Search

When operating large cloud computing infrastructures, ensuring healthiness of physical resources and software components is of paramount importance to meet the demanding service levels expected by customers. This is only possible using automations that can detect anomalies and alert the on-call personnel, or trigger healing procedures. In production-grade deployments, such automations are generally based on static thresholds or predefined pattern-matching rules, checked against relevant metrics and logs. Defining and maintaining them is cumbersome and, as the infrastructure grows, they need continuous adjustments. To tackle this problem, we propose an intelligent automation system for cloud operations that learns, from what operators have done in the past, what actions should be applied in response to the observed anomalies. Such system is designed to operate elastic groups of cloud instances realizing typical (replicated) cloud services. The mechanism is based on a 2-phase machine learning pipeline, composed of: a first, lighter, model that automatically detects anomalous patterns, based on past observations of the normal behavior, causing activation of the second, more involved, model; this is a model that recommends specific corrective actions, based on historical operational data reporting the actions applied to heal the faulty components. The approach was validated on an OpenStack deployment, where we deployed both a synthetic application and a multi-node Cassandra NoSQL data-store, and injected different types of anomalies while these systems were exercised using synthetic workloads. For both applications, we obtained a remarkable accuracy (mostly beyond 90%, and also going beyond 95% in some cases), for the anomaly detection and corrective action recommendation tasks, by applying the models on the respective test sets. This allows us to conclude that the presented mechanism constitutes an efficient and effective technique to help operating cloud services in presence of a number of faults, albeit the types and heterogeneity of faulty conditions might be expanded in future evolutions of the framework. The implementation and the material needed to reproduce our results are available under an open-source license.

With the rapid development of the IoT (Internet-of-Things), additional smart gadgets may be associated with the Internet, significantly enhancing data transfer and communication. Software-Defined Networking (SDN) is known as a new model that separates the control plane and the data plane, and is anticipated as a favorable solution for implementing Blockchain, to offer the scalability and adaptability required for IoT. The scalability of the network rises in direct proportion to the users’ enhanced privacy on the network. Blockchain and SDN are two top innovations utilized to create secure network architectures and provide trustworthy data transmission. They offer a strong and trustworthy platform to deal with dangers and problems, including security, privacy, adaptability, scalability, and secrecy. Unfortunately, the attackers can still inject traffic to disrupt a blockchain node’s regular functions. This study provides an optimized Blockchain-based SD IoT architecture for smart networks that is safe and energy-efficient. In this work, it is concentrated on blockchain-based SDN and creates an SDN-Blockchain Classifier. This IDS-based security tool provides a trust-based classifier by handling and reducing harmful traffic through traffic fusion and aggregation. Finally, it is concluded by evaluating the proposed framework SDN-Blockchain Classifier performance against MAC flooding attack in a simulation setting and demonstrating that it can attain optimized average throughput, response time, packet loss of crossing domain path, energy efficiency, end-to-end delay, file transfer operation, energy consumption, and CPU utilization compared to the baselines taken into consideration, thereby achieving efficacy and also security in the proposed smart network.

Resource management in cloud infrastructure is one of the key elements of quality of services provided by the cloud service providers. Resource management has its taxonomy, which includes discovery of resources, selection of resources, allocation of resources, pricing of resources, disaster management, and monitoring of resources. Specifically, monitoring provides the means of knowing the status and availability of the physical resources and services within the cloud infrastructure. This results in making “monitoring of resources” one of the key aspects of the cloud resource management taxonomy. However, managing the resources in a secure and scalable manner is not easy, particularly when considering a federated cloud environment. A federated cloud is used and shared by many multi-cloud tenants and at various cloud software stack levels. As a result, there is a need to reconcile all the tenants’ diverse monitoring requirements. To cover all aspects relating to the monitoring of resources in a federated cloud environment, we present the FEDerated Architecture for Resource manaGement and mOnitoring in cloudS Version 1.0 (FEDARGOS-V1), a cloud resource monitoring architecture for federated cloud infrastructures. The architecture focuses mainly on the ability to access information while monitoring services for early identification of resource constraints within short time intervals in federated cloud platforms. The monitoring architecture was deployed in a real-time OpenStack-based FEDerated GENomic (FEDGEN) cloud testbed. We present experimental results in order to evaluate our design and compare it both qualitatively and quantitatively to a number of existing Cloud monitoring systems that are similar to ours. The architecture provided here can be deployed in private or public federated cloud infrastructures for faster and more scalable resource monitoring.

More engaging and accessible solutions that offer outstanding user experience are needed. The virtual desktop infrastructure (VDI) is the first user access part of the cloud. Therefore, the performance of the VDI has a significant influence on the network. The graphics processing unit (GPU) can accelerate performance by assigning each virtual machine a dedicated GPU for performance-boosting to improve the user experience. In this paper, we propose a high-performance VDI using an integration of a GPU on OpenStack with a PCI pass-through. It might have certain benefits over using virtualized hardware, such as lower latency, better performance, and more functionality. The evaluation and comparison of the computer processing unit (CPU) and GPU are presented among the different benchmark tools.

The ever growing computational demands of users call for efficient cloud resource management to avoid service-level agreement (SLA) violation. Virtualization co-locates multiple virtual machines (VMs) on a single physical server to share the underlying resources for efficient resource management. However, the decision about “what” and “where” to place workloads significantly impacts performance of hosted workloads. Existing cloud schedulers consider a single resource (RAM) to co-locate workloads that as a result lead to SLA violation due to non-optimal VM placement. To handle this issue, current study has updated nova scheduler to propose a multi-resource based VM placement approach to improve application performance in terms of central processing unit (CPU) utilization and execution time. Experimentally we have shown that our proposed method has lessened application execution time by 50% when compared with one of the well-known technique.