公开(公告)号：US20140095076A1

公开(公告)日：2014-04-03

申请号：US13631480

申请日：2012-09-28

Applicant: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.

Inventor： Manish MARWAH ,  Martin ARLITT ,  Prithwish CHAKRABORTY ,  Naren Ramakrishnan

IPC: G06F19/00 ,  G06F17/18 ,  G01W1/00

CPC classification number: G06Q10/04 ,  F24S2201/00 ,  H02S50/00

Abstract: Systems and automated methods for predicting photovoltaic (PV) generation are provided. Weather forecast data and present-day and historical PV generation data are provided to respective predictors. The predictors derive weighted predictions that are used to calculate a Bayesian model average. Near-future generation by the PV system is predicted using the Bayesian model average. Production rates, worker scheduling, hours of operation and other planning decisions can be made in accordance with the predicted near-future generation.

Abstract translation: 提供了用于预测光伏（PV）一代的系统和自动化方法。 将天气预报数据和当前和历史PV生成数据提供给各个预测值。 预测因子得出用于计算贝叶斯模型平均值的加权预测。 使用贝叶斯模型平均预测PV系统的近一代。 生产率，工人安排，营业时间和其他规划决定可以根据预测的未来一代进行。

公开(公告)号：US20140324760A1

公开(公告)日：2014-10-30

申请号：US13874254

申请日：2013-04-30

Applicant: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.

Inventor： Manish MARWAH ,  Martin Arlitt ,  Amip J. Shah ,  Cullen E. Bash

IPC: G06N7/00

CPC classification number: G06N7/005

Abstract: According to an example, synthetic time series data generation may include receiving empirical meter data for a plurality of users, and using the empirical meter data to estimate parameters of a Markov chain. The Markov chain may be used to generate the synthetic time series data having statistical properties similar to the statistical properties of the empirical meter data.

Abstract translation: 根据示例，合成时间序列数据生成可以包括接收多个用户的经验表数据，并且使用经验计量器数据来估计马尔可夫链的参数。 马尔可夫链可用于产生具有与经验仪表数据的统计特性相似的统计特性的合成时间序列数据。

公开(公告)号：US20140325251A1

公开(公告)日：2014-10-30

申请号：US13874221

申请日：2013-04-30

Applicant: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.

Inventor： Manish MARWAH ,  Martin Arlitt ,  Amip J. Shah ,  Cullen E. Bash

IPC: G06F1/14

CPC classification number: G06F1/14 ,  G06F17/30551 ,  G06F17/30592 ,  G06Q10/06 ,  G06Q10/063 ,  G06Q10/1091

Abstract: According to an example, synthetic time series data generation may include receiving time series data for a plurality of users, and applying dimensionality reduction to transform the time series data from a high dimensional space n of the time series data to a low dimensional space m, where m

Abstract translation: 根据示例，合成时间序列数据生成可以包括接收多个用户的时间序列数据，并且应用维数降低来将时间序列数据从时间序列数据的高维空间n变换为低维空间m， 其中m