46 research outputs found
Cloud-Network Disaster Recovery against Cascading Failures
No full textCloud computing uses cloud networks (CNs) that integrate and virtualize computing servers and communication networks. In a CN, virtual machines (VMs) are interconnected through virtual networks (VNs) provisioned over a physical optical network. A disaster event is a serious threat to cloud computing infrastructure, not only for CN disconnections caused by multiple infrastructure failures, but by subsequent and unpredictable CN disconnections induced by cascading failures. Studies on disaster protection for CNs suggest large pre-provisioning of additional capacity before a possible disaster, with limited protection for later cascading failures. In this work, we propose an adaptive and cascading- failure-aware CN disaster recovery scheme that (re-)acts after the disaster, and uses risk modeling to reduce the capacity required for the recovery and minimize the post-disaster disconnection of CNs. Major power grid outages could cause cascading failures on cloud infrastructure operation. Thus, in this study, propagation patterns of power grid failures are used to estimate the location of cascading failures. Simulation results based on human-made disasters, e.g., weapon of mass destruction (WMD) attacks, show that our approach can lead to significant reduction in the risk of CN disconnections due to cascading failures, while reducing up to 50% of the capacity re-provisioning required for the recovery.</p
A survey on resiliency techniques in cloud computing infrastructures and applications
No full textToday's businesses increasingly rely on cloud computing, which brings both great opportunities and challenges. One of the critical challenges is resiliency: disruptions due to failures (either accidental or because of disasters or attacks) may entail significant revenue losses (e.g., US 25.5 billion in 2010 for North America). Such failures may originate at any of the major components in a cloud architecture (and propagate to others): 1) the servers hosting the application; 2) the network interconnecting them (on different scales, inside a data center, up to wide-area connections); or 3) the application itself. We comprehensively survey a large body of work focusing on resilience of cloud computing, in each (or a combination) of the server, network, and application components. First, we present the cloud computing architecture and its key concepts. We highlight both the infrastructure (servers, network) and application components. A key concept is virtualization of infrastructure (i.e., partitioning into logically separate units), and thus we detail the components in both physical and virtual layers. Before moving to the detailed resilience aspects, we provide a qualitative overview of the types of failures that may occur (from the perspective of the layered cloud architecture), and their consequences. The second major part of the paper introduces and categorizes a large number of techniques for cloud computing infrastructure resiliency. This ranges from designing and operating the facilities, servers, networks, to their integration and virtualization (e.g., also including resilience of the middleware infrastructure). The third part focuses on resilience in application design and development. We study how applications are designed, installed, and replicated to survive multiple physical failure scenarios as well as disaster failures
Load balancing and latency reduction in multi-user CoMP over TWDM-VPONs
No full textIn emerging cellular systems, optical fronthaul is expected to play a major role to support many control operations, e.g., Coordinated Multipoint (CoMP). CoMP is a promising technique for interference mitigation as it can transform interfing signals into joint transmission (reception) in which signals from adjacent cell sites are simultaneously transmitted (received) to (from) mobile terminals. But the exchange of information required by CoMP demands high flexibility and capacity. This paper proposes a new architecture for supporting CoMP operations in emerging cellular systems. It is based on a time-and-wavelength-division-multiplexed passive optical network (TWDM-PON) fronthaul, using virtualized base stations and a cloud radio access network (C-RAN) architecture. We also propose techniques to distribute the load on controllers to minimize the coordination delay. Results show that, for a typical setting, our methods can save up to 37% on the time required to distribute channel state information among multiple base stations
Resilient Cloud Network Mapping with Virtualized BBU Placement for Cloud-RAN
No full textCloud Radio Access Network (C-RAN) will improve mobile radio coordination and resource efficiency by allowing baseband processing unit (BBU) functions to be virtualized and centralized, i.e., deployed in a BBU hotel. We consider a BBU hoteling scheme based on the concept of access cloud network (ACN). An ACN consists of virtualized BBUs (vBBUs) placed in metro cloud data centers (metro DCs). A vBBU is connected to a set of remote radio heads (RRHs). ACN resiliency against network and processing failures is critical for C-RAN deployments. Hence, in this study, we propose three protection approaches: 1+1 ACN protection, 1+1 ACN and vBBU protection, and partial ACN protection. Simulation results show that both 1+1 ACN and 1+1 ACN and vBBU protection requires large capacity for backup to provide 100% survivability for singlelink and single-DC failures. As a result, we suggest a partial ACN protection approach which provides degraded services with only 8% additional network resources.</p
Risk-aware rapid data evacuation for large-scale disasters in optical cloud networks
No full textWe develop a risk-aware rapid data evacuation scheme for large-scale disasters in optical cloud networks. Simulations show that our algorithm significantly reduces the risk of data loss caused by disasters with minimum additional time consumption
Multiple traveling repairmen problem with virtual networks for post-disaster resilience
No full textIn network virtualization, when a disaster hits a physical network infrastructure, it is likely to break multiple virtual network connections. So, after a disaster occurs, the network operator has to schedule multiple teams of repairmen to fix the failed components, by considering that these elements may be geographically dispersed. An effective schedule is very important as different schedules may result in very different amounts of time needed to restore a failure. In this study, we introduce the multiple traveling repairmen problem (MTRP) for post-disaster resilience, i.e., to reduce the impact of a disaster. Re-provisioning of failed virtual links is also considered. We first formally state the problem, where our objective is to find an optimal schedule for multiple teams of repairmen to restore the failed components in physical network, maximizing the traffic in restored virtual network and with minimum damage cost. Then, we propose a greedy (GR) and a simulated annealing (SA) algorithm, and we measure the damage caused by a disaster in terms of disconnected virtual networks (DVN), failed virtual links (FVL), and failed physical links (FPL). Numerical result shows that both proposed algorithms can make good schedules for multiple repairmen teams, and SA leads to significantly lower damage in terms of DVN, FVL, and FPL than GR
Edge Computing and Networking: A Survey on Infrastructures and Applications
No full textAs a concept to enhance and extend cloud-computing capabilities, edge computing aims to provide Internet-based services in the close proximity to users by placing IT infrastructures at the network edge in forms of tiny datacenters. Taking advantage of the close distance to end user and access networks, edge datacenters can provide low-latency and context-aware services and further improve users' quality of experience. As the network edge is a geographically spread concept, the edge datacenters are usually highly distributed so that they can provide nearby storage and processing capabilities to most of the end users. Furthermore, edge datacenters also co-work with centralized cloud datacenters for service orchestration. Such decentralization and collaboration are expected to introduce significant transformations to both infrastructures and applications. To provide an overview of how edge can be integrated with cloud computing and how edge computing can benefit applications, this paper studies the infrastructure and application issues of edge computing and networking in several sub-aspects, including related concepts, infrastructures, resource management and virtualization, performance, and applications
Disaster-Survivable Cloud-Network Mapping
No full textCloud-computing services are provided to consumers through a network of servers and network equipment. Cloud-network (CN) providers virtualize resources [ e. g., virtual machine (VM) and virtual network (VN)] for efficient and secure resource allocation. Disasters are one of the worst threats for CNs as they can cause massive disruptions and CN disconnection. A disaster may also induce post-disaster correlated, cascading failures which can disconnect more CNs. Survivable virtual-network embedding (SVNE) approaches have been studied to protect VNs against single physical-link/-node and dual physical-link failures in communication infrastructure, but massive disruptions due to a disaster and their consequences can make SVNE approaches insufficient to guarantee cloud-computing survivability. In this work, we study the problem of survivable CN mapping from disaster. We consider risk assessment, VM backup location, and post-disaster survivability to reduce the risk of failure and probability of CN disconnection and the penalty paid by operators due to loss of capacity. We formulate the proposed approach as an integer linear program and study two scenarios: a natural disaster, e. g., earthquake and a human-made disaster, e. g., weapons-of-mass-destruction attack. Our illustrative examples show that our approach reduces the risk of CN disconnection and penalty up to 90% compared with a baseline CN mapping approach and increases the CN survivability up to 100% in both scenarios
Disaster-resilient virtual-network mapping and adaptation in optical networks
No full textToday's Internet applications include grid- and cloud-computing services which can be implemented by mapping virtual networks (VNs) over physical infrastructure such as an optical network. VN mapping is a resource-allocation problem where fractions of the resources (e.g., bandwidth and processing) in the physical infrastructure (e.g., optical network and servers/data-centers) are provisioned for specific applications. Researchers have been studying the survivable VN mapping (SVNM) problem against physical-infrastructure failures (typically by deterministic failure models), because this type of failure may disconnect one or more VNs, and/or reduce their capacities. However, disasters can cause multiple link/node failures which may disconnect many VNs and dramatically increase the post-disaster vulnerability to correlated cascading failures. Hence, we investigate the disaster-resilient and post-disaster- survivable VN mapping problem using a probabilistic model to reduce the expected VN disconnections and capacity loss, while providing an adaptation to minimize VN disconnections by any postdisaster single-physical-link failure. We model the problem as an integer linear program (ILP). Numerical examples show that our approach reduces VN disconnections and the expected capacity loss after a disaster.</p
5GCity Infrastructure Design and Definition (5.1)
No full textThis document is focused on the definition and/or design of the 5GCity Infrastructure on each one of the cities involved in 5GCity to support the different Use cases to be deployed in each one of them. To do so, this deliverable provide the needed level of detail (technical and deployment) to achieve the demonstration goals the project has within its timeframe. In fact, this deployment is very challenging, considering that new infrastructures in cities are particularly complex and sometimes subjected under non-expected circumstances that do not happen in the labs
