Siemens Aktiengesellschaft

Siemens Corporation

Sindhu Suresh

Justinian Rosca

Lingyun Wang

Alberto Avritzer

Paul J Bruschi

Parag Patre

Sanjeev Srivastava

Dong Wei

Yaosuo Xue

Jiaxing Pi

Bogdan Rosca

Bernardo Hermont

Anthony Weber

Phan Minh Nguyen

A computer-implemented method for power grid anomaly detection using a convolutional neural network (CNN) trained to detect anomalies in electricity demand data and electricity supply data includes receiving (i) electricity demand data comprising time series measurements of consumption of electricity by a plurality of consumers, and (ii) electricity supply data comprising time series measurements of availability of electricity by one or more producers. An input matrix is generated that comprises the electricity demand data and the electricity supply data. The CNN is applied to the input matrix to yield a probability of anomaly in the electricity demand data and the electricity supply data. If the probability of anomaly is above a threshold value, an alert message is generated for one or more system operators.

Deep convolutional neural network based anomaly detection for transactive energy systems

A system for managing data in an industrial production environment includes a distributed database system stored on a plurality of embedded controller devices. Each respective embedded controller device comprises: a distributed database instance and a database management application. The distributed database instance is configured to store data collected from the industrial production environment by the respective embedded controller device. The database management application is configured to facilitate distributed queries and transactions on the plurality of embedded controller devices.

Distributed data management systems for embedded controllers

Improvements to a distributed automation power grid are selected to improve storm survivability. Using historical information about storms, link sets are determined that, when added to the power grid, would restore connectivity after damage by each of the storms. One of the link sets is then selected based on costs and rewards, and is added to a grid representation. Survivability of the modified grid representation is then estimated, and additional link sets are determined and selected until survivability surpasses a minimum level or a budget is exceeded.

Holistic optimization of distribution automation using survivability modeling to support storm hardening

A flexible control architecture for an electrical power microgrid provides resiliency when operating under varying threat levels. The architecture includes a microgrid control layer, an intermediate layer and a component control layer. A contingency level is computed based on conditions of the microgrid such as weather and system state. When the contingency level indicates a low degree of threat, the system operates in a centralized, top-down control configuration. When the contingency level indicates a high degree of threat, the system operates in a decentralized control configuration with the microgrid control layer performing only a monitoring function.

Flexible control architecture for microgrid resiliency

A method for managing allocation of electrical power includes selecting one or more power consuming entities for receiving a request to reduce electrical power usage (S) based on data pertaining to past selections of entities for receiving requests to reduce power and a history of compliance with said requests (S). A customized request to reduce power usage for each of the selected one or more power consuming entities is generated (S). The generated customized request to reduce power usage is received at a corresponding power consuming entity and a cost associated with complying with the received customized request to reduce power usage is evaluated (S). A commitment to comply with the received customized request to reduce power usage is returned when the evaluated cost is within a threshold of acceptability and negotiating a new request to reduce power when the evaluated cost is greater than a threshold of acceptability (S).

Bidirectional demand response control

A solar energy system and method of cleaning photovoltaic panels is provided. Measurements relating to weather at a photovoltaic panel are received by the system. Measurements relating to output current and voltage at the photovoltaic panel are received by the system. Expected power of the photovoltaic panel is determined based on the measurements relating to weather. Actual power of the photovoltaic panel is determined based on the measurements relating to output current and voltage. In response to determining that the actual power is not within a predetermined range of the expected power (e.g. at least one photovoltaic panel is dirty), a cleaning of the photovoltaic panel is initiated.

System and method for autonomous adaptive cleaning of PV panels based on high level control signals

Transient survivability metrics are used to select improvements to distribution automation network designs. The approach combines survivability analysis and power flow analysis to assess the survivability of the distribution power grid network. Available investment decisions are then automatically optimized with respect to survivability and investment costs.

Holistic optimization of distribution automation using survivability modeling

A method for assessing survivability of a distributed automation power grid due to a failure including: identifying a location of a failed section of a grid and isolating the section; aggregating sections of the grid downstream from the failed section into a first group and sections of the grid upstream from the failed section into a second group; computing, using a Markov chain, a first parameter indicating whether a communication network of the grid is operational after the failure; computing, using a Markov chain, a second parameter indicating whether enough backup energy exists for the second group after the failure; and computing, using a Markov chain, a third parameter based on the first and second parameters, wherein the third parameter is indicative of the time required for the grid to be restored to its operating state prior to the failure, and the third parameter is computed by evaluating 

Growing community of inventors

Monroe Township, NJ, United States of America

Sindhu Suresh