Search

With the rapid development of global informatization, data center computing tasks are increasing, and the resulting energy consumption problems are particularly prominent in the context of carbon emission reduction, and affect the safe and green operation of data centers. Aiming at the problem of high and large fluctuation energy load of data center servers, this paper presents a method of optimizing data center servers load considering spatial-temporal load distribution of computing resources. Co-optimized allocation of computing resources and load is studied with examples from the property that computing resources is adjustable in time and space dimensions. The results show that the proposed method is able to reduce the peak electric and cooling loads of the data center room by 10.7 %, reduce the total annual electric consumption by 2.66 % and the total annual cooling consumption by 2.46 %, and reduce the economic and environmental costs of energy supply for the data center in the case study, which comprehensively shows that the load optimization of data center servers has been achieved through the optimal allocation of computing resources. [ABSTRACT FROM AUTHOR]

The network security issue of university laboratories needs to be taken seriously, as there is a large amount of academic data stored in the laboratory. In order to ensure the network security of university laboratories, a series of measures need to be taken. This article uses anomaly intrusion detection technology to optimize the network of university laboratories and designs a network management system for university laboratories. The system adopts cloud computing technology and data center technology, supports software clusters and hardware clusters, and adopts an advanced SOA system framework. The design and implementation of this system effectively improves the security and stability of the university laboratory network. Using anomaly intrusion detection technology, we can effectively identify and prevent abnormal network intrusion, and protect the security of Laboratory equipment and data. [ABSTRACT FROM AUTHOR]

The arrival of big data has changed and affected people's lives. To achieve better development, universities must attach importance to applying big data for talent development. An improved k-nearest neighbors density peak clustering algorithm (iKDPC) combined with principal components is suggested to enhance the impact of hierarchical classification in talent development in universities. For the hybrid wired/wireless data center network, we propose a virtual node fusion-based virtual network embedding with the wireless links assistance method (VnfVNE-WLA). The experimental results show that iKDPC can effectively classify talents in universities and provide scientific and quantitative references for scientifically and rationally exploring the classification issues in developing talents in universities. Moreover, the simulation results demonstrate that the VnfVNE-WLA method can successfully increase the utilization rate of talent resources from the virtual network to the physical network to better support talent development in universities using cloud computing. [ABSTRACT FROM AUTHOR]

• A hybrid cloud can be built across clouds, CDNs and private data centers. • We formulate the problem of delivering mixture media content using the platform. • The NP-hard optimization problem can be transformed into a Nash bargaining problem. • The Nash bargaining problem can be solved efficiently from a geometrical perspective. • The algorithm can reduce cost and improve QoS significantly. With the increase in the amount of dynamic and personalized content in media streaming systems, a solution that is based on only the cloud or content delivery network (CDN) cannot satisfy all application-specific requirements. Thus integrating the cloud with CDNs and private data centers can be advantageous. To efficiently deliver a huge amount of media content using a geographically distributed hybrid cloud, we propose a Multi-Resource Scheduling Algorithm for Hybrid Cloud-Based Large-Scale Media Streaming(MHLMS). The algorithm transforms resource scheduling into a Nash bargaining problem and solves it efficiently from a geometrical perspective. The simulation results show that compared to algorithms that use only the cloud or CDN, MHLMS can reduce the cost by approximately 60% and reduce the average delivery distance by up to 70%. Thus, compared with the existing video delivery methods, MHLMS can handle millions of channels effectively with much lower time complexity. [ABSTRACT FROM AUTHOR]

Nowadays Cyber–Physical System (CPS) is implemented in several areas, such as health care, agriculture, transportation, etc. The main aim of CPS is for automation or minimization of human interaction. The conventional Machine Learning (ML) based approach involves sensitive issues such as information leakage. That issue is resolved using the Federated Learning (FL) based approach partially. The FL uses a decentralized environment for training the models, where models are trained locally, and only the updated part is sent to the data center or cloud server. It improves data privacy as the clients send only the local updates (model gradients). But also there is a high risk of data leakage while publishing the data in FL based System. A Differential Privacy Preservation Technique (DPPT) is an efficient technique to preserve information leakage. In this paper, a differential privacy preservation technique has been proposed by adding random noise to a data sample in order to generate anonymity. The performance of the model, and data quality are evaluated as privacy preservation techniques often degrade data quality. [Display omitted] • The proposed work is based on differential privacy in the Federated Learning environment. • It generates random noise, which is added to actual data to generate anonymity and mitigate adversarial attacks. • The proposed model ensures data privacy and preserves information leakage in a cyber–physical system. • The performance and data quality of the model is measured and found promising results. [ABSTRACT FROM AUTHOR]

Virtual Machine (VM) placement consolidates VMs into a minimum number of Physical Machines (PMs), which can be viewed as a Vector Bin-Packing (VBP) problem. Recent literature reveals the significance of first-fit-decreasing variants in solving VBP problems, however they suffer from reduced packing efficiency and delayed packing speed. This paper presents VM NeAR (VM Nearest and Available to Residual resource ratios of PM), a novel heuristic method to address the above said challenges in VBP. Further, we have developed Bulk-Bin-Packing based VM Placement (BBPVP) and Multi-Capacity Bulk VM Placement (MCBVP) as a solution for VBP. The simulation results on real-time Amazon EC2 dataset and synthetic datasets obtained from CISH, SASTRA shows that VM NeAR based MCVBP achieves about 1.6% reduction in the number of PMs and possess a packing speed which was found to be 24 times faster than exisiting state-of-the-art VBP heuristics. [ABSTRACT FROM AUTHOR]

With the increasing consumption of energy in data centers, the demand for energy efficient multiprocessor job scheduling is growing dramatically. Besides flow time, energy conservation has become a significant issue and drawn enormous interest. In this paper, an online non-clairvoyant scheduling algorithm Significance-based Multiprocessor Round Robin (SbMRR) is proposed. SbMRR utilizes the unbounded speed model, where the range of the speed of any processor is from zero to infinity. To validate the effectiveness of the algorithm, mathematical and simulation-based analysis are conducted which demonstrates that SbMRR provides the minimum sum of significance-based flow time and energy consumed. SbMRR is O(α)-competitive, more precisely ((α + 1)⁄((1–1⁄αβ)))-competitive, where β ≥ 4 a constant. The competitive ratio of SbMRR is least to date. SbMRR provides the minimum sum of energy consumed and significance-based flow-time. [ABSTRACT FROM AUTHOR]

Cloud service providers are aggressively expanding their data centers to meet end-user demand, resulting in increased power and energy consumption. As a result, it becomes extremely important to implement server consolidation solutions in the context of cloud computing. One of the difficult problems in cloud data centers is efficient server consolidation, which is related to both environmental and financial aspects. Using resources efficiently and reducing energy consumption are the main goals of consolidating servers for cloud computing. Regrettably, the majority of methods now in use have been geared towards either lowering system performance or reducing energy consumption. Using the Markov chain principle for each server transition, we suggested a strategy in this study to optimize the server consolidation process. An early review of the study's findings is encouraging and comes to the conclusion that a successful server consolidation strategy may be implemented with the least amount of resources and the best possible energy use. The suggested strategy takes into account the following three elements: consolidating the resources, cutting down energy consumption, and trading off of both (composite case). [Display omitted] • Presented an optimized server consolidation approach in Cloud environment. • Shows how resource usage and energy consumption can be optimised together. • Employs Markov chain-based scenarios for cloud server consolidation. • Lowers the cost of VM migration by reducing the number of migration counts. • Shows how QoS has improved while categorising servers based on resource demand. [ABSTRACT FROM AUTHOR]

Applications perform massive and diverse tasks in data centers. Tasks completion condition seriously affects application performance. However, most existing flow-level or task-level scheduling methods treat flows in isolation, meanwhile, few works discuss the efficiency of task-level scheduling from the perspective of the task profit. In this paper, we introduce a profit-aware task-level scheduling scheme named PAT, whose target is to maximize the profit of completing tasks within their reasonable time. To this end, a maximizing profit optimization model is proposed on task-level, and an efficient approximate scheduling algorithm is presented. Furthermore, a situation of absent deadline information is discussed and an ePAT method is presented to solve this situation. Based on the proposed algorithm, we design and implement PAT and ePAT. Some comprehensive experiments are conducted to evaluate the performance of our methods. The experimental results show that our methods bring higher profit than other scheduling methods. [ABSTRACT FROM AUTHOR]

Cloud services are widely used in manufacturing, logistics, digital applications, and document processing. Cloud services must be able to handle tens of thousands of concurrent requests and to enable servers to seamlessly provide the amount of load balancing capacity required to respond to incoming application traffic in addition to allowing users to obtain information quickly and accurately. In the past, researchers have proposed the use of static load balancing or server response times to evaluate load balancing capacity, a lack of which may cause a server to load unevenly. In this study, a dynamic annexed balance method is used to solve this problem. Cloud load balancing (CLB) takes into consideration both server processing power and computer loading, thus making it less likely that a server will be unable to handle excessive computational requirements. Finally, two algorithms in CLB are also addressed with experiments to prove the proposed approach is innovative. [ABSTRACT FROM AUTHOR]

In recent years, cloud computing has emerged as a promising paradigm providing various resources in the Cloud Data Center (CDC), including computations, storage, and even platform as a service. The virtualization technology plays a pivotal role in CDC resources management and provides an enchanting feature of virtual machine (VM) migration which provides several benefits in terms of VM scheduling, fault tolerance, load balancing, energy efficiency, power management, and security. To achieve efficient VM migration, a plethora of VM migration schemes have been proposed in the literature aiming to serve the quality of service-driven user requirements. This paper surveys the most recent and state-of-the-art Artificial Intelligence (AI) based and conventional load balancing, energy-aware, SLA aware, and network-aware live VM migration schemes. Through an extensive literature review, this paper investigates the most critical aspects of conventional and AI-driven live VM migration schemes. Finally, a few open research challenges that require further consideration from the research community are highlighted. [Display omitted] • Overview of cloud computing, data centers, virtualization, and VM migration. • Conventional and AI-based Live VM migration schemes categorization. • Live VM migration survey of load, energy, SLA, and network schemes. • VM migration analysis based on migration cost and AI benefits and drawbacks. • Live VM migration research challenges and future directions. [ABSTRACT FROM AUTHOR]

Operation on demand flexibility in cloud computing services has resulted in great popularity and wide adoption. These services integrate thousands of computers, storage and communication networks, which implies a high consumption of electrical energy. Therefore, renewable energy-based cloud data centers are replacing traditional energy power grids. In this regard, the workload could be transferred to different nodes among different cloud data centers geographically distributed regarding renewable energy availability. In this sense, this paper presents a framework based on Cloudsim for virtual machine migrations among cloud data centers regarding sustainability optimization. Moreover, an approach for migrations among datacenters based on an expert system has been tested in several scenarios with renewable energy dynamically available. Experimental results show the improvements of the proposed framework and how expert systems can take advantage of renewable energy availability in terms of sustainability while preserving the QoS in terms of execution time. [Display omitted] [ABSTRACT FROM AUTHOR]

In Recent days, cloud computing technology is used as a remote-based virtual computer resource utilization to offer consumers quick and accurate massive data services. In the cloud, infrastructure as services have a significant impact on computing efficiency by Infrastructure as a services (IaaS). Cloud computing uses on-demand resource provisioning. In the cloud, a variety of metaheuristic algorithms are helpful for process allocation. Large-scale datacenters utilise a lot of electricity, which has an influence on the environment and the economy. Using a Micro-Genetic Algorithm, a stable combined process workload allocation method with Cat Swarm Optimization (MG-CSO) is introduced by addressing pre-convergence problems and optimal resource management. For optimal computing efficiency, the resources are dynamically consolidated and clustered. Additionally, the MG-CSO Algorithm produces positive outcomes when compared to other well-known algorithms, such as the Genetic Algorithm (GA) and the Bat Algorithm (BA).This research's focus is to reduce cost, time, Service Level Agreement(SLA), energy usage, and afford good Quality of Service(QoS). Our final scientific results were achieved with 91%. [Display omitted] [ABSTRACT FROM AUTHOR]

The increasing demand of cloud computing motivates the researchers to make cloud environment more efficient for its users and more profitable for the providers. Though virtualization technology helps to increase the resource utilization, still the operational cost of cloud gradually increases mainly due to the consumption of large amount of electrical energy. So to reduce the energy consumption virtual machines (VM) are dynamically consolidated to lesser number of physical machines (PMs) by live VM migration technique. But this may cause SLA violation and the provider is penalized. So to maintain an energy-performance trade-off, the number of VM migration should be minimized. VM migration primarily takes place in two cases: for hotspot mitigation and to switch off the underutilized nodes by migrating all its VMs. If a host is found to be overloaded then instead of immediately migrating some of its VMs we can check whether the migration is really required or not. For this we have proposed a load prediction algorithm to decide whether the migration will be performed or not. After the decision has been taken the algorithm finds a suitable destination host where the VM will be shifted. For this we have proposed a novel approach to decide whether a particular host is suitable as destination depending on its probable future load. We have simulated our algorithms in CloudSim using real world workload traces and compared them with the existing benchmark algorithms. Results show that the proposed methods significantly reduce the number of VM migration and subsequent energy consumption while maintaining the SLA. [ABSTRACT FROM AUTHOR]

Data centers use dynamic virtual machine consolidation to reduce power consumption. Existing consolidation mechanisms are not efficient in cloud data centers, which have heterogeneous hardware infrastructure, huge scale, and highly variable non-stationary workloads. We use game theory to develop a novel distributed mechanism for both heterogeneous and homogeneous data centers of cloud computing. Our mathematical analysis shows that our mechanism converges after a finite number of migrations. In addition, we show that our worst case power consumption is only 23% more than the theoretical minimum. In order to validate our claim, we preform simulation in CloudSim with real workload traces from Google data centers. [ABSTRACT FROM AUTHOR]

Proliferation of IT services provided by cloud service delivery model as well as diverse range of cloud users have led to the establishment of huge energy hungry data centers all around the world. Therefore, cloud providers are confronted with great pressures to reduce their energy consumption as well as their CO 2 emissions. In this direction, consolidation is proposed as an effective method of energy saving in cloud data centers. This paper proposes a new holistic cloud resource management procedure as well as novel heuristics based on multi-criteria decision making method for both determination of underloaded hosts and placement of the migrating VMs. The results of simulations using Cloudsim simulator validates the applicability of the proposed policies which shows up to 46%, 99%, and 95% reductions in energy consumption, SLA violation, and number of VM migrations, respectively in comparison with state of the arts. [ABSTRACT FROM AUTHOR]

• An ensured cloud storage service over client's virtual machine processing services is guaranteed. • Virtual machines and subsystems are even more powerful and useful by the proposals. • Mitigation of private cloud computing systems resources is done. • Improvement of Aggregated Migration Energy Consumption is obvious. This paper proposes an Internet of Everything (IoE) based private multi-data center cloud architecture framework to utilize the merits of multi-data centers. The inclusive security structure for the entire cloud data center presented here is to minimize the potential vulnerabilities from the adoption of the cloud. This work would leverage the novelty in allocating the distribution of data smartly and in a reliable manner to have the network for private cloud data centers. On the other hand, the architecture must have the ability to make out an enterprise's data and association applications in the cloud using the facility of contributing the opportunity. To overcome these shortcomings, a "Facility Overhead-aware multi-objective Dynamic Private Cloud Data Center Algorithm" (FOMDPC) is proposed with the merits of migration payload awareness, dynamic load balancing methodology, and facility infrastructure costs. The factors to be considered to determine the efficiency are time complexity and memory overhead. In addition, aggregated migration energy consumption and aggregated SLA violations are also taken into account. [Display omitted] [ABSTRACT FROM AUTHOR]

In today's shared datacenters, communications among tasks across jobs (applications) typically generate large amounts of coflows. System efficiency and job fairness oriented coflow scheduling is critical for improving both system performance and user satisfaction in the application level. Since the metrics of fairness and efficiency usually conflict to each other, how to schedule coflows at the desired tradeoff between the metrics is a challenging problem. Due to the great variety of jobs and tasks within each job, communications among them have different characteristics, resulting their coflows presented in different patterns. Existing coflow schedulers attempt to optimize either only one metric or a tradeoff of both for static patterns of coflows (within the same job) because of their incapability of capturing the inherent patterns of coflows that are dynamically changing specially for cross-job coflows. This paper proposes a novel fairness-aware coflow scheduling algorithm that combines a link-embedded multi-layer neural network with a meta-learning framework for unsupervised learning of dynamic coflows across different jobs and hence adaptive scheduling of the coflows to achieve the desired fairness–efficiency tradeoff. In our algorithm, while the neural network takes care of mining the relationships among coflow allocations, the meta-learning framework effectively captures the dynamic patterns of a large number of sample coflows and trains the neural network to achieve the desired scheduling performance. Extensive experimental results demonstrate that our algorithm outperforms the state-of-the-art coflow schedulers on scheduling performance for achieving the desired fairness–efficiency tradeoff. [ABSTRACT FROM AUTHOR]

With the advantages such as high-performance, low-maintenance, and reliability, more and more companies are moving their computing infrastructures to the cloud. In the meantime, with the increasing number of users continuously submitting jobs to cloud, energy consumed by the current cloud data centers has become a major concern for cloud service providers, due to financial and environmental reasons. In this paper, we propose a deep reinforcement learning (DRL) approach to handle real-time jobs. Specifically, we focus on allocating incoming jobs to appropriate virtual machines (VMs) in a way that energy consumption can be optimized while high quality of service (QoS) can be achieved. We give the detailed design and implementation of our approach, and our experimental results demonstrate that the proposed method can achieve better performance in job success rate and average response time with less energy consumption than the current approaches, in the presence of different real-time cloud workloads. [ABSTRACT FROM AUTHOR]

Abstract: Recent advances in optical communications not only increase the capacities of communication system but also improve the system dynamicity and survivability. Various new technologies are invented to increase the bandwidth of individual wavelength channels and the number of wavelengths transmitted per fiber. Multiple access technologies have also been developed to support various emerging applications, including real-time, on-demand and high data-rate applications, in a flexible, cost effective and energy efficient manner. In this paper, we overview recent research in optical communications and focus on the topics of modulation, switching, add-drop multiplexer, coding schemes, detection schemes, orthogonal frequency-division multiplexing, system analysis, cross-layer design, control and management, free space optics, and optics in data center networks. The primary purpose of this paper is to refresh the knowledge and broaden the understanding of advances in optical communications, and to encourage further research in this area and the deployment of new technologies in production networks. [Copyright &y& Elsevier]

Data centers are power hungry facilities. Energy-aware task scheduling approaches are of utmost importance to improve energy savings in data centers, although they need to know beforehand the energy consumption of the applications that will run in the servers. This is usually done through a full profiling of the applications, which is not feasible in long-running application scenarios due to the long execution times. In the present work we use an application signature that allows to estimate the energy without the need to execute the application completely. We use different scheduling approaches together with the information of the application signature to improve the makespan of the scheduling process and therefore improve the energy savings in data centers. We evaluate the accuracy of using the application signature by means of comparing against an oracle method obtaining an error below 1.5%, and Compression Ratios around 39.7 to 45.8. [Display omitted] • Energy-aware task scheduling approaches reduce energy consumption in data centers. • They rely on a full profiling, not feasible in long-running applications. • The application signature is used to avoid the full profiling. • The application signature makes the task scheduling approaches more efficient. [ABSTRACT FROM AUTHOR]

• Hybrid ant genetic algorithm for efficient task scheduling in cloud datacenter is proposed. • Reduces scheduling solution space. • Minimizes workflow execution time by load balancing. • Less response time than genetic algorithm. Cloud computing is a computing paradigm which meets the computational and storage demands of end users. Cloud-based data centers need to continually improve their performance due to exponential increase in service demands. Efficient task scheduling is essential part of cloud computing to achieve maximum throughput, minimum response time, reduced energy consumption and optimal utilization of resources. Bio-inspired algorithms can solve task scheduling difficulties effectively, but they need a lot of computational power and time due to high workload and complexity of the cloud environment. In this research work, Hybrid ant genetic algorithm for task scheduling is proposed. The proposed algorithm adopts features of genetic algorithm and ant colony algorithm and divides tasks and virtual machines into smaller groups. After allocation of tasks, pheromone is added to virtual machines. The proposed algorithm effectively reduces solution space by dividing tasks into groups and by detecting loaded virtual machines. Due to the minimum solution space of proposed algorithm, convergence and response time is significantly decreased. It finds a feasible scheduling solution to minimize the running time of workflows and tasks. The proposed algorithm achieved 64% decrease in execution time and 11% decrease in overall data center costs. [Display omitted] [ABSTRACT FROM AUTHOR]

In the modern era of digitalization, many applications exist that consume a huge computational processing power. These applications due to massive costs involved in procurement and maintenance, looks at resource abundant cloud environments as effective solution. However, cloud environments often suffer from challenges that threaten the performance due to inefficient resource utilization. Load balancing across multiple virtual machines in cloud deployment is one of the major issue that leads to under-utilization of cloud resources. In this research work, the problem of task to resource mapping is addressed using crow search based load balancing algorithm for greater optimization as solution. The solution uses parameters such as average power consumption of data center, average cost of the data center and data center loading for allocating the best resource to the submitted tasks. The proposed solution is validated against standard ant colony optimization based load balancing algorithm. It has been found that the proposed algorithm has outperformed standard algorithm and emerges out as a most optimal load balancing algorithm. [Display omitted] • CSLBA is suggested as a solution to load balancing problem in a cloud environment. • Performance metrics for dispersing the load among resources have been identified. • The proposed algorithm is validated in terms of load mapping ability. • CSLBA proved to be effective as it evenly distributed load among all data centers. [ABSTRACT FROM AUTHOR]

Network virtualization is widely regarded as a key enabler to improve the desired flexibility and scalability of cloud computing services. With the rapid expansion of data centers, it remains a challenge to provide efficient management of resources for virtual machine placement. Due to multi-dimensional physical resources in servers, there maybe resource fragmentation causing by an imbalanced usage of multi-dimensional resources, when multiple virtual machines carrying diverse requests are deployed on the same server simultaneously. In this paper, we devote to how to balance multiple resources usage to alleviate resource fragmentation while maximizing the service rate for virtual machine placement, so that it can prevent waste of physical resources and undesirable performance. In order to solve such a bi-objective optimization problem, we present a joint bin-packing heuristic and genetic algorithm which achieves an approximate optimal solution with much lower time complexity. [ABSTRACT FROM AUTHOR]