Data Center Load Research Articles

Virtual Machine Placement via Bin Packing in Cloud Data Centers

With the increasing size of cloud data centers, the number of users and virtual machines (VMs) increases rapidly. The requests of users are entertained by VMs residing on physical servers. The dramatic growth of internet services results in unbalanced network resources. Resource management is an important factor for the performance of a cloud. Various techniques are used to manage the resources of a cloud efficiently. VM-consolidation is an intelligent and efficient strategy to balance the load of cloud data centers. VM-placement is an important subproblem of the VM-consolidation problem that needs to be resolved. The basic objective of VM-placement is to minimize the utilization rate of physical machines (PMs). VM-placement is used to save energy and cost. An enhanced levy-based particle swarm optimization algorithm with variable sized bin packing (PSOLBP) is proposed for solving the VM-placement problem. Moreover, the best-fit strategy is also used with the variable sized bin packing problem (VSBPP). Simulations are done to authenticate the adaptivity of the proposed algorithm. Three algorithms are implemented in Matlab. The given algorithm is compared with simple particle swarm optimization (PSO) and a hybrid of levy flight and particle swarm optimization (LFPSO). The proposed algorithm efficiently minimized the number of running PMs. VM-consolidation is an NP-hard problem, however, the proposed algorithm outperformed the other two algorithms.

Flow-Aware Routing and Forwarding for SDN Scalability in Wireless Data Centers

Software-defined networking (SDN) paradigm and high-speed wireless technologies have been widely adopted by industries to improve the performance of data center networks. In SDN, a switch commonly uses ternary content addressable memory (TCAM) to store rules for fast flow table lookup. However, due to the limited TCAM entries, rule replacement will occur frequently when traffic load in data centers is heavy. This issue will be more serious when flow characteristics in data centers are diverse. Although wireless transmissions can benefit for reducing TCAM usage, we observe that routing and forwarding designs without considering the flow characteristics will result in rule replacement storm in switches and significantly harm the SDN scalability for wireless data centers. As a result, switches will issue massive flow setup requests which cannot be processed by an SDN controller in real time. This paper studies the SDN scalability problem with the objective of minimizing the number of flow setup requests under the hybrid architecture with wired and wireless links. We propose a routing and forwarding algorithm with the consideration of flow characteristics to tackle the problem. A series of simulation results agrees our observations and shows that our algorithm outperforms two well-known solutions for wired data centers and three approaches for wireless data centers. The results also provide useful insights and guidelines for designing SDN-based wireless data centers.

Load monitoring and system-traffic-aware live VM migration-based load balancing in cloud data center using graph theoretic solutions

This paper proposes solutions to monitor the load and to balance the load of cloud data center. The proposed solutions work in two phases and graph theoretical concepts are applied in both phases. In the first phase, cloud data center is modeled as a network graph. This network graph is augmented with minimum dominating set concept of graph theory for monitoring its load. For constructing minimum dominating set, this paper proposes a new variant of minimum dominating set (V-MDS) algorithm and is compared with existing construction algorithms proposed by Rooji and Fomin. The V-MDS approach of querying cloud data center load information is compared with Central monitor approach. The second phase focuses on system and network-aware live virtual machine migration for load balancing cloud data center. For this, a new system and traffic-aware live VM migration for load balancing (ST-LVM-LB) algorithm is proposed and is compared with existing benchmarked algorithms dynamic management algorithm (DMA) and Sandpiper. To study the performance of the proposed algorithms, CloudSim3.0.3 simulator is used. The experimental results show that, V-MDS algorithm takes quadratic time complexity, whereas Rooji and Fomin algorithms take exponential time complexity. Then the V-MDS approach for querying Cloud Data Center load information is compared with the Central monitor approach and the experimental result shows that the proposed approach reduces the number of message updates by half than the Central monitor approach. The experimental results show on load balancing that the developed ST-LVM-LB algorithm triggers lesser Virtual Machine migrations, takes lesser time and migration cost to migrate with minimum network overhead. Thus the proposed algorithms improve the service delivery performance of cloud data center by incorporating graph theoretical solutions in monitoring and balancing the load.

Orchestrating Data as a Services-Based Computing and Communication Model for Information-Centric Internet of Things

With the explosive growth of the Internet of Things, the gap between the rapidly growing demands of data rates and the existing bandwidth-limited network infrastructures has become increasingly prominent, leading to network congestion, high latency, and energy consumption and deterioration of the user’s quality of service. To narrow this gap, an orchestrating data as services-based computing and communication (ODAS-CC) model is proposed to reduce the data rate, latency, and energy consumption for information-centric Internet of Things. The main innovations of the ODAS-CC model that differ from previous strategies are as follows. First, the services-based network architecture proposed in this paper can run on the current network effectively. In the proposed architecture, the data are orchestrated to services when they route to the data center; therefore, the data are transmitted after the service conversion, thereby forming a service-based network, which can greatly reduce the amount of data transmitted in the network, latency, and energy consumption. Second, a service conversion is performed in the process of routing such that the user’s service request can be satisfied locally, thereby improving the user’s quality of experience. Third, based on the ODAS-CC model, the performance evaluation model for energy consumption, latency, and load is provided in detail, and the performance of the ODAS-CC model is evaluated comprehensively. The theoretical analyses and experimental results show that compared with the previous approach, the ODAS-CC model can reduce the network traffic, the average latency of data upload by 26.3%, the service latency by up to 30.1%, and the data center load, thereby reducing energy consumption from 20.0% to 30.0%.

Method of Resource Estimation Based on QoS in Edge Computing

With the development of Internet of Things, the number of network devices is increasing, and the cloud data center load increases; some delay‐sensitive services cannot be responded to timely, which results in a decreased quality of service (QoS). In this paper, we propose a method of resource estimation based on QoS in edge computing to solve this problem. Firstly, the resources are classified and matched according to the weighted Euclidean distance similarity. The penalty factor and Grey incidence matrix are introduced to correct the similarity matching function. Then, we use regression‐Markov chain prediction method to analyze the change of the load state of the candidate resources and select the suitable resource. Finally, we analyze the precision and recall of the matching method through simulation experiment, validate the effectiveness of the matching method, and prove that regression‐Markov chain prediction method can improve the prediction accuracy.

Load Balancing in Data Center Networks: A Survey

Data center networks usually employ the scale-out model to provide high bisection bandwidth for applications. A large amount of data is required to be transferred frequently between servers across multiple paths. However, traditional load balancing algorithms like equal-cost multi-path routing are not suitable for rapidly varying traffic in data center networks. Based on the special data center topologies and traffic characteristics, researchers have recently proposed some novel traffic scheduling mechanisms to balance traffic. In this paper, we present a comprehensive survey of recent solutions for load balancing in data center networks. First, recently proposed data center network topologies and the studies of traffic characteristics are introduced. Second, the definition of the load-balancing problem is described. Third, we analyze the differences between data center load balancing mechanisms and traditional Internet traffic scheduling. Then, we present an in-depth overview of recent data center load balancing mechanisms. Finally, we analyze the performance of these solutions and discuss future research directions.

Utilizing data center waste heat in district heating – Impacts on energy efficiency and prospects for low-temperature district heating networks

Data centers seek solutions to increase energy efficiency and lower costs by novel methods. Waste heat utilization is considered to be one of the major trends in the near future, especially in the Nordic countries, where heat demand is high. In this paper, waste heat utilization was analyzed from the perspectives of both the data center and district heating network operators. Timing of the data center waste heat production was considered based on an existing data center load profile. For the district heating network operator, the system level effects of increased waste heat utilization were quantified by simulating district heating production in the city of Espoo, Finland, with actual plant and heat demand data for 2013 and 2015. Results showed that with high shares of waste heat in the district heating system, i.e. 20–60 MW, the system level operational cost savings were 0.6–7.3% in the case study. Utilizing waste heat decreased utilization hours of both combined heat and power plants and heat-only boilers. The analysis showed that pricing of the procured waste heat affects the utilization level of waste heat, but operational hours of waste heat utilization were over 95% in all scenarios.

Load-Balancing Based Cross-Layer Elastic Resource Allocation in Mobile Cloud

The paper proposes a hybrid mobile cloud computing system, in which mobile applications can use different resources or services in local cloud and remote public cloud such as computation, storage and bandwidth. The cross-layer load-balancing based mobile cloud resource allocation optimization is proposed. The proposed approach augments local cloud service pools with public cloud to increase the probability of meeting the service level agreements. Our problem is divided by public cloud service allocation and local cloud service allocation, which is achieved by public cloud supplier, local cloud agent and the mobile user. The system status information is used in the hybrid mobile cloud computing system such as the preferences of mobile applications, energy, server load in cloud datacenter to improve resource utilization and quality of experience of mobile user. Therefore, the system status of hybrid mobile cloud is monitored continuously. The mathematical model of the system and optimization problem is given. The system design of load-balancing based cross-layer mobile cloud resource allocation is also proposed. Through extensive experiments, this paper evaluates our algorithm and other approaches from the literature under different conditions. The results of the experiments show a performance improvement when compared to the approaches from the literature.

A system for providing load‐aware virtual network service in a software‐defined data center network

SummaryVirtual networks may be used in a cloud data center to provide personalized networking services for the applications running in the cloud. As the virtual networks come to the data center and leave it, the data center network load may become unbalanced where some parts of the data center has accommodated many virtual networks while a few virtual networks are mapped to other parts of the data center. This situation may lead to packet loss and service level agreement violations in an oversubscribed data center. This unbalanced state of the load in data center can be resolved by migration of virtual networks from overloaded parts of the data center to places where the load is in a lower level.This paper presents implementation details of the prototype of a system that provides virtual networking service in a cloud data center and focuses primarily on virtual network migration as a means for controlling the state of load in data center. Experimental results show that the system has an acceptable performance in reducing the packet loss ratio and keeping the load in a balanced state.

Experimental Failure Analysis of a Rear Door Heat Exchanger With Localized Containment

The accelerated growth of heat load in high-density data centers presents challenges to the design of effective cooling solutions. Both energy efficiency and the information technology (IT) equipment reliability are key requirements. Localized hybrid air-water cooling systems such as Rear Door Heat eXchangers (RDHXs) are an effective means to achieve these requirements. In this paper, the transient aerodynamic and thermal performance of a commercial RDHX was investigated experimentally. The RDHX was attached to an isolated server cabinet with a controllable heat load. A localized containment system was used to direct the airflow to the equipment in the cabinet that emanates from a single perforated tile within the enclosure. The water flow rate and supply water temperature to the RDHX was controlled, and a grid of 36 air velocity/temperature sensors was employed to monitor the airside of the cooling system. The cooling performance of the RDHX in an air blower failure scenario was investigated. The failure scenario was designed to diminish different parts of the overall system. The impact on the IT equipment and the cabinet outlet temperatures was assessed. Also, there was a significant reduction in the airflow to the IT equipment. The impact of the reduced airflow on different parts of the cabinet as well as the cooling performance of the heat exchanger was characterized during both failure and recovery.

Efficient Load-Balancing Aware Cloud Resource Scheduling for Mobile User

The paper proposes an efficient load-balancing aware cloud resource scheduling approach for mobile users. The proposed approach augments local cloud service pools with public cloud to increase the probability of meeting the service level agreements. The proposed problem is divided by public cloud service scheduling and local cloud service scheduling. The system status information is used in the hybrid mobile cloud system such as the preferences of mobile applications, energy, server load in cloud data center to improve resource utilization and quality of experience of mobile user. Therefore, the system status of hybrid mobile cloud is monitored continuously. The mathematical model of the system and optimization problem is given. An example for hybrid cloud-based mobile multimedia application is also presented. Through extensive experiments, the paper evaluates our algorithm and other approaches from the literature under different conditions. The results of the experiments show our approach has better performance than the approaches from the literature.

Deep Recurrent Model for Server Load and Performance Prediction in Data Center

Recurrent neural network (RNN) has been widely applied to many sequential tagging tasks such as natural language process (NLP) and time series analysis, and it has been proved that RNN works well in those areas. In this paper, we propose using RNN with long short-term memory (LSTM) units for server load and performance prediction. Classical methods for performance prediction focus on building relation between performance and time domain, which makes a lot of unrealistic hypotheses. Our model is built based on events (user requests), which is the root cause of server performance. We predict the performance of the servers using RNN-LSTM by analyzing the log of servers in data center which contains user’s access sequence. Previous work for workload prediction could not generate detailed simulated workload, which is useful in testing the working condition of servers. Our method provides a new way to reproduce user request sequence to solve this problem by using RNN-LSTM. Experiment result shows that our models get a good performance in generating load and predicting performance on the data set which has been logged in online service. We did experiments with nginx web server and mysql database server, and our methods can been easily applied to other servers in data center.

Scalability of the DVFS Power Management Technique as Applied to 3-Tier Data Center Architecture in Cloud Computing

The increase in computing capacity caused a rapid and sudden increase in the Operational Expenses (OPEX) of data centers. OPEX reduction is a big concern and a key target in modern data centers. In this study, the scalability of the Dynamic Voltage and Frequency Scaling (DVFS) power management technique is studied under multiple different workloads. The environment of this study is a 3-Tier data center. We conducted multiple experiments to find the impact of using DVFS on energy reduction under two scheduling techniques, namely: Round Robin and Green. We observed that the amount of energy reduction varies according to data center load. When the data center load increases, the energy reduction decreases. Experiments using Green scheduler showed around 83% decrease in power consumption when DVFS is enabled and DC is lightly loaded. In case the DC is fully loaded, in which case the servers’ CPUs are constantly busy with no idle time, the effect of DVFS decreases and stabilizes to less than 10%. Experiments using Round Robin scheduler showed less energy saving by DVFS, specifically, around 25% in light DC load and less than 5% in heavy DC load. In order to find the effect of task weight on energy consumption, a set of experiments were conducted through applying thin and fat tasks. A thin task has much less instructions compared to fat tasks. We observed, through the simulation, that the difference in power reduction between both types of tasks when using DVFS is less than 1%.

DFA-VMP: An efficient and secure virtual machine placement strategy under cloud environment

The problem of Virtual Machine (VM) placement is critical to the security and efficiency of the cloud infrastructure. Nowadays most research focuses on the influences caused by the deployed VM on the data center load, energy consumption, resource loss, etc. Few works consider the security and privacy issues of the tenant data on the VM. For instance, as the application of virtualization technology, the VM from different tenants may be placed on one physical host. Hence, attackers may steal secrets from other tenants by using the side-channel attack based on the shared physical resources, which will threat the data security of the tenants in the cloud computing. To address the above issues, this paper proposes an efficient and secure VM placement strategy. Firstly, we define the related security and efficiency indices in the cloud computing system. Then, we establish a multi-objective constraint optimization model for the VM placement considering the security and performance of the system, and find resolution towards this model based on the discrete firefly algorithm. The experimental results in OpenStack cloud platform indicates that the above strategy can effectively reduce the possibility of malicious tenants and targeted tenants on the same physical node, and reduce energy consumption and resource loss at the data center.

INFRASTRUCTURAL ASSETS PROVISIONING IN CLOUD COMPUTING SYSTEMS

This paper presents a study on cloud computing infrastructure and hardware resources used. Using cloud computing environment, clients can develop their own services making accessible arrangement of virtual machines. Such methodology can be used in infrastructural assets provisioning and balancing load in data centers. The provisioning of Infrastructural asset can help in implementation of data parallelisms and can also handle user requests more effectively. This paper presents study on different parameters which customizes data center federated services on cloud optimizations platform. Keywords—Cloud Computing, Cloud Assets, Cloud Suppliers, Virtual Machine (VM) and Cloud Service in Data

Proactive Demand Response for Data Centers: A Win-Win Solution

In order to reduce the energy cost of data centers, recent studies suggest distributing computation workload among multiple geographically dispersed data centers, by exploiting the electricity price difference. However, the impact of data center load redistribution on the power grid is not well understood yet. This paper takes the first step towards tackling this important issue, by studying how the power grid can take advantage of the data centers' load distribution proactively for the purpose of power load balancing. We model the interactions between power grid and data centers as a two-stage problem, where the utility company chooses proper pricing mechanisms to balance the electric power load in the first stage, and the data centers seek to minimize their total energy cost by responding to the prices in the second stage. We show that the two-stage problem is a bilevel quadratic program, which is NP-hard and cannot be solved using standard convex optimization techniques. We introduce benchmark problems to derive upper and lower bounds for the solution of the two-stage problem. We further propose a branch and bound algorithm to attain the globally optimal solution, and propose a heuristic algorithm with low computational complexity to obtain an alternative close-to-optimal solution. We also study the impact of background load prediction error using the theoretical framework of robust optimization. The simulation results demonstrate that our proposed scheme can not only improve the power grid reliability but also reduce the energy cost of data centers.

Managing Load Balanced Machine in Cloud Data Center

Over utilization and under utilization of physical resources creates energy consumption, bottlenecks etc. Hence, balancing the load among physical machines assists in minimizing resource consumption, implementation of fail-over, enhancing scalability, avoiding bottlenecks and over-provisioning of resources in a cloud data center. Therefore, we propose load balance strategies to attain balance load in cloud data center. The proposed strategies are evaluated through simulation. We have identified that, the healthier load balance has been attained through our strategies.

DCCP: an effective data placement strategy for data-intensive computations in distributed cloud computing systems

Cloud computing systems provide high-performance computing resources and distributed storage space to deal with data-intensive computations. Data scheduling between data centers is becoming indispensable for the cloud computing systems in which a mass of large datasets is stored at different data centers and inter-center data accesses are needed in data analytics. However, the performance of data scheduling is highly dependent upon the rationality of data placement. Data placement is a key optimization method for reducing data scheduling between data centers and realizing statistical I/O load balancing, accordingly reducing the mean computation execution time. This paper proposes a data placement strategy, DCCP, which is developed based on dynamic computation correlation. DCCP places the datasets with high dynamic computation correlations at the same data center considering the I/O load and the capacity load of data centers; when computations are scheduled for this data center, most of the datasets they process are stored locally, and thus the mean computation execution time can be reduced. Evidence from a large number of experiments proves that the DCCP can achieve the statistical I/O load balancing and the capacity load balancing of data centers, thus reducing the total data scheduling between data centers as much as possible at a very low time complexity, even as the numbers of datasets and data centers increase.

I Q R based Approach for Energy Efficient Dynamic VM Consolidation for Green Cloud Data Centers

the advent of cloud computing in the arena of IT field energy consumption and service level agreement (SLA) violation emerge as a major problem, which reduces the profit of cloud service providers (CSP) and affect the cloud customers by fencing the reusability and scalability of the cloud data center services. This problem needs to be eradicate for the efficient resource provisioning in cloud data center. To satisfy the customer need virtual machine (VM) migration technique is required to balance the load of entire data center. Therefore we need to transfer the virtual machine of the overloaded host to the light weighted host using virtual machine migration technique. Due to frequent load balancing of cloud data center enormous amount of energy consumption takes place. This enhances the overall energy cost and degrades the performance of cloud data center. This paper proposes an Energy Efficient Dynamic VM Consolidation algorithm for reducing energy consumption. Keywordscomputing, Cloud service provider (CSP), Energy consumption, SLA violation, Load balancing, VM migration.

A Comparative Analysis of Task Scheduling Algorithms of Virtual Machines in Cloud Environment

Cloud computing is an interesting and beneficial area in modern distributed computing. It enables millions of users to use the offered services through their own devices or terminals. Cloud computing offers an environment with low cost, ease of use and low power consumption by utilizing server virtualization in its offered services (e.g., Infrastructure as a Service). The pool of Virtual Machines (VMs) in a cloud computing Data Center (DC) needs to be managed through an efficient task scheduling algorithm to maintain quality of service and resource utilization and thus ensure the positive impact of energy consumption in the cloud computing environment. In this study, an experimental comparative study is carried out among three task scheduling algorithms in cloud computing, namely, random resource selection, round robin and green scheduler. Based on the analysis of the simulation result, we can conclude which algorithm is the best for scheduling in terms of energy and performance of VMs. The evaluation of these algorithms is based on three metrics: Total power consumption, DC load and VM load. A number of experiments with various aims are completed in this empirical comparative study. The results showed that there is no algorithm that is superior to the others. Each has its own pros and cons. Based on the simulation performed, the green scheduler gives the best performance with respect to energy consumption. On the other hand, the random scheduler showed the best performance with respect to both VM and DC load. The round robin scheduler gives better VM and DC load than the green scheduler but have more energy consumption than both random and green schedulers. However, since the RR scheduler distributes the tasks fairly, the network traffic is balanced and neither the server nor the network node will get overloaded or congested.