You are on page 1of 6

IEEE CONECCT2014 1569822161

An Econometric based Model for Re source S carcity


Problem in Cloud Computing
Gaurav B aranwal Deo Prakash Vidyarthi
School of Computer and Systems Sciences School of Computer and Systems Sciences
lawaharlal Nehru University lawaharlal Nehru University
New Delhi, India New Delhi, India
gaurav l l_scs@jnu.ac.in dpv@mail.jnu.ac.in

Abstract-Resource provIsioning in Cloud computing is an There might be another possibility that users are not able to
important problem as the resources are scarce. Better utilization fully utilize the resources allocated to them. If provider is able
of the existing unutilized resources may solve the future resource to know the percentage of underutilized resources, provider
scarcity problem. To decide, how much percentage of unutilized may use the concept of redistribution implying the concept of
allocated resources the Cloud manager can take back to solve the distributive justice in order to satisfy its customer and to keep
problem of scarcity of resource in future, an econometric model its reputation intact. Provider may take some part (portion) of
of distributive j ustice is identified and mapped to resource unutilized resources back from the users and allocate them to
redistribution in Cloud computing. The proposed model uses a
the requesting client. Suppose a provider does not have enough
Probit model to get the value of coefficient which helps to
resources to accept a request, provider does a survey of its
determine the percentage of unutilized allocated resources to be
clients to identify those clients that are utilizing the allocated
taken back. Data is increasing at the enormous rate warranting
mass storage. Thus, Cloud storage has been considered an
resources below a defined threshold. Provider may give some
important scarce resource. The proposed model focuses on the lucrative offer to such clients in terms of cost slashing etc. if
Cloud storage as a resource. It is assumed that service provider they agree to leave some of their resources. That allows the
must reserve certain amount of resource to accept sharply provider in getting some resources back to be allocated to the
increased resource request. The proposed model also identifies requesting clients. In Cloud computing, resource reservation
this constraint and proposes a model of distributive j ustice that and on-demand plans are two provisioning plan which are
addresses this. Experimental results reveal the efficacy of the offered by Cloud providers for computing resources [2] .
proposed model. Reservation plan is a static Cloud resource provisioning policy.
In this plan, user rent computing resources for a long time and
Keywords-Cloud, econometric model, probit model, Cloud providers charge price one time (e.g. one year). Quick scale up
storage. or quick scale down is not possible in this plan. In on-demand
plan, providers charge by pay-per-use basis (e.g. 1 day).
I. INTRODUCTION
Therefore, with on-demand plan, when consumers need
Most of the internet connected devices use the Cloud resources for the fluctuated and unpredictable demands,
technology knowingly or unknowingly now days. Cloud consumers can dynamically provision resources. If provider
computing provides a platform for using computing resources gets some resources from reservation-plan-users and allocates
like CPU, bandwidth, memory etc. via internet without owning these resources to the on-demand-plan-requesting clients, it
these resources on a pay per-use basis. Thus, there is no need to will increase the provider' s profit and will meet the users
buy the required computing resources to run any application. demand also. It is to note that with the on-demand plan, the
Imperative is to rent the computing resources that too only for price for resources is costlier than that of the reservation plan
the time period in which the resources are needed. Cloud [2] .
resources are offered in form of a service on a payment basis.
This paper has identified the problem of resource scarcity
Many services of Yahoo, Microsoft and Google etc. have been
and proposed a model to solve this problem based on
designed to act as Cloud from time to time. Cloud users feel of
econometric model. Considering the importance of the Data
infmite resources in the Cloud, which is just an illusion. As
centre management, Cloud storage has been considered an
both the number of users and data are increasing at the rapid
important and scarce resource and the proposed model focuses
pace, scarcity of resources is bound to happen in future due to
on the Cloud storage as a resource.
limited resources. Service provider' s reputation may be
affected in the Cloud service market, if the provider declines a The paper is organized as follows. Section II mentions the
request due to limitation of resources. How to schedule these related work. Section III highlights the motivation behind this
scarce resources amongst the growing number of Cloud users work. Section IV details the proposed model based which is
are an important and a big challenge for the Cloud service based on Econometric model. Section V mentions the
providers. In order to satisfy the requests, provider may opt for experimental evaluation of the proposed model by inferring the
Cloud federation i.e. renting resources from some other results obtained. Section VI concludes the work.
providers [ 1 ] . Provider may have to periodically rent the
resources as and when the resources fall short of.
II. RELATED WORK using redistribution technique, proposed model gets some
percentage of unused allocated resources back and then Cloud
The demand-&-supply model of resources in distributed
provider may assign these resources to the new users.
system is analogous to demand-&-supply model of commodity
in economics. Resources provider in former is same as the III. MOTIVATION
commodity supplier that supplies variety of resources such as
CPU, memory, disks etc. for its consumer. Consumers, of Many countries devote large budget for redistribution of
aforementioned resources, in distributed system resemble the income though governmental redistribution is costly. There
commodity buyers in economics. Consumers have to pay a fee should be some knowledge about how much resources society
to acquire resources in order to meet its demand of resources is ready to pay for distributive justice. Giacmo Corneo and
[3 ] . Some resource allocation strategy, based on economics Christina M. Fong in [9], proposed an econometric model
model, has been proposed in the literatures that are listed as which helps to estimate the willingness of individual to pay for
follows. distributive justice. There may be different attitude for
redistribution within groups of individual with similar market
To investigate the effectiveness of resource allocation income. This work [9] assumes that people give preference to
strategy based on the economics model for the benefits to the equity, i.e. for living in a society where "one gets what one
providers, consumers and society, a grid economy is simulated deserves, and deserves what one gets". Measures of
in [4] , in which providers and consumers pursue their own individual' s support or individual' s opposition for
interests and resulting effects on system welfare is measured. It redistribution, fairness of market outcomes, and pre-fiscal
is found that economics based strategies fares well. Since in a incomes are only required for estimation of this model. It
grid system number of consumers, their resource demand and derives a formula
resource supply can be highly dynamic, a model is suggested in
[5] that consider an environment in which both providers and
consumers act as selfish agents. A distributed negotiation
mechanism is introduced where agents negotiate for both that defines maximum amount an individual is willing to
contract price and de-commitment penalty, allowing de­ pay for distributive justice from the fiscal data and estimated

scalars, W denotes the willingness to pay for justice, C is


commitment from contracts at some cost. The work in [6] also coefficients of a Probit model, where a and f3 are non-negative
considers problem of dynamic changes in the resource
availability over time. A market-based model for allocation and
consumption of a numeraire good.
pricing mechanism of resources is employed. Service consumer
and provider agents place their bid and ask prices using k­ IV. THE PROPSED MODEL
pricing (introduced in Schnizler et al. (2008) [7] for double­
sided combinatorial auctions) which sets the transaction price Fig. 1 suggests a one-to-one mapping of econometric model
individually for each matched buyer-service provider pair. to resource redistribution in Cloud computing.
These mechanisms are adaptive enough to meet the I Numcra i rc good IE )1 R esou rce in cloud I
customers/service provider' s requirement and constraints set by
the bundled services. An algorithm for j ob scheduling based on Social d i strihution Resource a l l ocat ion
Berger model is proposed in [3 ] . Expectation state is the base
for Berger model of distributive justice. It is assumed that users Just distribution of i ncome J ust d istribution of re sources
are able to judge that whether assignment of resources is fair or
not by the distribution relations comparison between itself and
other ordinary person in referential structure. In the j ob
scheduling process, dual fairness constraints is established by User's ut i l i ty i n cl oud
the algorithm. A combinatorial auction-based allocation
method to solve virtual machine allocation problem in Cloud is Figure 1 : Mapping between Cloud and econometric model for distributive
proposed in [8] . The proposed methods are CA-LP and CA­ justice
GREEDY, the two extensions of two existing combinatorial
auction mechanism. Experiments reveal that the allocation A broad vision about the structure of a future market-based
efficiency can be significantly improved by combinatorial Cloud [ 1 0] has been given in fig. 2. It shows a market-based
auction-based mechanisms while generating higher revenue for architecture which consists of provider' s coordinator service
the Cloud providers. and consumer' s brokering service supporting utility-driven
internetworking of Clouds. Job of Cloud broker is to identify
Application of different economic based resource allocation suitable Cloud service providers through the Cloud exchange.
schemes for ensuring even distribution of (computing) Cloud exchange acts as a market maker bringing together
resources in grid computing, distributed computing, and Cloud service providers, customers, and coordinator component.
computing have been well pursued in different scenario. So, it Cloud coordinator runs at each data centre which keeps track of
can be observed that economics-based resource allocation load on data centre and negotiates with other Cloud providers
schemes may be beneficial for provider and customer in a for exporting Cloud services across multiple data centre to
Cloud environment. handle the peak in demands. It also monitors the application
In the proposed work, economics based method execution and oversees that agreed SLAs are delivered [ 1 1 ] .
'redistribution of wealth' to establish a just society is used. By

2
user according to provider, and the redistribution Re of
unutilized resource. Let fairness f be 1 if ratio of unutilized
resource to total allocated resource to a particular user is less
than a threshold t and 0 otherwise, where 0 < t S; 1 . For
example, assume that a user has 1 00 units of resources, 40
units of unutilized resources and t = 0. 3 . Here, ratio (40/1 00)
is greater than t and according to provider, allocation of
resources to this user is unfair; i.e. f = O .
Similarly, let Re b e 1 i f the provider redistributes unutilized
resource and 0 otherwise. It is asswned that justice can be done
if either allocation of resources is fair and provider does not

redistributes unutilized resource as shown in table l .


redistribute or allocation of resource is unfair and provider
Figure 2: Market-based Cloud architecture
TABLE I : RELATIONSHIP BETWEEN FAIRNES S , REDISTRIBUTION AND
In the proposed work, it is asswned that coordinator will act PERCEPTION OF JUST DISTRIBUTION
as a Cloud storage manager on behalf of the provider. In case
f (fairness) Re (redistribution) J (just distribution)
of scarcity of resources, coordinator gives an offer to clients
that if they are willing to leave some of their unutilized 0 0 -I
resources. If yes, costs currently being paid will be slashed. 0 1 I
This way, coordinator will get some resources back and
allocate those resources to the requesting clients. I 0 I
1 1 -1
A. Resource Provisioning Model
Cloud users derive utility from the unutilized resource, R ,
and from the perception o f a just distribution o f resource, } . As indicated from the table, } = 1 � f =1= Re and} = -1 �
} = 1 if individual thinks that there i s just allocation of f = Re.
resources in Cloud and - 1 otherwise i.e. when individual
thinks that the allocation is unjust. It is assumed that there is no From the above relationships, utility can b e expressed a s a
partial just or partial unjust. Keeping other factors of utility function of f and Re as follows :
constant, it is assumed that unjust distribution of resources

URe = alogRRe + {J C 1 - 2 f)
Utility with redistribution
decreases a user's utility. Here, it is assumed that utility (U) is

U = alogR + {J} .
cardinally measurable and unit comparable and takes the form (6)

(1) under Re = 1, where RRe denote unutilized allocated resource


with redistribution and as
Where a and {J are non-negative scalars. I f a user thinks that
there is injustice i.e. } = - 1 , utility can be written as

UN = alogRN + {J (2f - 1)
Utility without redistribution
U = alogR - {J (2) (7)

and cloud will be a just cloud. Let W denote the willingness to


Now, if user sacrifices some resources, utility will not change under Re = 0, where RN denotes unutilized allocated resource
without redistribution. One can easily check equivalence of
leave unutilized resources for justice, i.e. the maximal above discussed definition of justice with ( 1 ) . For example,
unutilized resource a user is willing to sacrifice in order to suppose f = O . If there is no redistribution of resources,
establish a just Cloud i.e. } = 1 . Utility equation can now be Re = O ; then, j = - l . Since U = UN , ifRe = O , we obtain

U = a 1 0 g (R - W) + {J
written as {J} = -{J . The three remaining cases including first one are
(3) checked in table 2

Since utility is constant (i.e. does not change), from above two TABLE 2: RELATIONSHIP BETWEEN FAIRNES S , REDISTRIBUTION, PERCEPTION

a logCR - W) + {J
equations (2) and (3 ) we obtain, OF JUST DISTRIBUTION AND UTILITY

= alogR - {J (4) f Re (redistribution) J (just distribution) U �J


(fairness) (utility)

UN -fJ
Solving the equation (4), we get

W = 1 - exp
0 0 -I

[ (-�P) ] R (5) 0 I I URe fJ


I 0 I UN fJ
Hence, each user is willing to sacrifice a maximal fraction
1- exp (-�P) of its unutilized resources to obtain justice. 1 1 -I URe -fJ

Two factors, responsible for lack or existence of


distributive justice, are the fairness f of resource allocation to a

3
In this theoretical model, it is assumed that if redistribution of Therefore,
unutilized resource provides higher utility to the users then
only they support redistribution. 2f3 ( 1 - r ) Bf
a 2 AR u

((r -l)Bt)
Now for mathematical framework, it can be expressed in terms

URe = alogRRe + f3 ( 1 - 2f) + X'YRe + ERe


of a random utility model. Let utility with redistribution is Inserting above expressions into (2) gives

� - exp
(8) j =
R = 1 2AR u
(13)

UN = alogRN + f3 (2f - 1) + X'YN + EN


and utility without redistribution is
This gives the quantified value o f distributive justice with
(9) constant progressivity policy of redistribution.
where x is a vector of observable characteristics of storage and B. Algorithm Description
the fust element of x is normalized to 1 . ERe and EN are error
terms. It is necessary that coordinator must reserve certain amount
of storage (e.g. 20% of total storage) in its Cloud storage to
It has already been discussed that users support redistribution accept sharply increased storage request instantly without
when they get higher utility. In probabilistic form it can be waiting reclamation. Let us assume that reserved storage is T l
written as and a new threshold i s T2 where T2 > T l . W e assume that
whenever provider will have reserved storage less than T l e.g.
( 1 0)
T l - x, coordinator will rent x from other providers and will
Where, d is a dummy variable which equals 1 if add this rented x to its reserved storage. If Provider' s
redistribution of resources is supported by user and 0 Unallocated Storage (PUAS) i s less than T2, coordinator will
otherwise. use the proposed model to get some unused resources back
before going for allocation of reserved storage. Algorithm for
Let R u denote the user's unutilized resources. In the the above discussed logic is given in fig. 3 .
absence of redistribution, RN = R u . In the presence of
redistribution, unutilized resource depends on the functional input: Request for storage (m) by end user
Output: Allocation of memory space
Step 1 : Cloud coordinator receives the request.
form of the redistributive scheme. In this work, we consider the
model of governmental redistribution with constant Step 2: Cloud coordinator allocates the memory space (m) to user.
progressivity discussed in [9] . It is because, in constant Step 3: If (PUAS<T l )
progressivity, user with more unutilized resource can return Cloud coordinator rent allocated storage (m) from other provider,
higher percentage of the unutilized resource than those with Add m to its unallocated space, i.e.
less unutilized resource. PUAS = PUAS + m.
Step 4: Tf (PUAS<T2)
The considered redistributive scheme is as below, Cloud coordinator uses proposed model,
Collects unused allocated storage (m') from users,
RRe = sR� (1 1) Add m' to its unallocated storage, i.e.
PUAS = PUAS + m' .
and R N = R u , a s before. The parameter r i s the residual Step 5 : Stop
progression coefficient:
Figure 3 : Resource Provisioning Algorithm
dlogRRe
r= ---
=
=
dlogRN Suppose provider has 1 00 units of storage and Tl 20 and

=
T2 30 and at any instance provider has 28 unit unallocated
Here r > 0 and governmental redistribution of income IS
storage (PUAS 28), coordinator will go with the proposed
more progressive for smaller value of r. model to get some unused allocated storage back. If at any
Inserting the value of RN and RRe ' from ( 1 1 ) in (8) and (9), and instance provider has 1 5 units of unallocated storage, which is

r r
less than Tl and as well as T2, coordinator will go with the

P [ d = 1 I R u, [, x] = P [ a log(s) + (r - l) a 10g(R u) +
substituting the resulting equations into ( 1 0), one obtains
proposed model as well as for Cloud federation.

f3 (2 - 4f) + x ' y + E > 0 I R u, [, x] ( 1 2) V. EXPERIMENTAL EVALUATION

is must to have probit estimates ( Bf and AR u are probit


Above equation can be estimated as a binary probit model. Let To solve the resource scarcity problem using this model, it
Sf (JBf and A R u (JAR u be the estimates of the coefficients
= =

estimates, as discussed in section IVA) to decide that how


on f and 10g (R u ) , respectively, where Bf and AR u denote
much unused allocated resources Cloud coordinator may take
probit estimates and (J denotes the variance of the error term of back. To get the value of the estimates, it is necessary to have
the probit equation. data set containing unused allocated memory of user, whether
Hence, user is ready to leave some unused allocated memory or not,
fairness of allocation of resources to the user and
a (r - 1) = (JAR u characteristics of storage (e.g. type of Cloud storage network)
and used by individual user. It is assumed that provider has well
informed its customer about redistribution policy and also

4
provider has all customer related information like unused 5) Storage in Tier Context (tier) : Generally, three types of
allocated space of a particular user. tier storage are considered in Cloud; Tier l , Tier2 and Tier3 .
Different storage providers offer storage as a service with Tierl storage is most scalable, most reliable and highest
different characteristics. For example, as a service user of performing storage, generally used for business critical
AT&T Synaptic Storage, one can replicate two copies remotely applications. Tier2 storage is used for unstructured data,
but as a client of Peerl CloudeOne Storage, it is possible to backup, and multimedia etc. Tier3 provides low performance
have one ' s data replicated at any or all of the 1 7 data centers. with high scalable capacity, so is used for long term storage for
Nirvanix Cloud Storage offers one node, two nodes and three archival and offline storage. For three types of tiered storage,
nodes replication. Thus, characteristics of storage vary from one integer number between 1 and 3 inclusively has been
provider to provider. For experimental purposes here, we have
randomly assigned to each user.
considered types of user, replication of node, tiered memory,
6) Number of child account (ace) and supported
number of child account and number of supported application.
But these characteristics are not fixed for all service providers; application (app) : It is possible for more than one account to
provider can change characteristic parameter according to their access the same Cloud storage. For example, in a university, an
need easily in the proposed model. administrator can provide child account to each student to
access online library. Similarly, Cloud storage can be accessed
A. Parameters Used
by more than one application. For this, a number between 1 0
The proposed model uses various parameters that have and 1 000 has been randomly assigned to each user for number
been deliberated as follows : of supported child account and also between 5 and 1 00 to each

7) Dummy Variable (d) : A dummy variable d is considered


1) Type of user (Type) : Types of cloud users are user for number of supported application.
increasing day by day. These users may belong to different
fields like media, education etc. Also, users of one field can be in the model which equals 1 if the user supports redistribution
more active than users of the other field. Thus, it is possible to of unused allocated resource and 0 otherwise. Just like fairness,
categorize users on the basis of their activeness. In this work, o or 1 to each user has been assigned randomly for supporting

four types of users are assumed according to their affiliation in redistribution.


the different groups. These groups are field of education, This way, values of different variables for each user is
health-service, media & entertainment and financial sectors. randomly generated. Then 1 00 instances of 1 00 users, 1 00
These types have been referenced by randomly assigning one instances of 200 users, 1 00 instances of 3 00 users up to 1 000
integer value 1 ,2,3 ,4 to each user. users have been created. For each instance, we calculated the
2) Unused Allocated Storage (VAS) : Provider offers value of Bf /AR u (where Bf and AR u are probit estimates, as

r=
storage as a service to the users. It is possible that users will not discussed in section IV.A). Substituting the estimate
be utilizing all resources assigned to them by the provider. This of Bf /AR u as well as 0.85 into equation ( 1 3), an estimated
work assumes that storage is provided in GB . Different types value of j for each instance is obtained.
of users may have different units of unused allocated storage. B. Analysis ofExperimental Results
In the experiment, a number has been randomly assigned
Results have been analyzed by carrying out the experiment
between 1 0 and 1 000 to type 1 and type2 users, between 2 to
as below.
1 00 to type3 and type4 users. Suppose a user gets a number
Experiment 1 :
288, it means this user has 288GB unused allocated storage. Experiment 1 observes the posItIve response for varying
3) Fairness ofAllocation ofResource (f) : The term (t) has number of users. In fig. 4, it is shown that how many positive
already been discussed in section IV.A. Value of f can be 0 or responses U > 0) out of 1 00 instances, for different number of
1 . Here, without loss of generosity, we have assigned randomly users varying from 1 00 users to 1 000 users, are obtained. It is
o or 1 to each user for fairness of allocation of resources. If a found that number of positive response out of 1 00 instances
user has f= 1 , it means allocation of storage for this user is fair for fixed numbers of users vary irregularly.
N u m b e r of p o s i t i ve response Vs N u mber of u sers
otherwise unfair.
4) Replication of Nodes (RoN) : "Performance is highly w ,-----

50 +---�----------__��____--_.__
affected by the speed-of-light latency, TCP latency, (both of
which are directly correlated to circuit distance between user
40
and files), as well as packet loss. By placing the files closer to N u mber of
positive 30
the user, both speed-of-light latency and TCP latency are response
10
minimized. Packet loss is also minimized because the
probability of packet loss increases as distance increases" [ 1 2].
In this work, it is assumed that provider is providing three o ...."--
... ----"---�---'-------"------"-
1 00 2 00 300 400 ,00 GOO 1 00 BOO 900 1 00 U
types of node replication to place the data closer to the user. N u m ber of users
For three types of node replication, one integer number
between 1 and 3 inclusively has been randomly assigned to Figure 4: Number of positive response out of 1 00 instances
each user.

5
Experiment 2: VI. CONCLUSION
I n this, for the goodness of fit (i.e. measurement o f In this paper, problem of future resource scarcity in Cloud
discrepancy between expected value and observed value) o f is identified and a mathematical model is proposed that is
the proposed model, percentage of correctly predicted measure based on an econometric model to solve the identified problem.
(by comparing the actual value with predicted value) for each For the validity of the model, characteristics of cloud storage
instance has been calculated. Average of percent correctly have been observed from different available storage service
predicted measure of 1 00 instances of 1 00 users has been providers and on a randomly generated data set. It is possible
taken which has been repeated for instances of 200 users and that provider can change the parameters easily according to his
so on (fig. 5). It is observed that as nwnbers of users is need. By observing different results it is concluded that number
increasing, average of percent correctly predicted measure is of positive response and sum of positive response depends on a
decreasing. Notable is that this value is always greater than particular instance and do not depend on the number of users.
50%. This paper considers only the Data storage. Cloud resources
Ave rage goo d n e s s of f i t measu re N u m b e r of
,------
Vs are not limited to storage as other important resources also
users exist in Cloud such as CPU, memory, bandwidth etc. Future
62 work may address other Cloud resources and it will be possible
bO to apply this model on other Cloud resources.
58

• • •
Averag@
good n ess o f f i t 56 REFERENCES

• • •
m e a s u re
of 100 ' 4

• • •
[I] B. Rochwerger, D. Breitgand, E. Levy, A. Galis, K. Nagin, I. M.
Llorente, R. Montero, Y. Wolfsthal, E. Elmroth, 1. Caceres, M. Ben­
Instances
52
' 0
Yehuda, W. Emmerich, F. Galan, 'The reservoir model and architecture
48

1 00 2 00 JOO 400 500 6 00 700 BOO 900 1 000


for open federated Cloud computing", IBM Journal of Research and
N u m ber of u s e rs
Development 53 (4), Pages 1 - 1 1 , 2009.
[2] Sivadon Chaisiri, Bu-Sung Lee, Dusit Niyato, "Optimization of
Figure 5: Average goodness of fit measure of 100 instances Resource Provisioning Cost in Cloud Computing", IEEE Transactions
on Services Computing, Vol. 5, No. 2, April-June 2012.
Experiment 3 : [3] Baomin Xua, Chunyan Zhaob, Enzhao Hua, Bin Hu, "Job scheduling
algorithm based on Berger model in Cloud environment", Advances in
The value o f j for different values o f r has been estimated. Engineering Software, Vol. 42, Pages 4 1 9-425, 20 1 1 .
Since percent correctly predicted measure does not depend on [4] Kevin L . Mills, Christopher Dabrowski, "Can Economics-based
r, it will be fixed for different values of r . All instance in Resource Allocation Prove Effective in a Computation Marketplace?",
which we get positive response for r =.85, we also get positive Journal of Grid Computing, Vol. 6, Pages 291-3 1 1 , 2008.
response for different values of r . For the instances with [5] Bo An, Victor Lesser, David Irwin, Michael Zink, "Automated
Negotiation with Decommitment for Dynamic Resource Allocation in
negative response ; we get the negative response for different Cloud Computing", Proc. of 9th Int. Conf. on Autonomous Agents and
values of r. Multi-agent Systems (AAMAS 20 ( 0), van der Hoek, Kaminka,
To compare the results with different values ofr, we took Lesperance, Luck and Sen (eds.), Toronto, Canada, Pages 98 1 -988,
sum of values of j for each instance of 1 00 users with positive May 2010.
response and repeated the same with 200 users, 300 users and [6] Yee-Ming Chen, Hsin-Mei Yeh, "Autonomous Adaptive Agents for
Market-based Resource Allocation Of Cloud Computing", Proceedings
so on. It has been shown in fig. 6. It is observed, from this of the Ninth International Conference on Machine Learning and
experiment, that as the value of r is increasing, value of swn Cybernetics, Qingdao, Pages 2760-2764, 14 July 2010.
of positive response is decreasing for fixed number of users. It [7] B. Schnizler, D. Neumann, D. Veit, C. Weinhardt, 'Trading grid
is also observed that just like the nwnber of positive response services a multi-attribute combinatorial approach", European Journal of
Operational Research 1 87 (3), Pages 943-96 1 ,2008.
sum of positive response for 1 00 instances with fixed nwnber
[8] Sharrukh Zaman, Daniel Grosu, "Combinatorial auction-based
of users also vary irregularly. So it is clear that sum of positive allocation of virtual machine instances in Clouds", Journal of Parallel
response also does not depend on the number of users rather it and Distributed Computing, Vol. 73,Pages 495-508, 20 1 3 .
depends on a particular instance. [9] Giacomo Corneo, Christina M. Fong, "What's the monetary value of
Su m of positive r e p o n s e Vs Coeffi cient of
distributive justice?", Journal of Public Economics, Vol. 92, Pages 289-
308, 2008.
res i d u a l prog res s i o n [ 1 0] R. Buyya, C. S . Yeo, S . Venugopal, J. Broberg, T. Brandic, "Cloud
30 ,-
---
Computing and Emerging IT Platforms: Vision, Hype, and Reality for
. 1 W users
Delivering Computing as the 5th Utility", Future Generation Computer
. 2 00 us.ers
Systems , Vol. 25, Pages 599-6 1 6, 2009 .
• 3{U lI�el!l
[11] R. Buyya, R. Ranj an and R. N. Calheiros, "Modeling and simulation of
. 4 00 users
Sum of positive 1 � scalable Cloud computing environments and the CloudSim Toolkit:
response . SOO uw.!>
challenges and opportunities", Proceedings of the seventh high
10 . 600 users performance computing and simulation conference (HPCS 2009,
. /(Xl UM�f!> ISBN :978-1 -4244-49071), Leipzig, Germany. New York, USA: IEEE
• SOO users Press; June 2 1-24, 2009 .
o
0.5 0.55 0.6 0.65 0.7 0.75 0.8 0.85 0.9 0.95 900 u�ef'" [12] M. Staimer "The compelling price/performance economics of the
coeffic ient of residual progression . 1 000 users. Nirvanix storage delivery network versus in-house storage", Report by
Dragon Slayer Consulting, 2008.
Figure 6: Sum of positive response of 1 00 instances

You might also like