Background: Cloud computing is becoming prominent as it makes use of a model, in which
consumer must pay according to its usage, as described in various patents. The user pays as per his demand
and requirement. There are several issues faced by Datacenters for efficient scheduling of the
workload. Task implementation failure is a very common property of cloud computing environment and
is not given much attention in different scheduling techniques. In this research article, we propose a
technique which takes the heed of defects using the concepts of autonomous computing.
Methods: To assure the services related to quality to the consumers, an important task is to plot the
available resources according to the jobs. Clustering is used where the events are logged and the ranges
for CPU, Memory and Bandwidth are set as well. Fault tracing methodology is used with the help of
which, the violations are checked, and requests are scheduled according to the results obtained by comparing
the request with the cluster data.
Result: In our proposed model (FSBD), we have tried to overcome the shortcomings of the existing
techniques. The damage caused to the Service level agreement (SLA's) is less and at the same time, execution
time is reduced and performance is enhanced. The experimental result shows that the computing
which is sensitive towards the faults supports flexible contingency which is favourable in terms of lesser
SLA violation, better time to respond (up to 4.46 ms) and shorter execution time. The proposed approach,
when compared to the traditional approach of fault aware pattern recognition, showed better results
in terms of forbearance of faults. Also, the number of failed cloudlets is significantly lesser in
FSBD (4.9%) as compared to the traditional Round Robin (40%) approach.
Conclusion: As is evident from the results shown, we can conclude that faults are able to cause huge
damage to SLA's and lead to a lower performance in cloud computing. Further, we compared a system
having no fault with the system having faulty behaviour to quantify the damage. After justifying the seriousness
of the damage caused due to the fault, the proposed model recognizes the pattern of the
behaviours of each component of the virtual machine, thereby identifying the problematic Virtual machine
(VM) in the system. Post identification, very little number of requests is being allocated to the
faulty VMs to keep SLA intact. Experiments conducted for validating the architecture clearly showed
the effectiveness of the scheme.