Sunpower Corporation

Assia Spe, LLC

Sugumar Murugesan

Mehdi Mohseni

Saravanan Thulasingam

Mehdi Mohsen

Methods, systems, and computer storage media are disclosed for determining electric energy flow predictions for electric systems including photovoltaic solar systems. In some examples, a method is performed by a computer system and includes supplying a consumption time series and a predicted production time series for an electric system to a machine-learning predictor trained during a prior training phase using electric energy consumption training data and photovoltaic production training data. The consumption time series has a first data resolution, and the electric energy consumption training data and the photovoltaic production training data have a second data resolution greater than the first data resolution. The method includes determining, using an output of the machine-learning predictor, a predicted import time series of electric import values each specifying an amount of electric energy predicted to be imported by the electric system with a prospective photovoltaic solar system installed.

Energy flow prediction for electric systems including photovoltaic solar systems

A DSL management system predicts achieving improved DSL line performance before a DSL optimizer optimizes performance of the DSL line. The system obtains a current state of performance of the DSL line before optimization and a target state of performance after optimization. The system further obtains a measure of DSL line characteristics and identifies, from records of performance information associated with DSL lines, a subset of records associated with a subset of DSL lines that have a similar measure of the DSL line characteristics as the DSL line for which achieving improved performance is predicted. The system obtains a probability that the DSL optimizer will optimize the performance of the DSL line based on a frequency with which the identified subset of records indicates that the optimizer previously has optimized the performance of the subset of DSL lines.

Method and apparatus for predicting successful DSL line optimization

A DSL management system predicts achieving improved DSL line performance before a DSL optimizer in the DSL management system optimizes performance of the DSL line. The system obtains a current state of performance of the DSL line before optimization, and a target state of performance of the DSL line after optimization. The system further obtains a measure of the DSL line characteristics of the DSL line, and identifies, from among a plurality of records of performance information correspondingly associated with a plurality of DSL lines, a subset of the records of performance information correspondingly associated with a subset of DSL lines having a similar measure of the DSL line characteristics as the DSL line for which achieving improved DSL line performance is to be predicted. The system obtains a probability that the DSL optimizer will optimize the performance of the DSL line from the current state of performance to the target state of performance, based on a frequency with which the identified subset of records of information associated with the subset of DSL lines indicates that the DSL optimizer previously has optimized the performance of the subset of DSL lines from a same or similar state as the current state of performance to a same or similar state as the target state of performance.

Growing community of inventors

Foster City, CA, United States of America

Sugumar Murugesan