General Electric Company

General Electric Capital Corporation

Rajesh Tyagi

Jason Wayne Black

Bex George Thomas

Ronald Ray Larson

John Andrew Ellis

Matthew Christian Nielsen

Andrew Day

Rayette Ann Fisher

Michael Joseph Krok

Sahika Genc

Xiaofeng Wang

Kete Chalermkraivuth

Thomas Paul Repoff

Jayanth Kalle Marasanapalle

Augusto Ramon Sellhorn

Marc Anthony Garbiras

Abhinanda Sarkar

Nitish Umang

Angshuman Saha

Savanoor Pradeep Rai

James G Russo

Matthew Allen

Murali Mohan Baggu Data Venkata Satya

Martha Gardner

Shirley Au

Roy Wilson

Malcolm Craig Winslow

Michael Dion

Aristotelis Emmanouil Thanos Filis

Prasoon Tiwari

Systems and techniques for monitoring, predicting and/or alerting for census periods in medical inpatient units are presented. A system can perform a first machine learning process to learn patterns in patient flow data related to a set of patient identities and a set of operations associated with a set of medical inpatient units. The system can also perform a second machine learning process to detect abnormalities associated with the patterns in the patient flow data. Furthermore, the system can determine patient census data associated with a prediction for a total number of patient identities in the set of medical inpatient units during a period of time based on the patterns and the abnormalities. The system can also generate an alert for a user interface in response to a determination that the patient census data satisfies a defined criterion.

Monitoring, predicting and alerting for census periods in medical inpatient units

A method and system for controlling demand events in a utility network with multiple customer sites. The value of a demand response parameter threshold for invoking a demand response event is calculated based on the number of available demand response events and the number of opportunities remaining to issue the available demand response events. This parameter represents the utility objectives for using the demand response program (e.g., cost savings, reliability, avoided costs). A current value of the demand response parameter is compared to the threshold value, and a determination is made whether or not to call a demand response event for the current opportunity, or to save the event for a future opportunity based upon this comparison.

Method and system for demand response management in a network

Method and system to provide co-optimized utilization of demand response and energy storage resources in an electrical grid system. The system may include a module to evaluate a marginal savings relative to a dispatch cost, if a demand response event is performed. The system may further include a module to evaluate a marginal savings relative to the dispatch cost, if an energy storage event is performed, and a controller including circuitry may be configured to determine a control strategy to perform a dispatch including a demand response event and/or an energy storage event, based at least in part on the respective marginal savings of the demand response event and/or the energy storage event, which may be selected to co-optimize an integrated utilization of the demand response and energy storage resources to meet a given objective.

Method and system to co-optimize utilization of demand response and energy storage resources

A method includes receiving at least one event parameter for a demand response event and identifying a pool of customers. The pool of customers includes a plurality of customers potentially usable to support the demand response event. Characteristics of each customer in the pool of customers are retrieved and a plurality of groups of customers are created from the pool of customers based on the retrieved characteristics and the at least one event parameter.

Systems and methods to aggregate loads for demand response events

A system for optimal planning of electric power demand is presented. The system includes a node comprising one or more smart charging plug-in electric vehicles (SCPEVs), a processing subsystem, wherein the processing subsystem receives relevant data from one or more sources; and determines an optimized SCPEV load and optimal charging schedule for the node by applying an operations research technique on the relevant data.

System and method for optimal load planning of electric vehicle charging

A power forecasting module determines a load forecast of a distribution system (DS) and a power generation forecast of distributed energy resources (DERs) A demand response (DR) module estimates an available DR based on the load and the power generation forecast and modifies the load forecast by dispatching an optimal DR. An energy storage commitment module determines a charging/discharging schedule of energy storage devices in the system based on the modified load profile and generates a second load profile by incorporating the charging/discharging schedule of energy storage devices. An unit commitment (UC) module determines a DER schedule of supplying electrical power to the loads in the second load profile based on a first objective function. An economic dispatch (ED) module determines an optimum operating point for each DER and an Integrated Volt-VAR Control (IVVC) module controls distribution assets to maintain a voltage profile in the system.

Integrated distribution system optimization

A method and system for controlling load in a utility distribution network are provided that initiates a shed event for a node in the distribution network by selecting premisess associated with the node that are participating in a demand response program to reduce the load at the node to desired levels. More specifically, the system and method provide for selecting only enough participating premisess associated with the node that are necessary to reduce the load to desired levels.

Method and system for demand response in a distribution network

A method of load dispatch generates a load dispatch curve in response to both the opportunity cost of dispatching resources with a contractually limited number of dispatches in a given time period and estimated rebound effect data. The method identifies a best time period for dispatch based on the load dispatch curve and also supply curve data and generates a resultant load dispatch schedule. The resultant load dispatch schedule is transmitted to one or more smart home meters to dispatch loads in a manner that provides the greatest economic benefit.

Optimal dispatch of demand side electricity resources

A method and system for assessing and optimizing crude selection are provided. A predictive engine uses data from a database to execute at least one predictive performance model and/or at least one risk assessment model designed to optimize or improve refining operations during a refining process. The predictive engine takes as input key crude information corresponding to a particular crude or crude blend, e.g., at least one crude slate, and refinery operating parameters and/or conditions corresponding to a specific refinery and uses desirability metrics to assess the similarity to data in the database. Based on the resulting output, at least one predictive performance and/or at least one risk assessment model uses the output to predict performance or risk measures of refining the particular crude or crude blend using the specific refinery during the refining process, the probability of problems occurring during the refining process, the distribution of the problems throughout the refining process, etc.

Method and system for assessing and optimizing crude selection

A method of operating a computer system includes storing, in the computer system, a database containing performance measure data regarding performance measures of a plurality of items. The method further includes inputting into the computer system a plurality of performance measure constraints. The method also includes modeling the performance measure constraints with a set of equations. The equations include a plurality of variables. Each of the variables corresponds to a respective one of the items. Each variable is, for example, to be assigned either the value '1' or the value '0'. The value &#x201c;1&#x201d; may represent a recommendation to take an action relative to the corresponding item in the portfolio and the value &#x201c;0&#x201d; may represent a recommendation to take another action. The computer system is used to solve the set of equations to generate one or more solutions that satisfy the performance measure constraints.

System and software for providing recommendations to optimize a portfolio of items

Growing community of inventors

Niskayuna, NY, United States of America

Rajesh Tyagi