Principles of Cloud Computing Capacity Planning
The term «Cloud» is used an abstraction of the Internet infrastructure. The cloud infrastructure provides for a computer infrastructure platform as a service. The cloud computing providers offer online common business applications accessed by Web browsers, and the software and data are stored in ser...
Gespeichert in:
| Datum: | 2010 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | Ukrainian |
| Veröffentlicht: |
Інститут кібернетики ім. В.М. Глушкова НАН України
2010
|
| Schriftenreihe: | Математичне та комп'ютерне моделювання. Серія: Фізико-математичні науки |
| Online Zugang: | http://dspace.nbuv.gov.ua/handle/123456789/18765 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Назва журналу: | Digital Library of Periodicals of National Academy of Sciences of Ukraine |
| Zitieren: | Principles of Cloud Computing Capacity Planning / D.G. Velev, P.V. Zlateva // Математичне та комп'ютерне моделювання. Серія: Технічні науки: зб. наук. пр. — Кам’янець-Подільський: Кам'янець-Подільськ. нац. ун-т, 2010. — Вип. 3. — С. 20-26. — Бібліогр.: 10 назв. — англ. |
Institution
Digital Library of Periodicals of National Academy of Sciences of Ukraine| id |
irk-123456789-18765 |
|---|---|
| record_format |
dspace |
| spelling |
irk-123456789-187652013-02-13T03:19:27Z Principles of Cloud Computing Capacity Planning Velev, D.G. Zlateva, P.V. The term «Cloud» is used an abstraction of the Internet infrastructure. The cloud infrastructure provides for a computer infrastructure platform as a service. The cloud computing providers offer online common business applications accessed by Web browsers, and the software and data are stored in servers. One of the most advertised advantages of the cloud-computing paradigm is the reduction of hardware deployment and installation times. Cloud storage and compute instances must be viewed as another type of resource. The promise of cloud computing is that it can increase capacity «on-demand» easily and not necessarily automatically. Since every compute instance is a service, many cloud providers put the control of those instances in the hands of their customers. The decision when to launch new instances and their number can be crucially important regarding the rising traffic and computing capabilities and in those circumstances all could end with inefficiencies in cloud capacity. The current article attempts to propose guidelines for efficient planning of cloud capacity. Термин cloud (облако) использется как абстракция Интернет инфраструктуры. Инфраструктура облака (cloud infrastructure) предоставляет компьютерную инфраструктуру под платформой для виртуализации (virtualization) как сервис (обслуживание). Поставщики облачных вычислительный (cloud computing) предоставляют в онлайн режиме общие бизнес приложения, доступ к которым осуществляется web-браузером, в то время как программное обеспечение и данные сохранены на серверах. Одно из наиболее рекламируемых преимуществ облачных вычислений — сокращение времен развертывания и установки аппаратных средств. Сохранение данных и вычислительные операции в облаке должны быть рассмотрены как другой тип ресурса. Так как каждая вычислительная операция является облачным сервисом, оплачиваемым пользователями, многие поставщики облачных сервисов помещают их контроль в руках своих клиентов. Решение о запуске нового сервиса и их число может быть кардинально важным по отношению наращивания трафика транзакций и вычислительных способностей, что в пиковых ситуациях могли бы закончить неэффективностью в возможностях облака. Настоящая статья пытается предложить набор принципов для эффективного планирования возможности облачных вычислений. 2010 Article Principles of Cloud Computing Capacity Planning / D.G. Velev, P.V. Zlateva // Математичне та комп'ютерне моделювання. Серія: Технічні науки: зб. наук. пр. — Кам’янець-Подільський: Кам'янець-Подільськ. нац. ун-т, 2010. — Вип. 3. — С. 20-26. — Бібліогр.: 10 назв. — англ. XXXX-0060 http://dspace.nbuv.gov.ua/handle/123456789/18765 uk Математичне та комп'ютерне моделювання. Серія: Фізико-математичні науки Інститут кібернетики ім. В.М. Глушкова НАН України |
| institution |
Digital Library of Periodicals of National Academy of Sciences of Ukraine |
| collection |
DSpace DC |
| language |
Ukrainian |
| description |
The term «Cloud» is used an abstraction of the Internet infrastructure. The cloud infrastructure provides for a computer infrastructure platform as a service. The cloud computing providers offer online common business applications accessed by Web browsers, and the software and data are stored in servers. One of the most advertised advantages of the cloud-computing paradigm is the reduction of hardware deployment and installation times. Cloud storage and compute instances must be viewed as another type of resource. The promise of cloud computing is that it can increase capacity «on-demand» easily and not necessarily automatically. Since every compute instance is a service, many cloud providers put the control of those instances in the hands of their customers. The decision when to launch new instances and their number can be crucially important regarding the rising traffic and computing capabilities and in those circumstances all could end with inefficiencies in cloud capacity. The current article attempts to propose guidelines for efficient planning of cloud capacity. |
| format |
Article |
| author |
Velev, D.G. Zlateva, P.V. |
| spellingShingle |
Velev, D.G. Zlateva, P.V. Principles of Cloud Computing Capacity Planning Математичне та комп'ютерне моделювання. Серія: Фізико-математичні науки |
| author_facet |
Velev, D.G. Zlateva, P.V. |
| author_sort |
Velev, D.G. |
| title |
Principles of Cloud Computing Capacity Planning |
| title_short |
Principles of Cloud Computing Capacity Planning |
| title_full |
Principles of Cloud Computing Capacity Planning |
| title_fullStr |
Principles of Cloud Computing Capacity Planning |
| title_full_unstemmed |
Principles of Cloud Computing Capacity Planning |
| title_sort |
principles of cloud computing capacity planning |
| publisher |
Інститут кібернетики ім. В.М. Глушкова НАН України |
| publishDate |
2010 |
| url |
http://dspace.nbuv.gov.ua/handle/123456789/18765 |
| citation_txt |
Principles of Cloud Computing Capacity Planning / D.G. Velev, P.V. Zlateva // Математичне та комп'ютерне моделювання. Серія: Технічні науки: зб. наук. пр. — Кам’янець-Подільський: Кам'янець-Подільськ. нац. ун-т, 2010. — Вип. 3. — С. 20-26. — Бібліогр.: 10 назв. — англ. |
| series |
Математичне та комп'ютерне моделювання. Серія: Фізико-математичні науки |
| work_keys_str_mv |
AT velevdg principlesofcloudcomputingcapacityplanning AT zlatevapv principlesofcloudcomputingcapacityplanning |
| first_indexed |
2025-07-02T19:44:04Z |
| last_indexed |
2025-07-02T19:44:04Z |
| _version_ |
1836565602252095488 |
| fulltext |
Математичне та комп’ютерне моделювання
20
D. G. Velev, Assoc. prof., Ph.D.
Department of Information Technologies and Communications
University of National and World Economy, Sofia, Bulgaria
P. V. Zlateva, Assoc. prof., Ph.D.
Institute of Control and Systems Research Bulgarian Academy of
Sciences, Sofia, Bulgaria
PRINCIPLES OF CLOUD COMPUTING CAPACITY PLANNING
The term «Cloud» is used an abstraction of the Internet infra-
structure. The cloud infrastructure provides for a computer infra-
structure platform as a service. The cloud computing providers of-
fer online common business applications accessed by Web brows-
ers, and the software and data are stored in servers.
One of the most advertised advantages of the cloud-computing
paradigm is the reduction of hardware deployment and installation
times. Cloud storage and compute instances must be viewed as
another type of resource.
The promise of cloud computing is that it can increase capacity
«on-demand» easily and not necessarily automatically. Since every
compute instance is a service, many cloud providers put the control
of those instances in the hands of their customers. The decision
when to launch new instances and their number can be crucially
important regarding the rising traffic and computing capabilities
and in those circumstances all could end with inefficiencies in
cloud capacity.
The current article attempts to propose guidelines for efficient
planning of cloud capacity.
Key words: Capacity planning, cloud computing, resources
Introduction. The National Institute of Standards and Technolo-
gy (NIST) defines Cloud Computing as based on five key characteristics
(on-demand self-service, broad network access, resource pooling, rapid
elasticity and measured service), three delivery models (SaaS — Software
as a Service, PaaS — Platform as a Service and IaaS — Infrastructure as a
Service) plus four deployment models (Public/Consumer Private, Hybrid
and Community) and describes Cloud computing as a model for enabling
convenient, on-demand network access to a shared pool of configurable
computing resources (networks, servers, storage, applications, and servic-
es) that can be rapidly provisioned and released with minimal management
effort or service provider interaction [8]. The cloud model promotes avail-
ability and is composed of five essential characteristics, three delivery
models, four deployment models in two types external and internal.
Capacity planning is long-term decision that establishes a firms'
overall level of resources. It extends over time horizon long enough to
© D. G. Velev, P. V. Zlateva, 2010
Серія: Технічні науки. Випуск 3
21
obtain resources. Capacity decisions affect the production lead time, cus-
tomer responsiveness, operating cost and company ability to compete.
Inadequate capacity planning can lead to the loss of the customer and
business. Excess capacity can drain the company's resources and prevent
investments into more lucrative ventures. The question of when capacity
should be increased and by how much are the critical decisions.
Capacity Planning. Capacity is defined as the maximum amount of
work that an organization is capable of completing in a given period of
time with the following calculation, Capacity = (number of machines or
workers) × (number of shifts) × (utilization) × (efficiency). A discrepancy
between the capacity of an organization and the demands of its customers
results in inefficiency, either in under-utilized resources or unfulfilled cus-
tomers. The broad classes of capacity planning are lead strategy, lag strat-
egy, and match strategy [2, 3, 10].
Lead strategy is adding capacity in anticipation of an increase in de-
mand. Lead strategy is an aggressive strategy with the goal of luring
customers away from the company's competitors. The possible dis-
advantage to this strategy is that it often results in excess inventory,
which is costly and often wasteful.
Lag strategy refers to adding capacity only after the organization is
running at full capacity or beyond due to increase in demand. This is
a more conservative strategy. It decreases the risk of waste, but it
may result in the loss of possible customers.
Match strategy is adding capacity in small amounts in response to
changing demand in the market. This is a more moderate strategy.
Capacity planning is the process of determining the production ca-
pacity needed by an organization to meet changing demands for its prod-
ucts. In the context of capacity planning, «capacity» is the maximum
amount of work that an organization is capable of completing in a given
period of time [1, 10]. Capacity Planning is the process of measuring the
amount of work that can be completed within a given time and determin-
ing the necessary physical and human resources needed to accomplish it.
Capacity planning uses capacity utilization to ensure that the maximum
amount of product is made and sold. The planning involves a regulation
process that identifies deviations from the plan, allowing corrective action
to be taken. A capacity requirements planning program can aid in the
process of capacity planning.
A discrepancy between the capacity of an organization and the de-
mands of its customers results in inefficiency, either in under-utilized re-
sources or unfulfilled customers. The goal of capacity planning is to mi-
nimize this discrepancy. Demand for an organization's capacity varies
based on changes in production output, such as increasing or decreasing
Математичне та комп’ютерне моделювання
22
the production quantity of an existing product, or producing new products.
Better utilization of existing capacity can be accomplished through im-
provements in overall equipment effectiveness (OEE). Capacity can be
increased through introducing new techniques, equipment and materials,
increasing the number of workers or machines, increasing the number of
shifts, or acquiring additional production facilities.
According to Gartner [4, 5], capacity planning today is all about try-
ing to ensure the provision of enough capacity and memory cycles to meet
workload demand. Nevertheless, virtualization causes new variables to be
taken into consideration and power consumption is just one among many.
For IT resource planning (ITRP) there are several more elements to con-
sider and the process must become much more strategic within an enter-
prise. Gartner analysts detailed the many variables that must be taken into
account for appropriate enterprise ITRP. Traditional IT capacity metrics
need to be considered alongside business requirements, human capital,
financial metrics, facilities and power data, risk and compliance informa-
tion as well as workload placement. Other considerations include configu-
ration management, asset management, change management, event man-
agement and performance management, according to the Gartner report.
Cloud Computing Capacity Planning. The IT industry has been
migrating a huge amount of computation and storage into compute clouds.
A modern compute cloud allows users to share the underlying computing
resources (such as CPU, memory and networking bandwidth) in an elastic
manner and thus achieves an economy of scale. In a virtualization-based
compute cloud, capacity planning refers to the procedure of allocating
resources to virtual machines for supporting their workload. Capacity
planning is a vital technology for making a cloud profitable from the cloud
provider's perspective.
As data centers evolve to incorporate emerging technologies such as
virtualization and cloud computing, the practice of planning for IT re-
sources must also change. Cloud customers benefit from economies of
scale such as volume purchasing, network bandwidth, operations, and ad-
ministration when a cloud provider like handles these operations. Average
unit costs of computing are reduced because fixed costs are spread
over more units of capacity and utilized by more users.
Cloud capacity planning will affect cloud service performance assur-
ance and how service level objectives/agreements will be met. To achieve
elasticity and the provision of infinite computing resources available on
demand, Cloud Computing providers typically rely on statistical multip-
lexing algorithms and load balancing mechanisms [6, 9]. Consequently,
they will require various forms of «virtualization /abstraction» to mask the
physical implementations of how resources are multiplexed and shared
Серія: Технічні науки. Випуск 3
23
regardless of whether commercial server virtualization technology is ac-
tually in use.
Old-fashioned capacity planning focuses on the peak usage of the
application. However, now there are new capacity goals that can be sum-
marized into the following:
Performance (External service monitoring, Business requirements,
User expectations).
Capacity (System metrics).
One of the most advertised advantages of the cloud-computing idea
is the reduction of hardware deployment and installation times. As far as
capacity planning goes, cloud storage and compute instances should be
viewed as just another type of resource. Just like a single server, for each
instance of cloud-based computing, you have some amount of: CPU,
RAM, Disk and I/O network transfer.
Each cloud resource still has its limits and costs as with any existing
infrastructure. The capacity planning process is exactly the same [1, 7, 10]:
Measuring the used resources (number of instances, CPU or storage).
Determing the limits (needed resources to launch/stop new instance).
Forecasting according to the past usage.
The promise of cloud computing is that capacity can be increased
easily on-demand. Since every instance is essentially a purchase, many
cloud providers put the control of those instances in the hands of their cus-
tomers and making the decision when to launch new instances and their
number can be crucially important in the face of spiking traffic. An en-
hanced operation that is using cloud computing might automate the
process, but the automation should be tuned carefully to react not only to
the load behavior of their website, but the load behavior of the cloud itself.
Clouds reduce shrink deployment time and provide for a more strin-
gent control over capacity. Possible capacity planning principles that can
be applied to cloud are as follows [1, 10]:
Put capacity measurement into place — both metric collection and
event notification systems — to collect and record systems and ap-
plication statistics.
Discover the current limits of your resources and determine how
close you are to those limits.
Use historical data not only to predict what you’ll need, but to com-
pare against what you will actually use.
Useful feature of cloud infrastructures is the ability to automatically
scale an infrastructure vertically and horizontally with little or no impact
to the applications running in that infrastructure.
Математичне та комп’ютерне моделювання
24
The obvious benefit of cloud scaling is that the user pays only for the
resources you use. The noncloud approach is to buy infrastructure for peak
capacity. The downside of cloud scaling is that it can become a way of
behavior system architects use to avoid capacity planning.
Cloud capacity planning is basically developing a strategy that guarantees
a given infrastructure can support the resource demands placed on it [3, 7]:
Knowledge of expected usage patterns as they vary in time and ac-
cording to the nature of the business;
Knowledge of how applications responds to load so that it could be
identified when and what kind of additional capacity will be needed;
Knowledge of the value of the systems towards business so you it is
known when adding capacity provides value.
Capacity planning is just as important in the cloud as it is in a physi-
cal infrastructure. The general objective is to guarantee that when addi-
tional cost occurs by scaling a given infrastructure, the additional cost will
be supporting the objectives for that infrastructure.
Certain principles must be followed for efficient cloud capacity plan-
ning [1, 7, 10]:
Plans must be developed for an infrastructure to support expected
loads.
Recognize when actual load is diverging in a meaningful way from
expected load.
Understand the impact of changing application requirements on your
infrastructure.
Extensive support for optimizing virtual machines and hosts helps cut
costs and consolidate operations without compromising service quali-
ty. Automatically identifies underutilized virtual machines and safe
consolidation candidates.
Broad support for virtualization environments from VMware, Micro-
soft, Citrix, Sun, HP and IBM, in addition to comprehensive support
for modeling hardware, OS and other components.
Reporting and automated dashboards engage business users and con-
vey complex data in an interactive format, allowing users and IT
stakeholders to quickly and intuitively identify cost saving opportuni-
ties. Business data such as hardware costs and power consumption
can be correlated into reports for informed decisions.
Solution kits help users successfully navigate common business
problems such as server consolidations, new functionality rollouts.
The future cannot be automatically foreseen. Cloud capacity planning
is not to eliminate unexpected peaks in demand, but to help plan for the ex-
pected, recognize and react to the unexpected appropriately to the deviation.
Серія: Технічні науки. Випуск 3
25
Conclusion. Using cloud computing it is possible to simply add ca-
pacity as needed. Since it offers a pay-as-you-use model, the cloud capaci-
ty can very efficiently planned using the clearly defined steps for planning
main resources of the cloud infrastructure:
Storage capacity (GB)
Server processing (CPU cycles) & RAM capacity (GB)
Network bandwidth (Gbps)
Database transactions per second (TPS)
Storage input/output operations per second (IOPS).
Literature:
1. Allspaw J. The Art of Capacity Planning, O’Reilly Media, Inc., 2008. — 154 p.
2. Capacity Planning, http://en.wikipedia.org/wiki/Capacity_planning.
3. Cohen R. Cloud Computing Infrastructure Capacity Planning, http://cloud-
computing.sys-con.com/node/1114572.
4. Dubie D. Are you ready for IT resource planning, http://www.networ-
kworld.com/newsletters/nsm/2009/022309nsm1.html.
5. Gardner D. HP's Cloud Assure for Cost Control allows elastic capacity plan-
ning to better manage cloud-based services, http://www.zd-
net.com/blog/gardner/hps-cloud-assure-for-cost-control-allows-elastic-сapaci-
ty-planning-to-better-manage-cloud-based-services
6. Hess K. Has Virtualization Made Capacity Planning Obsolete,
http://www.linux-mag.com/id/7423.
7. Langley K. Things to Consider When Planning Your Application System and
Software Architecture for Scalability Over Time, http://www.productions-
cale.com/home/2008/10/24/things-to-consider-when-planning-your-applica-
tion-system-and.html.
8. Reese J. Cloud Application Architectures, O’Reilly Media, Inc., 2009, 206 p.
9. Sayegh E., Cloud Economics, http://www.rackspacecloud.com/blog/2009/
02/20/cloud-economics/.
10. Shum A. A Measured Approach To Cloud Computing Capacity Planning and
Performance Assurance, http://www.bsmreview.com/bsm_cloudcompu-
ting.html.
Термин cloud (облако) использется как абстракция Интернет ин-
фраструктуры. Инфраструктура облака (cloud infrastructure) предос-
тавляет компьютерную инфраструктуру под платформой для виртуа-
лизации (virtualization) как сервис (обслуживание). Поставщики об-
лачных вычислительный (cloud computing) предоставляют в онлайн
режиме общие бизнес приложения, доступ к которым осуществляется
web-браузером, в то время как программное обеспечение и данные
сохранены на серверах.
Одно из наиболее рекламируемых преимуществ облачных вычис-
лений — сокращение времен развертывания и установки аппаратных
средств. Сохранение данных и вычислительные операции в облаке
Математичне та комп’ютерне моделювання
26
должны быть рассмотрены как другой тип ресурса. Так как каждая
вычислительная операция является облачным сервисом, оплачивае-
мым пользователями, многие поставщики облачных сервисов поме-
щают их контроль в руках своих клиентов. Решение о запуске нового
сервиса и их число может быть кардинально важным по отношению
наращивания трафика транзакций и вычислительных способностей,
что в пиковых ситуациях могли бы закончить неэффективностью в
возможностях облака.
Настоящая статья пытается предложить набор принципов для эф-
фективного планирования возможности облачных вычислений.
Ключевые слова: планирование, облачные вычисления, ресурсы.
Отримано 25.05.10
УДК 681.3.057:518.12:621.314.6:537:312.62
А. А. Верлань, канд. техн. наук
НТУУ «КПИ», г. Киев.
ОБ ОДНОМ ПОДХОДЕ К РАСЧЕТУ ПЕРЕХОДНЫХ
ПРОЦЕССОВ В СЛОЖНЫХ ПОЛУПРОВОДНИКОВЫХ И
СВЕРХПРОВОДНИКОВЫХ ВЕНТИЛЬНЫХ
ПРЕОБРАЗОВАТЕЛЯХ
Описаний та проаналізований підхід до розв’язування за-
дач динаміки складних напівпровідникових та надпровіднико-
вих вентильних перетворювачів на основі декомпозиції схеми,
що розраховується, і застосування інтегральних рівнянь як ди-
намічних моделей утворених лінійних підсхем. Показана ефе-
ктивність даного підходу, що обумовлена згладжуючими влас-
тивостями інтегральних моделей та обчислювальною економі-
чністю відповідних чисельних алгоритмів.
Ключові слова: комп’ютерне моделювання, вентильні пере-
творювачі, динамічні моделі, інтегральні рівняння, декомпозиція
Введение. Задачи анализа динамики устройств преобразова-
тельной техники в современных энергетических полупроводниковых
(ПП) и сверхпроводниковых (СП) объектах и системах является од-
ной из наиболее сложных. Безальтернативным путем к эффективному
решению данной задачи является применение методов и средств
компьютерного моделирования. Компьютеризация научно-исследова-
тельских и проектно-конструкторских работ все больше внедряется в
практику разработки новых ПП и СП преобразователей, оказывает
большое влияние на совершенствование методов научных исследова-
© А. А. Верлань, 2010
|