SLA Violation Detection Model and SLA Assured Service Brokering (SLaB) in Multi-Cloud Architecture

Cloud brokering facilitates Cloud Service Users (CSUs) to find cloud services
according to their requirements. In the current practice, CSUs or
Cloud Service Brokers (CSBs) select cloud services according to Service
Level Agreement (SLA) committed by Cloud Service Providers (CSPs) in
their website. In our observation, it is found that most of the CSPs do not
fulfill the service commitment mentioned in the SLA agreement. Verified
cloud service performances against their SLA commitment of CSPs provide
an additional trust on CSBs to recommend services to the CSUs. In this
thesis work, we propose a SLA assured service-brokering framework, which
considers both committed and delivered SLA by CSPs in cloud service recommendation
to the users. For the evaluation of the performance of CSPs, two evaluation techniques:
Heat Map and Intuinistic Fuzzy Logic (IFL) are proposed, which include
both directly measurable and non-measurable parameters in the performance
evaluation CSPs. These two techniques are implemented using real
data measured from CSPs. Both performance evaluation techniques rank/-
sort CSPs according to their service performances. The result shows that
Heat Map technique is more transparent and consistent in CSP performance
evaluation than IFL technique. As cloud computing is location independent
technology, CSPs should respect the current regulatory framework in delivering
services to the users. In this work, regulatory compliance status of the CSPs is also analyzed and visualized in performance heat map table to provide legal status of CSPs. Moreover, missing points in their terms of service
and SLA document are analyzed and recommended to add in the contract
document. In the revised European data protection regulation (GPDR),
data protection impact assessment (DPIA) is going to be mandatory for
all organizations/tools. The decision recommendation tool developed using
above mentioned evaluation techniques may cause potential harm to individuals
in assessing data from multiple CSPs. So, DPIA is carried out to
assess the potential harm/risks to individuals due to decision recommendation
tool and necessary precaution to be taken in decision recommendation
tool to minimize possible data privacy risks.
To help CSUs in easy decision making to select cloud services from multi-cloud
environment, service pattern analysis techniques and prediction of
future performance behavior of CSPs are also proposed in the thesis work.
Prediction patterns and error measurement shows that automatic prediction
methods can be implemented for short time period as well as longer time
period.