Helen Karatza
ABSTRACT
Recent advances in networks and computing systems have led many aspects of our daily life to depend on distributed interconnected computing resources. Large scale distributed systems such as computational and data grids and clouds are used for serving large and complex applications [1].
Grids and clouds performance became more important due to the increase of users and computationally intensive applications. However, the usage of energy has become a major source of concern for these systems due to the price of electricity and the impact on the environment.
Energy efficiency in large scale distributed systems reduces energy consumption and operational costs [2]. However, energy conservation should be considered together with users' satisfaction regarding QoS. Complex multiple-task applications may have precedence constraints and specific deadlines and may impose several restrictions and QoS requirements [3, 4], therefore energy-efficient job scheduling is a difficult task in grids and clouds where there are many alternative heterogeneous computers. Advanced modelling and simulation techniques are a basic aspect of performance evaluation that is needed before the costly prototyping actions required for large scale distributed systems [5].
In this talk we will present state-of-the-art research covering a variety of concepts on resource allocation and job scheduling in large scale existing or simulated distributed systems that provide insight into energy conservation problems solving. We will also provide future directions in the area of energy efficiency in grids and clouds.
- G. L. Stavrinides, F. R. Duro, H. D. Karatza, J. G. Blas, and J. Carretero. Different aspects of workflow scheduling in largescale distributed systems. Simulation Modelling Practice and Theory, 70:120--134, Jan. 2017. Google Scholar
Cross Ref
- G. Terzopoulos and H. D. Karatza. Power-aware bag-of-tasks scheduling on heterogeneous platforms. Cluster Computing, 19(2):615--631, June 2016. Google ScholarDigital Library
- G. L. Stavrinides and H. D. Karatza. A cost-effective and qosaware approach to scheduling real-time workflow applicationsin paas and saas clouds. In Proceedings of the 3rd International Conference on Future Internet of Things and Cloud (FiCloud'15), pages 231--239, Aug. 2015.Google Scholar
- G. L. Stavrinides and H. D. Karatza. Scheduling real-time parallel applications in saas clouds in the presence of transient software failures. In Proceedings of the 2016 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS'16), pages 1--8, July 2016. Google ScholarCross Ref
- G. L. Stavrinides and H. D. Karatza. The impact of input error on the scheduling of task graphs with imprecise computations in heterogeneous distributed real-time systems. In Proceedings of the 18th International Conference on Analytical and Stochastic Modelling Techniques and Applications (ASMTA'11), pages 273--287, June 2011. Google ScholarCross Ref
Index Terms
- Energy Efficiency in Large Scale Distributed Systems: The Role of Simulation
Recommendations
A survey on techniques for improving the energy efficiency of large-scale distributed systems
The great amounts of energy consumed by large-scale computing and network systems, such as data centers and supercomputers, have been a major source of concern in a society increasingly reliant on information technology. Trying to tackle this issue, the ...
Improving energy-efficiency of large-scale workflows in heterogeneous systems
With the rapid growth of grid computing, more and more data-intensive applications have been deployed in grid environments, which in turn increase the energy consumption in high-performance computing platforms. To address the issue of energy consumption ...
Energy efficiency management in computational grids through energy-aware scheduling
SAC '13: Proceedings of the 28th Annual ACM Symposium on Applied ComputingEnergy consumption in High Performance Computing (HPC) has become an important issue in the past few years. The performance gain obtained by these environments is matched by a proportional increase of energy use. Example of such environments are ...
Comments