Moisés Rodrigues

A case for virtualization of content delivery networks

Content Delivery Networks have gained a popular role among application service providers (ASPs) and infrastructural companies. A CDN is an overlay network that gives more control of asset delivery by strategically placing servers closer to the end-user, reducing response time and network congestion. Many strategies have been proposed to deal with aspects inherent to the CDN distribution model. Though mostly very effective, a traditional CDN approach of statically positioned elements often fails to meet quality of experience (QoE) requirements when network conditions suddenly change. In this paper, we introduce the idea of CDN virtualization. The goal is to allow programmatically modification in CDN infrastructure designed for video distribution, adapting it to new operating conditions. We developed a complete simulator focused on CDN overlay network characteristics where we implemented several approaches for each of the CDN elements. Our results show a decrease of 20% in startup delay and network usage.

High availability in clouds: systematic review and research challenges

Cloud Computing has been used by different types of clients because it has many advantages, including the minimization of infrastructure resources costs, and its elasticity property, which allows services to be scaled up or down according to the current demand. From the Cloud provider point-of-view, there are many challenges to be overcome in order to deliver Cloud services that meet all requirements defined in Service Level Agreements (SLAs). High availability has been one of the biggest challenges for providers, and many services can be used to improve the availability of a service, such as checkpointing, load balancing, and redundancy. Beyond services, we can also find infrastructure and middleware solutions. This systematic review has as its main goal to present and discuss high available (HA) solutions for Cloud Computing, and to introduce some research challenges in this area. We hope this work can be used as a starting point to understanding and coping with HA problems in Cloud.

Risk-based model for availability estimation of SAF redundancy models

Cloud outages, no matter how long, are responsible for large financial losses. Cloud providers look for solutions that provide high availability even in failure cases. Redundancy has been often used as an alternative; however it has a cost, and depending on the redundancy model, we can have different levels of availability. Beyond that, adding more resources also means adding more complexity and more point of failures. In this paper, we propose a risk-based model for estimating the availability of a redundancy setup. In order to analyze our model, we conduct Monte Carlo simulations and results show that for all models, the number of applications we deploy in a Cloud environment impacts on its availability.

Enabling transparent caching in LTE mobile backhaul networks with SDN

Todays mobile network architecture lacks the flexibility to efficiently handle the fast increasing amount of data traffic. SDN could potentially provide the required flexibility in future mobile architectures, however its introduction into the existing architecture is challenging. In this paper we propose a solution to improve the mobile backhauls flexibility based on SDN, compatible with the current architecture, focusing on the transparent in-network cachings use case. We explore the design space in terms of function placement, and propose a scalable solution for in-network caching based on stateless DPI and stateful connection tracking. We implemented a prototype of the proposed solution to evaluate its impact on MPEG DASH streaming performance. Our experimental results show that the delay introduced by our module is less than 5ms for 99% of the packets, which is negligible in todays LTE networks, and the slight negative impact on streaming rate selection is easily outweighed by the increased flexibility.

Self-organizing strategies for resource management in Cloud Computing: State-of-the-art and challenges

Due to the growth of Cloud Computing, the supporting infrastructure has become more complex, and the centralized solutions suffer resource management difficulties due to the large scale and the dynamicity of the scenario. Consequently, distributed solutions have been proposed in the literature and the self-organizing ones have attracted particular interest due to their robustness and adaptability characteristics. Techniques, such as bio-inspired computing, multi-agent systems, and evolutionary techniques are used to manage resources. The main goal of this paper is to present a start study about how self-organizing solutions are applied in resource management of Cloud providers, as well as to highlight the main research challenges in this area.

Joint Allocation of Nodes and Links with Load Balancing in Network Virtualization

Network virtualization is seen as the fundamental underlying technology for enabling future Internet services. Mapping virtual networks onto a substrate network is a well-known NP-hard problem. Therefore, some authors propose heuristic based strategies by allocating virtual networks in two uncoordinated steps: mapping virtual nodes and virtual links separately. However, this strategy could result in poor performance. In this work, we propose an algorithm for the joint allocation of virtual nodes and links with the focus on balancing the load in the substrate resources. Such an algorithm is designed to cope with capacity constraints and network delay, it also offers an abstraction to consider functional requirements like geographical location or hardware characteristics. Simulation results show that the proposed algorithm has similar or better performance than other coordinated strategies from the Literature, while requiring a considerably lower processing time, finding solutions up to 269 times faster than others solutions.

An Analytical View of Multiple CDNs Collaboration

Content Distribution Networks (CDN) are a well-known and accepted way to deliver content. Considering the ever growing number of users and also the growing number of small localized CDNs, there is a strong trend for collaboration among them. CDN collaboration may cause cost reduction for CDN providers and better quality of experience for the end user. However, CDN collaboration raises performance issues. This paper presents an analytical view of collaboration among CDNs. Our analytical approach provides studies of collaboration performance through metrics such as cache hit, latency, and number of caches. Then, we present a collaboration overhead representation, considering two collaboration request routing strategies. From our performance analyses, we show that CDN collaboration can reduce response time and could also help a primary CDN deal with a flash crowd event.

Analyzing strategies to effectively detect changes in content delivery networks

Content Delivery Networks have gained a popular role among application service providers (ASPs) and infrastructural companies. A CDN is an overlay network that gives more control of asset delivery by strategically placing servers closer to the enduser, reducing response time and network congestion. Many strategies have been proposed to deal with aspects inherent to the CDN distribution model. Though mostly very effective, a traditional CDN approach of statically positioned elements often fails to meet quality of experience (QoE) requirements when network conditions suddenly change. In this paper, we introduce a technique to detect significant changes in a monitored metric of a CDN in order to allow provisioning adaptation of resources, using easy access information with great practical viability. Results show decrease on network resources usage without considerable changes on quality of service (QoS). Furthermore, our technique has similar performance in comparison to an omniscient strategy.

Prototyping an Autonomic Cloud Infrastructure to Manage Live Streaming Applications Using a Software Defined Network: Performance Analysis and Challenges

Resource management in distributed environments, such as Cloud virtualized networks, is one of the main concerns of infrastructure providers. Despite the many advantages of centralized solutions, their unique point of failure and the lack of scalability make us consider the use of distributed and autonomic solutions. Beyond this, centralized solutions would be inefficient to deal with dynamic and peak situations. By using simple rules, each autonomic node can independently act and react according to the scenarios changes without the knowledge of the whole system, making autonomic management robust and adaptable. The main goal of this paper is to present the Role-Based Self-Appointment for Live Streaming (RBSA4LS) prototype, developed considering Software Defined Network technologies. The prototyped was developed and used to evaluate RBSA4LS performance. Our results show a significant decrease in network traffic and an increase of client Quality of Experience (QoE).

Self-management of Live Streaming Application in Distributed Cloud Infrastructure

Currently, live streaming traffic is responsible for more than half of aggregated traffic from fixed access networks in North America. But, due to traffic redundancy, it does not suitably utilize bandwidth and network resources. To cope with this problem in the context of Distributed Clouds (DClouds) we present RBSA4LS, an autonomic strategy that manages the dynamic creation of reflectors for reducing redundant traffic in live streaming applications. Under this strategy, nodes continually assess the utilization level by live streaming flows. When necessary, the network nodes communicate and self-appoint a new reflector node, which switches to multicasting video flows hence alleviating network links. We evaluated RBSA4LS through extensive simulations and the results showed that such a simple strategy can provide as much as 40 % of reduction in redundant traffic even for random topologies and reaches 85 % of bandwidth gain in a scenario with a large ISP topology.