Browse Prior Art Database

Method of scalable visualization for management of multidimentional systems Disclosure Number: IPCOM000196661D
Publication Date: 2010-Jun-10
Document File: 2 page(s) / 472K

Publishing Venue

The Prior Art Database


Disclosed is a method to visually represent and organize information on high-dimensional systems in an interface. This method provides a quick view of the overall health of a complex network of systems and is able to represent the entities individually and allow for entity manipulations by people interested in the performance and characteristics of the network.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 52% of the total text.

Page 1 of 2

Method of scalable visualization for management of multidimentional systems

Nodes, each representing a system (or systems), within a datacenter will be plotted on an information display, and detailed information about the entity the node represents is provided when a user interacts with it via mouse click, hover, touch, or other means. Multiple configurable attributes relating to the systems (e.g. memory, error count, CPU, heat, network usage, etc.) are available for use to set classification mechanism for the visualization. An operator would specify the levels of importance for specific attributes and these levels would be aggregated and calculated to create values for a set of location dimensions of the display grid. Additional attributes can be represented by color, texture, opacity, movement, size and/or shape of the representative nodes. The resulting display can be used to give an idea of the overall real-time health of the datacenter.

A "cluster" of management entities represent nodes that have similar calculated location values and can be visually indicated through a means such as proximity of nodes to one another. Since location calculations are determined through a weighting of attributes, nodes within a cluster may include systems whose overall calculated values are similar but whose measurements for individual factors differ greatly. To address this, "grouping" within a cluster can be used to differentiate between highly weighted attributes on the sam...