skip to main content

Search for: All records

Award ID contains: 1413998

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Environmental concerns and rising grid prices have motivated data center owners to invest in on-site renewable energy sources. How- ever, these sources present challenges as they are unreliable and intermittent. In an effort to mitigate these issues, data centers are incorporating energy storage systems. This introduces the oppor- tunity for electricity bill reduction, as energy storage can be used for power market arbitrage. We present two supervised learning-based algorithms, LearnBuy, that learns the amount to purchase, and LearnStore, that learns the amount to store, to solve this energy procurement problem. These algorithms utilize the idea of "learning from optimal" by using the values generated by the offline optimization as a label for training. We test our algorithms on a general case, considering buying and selling back to the grid, and a special case, considering only buying from the grid. In the general case, LearnStore achieves a 10-16% reduction compared to baseline heuristics, whereas in the special case, LearnBuy achieves a 7% reduction compared to prior art.
  2. The widespread adoption and popularity of Internet-scale Distributed Networks (IDNs) has led to an explosive growth in the infrastructure of these networks. Unfortunately, this growth has also led to a rapid increase in energy consumption with its accompanying environmental impact. Therefore, energy efficiency is a key consideration in operating and designing these power-hungry networks. In this paper, we study the greening potential of combining two contrasting sources of renewable energy, namely solar energy and Open Air Cooling (OAC). OAC involves the use of outside air to cool data centers if the weather outside is cold and dry enough. Therefore OAC is likely to be abundant in colder weather and at night-time. In contrast, solar energy is correlated with sunny weather and day-time. Given their contrasting natures, we study whether synthesizing these two renewable sources of energy can yield complementary benefits. Given the intermittent nature of renewable energy, we use batteries and load shifting to facilitate the use of green energy and study trade-offs in brown energy reduction based on key parameters like battery size, number of solar panels, and radius of load movement. We do a detailed cost analysis, including amortized cost savings as well as a break-even analysis formore »different energy prices. Our results look encouraging and we find that we can significantly reduce brown energy consumption by about 55% to 59% just by combining the two technologies. We can increase our savings further to between 60% to 65% by adding load movement within a radius of 5000kms, and to between 73% to 89% by adding batteries.« less