Neki Frasheri

Datacenters powered by renewable energy: A case study for 60 degrees latitude north

Attention paid to energy efficiency in datacenters has been increasing significantly in the last decade. One of the latest trends on this issue is supplying datacenters with renewable energy, and reducing the carbon footprint of datacenters is a major step towards green computing. Following this trend, more and more datacenters are built in cold climate areas for cheaper cooling and increased energy efficiency of the facilities. However, such geographical locations have a very varying availability of renewable energy (especially solar energy), depending on the annual month and fitting the datacenters completely with renewable energy is hence more difficult. This paper analyzes the feasibility of using renewable energies for a datacenter located on the 60° latitude north. We analyze the energy consumption caused by the server workload and the cost-to-energy trade-off related to available wind and solar energy sources. A wind and solar power model is built based on real weather data for the city of Turku, Finland, and a feasibility study is conducted for fitting a datacenter with renewable energy sources on such a location. The available monthly and annual renewable energy is analyzed for different scenarios and compared with the energy consumption of a simulated datacenter. We also analyze the ratio between number of wind turbines and m2 solar panel to achieve a desired fraction of renewable energy sources for a given datacenter.

Analysis of the Convergence of Iterative Geophysical Inversion in Parallel Systems

Geophysical inversion is an ill-posed problem, resolved partially mostly in 2D or with specific constrains. We analyze the convergence of iterative 3D gravity inversion based in the idea of the CLEAR algorithm in both cases of sequential and parallel processing, focusing in the time and number of iterations depending in number of discretization nodes and number of processors involved. Variations of calculation runtime and number of iterations depending on the size of the model indicate the usefulness of parallel processing for large models of 3D geophysical inversion with simple algorithms. The work is done for the FP7 project HP-SEE.

Scalability of Gravity Inversion with OpenMP and MPI in Parallel Processing

The geophysical inversion of gravity anomalies is experimented using the application GMI based on the algorithm CLEAR, run in parallel systems. Parallelization is done using both OpenMP and MPI. The scalability in time domain of the iterative process of inversion is analyzed, comparing previously reported results based in OpenMP with recent data from tests with MPI. The runtime for small models was not improved with the increase of the number of processing cores. The increase of user runtime due to the size of the model resulted faster for MPI compared with OpenMP and for big models the latter would offer better runtime. Walltime scalability in multi-user systems did not improved with the increase of processing cores as result of time sharing. Results confirm the scalability of the runtime at the order of O(N8) relative to the linear size N of 3D models, while the impact of increasing the number of involved cores remains disputable when walltime is considered. Walltime upper limit for modest resolution 3D models with 41*41*21 nodes was 105 seconds, suggesting the need of using MPI in multi-cluster systems and of GPUs for better resolution. The results are in framework of FP7 Infrastructure project HP-SEE.

Processing of satellite images in space-time domain

Proposed methodology aims at processing of remote sensing images of a single area taken in different times. The suite of images represents a 3D data array structure. Images can be produced combining different bands in order to obtain a space-time representation of environmental parameters as vegetation index, humidity, pollution, temperatures etc. We have experimented calculation of trend polynomials for suites of NDVI values in time of each pixel separately. Polynomial coefficients for the trend of each pixel were used to generate false color images representing the evolution in time of NDVI values for the whole area in study. The work was done in the frame of FP7 project SEE-GRID-SCI, using the application framework CHERS.

Scalability Issues for Wind Simulation Using OpenFOAM

Abstract The use of the OpenFOAM software for wind simulation over rugged terrain is studied in the paper. OpenFOAM requirements for runtime, virtual memory and disk space are considered using small and medium resolution Digital Elevation Models (DEM) models for single-process and multi-process cases when running on local workstation and small parallel systems. Based on obtained data, extrapolation of requirements for relatively high resolution models are made and issues concerning the scalability are discussed.

New Trends in Information Technologies and Their Integration in University Curricula: a Brief Study in the Context of the FETCH European Thematic Network

Starting from general considerations about the fast evolution of Information Technology, in this paper we focus on the need for integrating new up-to-date topics in existing computing curricula. In particular, we summarize the data obtained from surveys developed within the FETCH European thematic network and directed to professors, alumni and industry representatives. We also provide suggestions derived from the FETCH European Strategic Framework for Computing Education and Training (ESFCET 2020), stressing the importance of computing curricula that incorporate timely technological targets.

Error reduction in parallel gravity inversion

In previous work we have analyzed the scalability and quality of approximation of modified CLEAN algorithm applied in geophysical 3D gravity inversion in parallel systems. In this paper we focus on detailed presentation of error calculation applied for the inversion, necessary for realistic solution of multimodal inversion cases. At the end, a comparison of error results from different used formulas is presented

Microcontrollers as components of service oriented architectures

Implementing service oriented architectures in primitive devices such are microcontrollers is a challenge. This is due to high bandwidth and code size required by corresponding technologies such are Web Services and CORBA. In this paper, we present an alternative of realization of CORBA service in 8051 microcontroller. We compromise between common and compression approaches commonly used for this case. In common approach, there is no compiler for generated code for primitive devices target such is 8051. In compression approach, there is large code size required for compression/decompression and processing algorithm realization. Our approach outperforms in resulting code size comparing to common and compression approaches. Other advantage is that it is not dependent on particular service oriented architecture technology.

Some Results for 3D Gravity Inversion in Parallel Systems

The aim of the paper is presentation of some results obtained for the 3D gravity inversion in high performance parallel computer systems (HPC). Calculations were based on CLEAN algorithm parallelized with OpenMP and MPI using HPC capacities offered by FP7 project HP-SEE. Scalability of runtime in terms of model sizes and number of computing cores was analyzed. The quality of inversion was evaluated for single and two body models, and concrete tests with field data were carried out. Runtime analysis results matched theoretical expectations for the order of magnitude of calculation time O(N^8) where N represents the linear size of the geosection, and permitted an evaluation of effective runtime for small and medium models. Two modified least squares schemes were applied for the inversion of multi-modal anomalies and respective errors compared. The link between symmetries of geosections and respective anomaly approximation errors was observed. Obtained inverted geosections are characterized by distinguished contrast of mass density between anomalous bodies and surrounding rocks. But more work is required to deal with multi-body geosections (multi-modal anomalies) to reduce the lack of discrimination capacity of the algorithm for in-depth bodies.