José Ángel Bañares

Enforcing QoS in scientific workflow systems enacted over Cloud infrastructures

The ability to support Quality of Service (QoS) constraints is an important requirement in some scientific applications. With the increasing use of Cloud computing infrastructures, where access to resources is shared, dynamic and provisioned on-demand, identifying how QoS constraints can be supported becomes an important challenge. However, access to dedicated resources is often not possible in existing Cloud deployments and limited QoS guarantees are provided by many commercial providers (often restricted to error rate and availability, rather than particular QoS metrics such as latency or access time). We propose a workflow system architecture which enforces QoS for the simultaneous execution of multiple scientific workflows over a shared infrastructure (such as a Cloud environment). Our approach involves multiple pipeline workflow instances, with each instance having its own QoS requirements. These workflows are composed of a number of stages, with each stage being mapped to one or more physical resources. A stage involves a combination of data access, computation and data transfer capability. A token bucket-based data throttling framework is embedded into the workflow system architecture. Each workflow instance stage regulates the amount of data that is injected into the shared resources, allowing for bursts of data to be injected while at the same time providing isolation of workflow streams. We demonstrate our approach by using the Montage workflow, and develop a Reference net model of the workflow.

Approaching web service coordination and composition by means of petri nets. the case of the nets-within-nets paradigm

Web service coordination and composition have become a central topic for the development of Internet-based distributed computing. A wide variety of different standards have been defined to deal with the composition of Web services (usually represented as workflows) and the execution of coordination protocols. On the other hand, some relevant research proposals have already pointed to the use of the same formalism for both aspects, being Petri nets one of the adopted formalisms. In this work we present a case study showing how the adoption of the Nets-within-Nets paradigm helps in the modelling of complex coordination protocols and workflows. We first propose a Petri net model for a Web service peer able to run any workflow and to dynamically interpret the coordination required protocols. The execution of these protocols allows the peer to integrate functionalities offered by external peers. The Linda communication model has been used to support the integration among peers.

Autonomic streaming pipeline for scientific workflows

Interest in data streaming within scientific workflow has increased significantly over the recent years—mainly due to the emergence of data‐driven applications. Such applications can include data streaming from sensors and data coupling between scientific simulations. To support resource management to enact such streaming‐based workflow, autonomic computing techniques for transmission have been combined with in‐transit processing, so that data elements may be processed in advance, enroute, prior to arrival at the destination. We propose the integration of an autonomic data streaming service (ADSS) with in‐transit processing into a workflow specification. This integration may imply that the associated runtime resource allocation is dependent on environmental conditions and can change for different enactments of the same workflow. In our proposal, our workflow specifications are independent of the constraints imposed by the resource allocation. We express our solutions in terms of Reference nets. We also implement an ADSS utilizing a timed Reference net simulation for predicting future states of the ADSS. There are two advantages: the Reference net which implements the ADSS and the timed model are coincident, and second, token distribution obtained from the Petri net implementation can be utilized to better understand the demand for particular types of resources in the system. Copyright

A CORBA infrastructure to provide distributed GPS data in real time to GIS applications

This paper shows a distributed object-oriented architecture to provide global positioning system (GPS) data for geographical information system (GIS) applications. Data captured in real time by GPS units are sent via radio to the computer. Several sources of this real data, in addition to simulated GPS data, are distributed in a computer network. These servers of GPS data can be accessed by distributed client applications. A Common Object Request Broker Architecture (CORBA)-based infrastructure provides the integration and distribution mechanisms. Client applications range from simple graphical user interfaces (GUIs) for GPS remote control to GIS applications used for automatic vehicle monitoring. The basic components which provide the radio communication and GPS data servers are presented in detail.

RLinda: a petri net based implementation of the linda coordination paradigm for web services interactions

The core functionality of Web-service middlewares tries to wrap existing business logics and make them accessible as Web services. Recently, well-known standardization initiatives have proposed some high-level declarative languages for the description of coordination protocols and the implementation of coordination middlewares. In parallel to these initiatives, an increasing interest on the use of classical coordination models on distributed environments has been shown. In this work we present a Linda-like coordination framework using Petri nets, which is executed by the Renew tool, a high-level Petri net interpreter developed in Java, and subsequently exposed as a Web service able to be used by other services for coordination purposes. The implementation is based on an extension of the original Linda model that improves the tuple representation capabilities and extends the matching functions used for the recovery of tuples from the coordination space. The efficiency of the proposed implementation has been empirically evaluated on a cluster computing environment, and its performances compared with the previously reported ones related to JavaSpaces.

Knowledge representation-oriented nets for discrete event system applications

This paper presents knowledge representation-oriented nets (KRON), a knowledge representation schema for discrete event systems (DES). KRON enables the representation and use of a variety of knowledge about a DES static structure and its dynamic states and behavior. It is based on the integration of high-level Petri nets with frame-based representation techniques and follows the object-oriented paradigm. The main objective considered in its definition is to obtain a comprehensive and powerful representation model for data and control of DES. The use of the DES behavioral knowledge is governed by a control mechanism stored in a separate inference engine. KRON provides an efficient execution mechanism to make the models evolve. This is an adaptation of the RETE matching algorithm in order to deal with the features provided by high-level Petri nets and it takes advantage of its integration with a frame/object-oriented representation schema, Moreover, KRON facilitates dealing with decision points in the execution of nondeterministic models. A prototype of a simulation tool with graphical display and animation facilities has been implemented for KRON and it has been used in several case studies in the manufacturing systems domain.

Resource management for bursty streams on multi-tenancy cloud environments

The number of applications that need to process data continuously over long periods of time has increased significantly over recent years. The emerging Internet of Things and Smart Cities scenarios also confirm the requirement for real time, large scale data processing. When data from multiple sources are processed over a shared distributed computing infrastructure, it is necessary to provide some Quality of Service (QoS) guarantees for each data stream, specified in a Service Level Agreement (SLA). SLAs identify the price that a user must pay to achieve the required QoS, and the penalty that the provider will pay the user in case of QoS violation. Assuming maximization of revenue as a Cloud providers objective, then it must decide which streams to accept for storage and analysis; and how many resources to allocate for each stream. When the real-time requirements demand a rapid reaction, dynamic resource provisioning policies and mechanisms may not be useful, since the delays and overheads incurred might be too high. Alternatively, idle resources that were initially allocated for other streams could be re-allocated, avoiding subsequent penalties. In this paper, we propose a system architecture for supporting QoS for concurrent data streams to be composed of self-regulating nodes. Each node features an envelope process for regulating and controlling data access and a resource manager to enable resource allocation, and selective SLA violations, while maximizing revenue. Our resource manager, based on a shared token bucket, enables: (i) the re-distribution of unused resources amongst data streams; and (ii) a dynamic re-allocation of resources to streams likely to generate greater profit for the provider. We extend previous work by providing a Petri-net based model of system components, and we evaluate our approach on an OpenNebula-based Cloud infrastructure. We provide a system for simultaneous bursty data streams on shared Clouds.We enforce QoS based on a profit-based resource management model.We provide real experiments within an OpenNebula based data centre.

Towards Autonomic Cloud Services Engineering via Intention Workflow Model

In recent years, the rise and rapid adoption of cloud computing has acted as a catalyst for research in related fields: virtualization, distributed and service-oriented computing to name but a few. Whilst cloud computing technology is rapidly maturing, many of the associated long-standing socio-technical challenges including the dependability of cloud-based service composition, services manageability and interoperability remain unsolved. These can be argued to slow down the migration of serious business critical applications to the cloud model. This paper reports on progress towards the development of a method to generate cloud-based service compositions from requirements metadata. The paper presents a formal approach that uses Situation Calculus to translate service requirements into an Intention Workflow Model (IWM). This IWM is then used to generate autonomic cloud service composition. The Petshop benchmark is used to illustrate and evaluate the proposed method.

A framework for the development and execution of horizontal protocols in open BPM systems

A new generation of open Business Process Management (BPM) systems based on the service-oriented architecture and Web service technologies has recently emerged. The general tendency for these systems should be governed by the integration of independent Web-service specifications. Web services requirements guide the description, execution and choreography of business process and the implementation of frameworks for supporting the coordination, synchronization and creation of business transactions. However, a wide variety of open research issues related to the lack of maturity of the involved specifications makes the development of standard-based BPM systems difficult. In this paper we propose an abstract architecture inspired by Web service specifications to overcome these difficulties. Also, a particular implementation based on the Nets-within-Nets paradigm and the Renew tool is presented. The result is an executable infrastructure able to run business processes (their workflows and coordination protocols) as well as the horizontal protocols that guarantee a coherent outcome of their whole execution, such as the WS-Atomic Transaction protocol.

A Taxonomy for the Analysis of Scientific Workflow Faults

Scientific workflows generally involve the distribution of tasks to distributed resources, which may exist in different administrative domains. The use of distributed resources in this way may lead to faults, and detecting them, identifying them and subsequently correcting them remains an important research challenge. We introduce a fault taxonomy for scientific workflows that may help in conducting a systematic analysis of faults, so that the potential faults that may arise at execution time can be corrected (recovered from). The presented taxonomy is motivated by previous work [4], but has a particular focus on workflow environments (compared to previous work which focused on Grid-based resource management) and demonstrated through its use in Weka4WS.