Cloud computing infrastructure has been evolving as a cost-effective platform for providing computational resources in the form of high-performance computing as a service(HPCaaS)to users for executing HPC applications...Cloud computing infrastructure has been evolving as a cost-effective platform for providing computational resources in the form of high-performance computing as a service(HPCaaS)to users for executing HPC applications.However,the broader use of the Cloud services,the rapid increase in the size,and the capacity of Cloud data centers bring a remarkable rise in energy consumption leading to a significant rise in the system provider expenses and carbon emissions in the environment.Besides this,users have become more demanding in terms of Quality-of-service(QoS)expectations in terms of execution time,budget cost,utilization,and makespan.This situation calls for the design of task scheduling policy,which ensures efficient task sequencing and allocation of computing resources to tasks to meet the trade-off between QoS promises and service provider requirements.Moreover,the task scheduling in the Cloud is a prevalent NP-Hard problem.Motivated by these concerns,this paper introduces and implements a QoS-aware Energy-Efficient Scheduling policy called as CSPSO,for scheduling tasks in Cloud systems to reduce the energy consumption of cloud resources and minimize the makespan of workload.The proposed multi-objective CSPSO policy hybridizes the search qualities of two robust metaheuristics viz.cuckoo search(CS)and particle swarm optimization(PSO)to overcome the slow convergence and lack of diversity of standard CS algorithm.A fitness-aware resource allocation(FARA)heuristic was developed and used by the proposed policy to allocate resources to tasks efficiently.A velocity update mechanism for cuckoo individuals is designed and incorporated in the proposed CSPSO policy.Further,the proposed scheduling policy has been implemented in the CloudSim simulator and tested with real supercomputing workload traces.The comparative analysis validated that the proposed scheduling policy can produce efficient schedules with better performance over other well-known heuristics and meta-heuristics scheduling policies.展开更多
Vendor lock-in can occur at any layer of the cloud stack-Infrastructure,Platform,and Software-as-a-service.This paper covers the vendor lock-in issue at Platform as a Service(PaaS)level where applications can be creat...Vendor lock-in can occur at any layer of the cloud stack-Infrastructure,Platform,and Software-as-a-service.This paper covers the vendor lock-in issue at Platform as a Service(PaaS)level where applications can be created,deployed,and managed without worrying about the underlying infrastructure.These applications and their persisted data on one PaaS provider are not easy to port to another provider.To overcome this issue,we propose a middleware to abstract and make the database services as cloud-agnostic.The middleware supports several SQL and NoSQL data stores that can be hosted and ported among disparate PaaS providers.It facilitates the developers with data portability and data migration among relational and NoSQL-based cloud databases.NoSQL databases are fundamental to endure Big Data applications as they support the handling of an enormous volume of highly variable data while assuring fault tolerance,availability,and scalability.The implementation of the middleware depicts that using it alleviates the efforts of rewriting the application code while changing the backend database system.A working protocol of a migration tool has been developed using this middleware to facilitate the migration of the database(move existing data from a database on one cloud to a new database even on a different cloud).Although the middleware adds some overhead compared to the native code for the cloud services being used,the experimental evaluation on Twitter(a Big Data application)data set,proves this overhead is negligible.展开更多
文摘Cloud computing infrastructure has been evolving as a cost-effective platform for providing computational resources in the form of high-performance computing as a service(HPCaaS)to users for executing HPC applications.However,the broader use of the Cloud services,the rapid increase in the size,and the capacity of Cloud data centers bring a remarkable rise in energy consumption leading to a significant rise in the system provider expenses and carbon emissions in the environment.Besides this,users have become more demanding in terms of Quality-of-service(QoS)expectations in terms of execution time,budget cost,utilization,and makespan.This situation calls for the design of task scheduling policy,which ensures efficient task sequencing and allocation of computing resources to tasks to meet the trade-off between QoS promises and service provider requirements.Moreover,the task scheduling in the Cloud is a prevalent NP-Hard problem.Motivated by these concerns,this paper introduces and implements a QoS-aware Energy-Efficient Scheduling policy called as CSPSO,for scheduling tasks in Cloud systems to reduce the energy consumption of cloud resources and minimize the makespan of workload.The proposed multi-objective CSPSO policy hybridizes the search qualities of two robust metaheuristics viz.cuckoo search(CS)and particle swarm optimization(PSO)to overcome the slow convergence and lack of diversity of standard CS algorithm.A fitness-aware resource allocation(FARA)heuristic was developed and used by the proposed policy to allocate resources to tasks efficiently.A velocity update mechanism for cuckoo individuals is designed and incorporated in the proposed CSPSO policy.Further,the proposed scheduling policy has been implemented in the CloudSim simulator and tested with real supercomputing workload traces.The comparative analysis validated that the proposed scheduling policy can produce efficient schedules with better performance over other well-known heuristics and meta-heuristics scheduling policies.
文摘Vendor lock-in can occur at any layer of the cloud stack-Infrastructure,Platform,and Software-as-a-service.This paper covers the vendor lock-in issue at Platform as a Service(PaaS)level where applications can be created,deployed,and managed without worrying about the underlying infrastructure.These applications and their persisted data on one PaaS provider are not easy to port to another provider.To overcome this issue,we propose a middleware to abstract and make the database services as cloud-agnostic.The middleware supports several SQL and NoSQL data stores that can be hosted and ported among disparate PaaS providers.It facilitates the developers with data portability and data migration among relational and NoSQL-based cloud databases.NoSQL databases are fundamental to endure Big Data applications as they support the handling of an enormous volume of highly variable data while assuring fault tolerance,availability,and scalability.The implementation of the middleware depicts that using it alleviates the efforts of rewriting the application code while changing the backend database system.A working protocol of a migration tool has been developed using this middleware to facilitate the migration of the database(move existing data from a database on one cloud to a new database even on a different cloud).Although the middleware adds some overhead compared to the native code for the cloud services being used,the experimental evaluation on Twitter(a Big Data application)data set,proves this overhead is negligible.
