Multi-objective optimization technique for resource allocation and task scheduling in vehicular cloud architecture: A hybrid adaptive nature inspired approach

Midya, Sadip; Roy, Asmita; Majumder, Koushik; Phadikar, Santanu

doi:10.1016/j.jnca.2017.11.016

Cited by 95 publications

(58 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Midya et al 43 have proposed an optimized resource allocation and task scheduling method to respond to a large number of submitted task requests while considering the Quality of Service (QoS). The task requests are mapped to cloud resources among the three cloud layers.…”

Section: Related Workmentioning

confidence: 99%

A fuzzy logic‐based method for solving the scheduling problem in the cloud environments using a non‐dominated sorted algorithm

Wakil

Badfar

Dehghani

et al. 2019

Concurrency and Computation

View full text Add to dashboard Cite

Cloud computing as a new model of delivering IT services on the Internet has attained high attention recently. In this new paradigm, efficient service management causes the high quality of provided services. Scheduling as one of the most important duties of service management is a key problem in cloud computing that affects the total system performance. In most cases, the meta-heuristic methods are used for optimizing the scheduling issues instead of traditional methods. One of the influential evolutionary algorithms for optimizing the complicated problems is a non-dominated sorting particle swarm optimization (NSPSO) technique. In this paper, we propose a meta-heuristic technique using the NSPSO model for decreasing total cost and consumed total time. Furthermore, fuzzy set theory is applied to select the best solution.Simulation results have indicated that the efficiency of NSPSO is improved. In the many types of experiment, the proposed NSPSO algorithm was appropriate to keep a good spread of solutions and good converge. In addition, the diversity preserving mechanism applied in NSPSO has improvement against the other two investigated algorithms. KEYWORDScloud computing, multi-objective optimization, particle swarm optimization algorithm, task scheduling INTRODUCTIONCloud computing as an innovative distributed computing can provide dynamic resources, which are highly virtualized. 1,2 In addition, cloud providers deliver their services (such as software, hardware, platform, and storage) over the Internet. 3,4 Therefore, there are no shrink-wrapped boxes containing discs or hardware for users to buy. The cloud providers typically charge monthly recurring fees based on usage. 5-7 Many benefits, including the cost reduction and flexibility, make cloud computing to be superior technology in computing. 8 Due to the numerous benefits of cloud computing, many users have been attracted to use cloud-based services. 9,10 There are some issues in the cloud computing that must be addressed, such as resource discovery, 11,12 trust evaluation, 13-15 task, 16-18 resource allocation, 19-21 and so on. 22 Among them, task scheduling has a primary role in reaching the efficiency of distributed computing systems such as clouds and grids. [23][24][25] In the cloud systems, a task scheduler allocates the submitted tasks to proper resources for performing. 26-28 From the creation of cloud computing, task scheduling has gained significant attention, and many researchers have investigated many methods based on artificial intelligence-based algorithms to solve it. 29 It is responsible for finding potential cloud resources for satisfying the users' requests in the cloud environment. The main aim of task scheduler is decreasing the total cost, completion time and the computational complexity. 30,31 However, most of the existing research has focused on a single objective task scheduling in cloud systems. However, in real cases, more than one factor should be considered. 29 Since task scheduling is an NP-hard issue, many meta-heuristic algo...

show abstract

Section: Related Workmentioning

confidence: 99%

A fuzzy logic‐based method for solving the scheduling problem in the cloud environments using a non‐dominated sorted algorithm

Wakil

Badfar

Dehghani

et al. 2019

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Zuo et al applied this self‐adaptive PSO algorithm in cloud environment for optimized resource allocation. However, Midya et al showed that applying self‐adaptive PSO in vehicular environment for resource allocation fails to give the desired result. So, Midya et al proposed a hybrid adaptive PSO method, which combines GA with adaptive PSO for optimized resource allocation in vehicular cloud environment.…”

Section: Related Workmentioning

confidence: 99%

“…The task of the VM service scheduler is to allocate resources to a task residing in the request vector from the VM vector optimally while maintaining the required QoS of the clients. Many resource allocation strategies are researched upon . The decision is taken based on one of these algorithms to allocate the resource. f. Migration scheduler .…”

Section: Proposed System Architecture Of Vehicular Cloud Networkmentioning

confidence: 99%

“…Several task requests arrive from mobile or vehicular drivers at the CSE. VMs are provisioned for these requested tasks from either vehicular clouds or roadside cloudlet by the CSE based on the optimized resource allocation algorithm . However, pertaining to some inherent characteristics of vehicular nodes such as high mobility, frequent change in network topology, and various available communication technology, migration is required to maintain the following in vehicular network …”

Section: Description Of the Problemmentioning

confidence: 99%

“…Many resource allocation strategies are researched upon. [29][30][31][32][33] The decision is taken based on one of these algorithms to allocate the resource.…”

Section: Architectural Framework Of Client Service Enginementioning

confidence: 99%

See 2 more Smart Citations

An adaptive resource placement policy by optimizing live VM migration for ITS applications in vehicular cloud network

Midya

Roy

Majumder

et al. 2019

Trans Emerging Tel Tech

Self Cite

View full text Add to dashboard Cite

Vehicular cloud computing (VCC) is a promising approach that uses cloud computing techniques in vehicular environment to execute smart applications. Vehicular environment is characterized by high mobility. This requires the services executed by a vehicular resource in a vehicular cloud to be migrated before it leaves a network. Migration is also required when a service‐requesting vehicle has to leave a network before its request is executed. Moreover, to balance the network load, virtual machine (VM) migration is desired as, at times, a single physical host may become overloaded. In this work, we propose an adaptive resource placement policy by optimizing live VM migration process in vehicular cloud network. The Pareto optimal mapping of migrating VMs to a physical host is carried out using a hybrid optimized algorithm, which is the combination of particle swarm optimization and genetic algorithm. The optimization is done by maximizing a fitness function that is developed by considering significant quality‐of‐service (QoS) parameters, such as network latency, migration delay, power consumption, and vehicular mobility. These QoS parameters are mathematically formulated in view of a vehicular network. The proposed algorithm reduces migration latency, transmission latency, and service delay. It also distributes the load among the available physical hosts within a cloud system, thus reducing the average wait time for each cloud user. Simulation results exhibit significant decrease in waiting time, service delay, and migration delay. It is also shown that the proposed algorithm reduces total power consumption of the system.

show abstract

Task Scheduling in Cloud Environments

Ramezani¹,

Naderpour²,

Taheri³

et al. 2020

Evolutionary Computation in Scheduling

View full text Add to dashboard Cite

Multi-objective optimization technique for resource allocation and task scheduling in vehicular cloud architecture: A hybrid adaptive nature inspired approach

Cited by 95 publications

References 40 publications

A fuzzy logic‐based method for solving the scheduling problem in the cloud environments using a non‐dominated sorted algorithm

A fuzzy logic‐based method for solving the scheduling problem in the cloud environments using a non‐dominated sorted algorithm

An adaptive resource placement policy by optimizing live VM migration for ITS applications in vehicular cloud network

Task Scheduling in Cloud Environments

Contact Info

Product

Resources

About