Multiple Cloud Data Centers Research Articles

Reinforcement learning based task scheduling for environmentally sustainable federated cloud computing

The significant energy consumption within data centers is an essential contributor to global energy consumption and carbon emissions. Therefore, reducing energy consumption and carbon emissions in data centers plays a crucial role in sustainable development. Traditional cloud computing has reached a bottleneck, primarily due to high energy consumption. The emerging federated cloud approach can reduce the energy consumption and carbon emissions of cloud data centers by leveraging the geographical differences of multiple cloud data centers in a federated cloud. In this paper, we propose Eco-friendly Reinforcement Learning in Federated Cloud (ERLFC), a framework that uses reinforcement learning for task scheduling in a federated cloud environment. ERLFC aims to intelligently consider the state of each data center and effectively harness the variations in energy and carbon emission ratios across geographically distributed cloud data centers in the federated cloud. We build ERLFC using Actor-Critic algorithm, which select the appropriate data center to assign a task based on various factors such as energy consumption, cooling method, waiting time of the task, energy type, emission ratio, and total energy consumption of the current cloud data center and the details of the next task. To demonstrate the effectiveness of ERLFC, we conducted simulations based on real-world task execution data, and the results show that ERLFC can effectively reduce energy consumption and emissions during task execution. In comparison to Round Robin, Random, SO, and GJO algorithms, ERLFC achieves respective reductions of 1.09, 1.08, 1.21, and 1.26 times in terms of energy saving and emission reduction.

An energy‐efficient method of resource allocation based on request prediction in multiple cloud data centers

SummaryTo meet the ever‐increasing requirements of the applications, cloud service providers have further built and managed multiple cloud data centers in multiple regions across geographies with many physical machines (PMs). However, most of the existing resource allocation algorithms are developed for a single cloud data center, which normally cannot efficiently handle the load burst occasions where a single cloud data center may not be enough to satisfy the demands burst of applications. Therefore, it is necessary to consider how to efficiently manage multiple cloud data centers while meeting application requirements and reducing energy consumption. This paper first systematically analyzes multiple cloud data centers and energy consumption models. Then, an energy‐efficient method of Resource Allocation based on Request Prediction in multiple cloud data centers (RARP) is proposed. The RARP method constructs a resource allocation framework based on request prediction in multiple cloud data centers, which anticipates the application request volume in advance. At the same time, the RARP method allocates VMs and PMs based on the principle of minimum remaining resources available to achieve minimum usage of PMs, thus minimizing energy consumption to complete application requests. Extensive experiments are conducted on the proposed RARP method through the simulation platform CloudSim. Finally, the experimental test results show that the accuracy of request detection and the energy consumption of cloud data centers are significantly better than those of the comparison algorithms.

A multi-objective cloud energy optimizer algorithm for federated environments

Energy is a considerable portion of the cost of a cloud data center. In addition to energy, carbon emission tax imposes another cost on data centers, which have different policies in different cities around the world. Most of the cloud data centers are geographically distributed, which can have a huge advantage in reducing such costs. In addition, in recent years, cloud federation, in which multiple cloud providers share their IT infrastructures voluntarily, could play a crucial role in minimizing the energy consumption of cloud data centers. On the other hand, improper VM placement results frequent VM migration, constant turning off/on physical machines, service quality degradation and energy consumption increase. To tackle these weaknesses, we propose a multi-objective algorithm, Called OUR-ACS, to minimize data centers' energy consumption, carbon emission, and the total expenses (energy cost + carbon tax) in a federated environment considering both initial VM placement and VM consolidation approaches. We evaluate the efficiency of our proposed algorithm by using the ClousSim Plus simulator toolkit using real-world datasets. Compared to the competing algorithms, our simulation results indicate that our proposed algorithm could reduce the total energy consumption, carbon emission, and the total costs of multiple cloud data centers by an average of 37.6%, 41%, and 25%, respectively, in a federated environment.

IoTSim-SDWAN: A simulation framework for interconnecting distributed datacenters over Software-Defined Wide Area Network (SD-WAN)

Software-defined networking (SDN) has evolved as an approach that allows network administrators to program and initialize, control, change and manage networking components (mostly at L2-L3 layers) of the OSI model. SDN is designed to address the programmability shortcomings of traditional networking architectures commonly used in cloud datacenters (CDC). Deployment of SDN solutions have demonstrated significant improvements in areas such as flow optimization and bandwidth allocation in a CDC. However, the benefits are significantly less explored when considering Software-Defined Wide Area Networks (SD-WAN) architectures in the context of delivering solutions by networking multiple CDCs. To support the testing and bench-marking of data-driven applications that rely on data ingestion and processing (e.g., Smart Energy Cloud, Content Delivery Networks) across multiple cloud datacenters, this paper presents the simulator, IoTSim-SDWAN. To the best of our knowledge, IoTSim-SDWAN is the first simulator that facilitates the modeling, simulating, and evaluating of new algorithms, policies, and designs in the context of SD-WAN ecosystems and SDN-enabled multiple cloud datacenters. Finally, IoTSim-SDWAN simulator is evaluated for network performance and energy to illustrate the difference between classical WAN and SD-WAN environments. The obtained results show that SD-WAN surpasses the classical WAN in terms of accelerating traffic flows and reducing power consumption.

GA-Par: Dependable Microservice Orchestration Framework for Geo-Distributed Clouds

Recent advances in composing Cloud applications have been driven by deployments of inter-networking heterogeneous microservices across multiple Cloud datacenters. System dependability has been of the upmost importance and criticality to both service vendors and customers. Security, a measurable attribute, is increasingly regarded as the representative example of dependability. Literally, with the increment of microservice types and dynamicity, applications are exposed to aggravated internal security threats and externally environmental uncertainties. Existing work mainly focuses on the QoS-aware composition of native VM-based Cloud application components, while ignoring uncertainties and security risks among interactive and interdependent container-based microservices. Still, orchestrating a set of microservices across datacenters under those constraints remains computationally intractable. This paper describes a new dependable microservice orchestration framework GA-Par to effectively select and deploy microservices whilst reducing the discrepancy between user security requirements and actual service provision. We adopt a hybrid (both whitebox and blackbox based) approach to measure the satisfaction of security requirement and the environmental impact of network QoS on system dependability. Due to the exponential grow of solution space, we develop a parallel Genetic Algorithm framework based on Spark to accelerate the operations for calculating the optimal or near-optimal solution. Large-scale real world datasets are utilized to validate models and orchestration approach. Experiments show that our solution outperforms the greedy-based security aware method with 42.34 percent improvement. GA-Par is roughly 4x faster than a Hadoop-based genetic algorithm solver and the effectiveness can be constantly guaranteed under different application scales.

A Two-Stage Framework for the Multi-User Multi-Data Center Job Scheduling and Resource Allocation

With the development of artificial intelligence and the Internet of things, the prospects of cloud computing applications have become broader, and the number of users and cloud data centers (CDCs) has exploded. It is a challenge to realize efficient job scheduling and resource allocation of multiple users and data centers. However, the traditional scheduling model based on heuristic algorithm has some limitations in the complex and changeable cloud environment. In addition, many existing single-agent models rarely consider the multi-objective global optimization of the system. Therefore, this paper proposes a two-stage job scheduling and resource allocation framework that adopts multiple intelligent schedulers to solve the cooperative scheduling problem between job scheduling and resource allocation. A heterogeneous distributed deep learning (HDDL) model is used in the job scheduling stage to schedule multiple jobs to multiple cloud data centers. The deep Q-network (DQN) model is a resource scheduler to deploy virtual machine to physical servers for execution. Extensive numerical results show that both HDDL-baesd job scheduler and DQN-based resource allocator outperform the benchmark algorithm in terms of optimizing energy consumption and job delay. Furthermore, the proposed framework not only can achieve a global near-optimum by achieving local optimization at each stage but also has good scalability and low computation delay.

Latency-aware failover strategies for containerized web applications in distributed clouds

Abstract Despite advances in Cloud computing, ensuring high availability (HA) remains a challenge due to varying loads and the potential for Cloud outages. Deploying applications in distributed Clouds can help overcome this challenge by geo-replicating applications across multiple Cloud data centers (DCs). However, this distributed deployment can be a performance bottleneck due to network latencies between users and DCs as well as inter-DC latencies incurred during the geo-replication process. For most web applications, both HA and Performance (HAP) are essential and need to meet pre-agreed Service Level Objectives (SLOs). Efficiently placing and managing primary and backup replicas of applications in distributed Clouds to achieve HAP is a challenging task. Existing solutions consider either HA or performance but not both. In this paper we propose an approach for automating the process of providing a latency-aware failover strategy through a server placement algorithm leveraging genetic algorithms that factor in the proximity of users and inter-DC latencies. To facilitate the distributed deployment of applications and avoid the overheads of Clouds, we utilize container technologies. To evaluate our proposed approach, we conduct experiments on the Australia-wide National eResearch Collaboration Tools and Resources (NeCTAR - www.nectar.org.au) Research Cloud. Our results show at least a 23.3% and 22.6% improvement in response times under normal and failover conditions respectively compared to traditional, latency-unaware approaches. Also, the 95th percentile of response times in our approach are at most1.5 ms above the SLO compared to 11–32 ms using other approaches.

Optimized Big Data Management across Multi-Cloud Data Centers: Software-Defined-Network-Based Analysis

With an exponential increase in smart device users, there is an increase in the bulk amount of data generation from various smart devices, which varies with respect to all the essential V's used to categorize it as big data. Generally, most service providers, including Google, Amazon, Microsoft and so on, have deployed a large number of geographically distributed data centers to process this huge amount of data generated from various smart devices so that users can get quick response time. For this purpose, Hadoop, and SPARK are widely used by these service providers for processing large datasets. However, less emphasis has been given on the underlying infrastructure (the network through which data flows), which is one of the most important components for successful implementation of any designed solution in this environment. In the worst case, due to heavy network traffic with respect to data migrations across different data centers, the underlying network infrastructure may not be able to transfer data packets from source to destination, resulting in performance degradation. Focusing on all these issues, in this article, we propose a novel SDN-based big data management approach with respect to the optimized network resource consumption such as network bandwidth and data storage units. We analyze various components at both the data and control planes that can enhance the optimized big data analytics across multiple cloud data centers. For example, we analyze the performance of the proposed solution using Bloom-filter-based insertion and deletion of an element in the flow table maintained at the OpenFlow controller, which makes most of the decisions for network traffic classification using the rule-and-action-based mechanism. Using the proposed solution, developers can deploy and analyze real-time traffic behavior for the future big data applications in MCE.

Bandwidth Measurements within the Cloud

The search for availability, reliability, and quality of service has led cloud infrastructure customers to disseminate their services, contents, and data over multiple cloud data centers, often involving several Cloud service providers (CSPs). The consequence of this is that a large amount of data must be transmitted across the public Cloud. However, little is known about the bandwidth dynamics involved. To address this, we have conducted a measurement campaign for bandwidth between 18 data centers of four major CSPs. This extensive campaign allowed us to characterize the resulting time series of bandwidth as the addition of a stationary component and some infrequent excursions (typically downtimes). While the former provides a description of the bandwidth users can expect in the Cloud, the latter is closely related to the robustness of the Cloud (i.e., the occurrence of downtimes is correlated). Both components have been studied further by applying factor analysis, specifically analysis of variance, as a mechanism to formally compare data centers’ behaviors and extract generalities. The results show that the stationary process is closely related to the data center locations and CSPs involved in transfers that, fortunately, make the Cloud more predictable and allow the set of reported measurements to be extrapolated. On the other hand, although correlation in the Cloud is low, that is, only 10% of the measured pair of paths showed some correlation, we found evidence that such correlation depends on the particular relationships between pairs of data centers with little connection to more general factors. Positively, this implies that data centers either in the same area or within the same CSP do not show qualitatively more correlation than other data centers, which eases the deployment of robust infrastructures. On the downside, this metric is scarcely generalizable and, consequently, calls for exhaustive monitoring.

A Systematic Approach to Adaptive Dimensioning of Data Centers

Cloud data centers (CDCs) provide key infrastructure for Cloud computing. Accurately allocating computing resources is very important for the CDCs to function efficiently. Current allocation of resources in CDCs is mostly dedicated and static. However, workloads for Cloud applications are highly variable which cause poor application performance, poor resource utilization or both. In this paper, considering both blocking and delay probability by applying queuing theories to model different scenarios, systematic adaptive dimensioning methods for CDCs are developed so that right amount of computing resources are allocated for variable workloads to meet quality of service requirements in different situations. Both single CDC and multiple CDCs with and without delay are considered. The proposed methods can be applied to dimension data centers efficiently and dynamically.