Cable Television Laboratories, Inc.

Hewlett-packard Development Company, L.p.

Scott H Clearwater

Bernardo A Huberman

Scott L Caruso

Jun Zeng

Jerome Alexander Rolia

Eric Hoarau

Giordano Bruno Beretta

Henry W Sang, Jr

Stephen Arendt

Nicolas Metts

Charles A Untulis

Bemardo Huberman

A method for power event notification includes (a) receiving, from a plurality of sensors at different respective locations within an area served by an electric power grid, a respective data set from each sensor, each data set including metadata associated with its respective sensor and electric power data generated by its respective sensor, (b) identifying, from at least one of the data sets, occurrence of an electric power event in the electric power grid, and (c) generating a notification of the electric power event.

Systems and methods for power event notification

A system and method for data collection and aggregation using a distributed network of communications enabled sensors connected to another primary network to achieve a secondary out-of-band monitoring perspective, for example, in power grids. The data collection system includes an aggregation and processing server configured to collect data from a variety of sensors adjacent to the monitored network each sensor includes secondary power such that it can continue data transmission even during power grid outages. The data collection system includes a method for secure real-time data ingest, machine learning enabled analysis, risk assessment, and anomaly detection on a broad geographic scale irrespective of isolated network boundaries.

System and method for distributed, secure, power grid data collection, consensual voting analysis, and situational awareness and anomaly detection

The present disclosure generally relates to apparatus, software and methods for predicting future network traffic. The disclosed apparatus, software and methods alleviate congestion and/or increase overall traffic flow by providing methods for reallocating future idle capacity.

Machine learning algorithms for quality of service assurance in network traffic

The present disclosure generally relates to systems, methods and software for determining an optimal burst transmission time through a modem, such as a cable modem, a wireless access point, a node in a cable network, or a satellite communication link. Particularly, the present disclosure makes it possible for a burst of queued data, defined as data above a certain percentile of a monitored traffic rate, to be transmitted by the modem at a time that provides the best chance of avoiding a collision with a co-occurring burst of data from another user connected to the same modem. In an embodiment, the systems, methods and software disclosed herein use the optimal transmission time to replace a contention window transmission time, at least for bursty data, or they completely eliminate the need for contention windows, at least for bursty data.

Optimal burst transmission times through single modems

A method for predicting network-traffic bursts includes identifying, in data received by a networking device, a plurality of network-traffic bursts, each of the plurality of network-traffic bursts occurring at a respective one of plurality of burst-times {t, t, . . . , t}. The method includes determining a time-interval &#x3c4;of a next burst occurring at &#x3c4;after burst-time tby determining respective values of &#x3c4;, a parameter &#x3be;, and a parameter &#x3b7;, that minimize, to within a tolerance, a quantity (&#x192;(&#x3be;,&#x3b7;,k)&#x2212;(&#x3c4;&#x2212;t)) for at least three values of a integer k. Parameters &#x3be; and &#x3b7; are, respectively, a real and imaginary part of a power-law exponent of a power law relating predicted time-interval &#x3c4;to any of the plurality of burst-times. The method includes determining, from a cumulative distribution function of a normal distribution of previously-identified network-traffic bursts, a time-duration during which the networking device may reallocate bandwidth.

Network-traffic predictor and method

A method for predicting network-traffic bursts includes identifying, in data received by a networking device, a plurality of network-traffic bursts, each of the plurality of network-traffic bursts occurring at a respective one of plurality of burst-times {t, t, . . . , t}. The method includes determining a time-interval &#x3c4;of a next burst occurring at &#x3c4;after burst-time tby determining respective values of &#x3c4;, a parameter &#x3be;, and a parameter &#x3b7;, that minimize, to within a tolerance, a quantity (f(&#x3be;, &#x3b7;, k)&#x2212;(&#x3c4;&#x2212;t)) for at least three values of a integer k. Parameters &#x3be; and &#x3b7; are, respectively, a real and imaginary part of a power-law exponent of a power law relating predicted time-interval &#x3c4;to any of the plurality of burst-times. The method includes determining, from a cumulative distribution function of a normal distribution of previously-identified network-traffic bursts, a time-duration during which the networking device may reallocate bandwidth.

A non-transitory, computer-readable medium has embedded therein instructions executable by a processor. The instructions simulate an operation of a print service provider (PSP) using a model of a printing system with a set of operation parameters for performing the PSP operation. The instructions determine a monitoring strategy based on the simulated PSP operation. The monitoring strategy is for monitoring the PSP operation when performed in the printing system.

Collecting data for a print service provider

Embodiments of the present invention relate to a system and method for pricing resources. One embodiment of the present invention includes a historical usage database adapted to store historical customer usage and pricing data, and a pricing algorithm module adapted to perform a simulation using the historical customer usage and pricing data to establish resource usage prices and swing option prices that will maintain a profit margin near or equal to a profit margin setting.

System and method of pricing resources

Embodiments of the present invention relate to a system and method facilitating selection of a portfolio of computational resources for a project. The system and method may comprise determining computational resource capacity characteristics from historical usage data relating to use of a heterogeneous inventory of computational resources, the computational resource capacity characteristics comprising a trace history representative of the availability of various components of the heterogeneous inventory of computational resources at various points in time. Additionally, embodiments of the present invention may comprise calculating a plurality of finishing times for a project by performing a plurality of simulation runs based on the computational resource capacity characteristics, wherein each of the plurality of simulation runs begins at a different time in the trace history. Further, embodiments of the present invention may comprise assembling the plurality of finishing times into a distribution, constructing a risk measure using the distribution, and facilitating selection of a portfolio for the project from the heterogeneous inventory of computational resources based on the risk measure and the plurality of finishing times.

System and method for selecting a portfolio of resources in a heterogeneous data center

A method, apparatus, and system are disclosed for determining a size of a utility date center. In one embodiment, a computer system includes a bus, a computer-readable memory coupled to the bus, and a processor coupled to the memory via the bus. The processor executes code for calculating, based on historical usage data, resource usage for a plurality of different applications of a plurality of servers in the utility data center (UDC); calculating, for each server, penalties imposed against the UDC and penalties imposed against at least one user of resources of the servers; and calculating a number of servers required to make the UDC profitable.

Method and system for determining size of a data center

A method and apparatus for market-based document layout selection use an automated auction or bartering system, i.e., an automated page layout system, to place objects within a page and automatically generate a page layout that is pleasing to a user. An object refers to any item that can be individually selected and manipulated, and may include shapes and pictures that appear on a display screen. The method and apparatus improve the quality of page layout in terms of user preferences, and optimize the speed at which various objects are arranged on a page in a pleasing manner. In addition, the resulting page layout may be consistent among pages because all pages are arranged according to a common algorithm.

Growing community of inventors

Menlo Park, CA, United States of America

Scott H Clearwater