Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOpposites Attract: Virtual Cluster Embedding for Profit
60
0
0.0
(
0
)
Added by
Arne Ludwig
Publication date
2015
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
It is well-known that cloud application performance critically depends on the network. Accordingly, new abstractions for cloud applications are proposed which extend the performance isolation guarantees to the network. The most common abstraction is the Virtual Cluster V C(n, b): the n virtual machines of a customer are connected to a virtual switch at bandwidth b. However, today, not much is known about how to efficiently embed and price virtual clusters. This paper makes two contributions. (1) We present an algorithm called Tetris that efficiently embeds virtual clusters arriving in an online fashion, by jointly optimizing the node and link resources. We show that this algorithm allows to multiplex more virtual clusters over the same physical infrastructure compared to existing algorithms, hence improving the provider profit. (2) We present the first demand-specific pricing model called DSP for virtual clusters. Our pricing model is fair in the sense that a customer only needs to pay for what he or she asked. Moreover, it features other desirable properties, such as price independence from mapping locations.
rate research
Read More
Cloud computing has emerged as a powerful and elastic platform for internet service hosting, yet it also draws concerns of the unpredictable performance of cloud-based services due to network congestion. To offer predictable performance, the virtual cluster abstraction of cloud services has been proposed, which enables allocation and performance isolation regarding both computing resources and network bandwidth in a simplified virtual network model. One issue arisen in virtual cluster allocation is the survivability of tenant services against physical failures. Existing works have studied virtual cluster backup provisioning with fixed primary embeddings, but have not considered the impact of primary embeddings on backup resource consumption. To address this issue, in this paper we study how to embed virtual clusters survivably in the cloud data center, by jointly optimizing primary and backup embeddings of the virtual clusters. We formally define the survivable virtual cluster embedding problem. We then propose a novel algorithm, which computes the most resource-efficient embedding given a tenant request. Since the optimal algorithm has high time complexity, we further propose a faster heuristic algorithm, which is several orders faster than the optimal solution, yet able to achieve similar performance. Besides theoretical analysis, we evaluate our algorithms via extensive simulations.
We study the profit maximization problem of a cognitive virtual network operator in a dynamic network environment. We consider a downlink OFDM communication system with various network dynamics, including dynamic user demands, uncertain sensing spectrum resources, dynamic spectrum prices, and time-varying channel conditions. In addition, heterogenous users and imperfect sensing technology are incorporated to make the network model more realistic. By exploring the special structural of the problem, we develop a low-complexity on-line control policies that determine pricing and resource scheduling without knowing the statistics of dynamic network parameters. We show that the proposed algorithms can achieve arbitrarily close to the optimal profit with a proper trade-off with the queuing delay.
We study properties of some standard network models when the population is split into two types and the connection pattern between the types is varied. The studied models are generalizations of the ErdH{o}s-R{e}nyi graph, the configuration model and a preferential attachment graph. For the ErdH{o}s-R{e}nyi graph and the configuration model, the focus is on the component structure. We derive expressions for the critical parameter, indicating when there is a giant component in the graph, and study the size of the largest component by aid of simulations. When the expected degrees in the graph are fixed and the connections are shifted so that more edges connect vertices of different types, we find that the critical parameter decreases. The size of the largest component in the supercritical regime can be both increasing and decreasing as the connections change, depending on the combination of types. For the preferential attachment model, we analyze the degree distributions of the two types and derive explicit expressions for the degree exponents. The exponents are confirmed by simulations that also illustrate other properties of the degree structure.
Network virtualization provides a promising solution to overcome the ossification of current networks, allowing multiple Virtual Network Requests (VNRs) embedded on a common infrastructure. The major challenge in network virtualization is the Virtual Network Embedding (VNE) problem, which is to embed VNRs onto a shared substrate network and known to be $mathcal{NP}$-hard. The topological heterogeneity of VNRs is one important factor hampering the performance of the VNE. However, in many specialized applications and infrastructures, VNRs are of some common structural features $textit{e.g.}$, paths and cycles. To achieve better outcomes, it is thus critical to design dedicated algorithms for these applications and infrastructures by taking into accounting topological characteristics. Besides, paths and cycles are two of the most fundamental topologies that all network structures consist of. Exploiting the characteristics of path and cycle embeddings is vital to tackle the general VNE problem. In this paper, we investigated the path and cycle embedding problems. For path embedding, we proved its $mathcal{NP}$-hardness and inapproximability. Then, by utilizing Multiple Knapsack Problem (MKP) and Multi-Dimensional Knapsack Problem (MDKP), we proposed an efficient and effective MKP-MDKP-based algorithm. For cycle embedding, we proposed a Weighted Directed Auxiliary Graph (WDAG) to develop a polynomial-time algorithm to determine the least-resource-consuming embedding. Numerical results showed our customized algorithms can boost the acceptance ratio and revenue compared to generic embedding algorithms in the literature.
Structured P2P overlays provide a framework for building distributed applications that are self-configuring, scalable, and resilient to node failures. Such systems have been successfully adopted in large-scale Internet services such as content delivery networks and file sharing; however, widespread adoption in small/medium scales has been limited due in part to security concerns and difficulty bootstrapping in NAT-constrained environments. Nonetheless, P2P systems can be designed to provide guaranteed lookup times, NAT traversal, point-to-point overlay security, and distributed data stores. In this paper we propose a novel way of creating overlays that are both secure and private and a method to bootstrap them using a public overlay. Private overlay nodes use the public overlays distributed data store to discover each other, and the public overlays connections to assist with NAT hole punching and as relays providing STUN and TURN NAT traversal techniques. The security framework utilizes groups, which are created and managed by users through a web based user interface. Each group acts as a Public Key Infrastructure (PKI) relying on the use of a centrally-managed web site providing an automated Certificate Authority (CA). We present a reference implementation which has been used in a P2P VPN (Virtual Private Network). To evaluate our contributions, we apply our techniques to an overlay network modeler, event-driven simulations using simulated time delays, and deployment in the PlanetLab wide-area testbed.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
