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.

Predicting cloud resource provisioning using machine learning techniques

Abstract: In order to meet Service Level Agreement (SLA) requirements, Virtual Machine (VM) resources must be provisioned few minutes ahead due to the VM boot-up time. One way to do this is by predicting future resource demands. In this research, we have developed and evaluated cloud client prediction models for TPCW benchmark web application using three machine learning techniques: Support Vector Machine (SVM), Neural Networks (NN) and Linear Regression (LR). We included the SLA metrics for Response Time and Throughput to the prediction model with the aim of providing the client with a more robust scaling decision choice. Our results show that Support Vector Machine provides the best prediction model.

BG: A Benchmark to Evaluate Interactive Social Networking Actions

Abstract: BG is a benchmark that rates a data store for processing interactive social networking actions using a pre-specified service level agreement, SLA. An example SLA may require 95% of issued requests to observe a response time faster than 100 milliseconds. BG computes two different ratings named SoAR and Socialites. In addition, it elevates the amount of unpredictable data produced by a data store to a first class metric, including it as a key component of the SLA and quantifying it as a part of the benchmarking process. One may use BG for a variety of purposes ranging from comparing different data stores with one another, evaluating alternative physical data organization techniques given a data store, quantifying the performance characteristics of a data store in the presence of failures (either CP or AP in CAP theorem), among others. This study illustrates BG’s first use case, comparing a document store with an industrial strength relational database management system (RDBMS) deployed either in stand alone mode or augmented with memcached. No one system is superior for all BG actions. However, when considering a mix of actions, the memcached augmented RDBMS produces higher ratings.

System and method for managing a service level agreement

Abstract: A system and method for managing communications services of users of a packet network Parameters associated with service agreements of users of a packet network may be stored. Network performance information associated with the users may also be stored. The network performance information may be accessed to read a quality of service parameter of communications over the packet network for a user over a given time period. The parameters associated with a service agreement may also be accessed. A quality of service parameter for the user to receive during the time period as contracted by the user may be read. A determination as to whether the user has received a quality of service for communicating over the packet network below the contracted quality of service may be made and the user, in response to determining that the quality of service is below the contracted quality of service, may be compensated.

Security service level agreements: quantifiable security for the enterprise?

Abstract: A popular business paradigm for information systems treats the information infrastructure as a corporate utility. In this model, a fixed Total Cost of Ownership (TCO) is associated with a given workstation, the network infrastructure, user applications, and personnel required for operational support. Related to the TCO model is the Seat Management model, which exploits the economies of standardization and scale to reduce information technology expenses. In both of these models, a defined, measurable, service level is applied as a cost metric, For example, seven days per week, twenty-four hour help desk support is more costly than five clays per week, business hours support. These measurable service levels are defined as Service Level Agreements. Few security services have been specified in terms that are amenable to Service Level Agreements. This raises the question -- can security be adequately expressed in a Service Level Agreement context. This paper looks at a derivation of security related service level agreements for a large enterprise. The possible applications of this approach are presented, as is a discussion of the caveats an information technology organization should consider prior to adopting security service level agreements.

PANDA: Specifying Policies for Automated Negotiations of Service Contracts

Abstract: The Web and Grid services frameworks provide a promising infrastructure for cross-organizational use of online services. The use of services in large-scale and cross-organizational environments requires the negotiation of agreements that define these services. Buying at a fine granularity just when a need arises is only feasible if the costs of establishing new agreements are low. Today, negotiation is often a manual process yet many simple online services would allow full or partial automation. The PANDA approach automates decision-making and proposes to specify a negotiation policy, expressing a party’s private negotiation strategy, by combining rules and utility functions. In addition, the decision-making problem can be decomposed into different aspects that can be executed by different interacting decision-makers. Using PANDA for policy specification and negotiation decision-making reduces the costs of setting up new services and contracts. Hence, the use of fine-grained on-demand services becomes feasible.