International Business Machines Corporation

Ildar Khabibrakhmanov

Rui Zhang

Tarun Kumar

Hendrik F Hamann

Mark Alan Lavin

Younghun Kim

Siyuan Lu

Anthony Paul Praino

Richard D Lawrence

Lloyd Alan Treinish

Upendra D Chitnis

Prem Melville

James Peter Cipriani

Sharathchandra UmapathiRao Pankanti

Theodore Gerard Van Kessel

Wei Zhang

Ramachandran Muralidhar

Levente Klein

Bruce Gordon Elmegreen

Emmanuel Yashchin

Yan Liu

Kevin Wilson Warren

Conrad M Albrecht

Wang Zhou

Youngdeok Hwang

David L Jensen

Minwei Feng

Wojciech Gryc

Cezar Pendus

Carlo Siebenschuh

Vaughn Robert Evans

Timothy R Bowden

Andrew J Dubois, Jr

Stephen Restivo

Christopher D Ross

In some examples, a method of vector-raster data fusion includes receiving vector data for a geographical location, and statistically analyzing the vector data to obtain vector statistics. In some examples the method further includes rasterizing the vector statistics, and storing at least one of the vector data and the rasterized vector statistics together in a key-value store together with previously stored raster data for the geographical location. In some examples, the vector data further includes metadata, and the method further includes storing the metadata in at least one of the key-value store or a separate vector database.

Distributed vector-raster fusion

Methods and systems for predicting irradiance include learning a classification model using unsupervised learning based on historical irradiance data. The classification model is updated using supervised learning based on an association between known cloudiness states and historical weather data. A cloudiness state is predicted based on forecasted weather data. An irradiance is predicted using a regression model associated with the cloudiness state.

Solar forecasting using machine learned cloudiness classification

Embodiments are directed to a computer-implemented method, computer system, and computer program product for forecasting power generation. The method includes receiving a first power generation forecast. A second power generation forecast is received, along with actual observed power generation. A model is created for the observed power generation based on the second power generation forecast. A third power generation forecast is created using the model for the observed power generation, the second power generation forecast, and the first power generation forecast.

Forecasting solar power generation using real-time power data

A method, computer system, and computer program product. Weather forecast data is generated with respect to an area encompassing a location of a solar farm by a computer system. Solar power output by the solar farm is forecasted by the computer system based on the generated weather forecast data. Forecasted solar power output data is generated by the computer system based on the forecasted solar power output by the solar farm. A power grid operation, including one or both of a power grid balancing operation and a power grid optimization operation, is performed based on the forecasted solar power output data.

Forecasting solar power output

A set of characteristics of a period is extracted from a forecast that is applicable to the period and a geographical area. From a repository, a set of historical data is selected corresponding to a historical period, the set of historical data including a historical forecast related to the geographical area, and an actual measurement of wind at a location in the geographical area, the set of historical data having a subset of the set of characteristics. From the set of historical data, a function is computed to represent a discrepancy between the historical forecast and the actual measurement over the historical period. A bias value is computed from the function. By applying the bias to a value in the forecast, an adjusted forecast is produced of winds at a wind turbine located at a location in the geographical area.

Temporal bias correction in wind forecasting

Embodiments are directed to a computer-implemented method of forecasting power generation. The method includes analyzing, using a processor, a set of historical weather data. A set of historical power generation data is analyzed using the processor. The processor then determines a plurality of clusters, where each cluster of the plurality of clusters represents weather data for a time period and power generated during the time period. The processor then receives a weather forecast for a future time period. The processor determines which cluster of the set of cluster contains weather data that is most similar to the weather forecast. The processor then uses the historical power generation data of the cluster to forecast power generation for the future time period.

Forecasting solar power generation using weather forecasts

Embodiments are directed to a computer-implemented method, computer system, and computer program product of forecasting power generation. The method includes analyzing a set of historical power generation data. Thereafter a set of clusters is determined wherein each cluster of the set of clusters represents power generated during the time period. Then receiving actual power generation data for a portion of the time period. Thereafter, determining which cluster of the set of clusters contains historical power generation data that is most similar to the actual power generation data. Then forecasting power generation for a remainder of the time period, using the historical power generation data of the cluster.

Forecasting solar power generation using real-time power data, weather data, and complexity-based similarity factors

A method and a system to perform multi-model blending are described. The method includes obtaining one or more sets of predictions of historical conditions, the historical conditions corresponding with a time T that is historical in reference to current time, and the one or more sets of predictions of the historical conditions being output by one or more models. The method also includes obtaining actual historical conditions, the actual historical conditions being measured conditions at the time T, assembling a training data set including designating the two or more set of predictions of historical conditions as predictor variables and the actual historical conditions as response variables, and training a machine learning algorithm based on the training data set. The method further includes obtaining a blended model based on the machine learning algorithm.

Multi-model blending

A method for automatically determining an Internet home page corresponding to a named entity identified by a specified descriptor including building a trained machine-learning model, generating candidate matches from the specified descriptor, wherein each candidate match includes an Internet address, extracting content-based features from websites associated with the Internet addresses of the candidate matches, determining a model score for each candidate match based on the content-based features using the trained machine-learning model, and determining a match from among the candidate matches according to the scores, wherein the match is returned as the Internet home page corresponding to the named entity.

Method and system using machine learning to automatically discover home pages on the internet

A method for identifying companies with specific business objectives that includes using existing sources of company firmographic data to identify a broad set of companies and associated websites, crawling the websites associated with the identified companies and indexing web site content for each of the identified companies with the specific business objective to realize indexed web content. The method further includes joining the company firmographic data with the indexed web content using a business objective common identifier to generate a store of joined structured firmographic data and indexed web content and presenting a display image representation of the store of joined structured firmographic data and indexed web content for user review. The display image further receives user input to score each of said companies identified therein, and using a search interface, querying the store of scored, joined structured firmographic data and indexed web content. The method further includes augmenting the search interface, or search results from a query, with predictive, machine-leaning processes that allow rapid identification of companies possibly missed in the query.

Method and system for identifying companies with specific business objectives

A system and method for detecting trends in time-managed lifetime data for products shipped in distinct vintages within a time window. Data is consolidated from several sources and represented in a form amenable to detection of trends using a criterion for measuring failure. A weight is applied to the failure measures, the weight increasing over the time the products are in the time window. A function of weighted failures is used to define a severity index for proximity to an unacceptable level of failures, and an alarm signal is triggered at a threshold level that allows the level of false alarms to be pre-set.

System and method for early detection of system component failure

Growing community of inventors

Syosset, NY, United States of America

Ildar Khabibrakhmanov