Analytic tests are used to detect chaotic (power-tail) behavior in one or more computer system resources in a distributed computing environment. The analytic tests are used to determine if data (indicative of one or more parameters related to computer system resources) exhibit large deviations from a mean, a high variance and other properties consistent with large values in the tail portion of a power-tail distribution. The tests can be performed in any order, and fewer than three can be performed. If all three tests indicate the existence of power-tail behavior, chaotic behavior of the data is likely. If all three tests indicate the lack of power-tail behavior, chaotic behavior of the data is unlikely. If the results are mixed, then more data or analysis may be needed. The results may be used for modeling and/or altering the configuration of the distributed computing environment.

A set of algorithms for detecting a renewal power-tail behavior which often relates to chaotic system activities in one or more computer system resources of a distributed computing environment, i.e., an enterprise. Analysis and/or prediction software receives a set of metric data points from agent software on one or more computer systems. The analysis and/or prediction software performs three analytic tests relating to distinctive properties of power-tail distributions: a first test to determine whether the set of data points exhibits large deviations from the mean, a second test to determine whether the set of data points exhibits a high variance, and a third test to determine whether the set of the largest data points exhibits properties consistent with large values in a tail portion of a power-tail distribution. The tests can be performed in any order, and in other embodiments, fewer than three can be performed. Each test has two possible results: successful if the test indicates a likelihood of power-tail behavior, or unsuccessful if it indicates that power-tail behavior is unlikely. The results of the three tests are combined to determine the overall likelihood of a power-tail distribution. If all three tests are successful, then power-tail behavior is likely. If all three tests are unsuccessful, then power-tail behavior is unlikely. If the results are mixed, then typically more data or analysis is needed. The results are used for modeling and/or altering the configuration of the enterprise.

The present invention describes a system for automatically monitoring and managing Service Level Agreements on behalf of Service Providers (such as Application Service providers). The system is based on a specialized SLA language that can translate complex or simple Service Level Agreements into measurable and controllable criterion. The system enables Application Service providers to set up customized Service Level Agreements with customers, and monitor, modify and control all aspects of these agreements, including billing, sales, Customer Relation Management, customer support and Quality of Service. The technology on which the present invention is based is a formula driven language that translates Service Level Agreement details into commands. As such these details can be tracked and processed to produce detailed reports and summaries.

In a bandwidth control service management apparatus of a network operated by a network offerer and a customer, an available bandwidth of a premium bandwidth control service demand, accepted from the customer, with a higher priority than a regular bandwidth control service of best effort type, is compared with an applied threshold value, accepted from a network offerer through a network interface 7 to determine an availability of the premium bandwidth control service. The result is notified to the customer through the customer interface 2, and the serviceable bandwidth manager 3 is provided which demands that the network should secure a bandwidth in order that the customer who has received the notification of a service permission can start the premium bandwidth control service when the premium bandwidth control service is determined to be available. This serviceable bandwidth manager 3 notifies a present applied threshold value in response to a collection demand by the network offerer, and adopting a changed applied threshold value for the determination when the network offerer has changed the applied threshold value.

A system and method for automatically creating causal association models of complex information technology (IT) systems. System components and elements are subject to periodic monitoring associated with performance thresholds. Numerical data indicating component state information is converted to Boolean attributes by use of defined or discovered thresholds. Resulting data is accumulated and data mined for component relations within the IT system using association rules induction methods. Models of the system may then be adapted with results generated from the analysis to accurately reflect causal relations among various system components.