Guaranteeing high levels of availability is a huge challenge for cloud providers. The authors look at the causes failures and recommend ways to prevent them minimize their effects when they occur.

Distributed digital infrastructures for computation and analytics are now evolving towards an interconnected ecosystem allowing complex applications to be executed from IoT Edge devices the HPC Cloud (aka Computing Continuum, Digital or Transcontinuum). Understanding end-to-end performance in such a continuum is challenging. This breaks down reconciling many, typically contradicting application requirements constraints with low-level infrastructure design choices. One important challenge...

Cloud computing has gained popularity in recent years due to its pay-as-you-go business model, high availability of services, and scalability. Service unavailability does not affect just user experience but is also translated into direct costs for cloud providers companies. Part this SLA breaches, once interruption time greater than those signed the contract generate financial penalties. Thus, have tried identify failure points estimate their services. This paper proposes models assess...

A data center is divided into three basic subsystems: information technology (IT), power, and cooling. Cooling plays an important role related to availability, a failure in this subsystem may cause interruption of services. Generally, redundant cooling implemented based on replacing the failed component by standby one. However, it also can be rotation computer room air conditioners (CRACs). This paper proposes scalable models that represent behavior evaluate impact failures availability....

The cloud data center is a complex system composed of power, cooling, and IT subsystems. power subsystem crucial to feed the equipment. Power disruptions may result in service unavailability. This paper analyzes impact failures on services regarding different architecture configurations based TIA-942 standard such as non-redundant, redundant, concurrently maintainable, fault tolerant. We model both subsystems, IT, through Stochastic Petri Net (SPN). availability results show that tolerant...

Large data centers are complex systems that depend on several generations of hardware and software components, ranging from legacy mainframes rack-based appliances to modular blade servers modern rack scale design solutions. To cope with this heterogeneity, the center manager must coordinate a multitude tools, protocols, standards. Currently, managers, standardization bodies, hardware/software manufacturers joining efforts develop promote Redfish as main management standard for centers, even...

The Network Access Control (NAC) management is a critical task, especially in current networks that are composed of many heterogeneous things (Internet Things) connected to share data, resources and Internet access. Software-Defined Networking (SDN) simplifies the network design operation, offers new opportunities (programmability, flexibility, dy-namicity, standardization) manage network. Despite this, access control remains challenge, once managing security policies involves dealing with...

Traditional data center infrastructure suffers from a lack of standard and ubiquitous management solutions. Despite the achieved advances, existing tools interoperability are sometimes hardware dependent. Vendors already actively participating in specification design new software interfaces within different forums. Nevertheless, complexity variety components that includes servers, cooling, networking, power hardware, coupled with introduction defined paradigm, led to parallel development...

Summary Next‐generation cloud data centers are based on software‐defined center infrastructures that promote flexibility, automation, optimization, and scalability. The Redfish standard the Intel Rack Scale Design technology enable infrastructure disaggregate bare‐metal compute, storage, networking resources into virtual pools to dynamically compose create performance‐optimized (vPODs) tailored workload‐specific demands. This article proposes four chassis design configurations Distributed...

Many enterprises rely on cloud infrastructure to host their critical applications (such as trading, banking transaction, airline reservation system, and credit card authorization). The unavailability of these may lead severe consequences that go beyond the financial losses, reaching provider reputation too. However, maintain high availability in a data center is difficult task due its complexity. power subsystem crucial for entire operation because it supplies all other subsystems, including...

Making data centers highly available remains a challenge that must be considered since the design phase. The problem is selecting right strategies and components for achieving this goal given limited investment. Furthermore, center designers currently lack reliable specialized tools to accomplish task. In paper, we disclose formal method chooses optimize availability of while considering budget as constraint. For that, make use stochastic models represent cloud infrastructure based on...

Summary Emergency call services are expected to be highly available in order minimize the loss of urgent calls and, as a consequence, life due lack timely medical response. This service availability depends heavily on cloud data center which it is hosted. However, information alone cannot provide sufficient understanding how failures impact and users' perception. In this paper, we evaluate an emergency system, considering service‐level metrics such number affected per failure time takes...

Summary To assess the availability of different data center configurations, understand main root causes failures and represent its low‐level details, such as subsystem's behavior their interconnections, we have proposed, in previous works, a set stochastic models to architectures (considering three subsystems: power, cooling, IT) based on TIA‐942 standard. In this paper, propose Data Center Availability (DCAV), web‐based software system allow operators evaluate infrastructure through...

In more and application areas, we are witnessing the emergence of complex workflows that combine computing, analytics learning. They often require a hybrid execution infrastructure with IoT devices interconnected to cloud/HPC systems (aka Computing Continuum). Such subject constraints requirements in terms performance, resource usage, energy consumption financial costs. This makes it challenging optimize their configuration deployment. We propose methodology support optimization real-life...

The next-generation data center introduces the refactoring of traditional in order to create pools disaggregated resource units, such as processors, memory, storage, network, power, and cooling sources, named composable system (CSs) with purpose offering flexibility, automation, optimization, scalability. In this paper, we solve an optimization problem allocate CSs considering next- generation centers. main goal is maximize CS availability for application owner, having its minimum...

Enterprise network managers need to control the access their resources and protect them from malicious users. Current Network Access Control (NAC) solutions rely on approaches, such as firewalls, VLAN, ACL, LDAP that are inflexible require per-device vendor-specific configurations, being error-prone. Besides, misconfigurations may result in vulnerabilities could compromise overall security. Managing security policies involve dealing with many rules, conflicting policies, rule priorities, right...

Distributed digital infrastructures for computation and analytics are now evolving towards an interconnected ecosystem allowing complex applications to be executed from IoT Edge devices the HPC Cloud (aka Computing Continuum, Digital or Transcontinuum). Understanding end-to-end performance in such a continuum is challenging. This breaks down reconciling many, typically contradicting application requirements constraints with low-level infrastructure design choices. One important challenge...

In more and application areas, we are witnessing the emergence of complex workflows that combine computing, analytics learning. They often require a hybrid execution infrastructure with IoT devices interconnected to cloud/HPC systems (aka Computing Continuum). Such subject constraints requirements in terms performance, resource usage, energy consumption financial costs. This makes it challenging optimize their configuration deployment. We propose methodology support optimization real-life...