Supercomputing Centers and Electricity Service Providers: A Geographically Distributed Perspective on Demand Management
Supercomputing Centers (SCs) have high and variable power demands, which increase the challenges of the Electricity Service Providers (ESPs) with regards to efficient electricity distribution and reliable grid operation. High penetration of renewable ener
- PDF / 506,339 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 60 Downloads / 195 Views
2
Lawrence Livermore National Laboratory, Livermore, USA [email protected] Energy Efficient High Performance Computing Working Group, Livermore, USA 3 GreenLots and Lawrence Berkeley National Laboratory, Berkeley, USA 4 University of Southern Denmark, Odense, Denmark 5 The University of Mannheim, Mannheim, Germany 6 Create-Net, Trento, Italy
Abstract. Supercomputing Centers (SCs) have high and variable power demands, which increase the challenges of the Electricity Service Providers (ESPs) with regards to efficient electricity distribution and reliable grid operation. High penetration of renewable energy generation further exacerbates this problem. In order to develop a symbiotic relationship between the SCs and their ESPs and to support effective power management at all levels, it is critical to understand and analyze how the existing relationships were formed and how these are expected to evolve. In this paper, we first present results from a detailed, quantitative survey-based analysis and compare the perspectives of the European grid and SCs to the ones of the United States (US). We then show that contrary to the expectation, SCs in the US are more open toward cooperating and developing demand-management strategies with their ESPs. In order to validate this result and to enable a thorough comparative study, we also conduct a qualitative analysis by interviewing three large-scale, geographically-distributed sites: Oak Ridge National Laboratory (ORNL), Lawrence Livermore National Laboratory (LLNL), and the Leibniz Supercomputing Center (LRZ). We conclude that perspectives on demand management are dependent on the electricity market and pricing in the geographical region and on the degree of control that a particular SC has in terms of power-purchase negotiation.
1
Introduction
Current Supercomputing Centers (SCs) for High-Performance Computing (HPC) with peta-scale capabilities have high power demands, with peak requirements of over 30 MW and fluctuations of a few megawatts over short-time scales [4]. c Springer International Publishing Switzerland 2016 J.M. Kunkel et al. (Eds.): ISC High Performance 2016, LNCS 9697, pp. 243–260, 2016. DOI: 10.1007/978-3-319-41321-1 13
244
T. Patki et al.
This trend is expected to continue in the future as we push the limits of supercomputing further. As a result, Electricity Service Providers (ESPs) for such SCs need to support efficient electricity generation, transmission and distribution along with reliable grid operation. ESPs today already face reliability concerns for accommodating megawatt-level fluctuations from SCs and often require HPC client sites to forecast their electricity use. The acceptance and proliferation of renewable sources of energy further adds to the variability in electricity generation, making grid reliability even more challenging. A tighter integration and open communication between ESPs and their client SCs is thus critical as we proceed toward the next generation of supercomputing. At present, most ESP-SC relationships are linear and unidirectional.
Data Loading...