Siemens Aktiengesellschaft

Siemens Enterprise Communications Gmbh & Co. Kg

Joachim Bamberger

Andrei Szabo

Ulrich Münz

Ti-chiun Chang

Michael Metzger

Jan Ernst

Florian Steinke

Xiaofan Wu

Steffen Lamparter

Clemens Otte

Michael Bernhard Buhl

Joachim Horn

Jeremy Ralph Wiles

Patrick Reeb

Philipp Wolfrum

Amer Mesanovic

Henning Lenz

Peter Michau

Marian Grigoras

Clemens Hoffmann

Jan-Gregor Fischer

Kai Heesche

Silvio Becher

Rudolf Sollacher

Ulrich Muenz

Dagmar Beyer

Ralph Grothmann

Kurt Majewski

Kuan-Chuan Peng

Martin Kunz

Peter Mayer

Markus Reischböck

Bruno Betoni Parodi

Michael Krüger

Gunter Magin

Stefan Jessenberger

Aditi Roy

Spartak Rasov

Jeremy-Ralph Wiles

Mohit Sinha

Ulrich MÜNZ

In order to detect power production degradation of a solar power plant (SPP) with at least one photovoltaic module (PVM), by which the detection of power production degradation, affected for instance by long term aging or soiling of the photovoltaic module of the solar power plant, is automated and carried out sensorless, it is proposed to determine the degradation by calibrating local measurements of data related to module/plant-internal parameters (PT) such as irradiance I and temperature T or electric power P and temperature as measurement data (MD, MD, MDagainst irradiance reference data (RD) for instance satellite data in the form of weather data for the same time and then analyze a variation of the calibration.

Method, computer-implemented tool and power plant control device for detecting power production degradation of solar power plants and solar power plant system

Deep learning is used to train a neural network for end-to-end prediction of short term (e.g., 20 minutes or less) solar irradiation based on camera images and metadata. The architecture of the neural network includes a recurrent network for temporal considerations. The images and metadata are input at different locations in the neural network. The resulting machine-learned neural network predicts solar irradiation based on camera images and metadata so that a solar plant and back-up power source may be controlled to minimize output power variation.

Solar irradiation prediction using deep learning with end-to-end training

In order to estimate states of health of batteries storing electrical energy significantly indicated by battery capacity and battery internal resistance, by which the estimation of states of health of batteries, deteriorated over time usage, is automated and carried out without a need of any specific test such as a capacity test and the usage of data out of normal operation, it is proposed to collect data from normal operation of a battery storing electrical energy relating to battery-internal physical properties such as a terminal direct current I, a terminal direct voltage Uand a battery cell temperature T due to battery measurements and the determination or estimation, based on this data and a battery model, of a model parameter by solving an optimization-/model parameter estimation-problem and minimizing a difference between the battery model and the battery measurements.

Method, computer-implemented tool and battery management system for estimating states of health of batteries storing electrical energy and battery energy storage system

Systems, methods, and computer-readable media are disclosed for autonomous restoration of power systems after natural disasters. An operating mode of a circuit breaker that is in a power system grid and that is coupled to other circuit breakers in the power system grid via communication channels is determined. Based on determining that the operating mode is a normal operating mode, data to parameterize a plurality of power grid restoration scenarios is collected at the circuit breaker. Based on determining that the operating mode is an exception mode, measurement data that includes current and voltage data is received at the circuit breaker, and one of the power system grid restoration scenarios is initiated at the circuit breaker. The power system grid error restoration scenario is selected based at least in part on a status of the plurality of communication channels coupled to the circuit breaker and on the measurement data.

Autonomous restoration of power systems after natural disasters

A system and method for correcting short term irradiance prediction for control of a photovoltaic power station includes an irradiance data manager that generates an observed irradiance curve based on irradiance measurements received from an irradiation sensor, and a reference curve generation engine that generates a reference curve representative of irradiance values for a clear sky day. An irradiance prediction engine generates an irradiance prediction curve based on image segmentation and motion filtering of cloud pixels in sky images. A prediction correction engine corrects the irradiance prediction curve within a short term future time interval based on probabilistic analysis of time segmented intervals of the observed irradiance curve, the reference curve, and the irradiance prediction curve.

Automatic generation of reference curves for improved short term irradiation prediction in PV power generation

A method and device which operates to record and evaluate an output of electrical energy of a hybrid power plant, wherein, in accordance with time and/or load, at least one expected generable and usable energy contribution resulting from the utilization of renewable energy sources and one expected energy contribution resulting from the utilization of convention energy carriers are recorded with different tariffs.

Method and device for recording and evaluating an output of electrical energy of a hybrid power plant

Systems and methods are provided for adapting images from different cameras so that a single trained classifier or an analyzer may be used. The classifier or analyzer operates on images that include a particular color distribution or characteristic. A generative network is used to adapt images from other cameras to have a similar color distribution or characteristic for use by the classifier or analyzer. A generative adversarial process is used to train the generative network.

Color adaptation using adversarial training networks

To control a power network having a photovoltaic system, a time curve of a light radiation of the photovoltaic system is determined, wherein an increase of the time curve in relation to a reference curve of the light radiation is detected. As a result of the detection of the increase, a preparatory measure is then introduced to prepare the power network for an upcoming power drop of the photovoltaic system.

Method, forecasting device and control device for controlling a power network with a photovoltaic system

Systems, methods, and computer-readable media are described for addressing the unit commitment problem in a power grid by providing a communication-free control framework according to which each power generating unit in the power grid determines its own operating schedule for turning on or off based solely on local measurements.

Communication-free decentralized control framework for unit commitment in microgrids

Provided is a method for charging or discharging an electrochemical energy store, the ageing behavior of which energy store is modelled by describing its depth of discharge at which a depth of discharge value is associated with each time period between two adjacent local maxima and minima in a time-dependent state of charge profile, which depth of discharge value corresponds to the charging or discharging stroke between the state of charge values of the two adjacent local maxima and minima.

Method and apparatus for charging or discharging an energy store

A method for predicting a performance of an electrical energy storage system includes receiving, as input, time series of data points pertaining to a plurality of operational parameters of the electrical energy storage system. The input time series is provided to a model that simulates dynamics of the electrical energy storage system. A plurality of performance indicators of the electrical energy storage system may be calculated based on the simulated dynamics of the electrical energy storage system.

Performance tracking of an electrical energy storage system

A multi-generator power plant arrangement, energy supply network having a multi-generator power plant arrangement and method for distributing reactive power generation in a multi-generator power plant arrangement, is provided. A multi-generator power plant arrangement, and also a method for distributing reactive power generation in a multi-generator power plant arrangement, is provided. The control parameters for the controllers of the individual generators of a multi-generator power plant arrangement are thereby calculated individually on the basis of predetermined parameters and transmitted to the controllers of the individual generators. Consequently, the reactive power component to be generated in each case can be individually specified for each generator of a multi-generator power plant arrangement.

Multi-generator power plant arrangement, energy supply network having a multi-generator power plant arrangement and method for distributing reactive power generation in a multi-generator power plant arrangement

A control unit includes a power supply device with a battery store including at least one battery unit; a first energy conversion device that converts nonelectrical energy into electrical energy; and a connecting unit configured such that a summed energy for the electrical energy of the energy conversion device and battery store is deliverable. The control unit receives an instantaneous output power or a future output power requirement of the first energy conversion device and further receives a predicted power of the first energy conversion device for at least one future time. The instantaneous output power or the future output power requirement and the predicted power are used to ascertain a required power at the future time. At least one battery unit is switched on in response to the threshold value being exceeded by the required power.

Control unit

A method for the computer-assisted configuration of an electrical power grid is provided. Grid forming generating unit nodes are provided in the power grid as first grid nodes and grid-boosting generating unit nodes are optionally provided as second grid nodes. The latter nodes are regenerative energy generation plants such as, for example, photovoltaic systems. In the method, closed-loop control methods and in particular proportional control of the generating unit nodes are set on the basis of a suitable dynamic model of the power grid such that an optimization problem is solved with the aim of optimum operation of the power grid in respect of one or more optimization criteria.

Method for the computer-assisted configuration of an electrical power grid

A short-term cloud forecasting system includes a cloud segmentation processor that receives image data from images captured by an all sky camera. The cloud segmentation processor calculates a probability for each pixel in an image that the pixel is representative of a cloud. A cloud motion estimation processor calculates a motion vector representing estimated cloud motion calculates weights representing the likelihood that the cloud motion will cause a cloud to occlude the sun at a time in the near future. An uncertainty processor calculates one or more uncertainty indexes that quantify the confidence that a cloud forecast is accurate. Combining the cloud probabilities, the global motion vector and the at least one uncertainty index, in a sun occlusion prediction processor produces a short-term cloud forecast based on the image data that may be used as input to control systems for controlling a power grid.

Growing community of inventors

Munich, Germany

Joachim Bamberger