BitWorker, a Decentralized Distributed Computing System based on BitTorrent

In this paper we present BitWorker, a platform for community distributed computing based on BitTorrent. Any splittable task can be easily specified by a user in a meta-information task file, such that it can be downloaded and performed by other volunteers. Peers find each other using Distributed Hash Tables, download existing results, and compute missing ones. Unlike existing distributed computing schemes relying on centralized coordination point(s), our scheme is totally distributed, therefore, highly robust. We evaluate the performance of BitWorker using mathematical models and real tests, showing processing and robustness gains. BitWorker is available for download and use by the community.

Service level agreements-driven management of distributed applications in cloud computing environments

Advancements in cloud computing have enabled the proliferation of distributed applications, which require management and control of multiple services. However, without an efficient mechanism for scaling services in response to changing workload conditions, such as number of connected users, application performance might suffer, leading to violations of Service Level Agreements (SLA) and possible inefficient use of hardware resources. Combining dynamic application requirements with the increased use of virtualised computing resources creates a challenging resource Management context for application and cloud-infrastructure owners. In such complex environments, business entities use SLAs as a means for specifying quantitative and qualitative requirements of services. There are several challenges in running distributed enterprise applications in cloud environments, ranging from the instantiation of service VMs in the correct order using an adequate quantity of computing resources, to adapting the number of running services in response to varying external loads, such as number of users. The application owner is interested in finding the optimum amount of computing and network resources to use for ensuring that the performance requirements of all her/his applications are met. She/he is also interested in appropriately scaling the distributed services so that application performance guarantees are maintained even under dynamic workload conditions. Similarly, the infrastructure Providers are interested in optimally provisioning the virtual resources onto the available physical infrastructure so that her/his operational costs are minimized, while maximizing the performance of tenants’ applications. Motivated by the complexities associated with the management and scaling of distributed applications, while satisfying multiple objectives (related to both consumers and providers of cloud resources), this thesis proposes a cloud resource management platform able to dynamically provision and coordinate the various lifecycle actions on both virtual and physical cloud resources using semantically enriched SLAs. The system focuses on dynamic sizing (scaling) of virtual infrastructures composed of virtual machines (VM) bounded application services. We describe several algorithms for adapting the number of VMs allocated to the distributed application in response to changing workload conditions, based on SLA-defined performance guarantees. We also present a framework for dynamic composition of scaling rules for distributed service, which used benchmark-generated application Monitoring traces. We show how these scaling rules can be combined and included into semantic SLAs for controlling allocation of services. We also provide a detailed description of the multi-objective infrastructure resource allocation problem and various approaches to satisfying this problem. We present a resource management system based on a genetic algorithm, which performs allocation of virtual resources, while considering the optimization of multiple criteria. We prove that our approach significantly outperforms reactive VM-scaling algorithms as well as heuristic-based VM-allocation approaches.

Distributed Atomic Polarizabilities of Amino Acids and their Hydrogen-Bonded Aggregates

With the purpose of rational design of optical materials, distributed atomic polarizabilities of amino acid molecules and their hydrogen-bonded aggregates are calculated in order to identify the most efficient functional groups, able to buildup larger electric susceptibilities in crystals. Moreover, we carefully analyze how the atomic polarizabilities depend on the one-electron basis set or the many-electron Hamiltonian, including both wave function and density functional theory methods. This is useful for selecting the level of theory that best combines high accuracy and low computational costs, very important in particular when using the cluster method to estimate susceptibilities of molecular-based materials.

Full correction for spatially distributed speed-of-sound in echo ultrasound based on measuring aberration delays via transmit beam steering

Aberrations of the acoustic wave front, caused by spatial variations of the speed-of-sound, are a main limiting factor to the diagnostic power of medical ultrasound imaging. If not accounted for, aberrations result in low resolution and increased side lobe level, over all reducing contrast in deep tissue imaging. Various techniques have been proposed for quantifying aberrations by analysing the arrival time of coherent echoes from so-called guide stars or beacons. In situations where a guide star is missing, aperture-based techniques may give ambiguous results. Moreover, they are conceptually focused on aberrators that can be approximated as a phase screen in front of the probe. We propose a novel technique, where the effect of aberration is detected in the reconstructed image as opposed to the aperture data. The varying local echo phase when changing the transmit beam steering angle directly reflects the varying arrival time of the transmit wave front. This allows sensing the angle-dependent aberration delay in a spatially resolved way, and thus aberration correction for a spatially distributed volume aberrator. In phantoms containing a cylindrical aberrator, we achieved location-independent diffraction-limited resolution as well as accurate display of echo location based on reconstructing the speed-of-sound spatially resolved. First successful volunteer results confirm the clinical potential of the proposed technique.

Distributed transpressive continental deformation: The Varto Fault Zone, eastern Turkey

The convergence between the Eurasian and Arabian plates has created a complicated structural setting in the Eastern Turkish high plateau (ETHP), particularly around the Karlıova Triple Junction (KTJ) where the Eurasian, Arabian, and Anatolian plates intersect. This region of interest includes the junction of the North Anatolian Shear Zone (NASZ) and the East Anatolian Shear Zone (EASZ), which forms the northern border of the westwardly extruding Anatolian Scholle and the western boundary of the ETHP, respectively. In this study, we focused on a poorly studied component of the KTJ, the Varto Fault Zone (VFZ), and the adjacent secondary structures, which have complex structural settings. Through integrated analyses of remote sensing and field observations, we identified a widely distributed transpressional zone where the Varto segment of the VFZ forms the most northern boundary. The other segments, namely, the Leylekdağ and Çayçatı segments, are oblique-reverse faults that are significantly defined by uplifted topography along their strikes. The measured 515 and 265 m of cumulative uplifts for Mt. Leylek and Mt. Dodan, respectively, yield a minimum uplift rate of 0.35 mm/a for the last 2.2 Ma. The multi-oriented secondary structures were mostly correlated with “the distributed strike-slip” and “the distributed transpressional” in analogue experiments. The misfits in strike of some of secondary faults between our observations and the experimental results were justified by about 20° to 25° clockwise restoration of all relevant structures that were palaeomagnetically measured to have happened since ~ 2.8 Ma ago. Our detected fault patterns and their true nature are well aligned as being part of a transpressional tectonic setting that supports previously suggested stationary triple junction models.

Fault development and interaction in distributed strike-slip shear zones: an experimental approach

Analogue model experiments using both brittle and viscous materials were performed to investigate the development and interaction of strike-slip faults in zones of distributed shear deformation. At low strain, bulk dextral shear deformation of an initial rectangular model is dominantly accommodated by left-stepping, en echelon strike-slip faults (Riedel shears, R) that form in response to the regional (bulk) stress field. Push-up zones form in the area of interaction between adjacent left-stepping Riedel shears. In cross sections, faults bounding push-up zones have an arcuate shape or merge at depth. Adjacent left-stepping R shears merge by sideways propagation or link by short synthetic shears that strike subparallel to the bulk shear direction. Coalescence of en echelon R shears results in major, through-going faults zones (master faults). Several parallel master faults develop due to the distributed nature of deformation. Spacing between master faults is related to the thickness of the brittle layers overlying the basal viscous layer. Master faults control to a large extent the subsequent fault pattern. With increasing strain, relatively short antithetic and synthetic faults develop mostly between old, but still active master faults. The orientation and evolution of the new faults indicate local modifications of the stress field. In experiments lacking lateral borders, closely spaced parallel antithetic faults (cross faults) define blocks that undergo clockwise rotation about a vertical axis with continuing deformation. Fault development and fault interaction at different stages of shear strain in our models show similarities with natural examples that have undergone distributed shear.