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.

Efficient Orchestration Mechanisms for Congestion Mitigation in NFV: Models and Algorithms

Abstract: Network Functions Virtualization (NFV) has recently gained momentum among network operators as a means to share their physical infrastructure among virtual operators, which can independently compose and configure their communication services. However, the spatio-temporal correlation of traffic demands and computational loads can result in high congestion and low network performance for virtual operators, thus leading to service level agreement breaches. In this paper, we analyze the congestion resulting from the sharing of the physical infrastructure and propose innovative orchestration mechanisms based on both centralized and distributed approaches, aimed at unleashing the potential of the NFV technology. In particular, we first formulate the network functions composition problem as a non-linear optimization model to accurately capture the congestion of physical resources. To further simplify the network management, we also propose a dynamic pricing strategy of network resources, proving that the resulting system achieves a stable equilibrium in a completely distributed fashion, even when all virtual operators independently select their best network configuration. Numerical results show that the proposed approaches consistently reduce resource congestion. Furthermore, the distributed solution well approaches the performance that can be achieved using a centralized network orchestration system.

Online Virtual Machine Placement for Increasing Cloud Provider’s Revenue

Abstract: Cost savings have become a significant challenge in the management of data centers. In this paper, we show that, besides energy consumption, service level agreement (SLA) violations also severely degrade the cost-efficiency of data centers. We present online VM placement algorithms for increasing cloud provider’s revenue. First, First-Fit and Harmonic algorithm are devised for VM placement without considering migrations. Both algorithms get the same performance in the worst-case analysis, and equal to the lower bound of the competitive ratio. However, Harmonic algorithm could create more revenue than First-Fit by more than 10 percent when job arriving rate is greater than 1.0. Second, we formulate an optimization problem of maximizing revenue from VM migration, and prove it as NP-Hard by a reduction from 3-Partition problem. Therefore, we propose two heuristics: Least-Reliable-First (LRF) and Decreased-Density-Greedy (DDG). Experiments demonstrate that DDG yields more revenue than LRF when migration cost is low, yet leads to losses when SLA penalty is low or job arriving rate is high, due to the large number of migrations. Finally, we compare the four algorithms above with algorithms adopted in Openstack using a real trace, and find that the results are consistent with the ones using synthetic data.

Dynamic Service Management in Heterogeneous Networks

Abstract: Novel network architectures allow users to get specific performance guarantees via the definition of a document where QoS (Quality of Service) requirements are linked to the user traffic description. Such a document is defined SLA (Service Level Agreement), and it is a formal high level definition (user view) of characteristics for a communication service, whereas low level specification (network view) is obtained translating the SLA in a different document named SLS (Service Level Specification). Although in the case of static services the network configuration process is a well defined activity, when dynamic services come into play a more complicated scenario where SLA translation into the appropriate SLS is not a one-step and static process, but it needs an active and consistent evaluation with respect to the current situation. We claim that to make this process happen automatically, we need to have intelligent devices able to translate request specified inside SLAs in the most appropriate network configuration (by means of dynamic SLS) depending on client's current “service conditions.” In this paper we introduce a framework for distributed network management through an entity, namely AcMe (Active Mediator), which performs dynamic creation of network services in a transparent to the user fashion. A new protocol, HNMP (Heterogeneous Network Management Protocol), orchestrates all AcMe functionality. Finally, an experimental analysis is presented.

A statistical based resource allocation scheme in cloud

Abstract: Recently, cloud computing has emerged as a new computing paradigm on the Internet. With the development of cloud computing, enterprise data centers shift towards a utility computing model where many critical business applications share a common pool of infrastructure resources offering capacity on demand. The virtual machine with the features of strong isolation and flexible is usually assigned as the basic unit. However, as the demand of each type of VM can fluctuate independently at run time, it becomes a challenging problem to allocate data center resources to each VM to balance the workload in the cloud. In this paper, we introduce an approach (Statistic based Load Balance, SLB) that makes use of the statistical prediction and available resource evaluation mechanism to make online resource allocation decisions. Unlike the methods that balance load based on SLA (Service Level Agreement) of VMs, SLB achieves load balancing by predicting the VM's resource demand. The approach includes two parts:(1) A data analysis of on-line historical performance for forecasting the resource demand of each VM, and (2) An algorithm for choosing a proper host in the resource pool to run the VM. Experiments show that SLB can perform load balance in time, and also perform more balanced use of different resources.

Designing Service Level Agreements for Inventory Management

Abstract: Service level agreements (SLAs) are widely employed forms of performance-based contracts in operations management. They compare performance during a period against a contracted service level and penalize outcomes exceeding some allowed deviation. SLAs have a number of design characteristics that need careful tuning to ensure that incentives are properly aligned. However, there is little theoretical research in this area. Using an example of an SLA for outsourcing inventory management, we make a number of recommendations. First it is preferable, if possible, that penalties be proportional to the underperformance rather than lump-sum ones. This goes a long way towards mitigating strategic (�gaming�) behavior by the supplier. Second, it might be thought that giving �bonuses for good performance� rather than �penalties for bad performance� are essentially identical apart from the former being a more positive approach to management. This turns out to be incorrect in the case of large percentage service rate targets and that penalties will normally be preferred by the buying firm. Third, in order not to incorrectly penalize underperformance resulting purely from �noise� rather than supplier efforts, management might think it best to make allowed deviations from the target generous. Again intuition is not a helpful guide here: for proportional penalties, acceptable performance deviations should be close to the target. Although these results come from a particular inventory application, it is likely that the lessons are applicable to SLAs in general.