join-algorithm that provides Papnet with high fault-tolerance properties. We evaluated Papnet in a real distributed environment by setting up a network consisting of 50,000 nodes.

In this chapter, we describe the BabelPeers project. The idea of this project is to develop a system for Grid resource description and matching, which is semantically rich while maintaining scalability and reliability. This is achieved by the distribution of resource data over a p2p network, combined with sophisticated mechanisms for query processing, reasoning, and load balancing. We start by describing the benefits of semantically expressive languages for Grid resource description, and then continue to explain our methods, and how they help to maintain scalability. This includes distributed data storage and query processing strategies. Reliability is given by replication in the p2p network. Special emphasis is given on novel methods for load balancing and efficient query processing. Finally, we present benchmarks and simulations to show the good performance of the BabelPeers system.