Virtual Machine Placement Problem Research Articles

Optimizing Cloud Computing Resources: An Energy Efficient Multi-QoS Factor-Based VM Placement Strategy

Cloud computing is experiencing unprecedented demand, offering scalable and flexible resources for a wide range of applications. However, this surge in demand has raised concerns about energy consumption and the need for environmentally sustainable solutions. Green computing has emerged as a critical consideration in this context. Virtual Machine Placement (VMP) is a key component of optimizing cloud resources, aiming to allocate virtual machines efficiently while minimizing energy consumption, cost, and load balancing. This paper addresses the VMP problem by introducing a novel approach based on multifactor optimization, specifically the Diversity Constraint Digger Snake Optimizer (DCD-SO). It offers an innovative perspective on optimizing virtual machine placement by considering energy efficiency, load balancing, and resource utilization simultaneously with the aim to reduce VM migration count, time and cost. Proposed method provides a more comprehensive and sustainable solution, aligning with the principles of green computing. Through extensive simulations and experiments, we have rigorously evaluated the performance of DCD-SO in comparison to traditional optimization techniques such as Particle Swarm Optimization (PSO) and Snake Optimization. In our analysis of actual cloud environments, we compared the results of our method with existing state-of-the-art techniques. Result outcomes determine showed that proposed approach has reduced migration count of 5 and 3 for scheduling 42VMs and 84VMs on 16 and 32 host units respectively than traditional MOGANS, GA-S, GA-N and GA-NN methods. This comprehensive evaluation reinforces the effectiveness and practicality of our approach in addressing the intricate challenges of Virtual Machine Placement (VMP) in dynamic cloud computing settings. As cloud computing continues to evolve, our study contributes to more sustainable and efficient resource management, addressing both current demands and future needs.

Multiple objectives dynamic VM placement for application service availability in cloud networks

Ensuring application service availability is a critical aspect of delivering quality cloud computing services. However, placing virtual machines (VMs) on computing servers to provision these services can present significant challenges, particularly in terms of meeting the requirements of application service providers. In this paper, we present a framework that addresses the NP-hard dynamic VM placement problem in order to optimize application availability in cloud computing paradigm. The problem is modeled as an integer nonlinear programming (INLP) optimization with multiple objectives and constraints. The framework comprises three major modules that use optimization methods and algorithms to determine the most effective VM placement strategy in cases of application deployment, failure, and scaling. Our primary goals are to minimize power consumption, resource waste, and server failures while also ensuring that application availability requirements are met. We compare our proposed heuristic VM placement solution with three related algorithms from the literature and find that it outperforms them in several key areas. Our solution is able to admit more applications, reduce power consumption, and increase CPU and RAM utilization of the servers. Moreover, we use a deep learning method that has high accuracy and low error loss to predict application task failures, allowing for proactive protection actions to reduce service outage. Overall, our framework provides a comprehensive solution by optimizing dynamic VM placement. Therefore, the framework can improve the quality of cloud computing services and enhance the experience for users.

Deep Reinforcement Learning for Workload Prediction in Federated Cloud Environments.

The Federated Cloud Computing (FCC) paradigm provides scalability advantages to Cloud Service Providers (CSP) in preserving their Service Level Agreement (SLA) as opposed to single Data Centers (DC). However, existing research has primarily focused on Virtual Machine (VM) placement, with less emphasis on energy efficiency and SLA adherence. In this paper, we propose a novel solution, Federated Cloud Workload Prediction with Deep Q-Learning (FEDQWP). Our solution addresses the complex VM placement problem, energy efficiency, and SLA preservation, making it comprehensive and beneficial for CSPs. By leveraging the capabilities of deep learning, our FEDQWP model extracts underlying patterns and optimizes resource allocation. Real-world workloads are extensively evaluated to demonstrate the efficacy of our approach compared to existing solutions. The results show that our DQL model outperforms other algorithms in terms of CPU utilization, migration time, finished tasks, energy consumption, and SLA violations. Specifically, our QLearning model achieves efficient CPU utilization with a median value of 29.02, completes migrations in an average of 0.31 units, finishes an average of 699 tasks, consumes the least energy with an average of 1.85 kWh, and exhibits the lowest number of SLA violations with an average of 0.03 violations proportionally. These quantitative results highlight the superiority of our proposed method in optimizing performance in FCC environments.

Progressive-fidelity computation of the genetic algorithm for energy-efficient virtual machine placement in cloud data centers

Energy efficiency is a critical issue in the management and operation of data centers, which form the backbone of cloud computing. Virtual machine placement has a significant impact on the energy efficiency of virtualized data centers. Among various methods to solve the virtual-machine placement problem, the genetic algorithm has been well accepted for its quality of solution. However, it is computationally demanding largely due to the complex form of fitness function, limiting its applications in data centers. To enhance the computational efficiency of the genetic algorithm while maintaining its quality of solution, a progressive-fidelity approach is developed in this paper for genetic-algorithm computation. It starts with a low-fidelity genetic algorithm with a simple fitness function. Then, for solution refinement, it switches to a medium-fidelity genetic algorithm with a more complicated fitness function. Finally, it progresses to the fine tuning of solution through a high-fidelity genetic algorithm with the energy consumption of data centers as fitness function. Heuristics are presented for the adaptive switching of genetic-algorithm computation from low fidelity to medium fidelity and finally to high fidelity. Experiments show that compared with the standard genetic algorithm of high fidelity, our progressive-fidelity approach of genetic algorithm computation is 50% faster for large-scale data centers while maintaining similar quality of solution in terms of the energy consumption of data centers.

Virtual Machine Replica Placement Using a Multiobjective Genetic Algorithm

Virtual machine (VM) replication is a critical task in any cloud computing platform to ensure the availability of the cloud service for the end user. In this task, one primary VM resides on a physical machine (PM) and one or more replicas reside on separate PMs. In cloud computing, VM placement (VMP) is a well-studied problem in terms of different goals, such as power consumption reduction. The VMP problem can be solved by using heuristics, namely, first-fit and meta-heuristics such as the genetic algorithm. Despite extensive research into the VMP problem, there are few works that consider VM replication when choosing a VMP. In this context, we proposed studying the problem of optimal VMP considering VM replication requirements. The proposed work frames the problem at hand as a multiobjective problem and adapts a nondominated sorting genetic algorithm (NSGA-III) to address the problem. VM replicas’ placement should consider several dimensions such as the geographical distance between the PM hosting the primary VM and the other PMs hosting the replicas. In addition, to this end, the proposed model aims to minimize (1) power consumption, (2) performance degradation, and (3) the distance between the PMs hosting the primary VM and its replica(s). The proposed method is thoroughly tested on a variety of computing environments with various heterogeneous VMs and PMs, including compute-intensive and memory-intensive environments. The obtained results illustrate the performance disparity between the adapted NSGA-III and MOEA/D methods and other methods of comparison, including heuristic and meta-heuristic approaches, with NSGA-III outperforming other comparison methods. For instance, in memory-intensive and in heterogeneous environments, the NSGA-III method’s performance was superior to the first-fit, next-fit, best-fit, PSO, and MOEA/D methods by 58%, 62%, 64%, 55%, and 31%, respectively.

A Residual Resource Fitness-Based Genetic Algorithm for a Fog-Level Virtual Machine Placement for Green Smart City Services

Energy efficient information and communication technology (ICT) infrastructure at all levels of a city’s edifice constitutes a core requirement within the sustainable development goals. The ICT infrastructure of smart cities can be considered in three levels, namely the cloud layer infrastructure, devices/sensing layer infrastructure, and fog layer infrastructure at the edge of the network. Efficiency of a data-centre’s energy infrastructure is significantly affected by the placement of virtual machines (VMs) within the data-centre facility. This research establishes the virtual machine (VM) placement problem as an optimisation problem, and due to its adaptability for such complicated search issues, this paper applies the genetic algorithm (GA) towards the VM placement problem solution. When allocating or reallocating a VM, there is a large quantity of unused resources that might be used, however these resources are inefficiently spread over several different active physical machines (PMs). This study aims to increase the data-centre’s efficiency in terms of both energy usage and time spent on maintenance, and introduces a novel fitness function to streamline the process of computing the fitness function in GAs, which is the most computationally intensive component in a GA. A standard GA and first fit decreasing GA (FFD-GA) are applied on benchmark datasets to compare their relative performances. Experimental results obtained using data from Google data-centres demonstrate that the proposed FFD-GA saves around 8% more energy than a standard GA while reducing the computational overhead by approximately 66%.

Towards optimal virtual machine placement methods in cloud environments

The rapid growth of cloud services for hosting applications in the scientific, commercial, web, and social networks has led to enormous growth in the number of large-scale data centers. By shifting the costs of data center maintenance, hardware, and software from customers to service providers using a pay-as-you-go policy, service providers and customers are benefited. On the other hand, the massive growth of data centers has been accompanied by challenges that have limited the boundaries of this technology. Thus, researchers in this field tend to focus on eliminating these limitations. Since virtualization is at the core of cloud computing, allocating Virtual Machines (VMs) to physical hosts in the Infrastructure as a Service layer (IaaS) is one of the most significant challenges. Nonetheless, the VM allocation problem is a combinatorial optimization problem that is known to be NP-Hard. In this paper, we presented a comprehensive analysis of virtual machine placement problem and outlined different approaches to solving it. This paper aims to provide insight into the challenges and issues for recent virtual machine placement strategies. The current study aims to comprehensively classify the physical resource allocation for VMs by overviewing available trends.

Two-Phase Virtual Machine Placement in Cloud Computing Data Centers Using Extreme Learning Machine Prediction-Based Triggering Method

Background: Two-phase Optimization of Virtual Machine Placement (VMP) Problem considers both the Online Incremental VMP (iVMP) phase in which the new arrival of dynamic requests of Virtual Machines VMs are attended to and the Offline VMP reconfiguration (VMPr) phase that performs placement recalculation. In the two-phase scheme, the first part of the two-phase approach is the iVMP, where virtual machines (VMs) can be built, changed, or destroyed at runtime. While the second phase focuses on raising the standard of solutions produced by the iVMP, several studies have been done in different literature to solve the VMP problem. However, the methods used tend to be over-forecast and have long runs of a linear trend. This affects the prediction and produces a less optimal solution. Objective: The following four objective functions are optimized using the proposed Extreme Learning Machine Prediction-Based Triggering Method for Virtual Machine Placement in Cloud Computing Datacenters in Two-Phases, which combines the advantages of both online (dynamic) and static (offline) VMP formulations: the length of the reconfiguration process, the amount of energy used, the way resources are used, and the financial expenses. This study suggests a brand-new strategy for deciding when to start the VMP reconfiguration phase. Results: The Method provides more accuracy to the predicted requests as well as reduces the total economic penalties for service Level Agreement(SLA) violations. An experimental comparison with the existing approach is conducted utilizing 400 cases. Conclusion: The results demonstrated that, in comparison to the benchmark approach, the proposed work obtained a minimum cost function with a 10.5% improvement

Dynamic Virtual Machine Allocation in Cloud Computing Using Elephant Herd Optimization Scheme

Cloud computing is a computing technology that is expeditiously evolving. Cloud is a type of distributed computing system that provides a scalable computational resource on demand including storage, processing power and applications as a service via Internet. Cloud computing, with the assistance of virtualization, allows for transparent data and service sharing across cloud users, as well as access to thousands of machines in a single event. Virtual machine (VM) allocation is a difficult job in virtualization that is governed as an important aspect of VM migration. This process is performed to discover the optimum way to place VMs on physical machines (PMs) since it has clear implications for resource usage, energy efficiency, and performance of several applications, among other things. Hence an efficient VM placement problem is required. This paper presents a VM allocation technique based on the elephant herd optimization scheme. The proposed method is evaluated using real-time workload traces and the empirical results show that the proposed method reduces energy consumption, and maximizes resource utilization when compared to the existing methods.

An energy-efficient topology-aware virtual machine placement in Cloud Datacenters: A multi-objective discrete JAYA optimization

By the advent of cloud computing and the numerous related web applications, data center networks (DCNs) are becoming complex to provide all-to-all communications between underlying devices; it is done by spending a huge amount of electricity consumption. Energy consumption management is the first class concern for cloud providers in this energy hungry devices and also for the green computing goals. In the large DCs, the power management of hundreds or even many thousands idle switches can be a promising approach toward overall cost reduction. The virtual machine placement (VMP) scheme which is aware of both VMs affinity and underlying network topology for co-hosting dependent VMs as physically near as possible and lowering down power state of idle devices can enhance sustainability objectives. On the other hand, resource wastage lowers system utilization which leads more physical server usage causing more power consumption as a consequence. To address the issue, this paper presents an energy-efficient topology-aware VM placement scheme in the cloud DCs which is formulated to a multi-objective optimization problem with power consumption and resource wastage minimization perspective. To deal with this combinatorial problem, an advanced multi-objective discrete version of JAYA (MOD-JAYA) algorithm is presented since the search space of VMP is discrete in nature. The proposed algorithm is validated by intensively variable circumstances and simulations upon conducted scenarios. The simulation results prove the superiority of the proposed advanced MOD-JAYA algorithm in solving VMP problem in comparison with other existing schemes in terms of prominent assessment metrics.

Infrastructure-efficient Virtual-Machine Placement and Workload Assignment in Cooperative Edge-Cloud Computing Over Backhaul Networks

Edge computing provides computing capability at close-user proximity to reduce service latency for end users. To improve the efficiency of edge computing infrastructures, geographically-distributed edge datacenters can co-work with each other and with cloud datacenters, forming a new paradigm referred to as cooperative edge-cloud computing. In this context, applications typically run on a virtual machine (VM) that can be replicated at multiple sites, and thus user traffic can be served at all the sites where corresponding VMs reside. For the performance of many applications, latency is a critical parameter. In this work, taking applications latencies as the primary constraint, we model the problem of VM placement and workload assignment as a mixed integer linear program and develop heuristic algorithms accordingly. The goal is to minimize the consumption of information technology (IT) infrastructures for placing VMs in cooperative edge-cloud computing, while meeting the heterogeneous latency demands of different applications. Some preliminary results indicate that edge datacenters resource efficiency can be optimized by proper cross-site VM placement and workload re-direction.

Improving Virtual Machine Migration Effects in Cloud Computing Environments Using Depth First Inspired Opportunity Exploration

The cloud platform has established itself as the de-facto standard in IT outsourcing. This is resulting in large-scale migration of infrastructure and development platforms from in-house to cloud service providers. Many recent proposals on cloud platforms have addressed several issues that appeared on the cloud horizon. VM placement (VMP) has been a serious concern when it comes to placement of VMs after migration or VM reallocation. Most of the recent works have lacked multiple VM placement (MVMP) problem instances. A recently researched idea of MVMP through depth first opportunistic exploration (DFOE) is proposed in this paper. The performance of MVMP is compared with existing single VM placement benchmark algorithm. Improvement in terms of number of VM migrations, energy consumption, and VM reallocation is reported through simulation of real-time load scenario. Cloud environments can benefit from MVMP and improve operating margins in terms of power saving and load balancing.

Dynamic Resource Allocation Based on Priority in Various Data Centers Custom-Based Waiting Queue Technique in Cloud Computing

For delivering the cloud services over the internet, cloud computing has become proficient infrastructural model for hosting cloud services. Server virtualization is key technology that enables cloud computing as a service, which authorizes dynamic sharing of physical resources. Virtualization introduces the problem of virtual machine placement that increases the overheads in load balancing. Existing infrastructure needs the strategy for the VM Placement as it may create poor allocation and load balancing issues. In most of the cases, due to lack of input parameters physical machines are partially loaded that creates issue of fragmentation which leads to in sufficient resources that causes more utilization of physical machines in any infrastructure. We did extensive survey in the said domain and found that, In load balancing approach, when VM place mentis done without measuring its lifetime, that creates fragments on PM. So we propose dynamic priority based spill over technique and add the concept of short life/long life container for solving the fragmentation issue.

Accelerated computation of the genetic algorithm for energy-efficient virtual machine placement in data centers

Energy efficiency is a critical issue in the management and operation of cloud data centers, which form the backbone of cloud computing. Virtual machine (VM) placement has a significant impact on energy-efficiency improvement for virtualized data centers. Among various methods to solve the VM-placement problem, the genetic algorithm (GA) has been well accepted for the quality of its solution. However, GA is also computationally demanding, particularly in the computation of its fitness function. This limits its application in large-scale systems or specific scenarios where a fast VM-placement solution of good quality is required. Our analysis in this paper reveals that the execution time of the standard GA is mostly consumed in the computation of its fitness function. Therefore, this paper designs a data structure extended from a previous study to reduce the complexity of the fitness computation from quadratic to linear one with respect to the input size of the VM-placement problem. Incorporating with this data structure, an alternative fitness function is proposed to reduce the number of instructions significantly, further improving the execution-time performance of GA. Experimental studies show that our approach achieves 11 times acceleration of GA computation for energy-efficient VM placement in large-scale data centers with about 1500 physical machines in size.

Resource Optimization in Cloud Data Centers Using Particle Swarm Optimization

To meet the ever-growing demand for computational resources, it is mandatory to have the best resource allocation algorithm. In this paper, Particle Swarm Optimization (PSO) algorithm is used to address the resource optimization problem. Particle Swarm Optimization is suitable for continuous data optimization, to use in discrete data as in the case of Virtual Machine placement we need to fine-tune some of the parameters in Particle Swarm Optimization. The Virtual Machine placement problem is addressed by our proposed model called Improved Particle Swarm Optimization (IM-PSO), where the main aim is to maximize the utilization of resources in the cloud datacenter. The obtained results show that the proposed algorithm provides an optimized solution when compared to the existing algorithms.

Multi-Objective Virtual Machine Placement using Order Exchange and Migration Ant Colony System Algorithm

Order Exchange and Migration Ant Colony System(OEMACS) and Ant Colony System OEMACS approach based on ACS that finds solutions by combining order exchange and migration local search strategies, was developed after examining the ant colony system's (ACS) promising performance for combinatorial issues. The ACO algorithm, which is regarded as best approach solving for virtual machine placement(VMP) problem, is capable of significantly reducing the number of active servers from a optimization standpoint. These bio-inspired algorithms help in solving VMP problem. Using the pheromone deposition method, artificial ants are guided to the feasible solution in ACO. It also arranges virtual machines in a way that reduces resource waste. This strategy is used on servers with homogeneous and heterogeneous VM sizes. The VMP is implemented using the ACO algorithm and OEMACS, and a comparison is drawn between them that shows their efficiency in terms of execution time and Energy Conserved.

Utilization aware and network I/O intensive virtual machine placement policies for cloud data center

High-performance computing in the cloud environment uses ample virtual resources, which in turn require physical infrastructures provided by cloud service providers (CSPs). Naturally, CSPs would like to place virtual machines (VM) in a cost-effective way satisfying the resource requirement of the VMs and the capacity constraints of the hosts. Such consideration has led to the well known virtual machine placement (VMP) problem. In this paper, we consider a variant of the VMP, taking into account the communication among the VMs. We introduce the concept of Virtual Cluster, made up of VMs communicating among themselves. It is desirable to place the VMs of a cluster close to each other and thus reduce the communication cost. The objective for the Virtual Cluster Placement (VCP) problem is to reduce the communication cost. For this, we have to consider the network topology of the data center. In this paper, we have proposed some heuristics for both kinds of placement problems (VMP as well as VCP) and given Integer Linear Programming (ILP) formulations. We have also presented algorithms based on Semidefinite Programming (SDP) and meta-heuristic based on Genetic Algorithms. We have compared the performance of proposed heuristics with other existing works and the optimal solutions obtained from ILPs.

A Study on Transfer Functions of Binary Particle Swarm Optimization for Energy-Efficient VM Placement

Cloud computing has emerged as the backbone of the IT industry for infrastructural support. In cloud computing, resources are virtualized in form of Virtual Machines which eventually is mapped to physical infrastructure. Energy-efficient virtual machine placement is an important problem in cloud computing and has attracted the attention of researchers in recent. As virtual machine placement is an NP-hard problem, meta-heuristics have often been applied vastly for this. In one of our earlier works, Modified Binary Particle Swarm Optimization algorithm has been applied for the VM placement. It was observed therein that the transfer function, which plays an important role to obtain an optima, does not completely avoid the problem of local optima. Therefore, in this work, we have studied the behavior of eight different transfer functions towards this property. For this, energy-efficient VM placement problem is modelled as multi-objective optimization problem and Binary Particle Swarm Optimization is applied. The study is done by simulation and their statistical analysis.

Dynamic placement of virtual machines using an improved multi‐objective teaching‐learning based optimization algorithm in cloud

AbstractRecently, cloud computing is growing rapidly and contributing to the realization of other technologies. Cloud data centers use a lot of energy to host applications, which leads to high operating costs and increased carbon dioxide emissions into the environment. Dynamic consolidation of virtual machines (VMs) into the minimum number of physical servers is an efficient approach to managing energy consumption in cloud. Virtual machines placement (VMP) is an important problem in the proper consolidation of VMs and is the most common way to improve resource utilization. In VMP problem, VMs are consolidated to minimize the number of active physical servers. This consolidation is done using migration of VMs. After placement, the VMs execute on selected physical servers and the underloaded physical servers are off to optimize energy consumption. Basically, the purpose of VMP is to allocate a set of VMs to a subset of physical servers, taking into account some objectives such as reducing energy consumption and violating the service level agreement (SLA). In this article, an improved teaching‐learning based optimization (TLBO) algorithm is formulated to solve VMP as a multi‐objective problem, which we call VMP‐TLBO. VMP‐TLBO can perform optimal placement of migrated VMs to physical servers with the purpose of reducing energy consumption and SLA violation. VMP‐TLBO is implemented in MATLAB and the experimental results show that proposed algorithm does not violate SLA and compared to the best equivalence algorithm (ie, PAPSO), it improves energy consumption and SLA violation by 1.8% and 5.6%, respectively. In addition, VMP‐TLBO consolidates migrated VMs into the minimum number of physical servers to minimize the number of overloaded hosts as much as possible.

Energy-efficient virtual machine placement in data centres via an accelerated Genetic Algorithm with improved fitness computation

Energy efficiency is a critical issue in data centre management, which is the foundation for cloud computing. The VM placement has a considerable impact on a data centre's energy efficiency and resource utilisation. The assignment of VMs to PMs is an NP-hard problem without an easy way to find an optimal solution, particularly in large-scale data centres. In this study, the VM placement problem is formulated as a constrained optimisation problem. The Genetic Algorithm (GA) is a suitable method for solving this problem in terms of the quality of the solution. However, GA is time-consuming to obtain an optimal solution in the large scale optimisation problem. Therefore, this paper focuses on accelerated GA for energy-efficient VM placement. As the most time-consuming element of the GA is the calculation of its fitness function, this paper simplifies this calculation through a new fitness function in GA. Simulation results of small-, medium-, and large-scale data centres demonstrate that our accelerated GA is faster than the standard GA and gives better quality of solution than the First Fit Decreasing (FFD) algorithm, respectively. The findings of our GA with the new fitness function reveal an 8% energy saving for our GA compared to FFD and a 66% reduction in our GA execution time compared to the standard GA with standard energy formula as a fitness function. The number of generations in our GA is reduced by about 50% in comparison with the standard GA. Moreover, we started with 3000 PMs in the large-scale dataset, and only 1086 PMs were actually used after running our GA. Therefore, we may switch off far more PMs for energy savings from our GA results than those from the standard GA.