Patent Application
20100191998
Digital information management has now essentially replaced old, paper-based methods of information management. In comparison with more traditional methods of information management, digital information management is generally regarded as less expensive, less bulky, more reliable, and more secure. As such, in order to meet present and future computing needs, many commercial, academic, and governmental institutions are demanding increasingly sophisticated and energy intensive computing resources. In response to this demand, current investments in modern data and communications infrastructure are rapidly increasing, especially for the life-blood of this modern digital movement: the data center.
In general, a data center is a large facility that houses various computer systems and related components, such as, for example, microcomputers (i.e., servers), switches, uninterruptible power supplies (UPS), redundant systems, environmental controls, and the like. As a result of these various components, data centers play a vital role in providing resources necessary to power our modern methods of information management.
However, this trend towards complete digital information management has not come without cost. On the contrary, data centers and the computing resources they require are energy and resource intensive. For example, the United States Environmental Protection Agency estimated that in 2006 approximately 61 billion kilowatt-hours (kWh) of electricity was consumed to power our national data centers. As such, nearly 2% of all electricity consumed in the United States during 2006 went to power domestic data centers. Fueled by consumer demand, data center energy consumption is projected to nearly double within a few years and exceed 100 billion kWh of total electricity by 2011. As a majority of U.S. electricity is generated by carbon-based fuel sources that emit various greenhouse gases during the energy production process, potential environmental impacts associated with increased electricity consumption are garnering much attention from private and public institutions. Further, data center water usage also represents a non-trivial industry concern. For example, a one megawatt data center can use approximately 18,000 gallons per day to dissipate heat generated during operation of the data center. Just like electricity generation, water supply represents a limited natural resource that can substantially affect the overall environmental impacts of a data center.
Due to a conflicting need to employ increasingly resource-intensive computing devices and a desire to minimize overall environmental impacts, many modern institutions find themselves in a troubling situation.
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
Embodiments of the present invention relate to, among other things, calculating and apportioning an environmental impact associated with the operation of a data center. One or more data centers are identified and the environmental impacts attributable to the data centers are determined. By way of example and not limitation, the carbon dioxide emissions can be and are apportioned on the basis of a data center application. Accordingly, the present invention permits apportioning an environmental impact on a per application basis.
The present invention is described in detail below with reference to the attached drawing figures, wherein:
The subject matter of the present invention is described with specificity herein to meet statutory requirements. However, the description itself is not intended to limit the scope of this patent. Rather, the inventors have contemplated that the claimed subject matter might also be embodied in other ways, to include different steps or combinations of steps similar to the ones described in this document, in conjunction with other present or future technologies. Moreover, although the terms “step” and/or “block” may be used herein to connote different elements of methods employed, the terms should not be interpreted as implying any particular order among or between various steps herein disclosed unless and except when the order of individual steps is explicitly described.
Embodiments of the present invention provide a method for apportioning the carbon footprint and/or water usage of a data center on an application-specific basis. By way of example only and not limitation, the carbon dioxide emissions or water usage associated with consuming one data center application, for example, using an amount of storage at a data center, can be isolated and apportioned.
Data center consumers vary widely in sophistication, demand, and geography. Accordingly, our national data and communications network consists of an integrated, yet individually unique, system of data centers. Given the varying age of each data center, the varying geography, or the varying power grid surrounding this system of data centers, each data center has unique properties of electrical consumption, water usage, and/or environmental impact.
Accordingly, in one aspect, an embodiment of the present invention is directed to one or more computer-readable storage media embodying computer useable instructions for performing a method of apportioning an environmental impact of a data center. The method includes identifying at least one data center and an application. The application is selected from a group consisting of a server, a virtual machine, an amount of storage, and an amount of bandwidth. The method also includes calculating a total amount of electricity consumed by the at least one data center. The method further includes calculating an environmental impact at least one data center. The method also includes determining an apportioned amount of the environmental impact per the application
In another embodiment of the invention, an aspect is directed to a method of assessing relative carbon dioxide usage at a data center. The method includes identifying a first plurality of data centers, a second plurality data centers, and an application, wherein the first plurality of data centers are commonly owned or commonly operated. The method also includes calculating a first total amount of electricity consumed at the first plurality data centers and a second total amount of electricity at the second plurality data centers. The method still also includes calculating a first total amount of carbon dioxide emitted as a result of generation of the first total amount of electricity at the first plurality of data centers and calculating a second total amount of carbon dioxide emitted as a result of generation of the second total amount of electricity consumed at the second plurality data centers, wherein calculating the second total amount of carbon dioxide emitted as a result of generation of the second total amount of electricity consumed at the second plurality data centers comprises utilizing national, regional or industry averages representative of carbon dioxide emissions per unit of electricity consumed. The method further includes determining a first apportioned amount of carbon dioxide emitted as a result of generation of the first total amount of electricity consumed at the first plurality of data centers per the application. The method further includes determining a second apportioned amount of carbon dioxide emitted as a result of generation of the first total amount of electricity at the second plurality of data centers per the application. The method still further includes comparing the first apportioned amount of carbon dioxide emitted to the second apportioned amount of carbon dioxide emitted.
A further embodiment of the present invention is directed to one or more computer-readable storage media embodying computer useable instructions for performing a method of prospectively minimizing data center-related carbon dioxide emissions. The method first includes identifying a first data center. The method also includes identifying a second data center. The method still also includes identifying an application. The method further includes calculating an expected first amount of electricity consumption at the first data center. The method still further includes calculating an expected second amount of electricity consumption at the second data center. The method further includes calculating an expected first amount of carbon dioxide emitted as a result of the generation of the expected first amount of electricity consumption. The method still further includes calculating an expected second amount of carbon dioxide emitted as a result of the generation of the expected second amount of electricity consumption. The method also includes determining an expected first apportioned amount of the expected first amount of carbon dioxide. The method further includes determining an expected second apportioned amount of the expected second amount of carbon dioxide. The method still further includes comparing the expected first apportioned amount to the expected second apportioned amount. The method also includes determining whether the expected first apportioned amount or the expected second apportioned amount has a lower expected amount of carbon dioxide emission. The method also includes selectively utilizing the application at a data center determined to have the lower expected amount of carbon dioxide emitted.
Having briefly described an overview of embodiments of the present invention, an exemplary operating environment in which embodiments of the present invention may be implemented is described below in order to provide a general context for various aspects of the present invention. Referring initially to
The invention may be described in the general context of computer code or machine-useable instructions, including computer-executable instructions such as program modules, being executed by a computer or other machine, such as a personal data assistant or other handheld device. Generally, program modules including routines, programs, objects, components, data structures, etc., refer to code that perform particular tasks or implement particular abstract data types. The invention may be practiced in a variety of system configurations, including hand-held devices, consumer electronics, general-purpose computers, more specialty computing devices, etc. The invention may also be practiced in distributed computing environments where tasks are performed by remote-processing devices that are linked through a communications network.
With reference to
Computing device 100 typically includes a variety of computer-readable media. Computer-readable media can be any available media that can be accessed by computing device 100 and includes both volatile and nonvolatile media, removable and non-removable media. By way of example, and not limitation, computer-readable media may comprise computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by computing device 100. Communication media typically embodies computer-readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media. Combinations of any of the above should also be included within the scope of computer-readable media.
Memory 112 includes computer-storage media in the form of volatile and/or nonvolatile memory. The memory may be removable, nonremovable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard drives, optical-disc drives, etc. Computing device 100 includes one or more processors that read data from various entities such as memory 112 or I/O components 120. Presentation component(s) 116 present data indications to a user or other device. Exemplary presentation components include a display device, speaker, printing component, vibrating component, etc.
I/O ports 118 allow computing device 100 to be logically coupled to other devices including I/O components 120, some of which may be built in. Illustrative components include a microphone, joystick, game pad, satellite dish, scanner, printer, wireless device, etc.
Turning to
Data center system 200 includes a plurality of users 210, 212, 214, and 216 in communication with a data center 230 having computing resources 240 and associated components 245. In this exemplary system, four users 210, 212, 214, and 216 are shown. It will be understood by those of ordinary skill in the art that such is merely exemplary and that the system 200 may include any number of users in communication with data center 230. Each of the plurality of users 210, 212, 214, and 216 shown in
In
Power supply 260 is provided electricity 250 from power source 270. Power source 270 includes any facility capable of providing electricity 250 to power supply 260. By way of example only and not limitation, power source 270 is a power plant, power station, or any similar facility that operates to generate electricity 250. To generate electricity 250, power source 270 could utilize fossil fuels, renewable energy technology, or some combination thereof. Fossil fuel-based power sources include any power source that utilizes fossil fuels (e.g., coal, natural gas, petroleum, or any other carbon-based fuel) to generate electricity 250. Renewable energy-based power sources include any power source that utilizes renewable natural resources, such as sunlight, wind, rain, tides, geothermal heat, or the like. Renewable energy-based power sources may also include power sources utilizing nuclear fission.
One key difference between fossil fuel-based power sources and renewable energy-based power sources is the amount of greenhouse gases emitted during the generation of electricity 250. Fossil fuel-based power sources generally emit a myriad of greenhouse gases during the generation of electricity 250, such as, for example, carbon dioxide, methane, trioxygen (ozone), nitrous oxide, or the like. On the other hand, renewable energy-based power sources generally emit little to no greenhouse gases during the generation of electricity 250. As such, entities consuming energy, such as data center 230 operating computing resources 240 and associated components 245, may consume electricity 250 generated by fossil fuel-based power supplies, renewable energy-based power supplies, or some combination of thereof.
The manner in which electricity 250 is produced, of course, has environmental significance. When an entity consumes energy generated as a result of emitting greenhouse gases, that entity is said to have a “carbon footprint.” A “carbon footprint” is a measure of the impact an activity has on the environment, generally measured in units of carbon dioxide (CO2) or carbon dioxide equivalents (CDE) released into the atmosphere as a result of that activity.
Returning now to
Another result of running applications 220, 222, 224, and 226 on computing resources 240 is the need to consume large amounts of water 280. During the operation of a data center, water 280 is used in a variety of ways, including as a cooling fluid for heat dissipation. In
As those of ordinary skill of art will appreciate based upon the foregoing discussion, the hypothetical Oregon data center could have a relatively small carbon footprint (e.g., due to hydropower), but concurrently have a large fresh water footprint. In contrast, the hypothetical New Mexico data center could have a large carbon footprint (e.g., due to electricity generation), but also have no footprint as to fresh water. In the regard, each potential environmental impact of a data center, including a carbon and water footprint, is unique.
Turning to
Referring again to
Alternatively, block 314 may include utilizing data center-specific information to assess of the environmental impact of any data center or group of data centers. For example, block 314 may contemplate the manner in which electricity for a specific data center (e.g., electricity 250 of
As would be apparent to those of skill in the art, the result of method 300 is a known carbon footprint of an identified data center or data centers. Utilizing this known carbon footprint is addressed further in the various embodiments described below.
Having now discussed a general method for determining the carbon footprint of data centers, we now turn to
At block 414, a total amount of electricity consumed at the data center or data centers is determined. Various methods may be used to determine electricity consumption of a data center, such as, for instance, those methods discussed with reference to block 312 of
At block 418, an apportioned amount of carbon dioxide emitted per application is determined. Restated, the carbon footprint determined at block 416 is apportioned on the basis of the application selected at block 412. The process comprising block 418, namely, apportioning the carbon footprint on a per application basis, is relevant to other embodiments hereinafter addressed. As such, this detailed discussion of block 418 may apply equally to block 418 of
If the application selected at block 412 is a server, block 418 may include determining the total number of contributing servers at the data center or data centers and apportioning each contributing server a proportional share of the carbon footprint determined at block 416. The term “contributing” servers includes all servers that contributed at least partially to the carbon footprint determined at block 416. Generally, contributing servers will include only those servers that consumed electricity at the data center or data centers identified at block 410. Thus, for example, contributing servers would not likely include servers that are present at the data center but did not consume any electricity (e.g., powered off, disabled, emergency back-up). Alternatively, the number of contributing servers may optionally include any servers dedicated to operating the data center (e.g., servers utilized to service data center computing resources). In this embodiment, the carbon dioxide and carbon dioxide equivalent emissions contributed by servers dedicated to the data center would be apportioned to the data center itself (as the “user” of the servers). On the other hand, the data center could optionally exclude the number of servers dedicated to the operation of the data center from the apportionment process entirely (thereby decreasing the total number of contributing servers and increasing the footprint attributable to each individual contributing server). This would result in the carbon footprint associated with operating the data center being passed along to the data center users (i.e., a carbon premium passed on to the ultimate consumer). Those skilled in the art will now recognize, that after completing block 418 of method 400 where the application selected at block 412 is a server, each contributing server will have an apportioned amount of carbon dioxide emitted.
Referring again to block 418, if the application selected at block 412 is a virtual machine, block 418 may include determining the total number of virtual machines at the data center and apportioning each virtual machine a proportional share of the carbon footprint determined at block 416. In an embodiment, apportioning carbon footprint for virtual machines may essentially be equivalent to apportionment for servers. As such, the various considerations addressed with regard to apportioning for servers apply equally to this embodiment. As with the apportionment process for servers, any virtual machines dedicated to the operation of the data center or data centers may optionally be excluded for the apportionment process. Those skilled in the art will now recognize that, after completing block 418 of method 400 where the application selected at block 412 is a virtual machine, each virtual machine will have an apportioned amount carbon dioxide emitted.
Returning to block step 418, if the application selected at block 412 is an amount of storage, block 418 may include determining the total amount of contributing storage at the data center or data centers and apportioning each unit of contributing storage a proportional share of the carbon footprint determined at block 416. Here, the term “total amount of contributing storage” includes all storage that contributed at least partially to the carbon footprint determined at block 416. Generally, contributing storage will include only that amount of storage that consumed electricity at the data center or data centers identified at block 410. Thus, for example, contributing storage would not likely include any storage that was present at the data center, but are for some did not consume any electricity (i.e., portable media, powered off, disabled, emergency back-up). Further, contributing storage may optionally exclude storage that was unused during the period of time under examination by method 400, but otherwise consumed electricity. Still further, contributing storage may optionally include any storage dedicated to the operation of the data center (e.g., storage used to store data for the data center). Thus, the contributing storage may optionally include the raw storage ability of the data center, the actual amount of data stored in data center storage, the raw storage ability of the data center less any storage utilized for data center operations, the actual amount of data stored in the data center storage less any storage utilized for data center operations, or any other desired quantity of storage. Those skilled in the art will now recognize, that after completing block 418 of method 400 where the application selected at block 412 is an amount of storage, each unit of contributing storage will have an apportioned amount of carbon dioxide emitted.
Again referring to block step 418, if the application selected at block 412 is an amount of bandwidth, block 418 may include determining the adjusted amount of bandwidth at the data center or data centers and apportioning each unit of adjusted bandwidth a proportional share of the carbon footprint determined at block 416. Bandwidth, as the term is used herein, represents the capacity of the data center to transfer data through a medium (e.g., wireless) or over a physical connection (e.g., wires). Bandwidth is generally measured in bits per second or some multiple thereof (e.g., gigabits per second, gigabytes per hour, etc.). First, the total amount of bandwidth available from the identified data center or data centers is determined. Next, the total amount of data center utilized bandwidth is determined. Data center utilized bandwidth includes that amount of bandwidth that is dedicated to operation of the identified data center. For example, bandwidth used by the data center for a data center-required storage account or virtual machine could comprise the amount of data center utilized bandwidth. With these two bandwidth totals determined, an adjusted amount of bandwidth is calculated. The adjusted amount of bandwidth is the difference between the total amount of bandwidth available from the data center and the data center utilized bandwidth. For example, if a data center has 75 total gigabytes of available bandwidth, but 100 megabytes of bandwidth is used to operate the data center, the adjusted amount of bandwidth would be about 74.9023 gigabytes of bandwidth (assuming 1024 megabytes in a gigabyte).
After determining the adjusted amount of bandwidth, the amount of electricity consumed by the adjusted amount of bandwidth is determined. Any method previously identified with regard to step 312 of
As those skilled in the art would recognize, the contemplated apportionment process at block 418 can optionally include or optionally exclude a temporal dimension. For example, in one embodiment of the present invention, the carbon footprint identified at block 416 may optionally be expressed in tons of total carbon dioxide or carbon dioxide equivalents emitted. Alternatively, the carbon footprint identified at block 416 may optionally be expressed in tons of carbon dioxide or carbon dioxide equivalents emitted per some unit of time (e.g., an hour, a week, a month, a year, the expected life of the data center, etc.). Of course, desired analytics may dictate whether a temporal dimension is incorporated into method 400.
Turning now to
Referring again to method 500 at block 512, an application is identified for both the first set of data centers and the second set of data centers. The application identification process of block 512 has been previously disclosed at block 412 of
At blocks 518a and 518b, the amount of carbon dioxide emitted by each of the first set of data centers and the second set of data centers, determined at blocks 516a and 516b, is apportioned on the basis of the application selected at block 512. As such, completion of blocks 518a and 518b results in a first apportioned amount of carbon dioxide emitted and a second apportion amount of carbon dioxide emitted. The various methods, techniques, and considerations relevant to blocks 518a and 518b have been previously addressed at block 418 of
Finally, at block 520 of method 500, the first apportioned amount of carbon dioxide emitted and the second apportioned amount of carbon dioxide emitted are compared. It is contemplated that the comparison of block 520 will comprise a graphical, a numerical, and/or an auditory comparison. Utilizing the comparison at block 520, strategic decision-making, such as, for example, selectively pricing applications at data centers with a relatively lower carbon footprint, selectively pricing applications at data centers with a relatively greater carbon footprint, selectively utilizing existing applications or new applications to reduce or increase the carbon footprint of a data center, or the like
Turning to
At block 630, the lower expected carbon footprint is determined by identifying the data center whose application usage will result in a lower expected carbon footprint. Finally, block 632 comprises selectively utilizing the data center application whose usage will result in a lower expected carbon footprint. It is contemplated that the selective utilization of block 632 will be implemented as part or all of a software system stored as executable instructions on a computer-readable storage media. Of course, however, it is understood that the selected utilization of block 632 need not be performed as part of any software system or automated program. On the contrary, any manner of selectively utilizing data center resources is acceptable.
Referring now to
As described above, examples of various embodiments of the present invention may include systems, methods, and computer-readable media that determine and apportion the carbon dioxide emissions of a data center. The various features of the present invention have been described in relation to various embodiments, which are intended in all respects to be illustrative rather than restrictive. Alternative embodiments will become apparent to those of ordinary skill in the art to which the present invention pertains without departing from its scope.
In general, methods according to at least some embodiments of this invention include: (a) determining a carbon footprint of a data center or a set of data centers; (b) apportioning a carbon footprint of a data center or set of data centers on a per application basis; (c) comparing an apportioned carbon footprint; and (d) selectively utilizing data center resources to manage a carbon footprint.
The following tables provide an even more concrete example of carbon footprint apportionment that may be used in accordance with at least one embodiment of this invention. A list of potential data centers analytics may look as follows:
In the first row, a potential amount of electricity consumption will be determined. The methods discussed with reference to block 312 of
A second list of potential data centers analytics may look as follows:
Again in the first row, a potential amount of electricity consumption will be determined. The methods discussed with reference to block 312 of
With reference to these potential lists, other embodiments of the present invention may be realized. For example, if the first list provided was for a first data center and the second list provided was for a second data center, the lists could be compared in accordance with one embodiment of the present invention. Moreover, depending on the application selected, either the first data center or second data center might have a lower carbon footprint associated with a specific data center application. For example, under these hypothetical values, the first data will have a lower carbon footprint per server, but have a higher carbon footprint per unit of adjusted bandwidth. Those of ordinary skill in the art would readily appreciate how such a discrepancy will exist, such as, for example, aging computing resources at a data center, the manner in which electricity was generated and/or consumed, the amount of resources dedicated to operating the data center, or the like.
In addition to comparing the potential lists, other embodiments of the present invention may still further be realized. These potential lists may optionally be used to selectively utilize data center resources so as to adjust a carbon footprint of a consumer or client. For example, where a client demands a server application, the first data center application may optionally be selected. However, where a client demands an amount of bandwidth, the second data center application may optionally be selected. Moreover, utilizing this information will permit a discriminatory pricing scheme so as to encourage or discourage selected applications at selected data centers. For example, the server applications of the first data center may optionally be priced higher than the server application of the second data center. Alternatively, the information may be utilized to effectively barter “cap and trade” carbon credits. For example, carbon credits could be efficiently allocated by private actors in accordance with an embodiment of the invention. Any other manner for utilizing the resultant analytics is also contemplated.
From the foregoing, it will be seen that this invention is one well adapted to attain all the ends and objects set forth above, together with other advantages which are obvious and inherent to the system and method. It will be understood that certain features and subcombinations are of utility and may be employed without reference to other features and subcombinations. This is contemplated by and is within the scope of the claims. For example, although the discussion throughout a majority of the specification relates to apportioning a carbon footprint, embodiments of the present invention are not so limited. On the contrary, any environmental factor, including water consumption, is contemplated as being within the scope of embodiments of the present invention.
