Colocation Demand Response: Why Do I Turn Off My Servers?

نویسندگان

  • Shaolei Ren
  • Mohammad A. Islam
چکیده

Data centers are promising participants in demand response programs (i.e., reducing a large electricity demand upon utility’s request), making power grid more stable and sustainable. In this paper, we focus on enabling colocation data center demand response. Colocation is an integral yet unique segment of data center industry, where multiple tenants house their servers in one shared facility. Nonetheless, differing from owner-operated data centers (e.g., Google), colocation data center suffers from “split incentive”: colocation operator desires demand response for financial incentives but has no control over tenants’ servers, while tenants who own the servers may not desire demand response due to lack of incentives. To break “split incentive”, we propose a first-of-its-kind incentive mechanism, called iCODE (incentivizing COlocation tenants for DEmand response), based on reverse auction: tenants, who voluntarily submit energy reduction bids to colocation operator, will be financially rewarded if their bids are accepted. We formally model how each tenant decides its bids and how colocation operator decides winning bids. We perform a trace-based simulation to evaluate iCODE. We show that iCODE can reduce colocation energy consumption by over 50% during demand response periods, unleashing the potential of colocation demand response.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Optimality analysis of energy-performance trade-off for server farm management

A central question in designing server farms today is how to efficiently provision the number of servers to extract the best performance under unpredictable demand patterns while not wasting energy. While one would like to turn servers off when they become idle to save energy, the large setup cost (both, in terms of setup time and energy penalty) needed to switch the server back on can adversel...

متن کامل

PACEM: Cooperative Control for Citywide Energy Management

Proto/Amorphous Cooperative Energy Management (PACEM) controls energy demand across an entire metropolitan area by coordinating the behavior of individual electrical appliances. The goal of this project is to demonstrate the feasibility of PACEM by showing smooth demand shaping and additive scaling using cheap, decentralized communication hardware, both in simulation and on a test system of 50-...

متن کامل

MERCi-MIsS: Should I Turn off My Servers?

In recent years, the electrical consumption of data centers has increased considerably leading to a rise in the expenditure bill and in greenhouse gas emissions. Several existing on/off algorithms reduce energy consumption in data centers or Clouds by turning off unused (idle) machines. However, the turning off/on of servers consumes a certain amount of energy and also induces the wear and tear...

متن کامل

A Pragmatic Solution to the Value Problem of Knowledge

We value possessing knowledge more than true belief. Both someone with knowledge and someone with a true belief possess the correct answer to a question. Why is knowledge more valuable than true belief if both contain the correct answer? I examine the philosophy of American pragmatist John Dewey and then I offer a novel solution to this question often called the value problem of knowledge. I pr...

متن کامل

Scheduling Policies : Single Servers

Our high-level goal is the development and implementation of algorithms which reduce power consumption in data centers by as much as 40%, while still meeting response time service-level objectives (typically in the form of 95%-tiles). We are motivated by the facts that: (i) the load in data centers varies by a factor of 2–4 during the course of a day, with servers only busy 20% of the time on a...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014