StreamCloud: An Elastic Parallel-Distributed Stream Processing Engine

In recent years, applications in domains such as telecommunications, network security or large scale sensor networks showed the limits of the traditional store-then-process paradigm. In this context, Stream Processing Engines emerged as a candidate solution for all these applications demanding for high processing capacity with low processing latency guarantees. With Stream Processing Engines, data streams are not persisted but rather processed on the fly, producing results continuously. Current Stream Processing Engines, either centralized or distributed, do not scale with the input load due to single-node bottlenecks. Moreover, they are based on static configurations that lead to either under or over-provisioning. This Ph.D. thesis discusses StreamCloud, an elastic paralleldistributed stream processing engine that enables for processing of large data stream volumes. Stream- Cloud minimizes the distribution and parallelization overhead introducing novel techniques that split queries into parallel subqueries and allocate them to independent sets of nodes. Moreover, Stream- Cloud elastic and dynamic load balancing protocols enable for effective adjustment of resources depending on the incoming load. Together with the parallelization and elasticity techniques, Stream- Cloud defines a novel fault tolerance protocol that introduces minimal overhead while providing fast recovery. StreamCloud has been fully implemented and evaluated using several real word applications such as fraud detection applications or network analysis applications. The evaluation, conducted using a cluster with more than 300 cores, demonstrates the large scalability, the elasticity and fault tolerance effectiveness of StreamCloud. Resumen En los útimos años, aplicaciones en dominios tales como telecomunicaciones, seguridad de redes y redes de sensores de gran escala se han encontrado con múltiples limitaciones en el paradigma tradicional de bases de datos. En este contexto, los sistemas de procesamiento de flujos de datos han emergido como solución a estas aplicaciones que demandan una alta capacidad de procesamiento con una baja latencia. En los sistemas de procesamiento de flujos de datos, los datos no se persisten y luego se procesan, en su lugar los datos son procesados al vuelo en memoria produciendo resultados de forma continua. Los actuales sistemas de procesamiento de flujos de datos, tanto los centralizados, como los distribuidos, no escalan respecto a la carga de entrada del sistema debido a un cuello de botella producido por la concentración de flujos de datos completos en nodos individuales. Por otra parte, éstos están basados en configuraciones estáticas lo que conducen a un sobre o bajo aprovisionamiento. Esta tesis doctoral presenta StreamCloud, un sistema elástico paralelo-distribuido para el procesamiento de flujos de datos que es capaz de procesar grandes volúmenes de datos. StreamCloud minimiza el coste de distribución y paralelización por medio de una técnica novedosa la cual particiona las queries en subqueries paralelas repartiéndolas en subconjuntos de nodos independientes. Ademas, Stream- Cloud posee protocolos de elasticidad y equilibrado de carga que permiten una optimización de los recursos dependiendo de la carga del sistema. Unidos a los protocolos de paralelización y elasticidad, StreamCloud define un protocolo de tolerancia a fallos que introduce un coste mínimo mientras que proporciona una rápida recuperación. StreamCloud ha sido implementado y evaluado mediante varias aplicaciones del mundo real tales como aplicaciones de detección de fraude o aplicaciones de análisis del tráfico de red. La evaluación ha sido realizada en un cluster con más de 300 núcleos, demostrando la alta escalabilidad y la efectividad tanto de la elasticidad, como de la tolerancia a fallos de StreamCloud.

Relating goal scheduling, precedence, and memory management in and-parallel execution of logic programs

The interactions among three important issues involved in the implementation of logic programs in parallel (goal scheduling, precedence, and memory management) are discussed. A simplified, parallel memory management model and an efficient, load-balancing goal scheduling strategy are presented. It is shown how, for systems which support "don't know" non-determinism, special care has to be taken during goal scheduling if the space recovery characteristics of sequential systems are to be preserved. A solution based on selecting only "newer" goals for execution is described, and an algorithm is proposed for efficiently maintaining and determining precedence relationships and variable ages across parallel goals. It is argued that the proposed schemes and algorithms make it possible to extend the storage performance of sequential systems to parallel execution without the considerable overhead previously associated with it. The results are applicable to a wide class of parallel and coroutining systems, and they represent an efficient alternative to "all heap" or "spaghetti stack" allocation models.

OSIA: Out-of-order scheduling for in-order arriving in concurrent multi-path transfer.

One major problem of concurrent multi-path transfer (CMT) scheme in multi-homed mobile networks is that the utilization of different paths with diverse delays may cause packet reordering among packets of the same ?ow. In the case of TCP-like, the reordering exacerbates the problem by bringing more timeouts and unnecessary retransmissions, which eventually degrades the throughput of connections considerably. To address this issue, we ?rst propose an Out-of-order Scheduling for In-order Arriving (OSIA), which exploits the sending time discrepancy to preserve the in-order packet arrival. Then, we formulate the optimal traf?c scheduling as a constrained optimization problem and derive its closedform solution by our proposed progressive water-?lling solution. We also present an implementation to enforce the optimal scheduling scheme using cascaded leaky buckets with multiple faucets, which provides simple guidelines on maximizing the utilization of aggregate bandwidth while decreasing the probability of triggering 3 dupACKs. Compared with previous work, the proposed scheme has lower computation complexity and can also provide the possibility for dynamic network adaptability and ?ner-grain load balancing. Simulation results show that our scheme signi?cantly alleviates reordering and enhances transmission performance.

StreamCloud: An elastic and scalable data streaming system

Many applications in several domains such as telecommunications, network security, large scale sensor networks, require online processing of continuous data lows. They produce very high loads that requires aggregating the processing capacity of many nodes. Current Stream Processing Engines do not scale with the input load due to single-node bottlenecks. Additionally, they are based on static con?gurations that lead to either under or over-provisioning. In this paper, we present StreamCloud, a scalable and elastic stream processing engine for processing large data stream volumes. StreamCloud uses a novel parallelization technique that splits queries into subqueries that are allocated to independent sets of nodes in a way that minimizes the distribution overhead. Its elastic protocols exhibit low intrusiveness, enabling effective adjustment of resources to the incoming load. Elasticity is combined with dynamic load balancing to minimize the computational resources used. The paper presents the system design, implementation and a thorough evaluation of the scalability and elasticity of the fully implemented system.

Evaluación de la tecnología CAES como sistema de almacenamiento de energía eólica. Caso de estudio en España

Se presenta a continuación un modelo de una planta del almacenamiento de energía mediante aire comprimido siguiendo un proceso adiabático. En esta planta la energía eólica sobrante se usa para comprimir aire mediante un tren de compresión de 25 MW, el aire comprimido será después almacenado en una caverna de sal a 770 metros de profundidad. La compresión se llevará a cabo por la noche, durante 6 horas, debido a los bajos precios de electricidad. Cuando los precios de la electricidad suben durante el día, el aire comprimido es extraído de la caverna de sal y es utilizado para producir energía en un tren de expansión de 70 MW durante 3 horas. La localización elegida para la planta es el norte de Burgos (Castilla y León, España), debido a la coincidencia de la existencia de muchos parques eólicos y una formación con las propiedades necesarias para el almacenamiento. El aspecto más importante de este proyecto es la utilización de un almacenamiento térmico que permitirá aprovechar el calor de la compresión para calentar el aire a la entrada de la expansión, eliminando combustibles fósiles del sistema. Por consiguiente, este proyecto es una atractiva solución en un posible futuro con emisiones de carbono restringidas, cuando la integración de energía renovable en la red eléctrica supone un reto importante. ABSTRACT: A model of an adiabatic compressed air energy storage plant is presented. In this plant surplus wind energy is used to compress air by means of a 25 MW compression train, the compressed air will be later stored in a salt cavern at 770 meters depth. Compression is carried out at night time, during 6 hours, because power prices are lower. When power prices go up during the day, the compressed air is withdrawn from the salt cavern and is used to produce energy in an expansion train of 70 MW during 3 hours. The chosen location for the plant is in the north of Burgos (Castilla y León, Spain), due to both the existence of several wind farms and a suitable storage facility with good properties at the same place. The relevance of this project is that it is provided with a thermal storage, which allows using the generated heat in the compression for re-heating the air before the expansion, eliminating fossil fuels from the system. Hence, this system is an attractive load balancing solution in a possibly carbon-constrained future, where the integration of renewable energy sources into the electric grid is a major challenge.

Aplicación de la metodología GloBeM al servicio de cloud Hydra

El presente Proyecto de Fin de Máster consiste en crear una herramienta software capaz de monitorizar y gestionar la actividad de Hydra, una herramienta de gestión de entornos distribuidos, para que su estrategia de balanceo de carga se adecúe al modelo creado por GloBeM, una metodología de análisis de entornos distribuidos. GloBeM, que es una metodología externa, puede analizar y crear un modelo de máquina de estados finitos a partir de un sistema distribuido concreto. Hydra, una herramienta también externa, es un sistema de gestión de entornos cloud recientemente desarrollado y de código abierto, con un sistema de balanceo de carga efectivo pero algo limitado. El software construido recoge el modelo creado por GloBeM y lo analiza. A partir de ahí, monitoriza en tiempo real y a una frecuencia determinada la actividad de Hydra y el sistema cloud que ésta gestiona, y reconfigura sus parámetros para que su desempeño se ciña a lo estipulado por el modelo de GloBeM, extendiendo así el sistema de balanceo de carga original de Hydra.---ABSTRACT---This Master's Thesis Project involves creating a software able to monitor and manage the activity of Hydra, a tool for managing distributed environments, in order to adjust its load balancing strategy to the model created by GloBeM, an analysis methodology for distributed environments. GloBeM, which is an external methodology, can analyse and create a finite-state machine model from a particular cloud system. Hydra, also an external tool, is an open source management system for cloud environments recently developed, with a relatively limited system of load balancing. The created software gets the model created by GloBeM as an input and analyses it. From there, it monitors in real time and at a certain frequency Hydra’s activity and the cloud system that it manages, and reconfigures its parameters to adjust its performance to the stipulations by the GloBeM’s model, extending Hydra's original load balancing system.

Submodular Optimization and Data Processing

Thesis (Ph.D.)--University of Washington, 2016-06

Ensuring efficiency and robustness in MANET

This paper introduces a joint load balancing and hotspot mitigation protocol for mobile ad-hoc network (MANET) termed by us as 'load_energy balance + hotspot mitigation protocol (LEB+HM)'. We argue that although ad-hoc wireless networks have limited network resources - bandwidth and power, prone to frequent link/node failures and have high security risk; existing ad hoc routing protocols do not put emphasis on maintaining robust link/node, efficient use of network resources and on maintaining the security of the network. Typical route selection metrics used by existing ad hoc routing protocols are shortest hop, shortest delay, and loop avoidance. These routing philosophy have the tendency to cause traffic concentration on certain regions or nodes, leading to heavy contention, congestion and resource exhaustion which in turn may result in increased end-to-end delay, packet loss and faster battery power depletion, degrading the overall performance of the network. Also in most existing on-demand ad hoc routing protocols intermediate nodes are allowed to send route reply RREP to source in response to a route request RREQ. In such situation a malicious node can send a false optimal route to the source so that data packets sent will be directed to or through it, and tamper with them as wish. It is therefore desirable to adopt routing schemes which can dynamically disperse traffic load, able to detect and remove any possible bottlenecks and provide some form of security to the network. In this paper we propose a combine adaptive load_energy balancing and hotspot mitigation scheme that aims at evenly distributing network traffic load and energy, mitigate against any possible occurrence of hotspot and provide some form of security to the network. This combine approach is expected to yield high reliability, availability and robustness, that best suits any dynamic and scalable ad hoc network environment. Dynamic source routing (DSR) was use as our underlying protocol for the implementation of our algorithm. Simulation comparison of our protocol to that of original DSR shows that our protocol has reduced node/link failure, even distribution of battery energy, and better network service efficiency.

Improving scheduling techniques in heterogeneous systems with dynamic, on-line optimisations

Computational performance increasingly depends on parallelism, and many systems rely on heterogeneous resources such as GPUs and FPGAs to accelerate computationally intensive applications. However, implementations for such heterogeneous systems are often hand-crafted and optimised to one computation scenario, and it can be challenging to maintain high performance when application parameters change. In this paper, we demonstrate that machine learning can help to dynamically choose parameters for task scheduling and load-balancing based on changing characteristics of the incoming workload. We use a financial option pricing application as a case study. We propose a simulation of processing financial tasks on a heterogeneous system with GPUs and FPGAs, and show how dynamic, on-line optimisations could improve such a system. We compare on-line and batch processing algorithms, and we also consider cases with no dynamic optimisations.

Evolutionary market agents for resource allocation in decentralised systems

We introduce self-interested evolutionary market agents, which act on behalf of service providers in a large decentralised system, to adaptively price their resources over time. Our agents competitively co-evolve in the live market, driving it towards the Bertrand equilibrium, the non-cooperative Nash equilibrium, at which all sellers charge their reserve price and share the market equally. We demonstrate that this outcome results in even load-balancing between the service providers. Our contribution in this paper is twofold; the use of on-line competitive co-evolution of self-interested service providers to drive a decentralised market towards equilibrium, and a demonstration that load-balancing behaviour emerges under the assumptions we describe. Unlike previous studies on this topic, all our agents are entirely self-interested; no cooperation is assumed. This makes our problem a non-trivial and more realistic one.

Dynamic Distribution Simulation Model Objects Based on Knowledge

This paper presents the process of load balancing in simulation system Triad.Net, the architecture of load balancing subsystem. The main features of static and dynamic load balancing are discussed and new approach, controlled dynamic load balancing, needed for regular mapping of simulation model on the network of computers is proposed. The paper considers linguistic constructions of Triad language for different load balancing algorithms description.

Semantic distributed database management with applications to the Internet dissemination of environmental data

The research presented in this dissertation is comprised of several parts which jointly attain the goal of Semantic Distributed Database Management with Applications to Internet Dissemination of Environmental Data. ^ Part of the research into more effective and efficient data management has been pursued through enhancements to the Semantic Binary Object-Oriented database (Sem-ODB) such as more effective load balancing techniques for the database engine, and the use of Sem-ODB as a tool for integrating structured and unstructured heterogeneous data sources. Another part of the research in data management has pursued methods for optimizing queries in distributed databases through the intelligent use of network bandwidth; this has applications in networks that provide varying levels of Quality of Service or throughput. ^ The application of the Semantic Binary database model as a tool for relational database modeling has also been pursued. This has resulted in database applications that are used by researchers at the Everglades National Park to store environmental data and to remotely-sensed imagery. ^ The areas of research described above have contributed to the creation TerraFly, which provides for the dissemination of geospatial data via the Internet. TerraFly research presented herein ranges from the development of TerraFly's back-end database and interfaces, through the features that are presented to the public (such as the ability to provide autopilot scripts and on-demand data about a point), to applications of TerraFly in the areas of hazard mitigation, recreation, and aviation. ^

Resource management and optimization in wireless mesh networks

A wireless mesh network is a mesh network implemented over a wireless network system such as wireless LANs. Wireless Mesh Networks(WMNs) are promising for numerous applications such as broadband home networking, enterprise networking, transportation systems, health and medical systems, security surveillance systems, etc. Therefore, it has received considerable attention from both industrial and academic researchers. This dissertation explores schemes for resource management and optimization in WMNs by means of network routing and network coding.^ In this dissertation, we propose three optimization schemes. (1) First, a triple-tier optimization scheme is proposed for load balancing objective. The first tier mechanism achieves long-term routing optimization, and the second tier mechanism, using the optimization results obtained from the first tier mechanism, performs the short-term adaptation to deal with the impact of dynamic channel conditions. A greedy sub-channel allocation algorithm is developed as the third tier optimization scheme to further reduce the congestion level in the network. We conduct thorough theoretical analysis to show the correctness of our design and give the properties of our scheme. (2) Then, a Relay-Aided Network Coding scheme called RANC is proposed to improve the performance gain of network coding by exploiting the physical layer multi-rate capability in WMNs. We conduct rigorous analysis to find the design principles and study the tradeoff in the performance gain of RANC. Based on the analytical results, we provide a practical solution by decomposing the original design problem into two sub-problems, flow partition problem and scheduling problem. (3) Lastly, a joint optimization scheme of the routing in the network layer and network coding-aware scheduling in the MAC layer is introduced. We formulate the network optimization problem and exploit the structure of the problem via dual decomposition. We find that the original problem is composed of two problems, routing problem in the network layer and scheduling problem in the MAC layer. These two sub-problems are coupled through the link capacities. We solve the routing problem by two different adaptive routing algorithms. We then provide a distributed coding-aware scheduling algorithm. According to corresponding experiment results, the proposed schemes can significantly improve network performance.^

Performance analysis of disk mirroring techniques

Unequaled improvements in processor and I/O speeds make many applications such as databases and operating systems to be increasingly I/O bound. Many schemes such as disk caching and disk mirroring have been proposed to address the problem. In this thesis we focus only on disk mirroring. In disk mirroring, a logical disk image is maintained on two physical disks allowing a single disk failure to be transparent to application programs. Although disk mirroring improves data availability and reliability, it has two major drawbacks. First, writes are expensive because both disks must be updated. Second, load balancing during failure mode operation is poor because all requests are serviced by the surviving disk. Distorted mirrors was proposed to address the write problem and interleaved declustering to address the load balancing problem. In this thesis we perform a comparative study of these two schemes under various operating modes. In addition we also study traditional mirroring to provide a common basis for comparison.

Simulation and analysis of network traffic for efficient and reliable information transfer

With the growing commercial importance of the Internet and the development of new real-time, connection-oriented services like IP-telephony and electronic commerce resilience is becoming a key issue in the design of TP-based networks. Two emerging technologies, which can accomplish the task of efficient information transfer, are Multiprotocol Label Switching (MPLS) and Differentiated Services. A main benefit of MPLS is the ability to introduce traffic-engineering concepts due to its connection-oriented characteristic. With MPLS it is possible to assign different paths for packets through the network. Differentiated services divides traffic into different classes and treat them differently, especially when there is a shortage of network resources. In this thesis, a framework was proposed to integrate the above two technologies and its performance in providing load balancing and improving QoS was evaluated. Simulation and analysis of this framework demonstrated that the combination of MPLS and Differentiated services is a powerful tool for QoS provisioning in IP networks.