Service-level agreement

About: Service-level agreement is a research topic. Over the lifetime, 4358 publications have been published within this topic receiving 75333 citations. The topic is also known as: SLA.

Service chain modeling and embedding for NFV-based content delivery

Abstract: Increasing over-the-top video consumption endangers the sustainability of content delivery over the Internet. Internet Service Providers (ISP) face difficulties in competing on value-added services with content providers and Content Delivery Network (CDN) operators. In this respect, we propose a new model for the collaboration between content delivery stakeholders, so that CDN operators can deploy their software in ISP infrastructures leveraging on Network Function Virtualization (NFV). As the ISP network topology and utilization is deemed confidential, we use a high-level Service Level Agreement (SLA) for the negotiation of both computing resources and connectivity, allowing the ISP to optimize server selection, while providing at the same time sufficient flexibility to the CDN operators for content delivery. Furthermore, we present a linear programming formulation for the VNF Service Chain Embedding and an heuristic to increase problem tractability with a small cost overhead. Finally, we validate the efficiency of the proposed service chain model for virtual CDN management.

Profile-Based Resource Allocation for Virtualized Network Functions

Abstract: The virtualization of compute and network resources enables an unseen flexibility for deploying network services. A wide spectrum of emerging technologies allows an ever-growing range of orchestration possibilities in cloud-based environments. But in this context it remains challenging to rhyme dynamic cloud configurations with deterministic performance. The service operator must somehow map the performance specification in the Service Level Agreement (SLA) to an adequate resource allocation in the virtualized infrastructure. We propose the use of a VNF profile to alleviate this process. This is illustrated by profiling the performance of four example network functions (a virtual router, switch, firewall and cache server) under varying workloads and resource configurations. We then compare several methods to derive a model from the profiled datasets. We select the most accurate method to further train a model which predicts the services’ performance, in function of incoming workload and allocated resources. Our presented method can offer the service operator a recommended resource allocation for the targeted service, in function of the targeted performance and maximum workload specified in the SLA. This helps to deploy the softwarized service with an optimal amount of resources to meet the SLA requirements, thereby avoiding unnecessary scaling steps.

Service level objective for cloud hosted applications

Abstract: Embodiments are directed to declaratively managing software applications, dynamically applying configuration changes to a specified software application based on a service level objective (SLO) and to efficiently performing an impact analysis for a specified service level agreement SLO.

Third-Party Auditor (TPA): A Potential Solution for Securing a Cloud Environment

Abstract: The confidentiality and verification of customer's data at the cloud service provider (CSP) side becomes a critical issue in terms of both reliability (i.e., the trust aspect) and efficiency (i.e., the ease of performing such verifications). As data owners no longer physically possess their data storage, traditional cryptographic primitives for the purpose of data security protection cannot be directly adopted. In such a scenario, the use of a third-party auditor (TPA) provides both efficiency, transparency, and the fairness in performing the required auditing tasks as well as it serves as a bridge between the cloud service users (CSUs) and the CSPs. Thus, for practical use, it seems more rational to equip the verification capabilities with public auditability, which is expected to play a more important role in achieving economies of scale for cloud computing. Although the use of TPA provides several advantages, the fact that TPA is an untrusted entity and it can turn into a malicious user or promote insider threats cannot be ignored. Thus, for a complete realistic security solution where CSUs achieve maximum cloud benefits at minimum computational cost, the auditing of TPA is required. In this paper, we develop an auditing method for CSUs/CSPs to ensure the integrity of the TPA and minimize the possibility of insider threats or malicious activities. The integrity of TPA will be verified using the time-released session keys and the service level agreement (SLA).

Probabilistic demand allocation for cloud service brokerage

Abstract: Functioning as an intermediary between cloud tenants and providers, cloud service brokerages (CSBs) bring about great benefits to the cloud market. To maximize its own profit, a CSB is faced with a challenge: how to reserve servers and distribute tenant demands to the reserved servers such that the total reservation cost is minimized while the reserved servers can satisfy the tenant service level agreement (SLA)? Demand prediction and demand allocation are two steps to solve this problem. However, previous demand prediction methods cannot accurately predict tenant demands since they cannot accurately estimate prediction errors and also assume the existence of seasonal periods of demands. Previous demand allocation methods only aim to minimize the number of reserved servers rather than the server reservation cost, which is more challenging. To solve this challenge, we propose a Probabilistic Demand Allocation system (PDA). It predicts demands and more accurate prediction errors without the assumption of the existence of seasonal periods. It then formulates a nonlinear programming problem and has a decentralized method to find the problem solution. In addition to overcoming the shortcomings in previous methods, PDA is novel in that rather than separately conducting the prediction and demand allocation, it considers prediction errors in demand allocation in order to allocate demands with offsetting prediction errors (e.g., −1 and +1) to the same server, which helps find the problem solution. Both simulation and real-world experimental results demonstrate the superior performance of our system in reducing servers' reservation cost.