EP2954467A1 - Procédé et dispositif de commande d'une installation de production d'énergie exploitable avec une source d'énergie renouvelable - Google Patents

Procédé et dispositif de commande d'une installation de production d'énergie exploitable avec une source d'énergie renouvelable

Info

Publication number
EP2954467A1
EP2954467A1 EP13802316.3A EP13802316A EP2954467A1 EP 2954467 A1 EP2954467 A1 EP 2954467A1 EP 13802316 A EP13802316 A EP 13802316A EP 2954467 A1 EP2954467 A1 EP 2954467A1
Authority
EP
European Patent Office
Prior art keywords
output
input
energy
data
vector
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP13802316.3A
Other languages
German (de)
English (en)
Inventor
Martin Bischoff
Terrence Chen
Ralph Grothmann
Oliver Hennig
Johann Kim
Eberhard Ritzhaupt-Kleissl
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Original Assignee
Siemens AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens AG filed Critical Siemens AG
Publication of EP2954467A1 publication Critical patent/EP2954467A1/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
    • H02S10/00—PV power plants; Combinations of PV energy systems with other systems for the generation of electric power
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B17/00—Systems involving the use of models or simulators of said systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/50—Photovoltaic [PV] energy
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Definitions

  • the present invention relates to a method and a device for controlling a power generating plant which can be operated with a renewable energy source.
  • renewable energy generation systems are being used more and more frequently.
  • the energy yield of such power generation plants depends strongly on external variables, in particular on weather conditions. It is therefore of such regenerative energy generation plants desirable to predict the future generated Energymen ⁇ ge suitable, to thereby schedule the Energyeinspei ⁇ solution of such a power generation plant, and thus the loading ⁇ drove a power grid better.
  • An object of the invention is therefore to improve the control of a renewable energy source operable power plant.
  • a method for controlling a power generating plant operable with a renewable energy source is proposed.
  • a computer-aided generation of a prognosis is made about an energy yield of the energy generation plant for a predefined prognosis period and a given area using a learning system with an input vector and an output vector.
  • the output vector includes one or more operation ⁇ sizes of the power generation plant for a plurality of on ⁇ successive future points in time of the predetermined forecast period.
  • the input vector comprises one or more input variables influencing the operating variable or operating variables for a time from a plurality of times of a predetermined observation period.
  • the input quantities comprise at least three of the following data for the given observation period and the given area: weather data; first be ⁇ riding asked by means of a satellite image data of a Wolkenzugs; second means provided ei ⁇ ner floor camera image data of the Wolkenzugs; and by a physical model to simulate the energy output of the energy generation plant using the Wet ⁇ ter Scheme generated simulation data. Furthermore, in the method, the power generation plant is controlled based on the generated prognosis such that weather-related
  • the operable with a renewable energy source energy ⁇ generation plant is for example a power plant or a hybrid power plant such as a photovoltaic power plant or a solar thermal power plant.
  • a learning system is a system that can adapt its properties depending on its inputs and outputs. It is thus possible, for example, to train a learning system by means of a set of training data to recognize certain predefined or automatically determinable patterns or generalizable structures in the training data. After learning such a learning system able to recognize to be determined pattern or generalisierba ⁇ ren structures in other data as the training data and adorn these other data according to classifi ⁇ is.
  • the operating parameters of the power generation plant is in ⁇ play as generated by the power generation plant amounts of energy.
  • the method makes it possible to predict the amount of energy to be generated in the future in order to better plan the energy supply of such a power generation plant and thus the operation of a power grid. Furthermore, the method allows, the power generation plant ⁇ based on the generated prediction to such steu ⁇ ren that weather-related variations in the energy output of the power generation plant are reduced or are prevented.
  • Another advantage of the method is the possible ⁇ ness, to use at least three different data sources to be generated prognosis.
  • the advantages of the different data sources can be, such as the accuracy and / or fault tolerance combine a ⁇ of individual measuring points, time horizon or temporal resolu ⁇ solution.
  • the generated forecast is thus more accurate and stable than when using only one or only two data sources.
  • the input vector is compressed by a Hauptkomponentenana ⁇ analysis of the components of the learning system prior to generating the forecast.
  • Principal Component Analysis is a statistics technique for lossless compression of the data included in the input vector. Particularly advantageous is the use of a non-linear principal component analysis, which is realized in the form of a learning system, for example a neural network. In this way even very large input vectors can be processed efficiently and quickly.
  • the learning system is formed by a number n of neural networks.
  • Neural networks are universal function approximators, whose structure was chosen on the basis of biological nerve cells.
  • Neural networks are particularly suitable for the control and regulation of technical installations such as the power generation plant. suitable. It is possible to replace conventional regulators with neural networks or to specify desired values which a neural network has determined from the generated prognosis. Thus, it is also possible to control the power generation plant based on the generated forecast such that weather-related fluctuations in the energy yield of the energy ⁇ generation plant are further reduced. Neural networks also make it possible to minimize forecasting errors over time and thus to improve the ultimately generated prognosis.
  • the n neural networks may have identical or different architectures.
  • the input vector for the i-th neural network comprises, ie with [l, ..., n], to ⁇ addition to those input variables, the output vector of the (i-1) - th neural network.
  • the learning system consists of a sequence intrinsically ⁇ permanent, self-learning sub-systems in the form of neural networks.
  • each subsystem receives the generated forecast of the respective preceding subsystem as further input data. In this way, the prediction errors of the preceding subsystems can be reduced by the respectively subsequent subsystem.
  • each of the n neural networks is formed as an artificial neural feed-forward network with a plurality of interconnected layers comprising an input layer, a plurality of hidden layers
  • the Einga ⁇ coating contains a number of input neurons to describe the input vectors and wherein a respective Ver ⁇
  • the output layer comprises a number of output neurons for describing the output vectors, and wherein the output layer comprises a plurality of output clusters corresponding to the plurality of hidden layers, each of one or more output neurons, each output chandelier same output vector and connected to another hidden layer.
  • Each of the n neural networks thus represents a special Va ⁇ riante a feed-forward network.
  • a feed-forward network is characterized in that a plurality of superimposed lie ⁇ constricting neuron layers in a processing direction of lower of higher layers via suitable weights in Form of weight matrices are coupled together, wherein the neurons within a layer have no connections with each other.
  • Each of the n neural networks is characterized in that the output layer comprises a plurality of output clusters corresponding to the plurality of hidden layers, each comprising one or more output neurons, each output clusters describing the same output vector and connected to another hidden layer. It is thus an output of each hidden layer associated cluster, said hidden layer being ge ⁇ coupled with that output cluster. Consequently, separate output clusters are created which independently of one another in the neural network describe the same operating variables of the power generation plant.
  • the hidden layers lying below the uppermost hidden layer are connected not only to a higher hidden layer but also to an output cluster of the output layer.
  • additional error information is supplied to the output layer, so that a suitably trained neural network can better predict the size of the power plant.
  • the input vector is associated with each hidden layer.
  • the data comprised of the input variables is provided individually for each of the n neural networks.
  • Each sub-system therefore has specific characteristics of the input variables as input data. For example, corresponding to input variables for the first sub-system of a high temporal resolution of the observed meteorological data, which ultimately lead to a short-term prognosis, whereas the input ⁇ sizes correspond to the second sub-system of a low temporal resolution of the observed weather data and thus a lead long-term forecast.
  • High temporal resolu ⁇ solution means, for example, one minute or Stun ⁇ -precise temporal resolution while low temporal resolution, for example, means a day precise resolution.
  • an order of the n neural networks can be predetermined.
  • a sorting of the sub-systems according to the input data makes it possible to further improve the quality of the generated forecast.
  • multiple times performing the step of generating a Prog ⁇ nose to generate multiple projections, whereby in each case a different forecast period and / or a different observation period is set for generating a respective prognosis.
  • the merging of the multiple generated forecasts into a combined forecast takes place.
  • the merging of the multiple generated forecasts is performed by a weighted summation.
  • weighted summation allows equal weighting of each of the multiple forecasts generated.
  • the merging of the multiple generated forecasts is effected by a further neural network.
  • a neural network is particularly suitable for processing and evaluating statistical data such as observed weather data.
  • the merged forecast can be further improved.
  • the first and / or the second image data comprise image features provided by pattern recognition.
  • Pattern recognition is a particularly suitable method for ⁇ From evaluation of images.
  • the image features provided by the pattern recognition represent a summary of the relevant information in the image data, thereby making the process more efficient.
  • a computer program product such as a computer program means can be provided or supplied, for example, as a storage medium, such as a memory card, USB stick, CD-ROM, DVD or even in the form of a downloadable file from a server in a network. This can be done, for example, in a wire-less ⁇ communication network by the transmission of a corresponding file with the computer program product or computer program means.
  • a program- controlled device is in particular a ⁇ as described below ⁇ ne device in question.
  • the device comprises a Prog ⁇ nose-generating means for generating a prediction of an energy yield of the power generation plant for a specified differently surrounded forecast period and a predetermined area using a learning system with an input vector and an output vector.
  • the output vector includes one or more operating quantities of the power plant for a plurality of consecutive future times of the predetermined forecast period.
  • the input vector um- summarizes one or more, the operation amount or Radio Fund ⁇ SEN affecting input variables for a time from egg ⁇ ner plurality of time points of a predetermined observation period.
  • the input quantities comprise at least three of the following data for the given observation period and the given area:
  • the device further comprises a control means for
  • the device makes it possible to predict the future generated Ener ⁇ giemenge suitable, thereby thus be able to plan the operation of a power grid better the energy feed of such a power generation plant and. Furthermore, it enables the device to control the power generating installation based on the generated prediction such that weather-related variations of the Energyertra ⁇ ges the power generation plant are reduced.
  • the respective means forecasting generating means and Steue ⁇ insurance agents can also be implemented using software, hardware and / or electronically.
  • the respective unit may be embodied as a device or as part of a device, for example as a computer or as a microprocessor.
  • the respective unit as a computer program product, as a function, as a routine, be formed as part of a program code or as an executable object.
  • Figure 2 is a block diagram of an embodiment of an apparatus for controlling an operable with a source of renewable energy power generating installation.
  • FIG. 3 is a block diagram of a first embodiment of a learning system for a method of controlling a renewable energy source power plant.
  • FIG. 4 is a block diagram of a second embodiment of a learning system for a method for controlling a power generating plant operable with a renewable energy source;
  • FIG. 5 is a block diagram of a third embodiment of a learning system for a method of controlling a renewable energy source power plant.
  • FIG. 1 shows a flowchart of an embodiment of a method for controlling a power generating plant which can be operated with a renewable energy source.
  • a prognosis is made about an energy yield of the energy generation plant for a predefined prognosis period and a predefined area using a learning system with an input vector and an output vector.
  • the output vector includes one or more operating quantities of the power plant for a plurality of consecutive future times of the predetermined forecast period. Includes the Eingabevek- tor one or more, the operating variable or operating variables influencing Be ⁇ input variables for a time of a plurality of points in time a predetermined observation period.
  • the input variables include Minim ⁇ least three of the following data for the predetermined observation period and the predetermined tung-Area: weather data; ers ⁇ te, provided by means of a satellite image data of a cloud of clouds; second image data of the cloud train provided by a ground camera; and simulation data generated by a physical model for simulating the energy yield of the power generation plant using the weather data.
  • a control of the power generating plant is based on the generated forecast ⁇ art that weather-related variations in the energy output of the power generation plant are reduced.
  • FIG. 2 shows a block diagram of one embodiment of a device 212 for controlling a renewable energy source power plant.
  • the device 212 comprises a prognosis generating means 213 for generating a prognosis about an energy yield of the energy generating plant for a predefined prognosis period and a given area as well as a control means 214 for controlling the energy generating plant based on the generated prognosis.
  • Fig. 3 shows a block diagram of a first game personssbei ⁇ a learning system for a process for a Steue- tion with a renewable energy source operable power generation plant.
  • the learning system 205 has an input vector 206 and ei ⁇ NEN output vector 207.
  • the input vector 206 comprises a plurality of the operating variable or operating variables 208, the power generating installation affecting input variables for a time of a plurality of points in time a predetermined observation period.
  • the input parameters include data such as the weather data 201, first image data 202 and second image data 203.
  • first image data 202 is provided by means of a satellite image data of a cloud ⁇ train.
  • the second image data 203 is provided by means of a bottom camera image data of the clouds ⁇ train.
  • the input parameters include simulation data 204.
  • the simulation data 204 are thereby produces by a physical model to simulate the energy output Ener ⁇ gieer Wegungsstrom using the weather data two hundred and first
  • the data 201-204 first learn a treatment.
  • the cloud images recorded by the satellite and the ground camera are subjected to pattern recognition.
  • the image features or image data provided by the pattern recognition is a summary of the relevant information contained in the clouds images with respect to the weather conditions of the predetermined area.
  • These data 201-204 form the input for the learning system 205.
  • the output of the learning system 205 forms the output vector 207 with the operating variables 208.
  • the output vector 207 thus serves to generate the forecast 209.
  • the simulation data 204 it is possible to use the simulation data 204 alternatively or in addition to the input to the learning system 205 for a correction of the generated prognosis 209, indicated by the dashed arrow in FIG. 3. Thus it is possible, possibly improbable or implausible prognosis results by the simulation data 204.
  • 4 shows a block diagram of a second embodiment of a learning system for a method of controlling a renewable energy source power plant.
  • the learning system 205 comprises two neural networks 210, 211. Each of the two neural networks 210, 211 has as input the input vector 206.
  • the two neural networks 210, 211 use the same input vector 206.
  • each of the two neural networks 210, 211 has its own input vector as an input, wherein, for example, the input vector for the first neural network 210 comprises data of a low temporal resolution of the observed weather data while the input vector for the second neural network 211 comprises data of a higher temporal resolution of the observed weather data.
  • the second neural network 211 receives the output vector of the first neural network 210 as input.
  • FIG. 4 thus represents a corrective system.
  • This system consists of a sequence of independent self-learning subsystems in FIG. 4
  • Each sub-system can have as input data separate data sources in the sense of the above-described, different forms of data 201-204 comprising input vectors.
  • each subsystem receives the prediction of the predecessor system in the form of the respective output vector as further input data. In this way, prediction errors of the predecessor systems can be reduced by the respective subsequent subsystem.
  • a sorting of the subsystems according to the input data for example, in terms of their quality, their time horizon or their temporal resolution.
  • FIG. 5 shows a block diagram of a third exemplary embodiment of a learning system for a method for controlling tion of a renewable energy source.
  • each of the two learning ⁇ systems 205 has as input data, the data 201-204 of the input vector 206th
  • each of the two learning systems 205 can have as input data separate data sources in the sense of the above-described, different forms of data 201- 204 comprising input vectors.
  • the output vectors 207 of each of the two learning systems 205 are merged into a merged forecast 209.
  • the merging can take place for example by a weighted summation or by another learning system such as a neural network. It is also possible to select one of the two forecasts of the independent learning systems 205 based on one of the two output vectors 207 according to specific criteria.
  • Such learning overall system is thus able, egg ⁇ ne overall forecast 209 to determine and learn the conditions under which that forecast has the highest probability.

Landscapes

  • Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé et un dispositif permettant la commande d'une installation de production d'énergie exploitable avec une source d'énergie renouvelable. Le procédé consiste à établir un pronostic sur un rendement énergétique de l'installation de production d'énergie pour une période de pronostic prédéfinie et pour un site prédéfini à l'aide d'un système d'apprentissage ayant un vecteur d'entrée et un vecteur de sortie. Le vecteur de sortie comprend une ou plusieurs grandeurs de fonctionnement de l'installation de production d'énergie pour une pluralité d'instants futurs successifs de la période de pronostic prédéfinie. Le vecteur d'entrée comprend une ou plusieurs grandeurs d'entrée influençant la grandeur de sortie ou les grandeurs de sortie pour un instant parmi une pluralité d'instants d'une période d'observation prédéfinie. Les grandeurs d'entrée comprennent au moins trois données pour la période d'observation prédéfinie et pour le site prédéfini. Par ailleurs, lors du procédé est effectuée une commande de l'installation de production d'énergie sur la base des pronostics établis de manière à réduire des fluctuations, dues aux conditions météorologiques, du rendement énergétique de l'installation de production d'énergie. De ce fait, il est possible de commander l'installation de production d'énergie sur la base des pronostics établis de manière à réduire des fluctuations, dues aux conditions météorologiques, du rendement énergétique de l'installation de production d'énergie.
EP13802316.3A 2013-02-05 2013-12-03 Procédé et dispositif de commande d'une installation de production d'énergie exploitable avec une source d'énergie renouvelable Withdrawn EP2954467A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201361760766P 2013-02-05 2013-02-05
PCT/EP2013/075305 WO2014121863A1 (fr) 2013-02-05 2013-12-03 Procédé et dispositif de commande d'une installation de production d'énergie exploitable avec une source d'énergie renouvelable

Publications (1)

Publication Number Publication Date
EP2954467A1 true EP2954467A1 (fr) 2015-12-16

Family

ID=49726744

Family Applications (1)

Application Number Title Priority Date Filing Date
EP13802316.3A Withdrawn EP2954467A1 (fr) 2013-02-05 2013-12-03 Procédé et dispositif de commande d'une installation de production d'énergie exploitable avec une source d'énergie renouvelable

Country Status (4)

Country Link
US (1) US9853592B2 (fr)
EP (1) EP2954467A1 (fr)
CN (1) CN105164593A (fr)
WO (1) WO2014121863A1 (fr)

Families Citing this family (48)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10303035B2 (en) 2009-12-22 2019-05-28 View, Inc. Self-contained EC IGU
US8213074B1 (en) 2011-03-16 2012-07-03 Soladigm, Inc. Onboard controller for multistate windows
US11592723B2 (en) 2009-12-22 2023-02-28 View, Inc. Automated commissioning of controllers in a window network
US20130271813A1 (en) 2012-04-17 2013-10-17 View, Inc. Controller for optically-switchable windows
US10533892B2 (en) 2015-10-06 2020-01-14 View, Inc. Multi-sensor device and system with a light diffusing element around a periphery of a ring of photosensors and an infrared sensor
US11314139B2 (en) 2009-12-22 2022-04-26 View, Inc. Self-contained EC IGU
US10690540B2 (en) 2015-10-06 2020-06-23 View, Inc. Multi-sensor having a light diffusing element around a periphery of a ring of photosensors
US9778532B2 (en) 2011-03-16 2017-10-03 View, Inc. Controlling transitions in optically switchable devices
US9454055B2 (en) 2011-03-16 2016-09-27 View, Inc. Multipurpose controller for multistate windows
US8705162B2 (en) 2012-04-17 2014-04-22 View, Inc. Controlling transitions in optically switchable devices
US9645465B2 (en) 2011-03-16 2017-05-09 View, Inc. Controlling transitions in optically switchable devices
US10935865B2 (en) 2011-03-16 2021-03-02 View, Inc. Driving thin film switchable optical devices
US11630367B2 (en) 2011-03-16 2023-04-18 View, Inc. Driving thin film switchable optical devices
US9412290B2 (en) 2013-06-28 2016-08-09 View, Inc. Controlling transitions in optically switchable devices
US11054792B2 (en) 2012-04-13 2021-07-06 View, Inc. Monitoring sites containing switchable optical devices and controllers
US9030725B2 (en) 2012-04-17 2015-05-12 View, Inc. Driving thin film switchable optical devices
EP2769042B1 (fr) 2011-10-21 2018-02-21 View, Inc. Atténuation de choc thermique dans des fenêtres pouvant être colorées
US11635666B2 (en) 2012-03-13 2023-04-25 View, Inc Methods of controlling multi-zone tintable windows
US11950340B2 (en) 2012-03-13 2024-04-02 View, Inc. Adjusting interior lighting based on dynamic glass tinting
US11674843B2 (en) 2015-10-06 2023-06-13 View, Inc. Infrared cloud detector systems and methods
US10048561B2 (en) 2013-02-21 2018-08-14 View, Inc. Control method for tintable windows
US10503039B2 (en) 2013-06-28 2019-12-10 View, Inc. Controlling transitions in optically switchable devices
US9638978B2 (en) 2013-02-21 2017-05-02 View, Inc. Control method for tintable windows
US10964320B2 (en) 2012-04-13 2021-03-30 View, Inc. Controlling optically-switchable devices
US11300848B2 (en) 2015-10-06 2022-04-12 View, Inc. Controllers for optically-switchable devices
EP3611707B1 (fr) 2012-04-13 2024-01-17 View, Inc. Applications pour commander des dispositifs commutables optiquement
US11719990B2 (en) 2013-02-21 2023-08-08 View, Inc. Control method for tintable windows
US11960190B2 (en) 2013-02-21 2024-04-16 View, Inc. Control methods and systems using external 3D modeling and schedule-based computing
US11966142B2 (en) 2013-02-21 2024-04-23 View, Inc. Control methods and systems using outside temperature as a driver for changing window tint states
US9885935B2 (en) 2013-06-28 2018-02-06 View, Inc. Controlling transitions in optically switchable devices
JP6223833B2 (ja) * 2014-01-09 2017-11-01 株式会社東芝 電力系統安定化装置
US10221612B2 (en) 2014-02-04 2019-03-05 View, Inc. Infill electrochromic windows
CA2941526C (fr) 2014-03-05 2023-02-28 View, Inc. Surveillance de sites comprenant des dispositifs optiques commutables et des organes de commande
TW202130977A (zh) 2014-09-29 2021-08-16 美商唯景公司 組合式感測器系統
EP3201613B1 (fr) 2014-09-29 2021-01-06 View, Inc. Detection de l'intensite de lumiere solaire ou de nuages avec capteur de distance variable
US11566938B2 (en) 2014-09-29 2023-01-31 View, Inc. Methods and systems for controlling tintable windows with cloud detection
US11781903B2 (en) 2014-09-29 2023-10-10 View, Inc. Methods and systems for controlling tintable windows with cloud detection
KR101641258B1 (ko) * 2014-10-10 2016-07-20 엘지전자 주식회사 설비를 관제하는 중앙 제어 장치, 이를 포함하는 설비 제어 시스템 및 설비 제어 방법
TWI823168B (zh) 2015-07-07 2023-11-21 美商唯景公司 用於可著色窗戶之控制方法
US11255722B2 (en) 2015-10-06 2022-02-22 View, Inc. Infrared cloud detector systems and methods
EP3368736A4 (fr) 2015-10-29 2019-07-03 View, Inc. Dispositifs de commande pour dispositifs à commutation optique
US11482147B2 (en) 2016-04-29 2022-10-25 View, Inc. Calibration of electrical parameters in optically switchable windows
US11513412B2 (en) 2017-04-26 2022-11-29 View, Inc. Displays for tintable windows
US11196380B2 (en) * 2017-07-04 2021-12-07 Taiwan Power Company Power generation prediction system and method thereof
EP3506026A1 (fr) * 2017-12-29 2019-07-03 Siemens Aktiengesellschaft Procédé de prédiction assistée par ordinateur d'au moins une grandeur opérationnelle globale d'un système technique
DE102018222803A1 (de) * 2018-12-21 2020-06-25 Siemens Aktiengesellschaft Verfahren zum Betreiben einer Anlage zur Umwandlung und/oder Speicherung von wenigstens einer Energieform, elektronische Recheneinrichtung zum Durchführen eines Verfahrens sowie Computerprogramm und elektronisch lesbarer Datenträger
TW202206925A (zh) 2020-03-26 2022-02-16 美商視野公司 多用戶端網路中之存取及傳訊
US11631493B2 (en) 2020-05-27 2023-04-18 View Operating Corporation Systems and methods for managing building wellness

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007184354A (ja) * 2006-01-05 2007-07-19 Mitsubishi Electric Corp 太陽光発電システム
EP2223260A2 (fr) * 2007-11-07 2010-09-01 EDSA Micro Corporation Systèmes et procédés pour une prévision et une prédiction en temps réel de pics électriques et une gestion de l'énergie, de la santé, de la fiabilité et de la performance de systèmes d'énergie électrique sur la base d'un réseau neuronal adaptatif artificiel
US9065371B2 (en) * 2008-12-03 2015-06-23 Sun Synchrony, Inc. Solar energy collection system
US20100198420A1 (en) * 2009-02-03 2010-08-05 Optisolar, Inc. Dynamic management of power production in a power system subject to weather-related factors
US20110231320A1 (en) * 2009-12-22 2011-09-22 Irving Gary W Energy management systems and methods
WO2011124720A2 (fr) * 2010-04-09 2011-10-13 Siemens Concentrated Solar Power Ltd. Système de gestion d'ennuagement pour un champ solaire, procédé de fonctionnement associé, et champ solaire le comprenant
JP2013529051A (ja) * 2010-05-07 2013-07-11 アドバンスド エナージィ インダストリーズ，インコーポレイテッド 太陽光発電予測システム並びに方法
DE102011017694A1 (de) * 2011-04-28 2012-10-31 Siemens Aktiengesellschaft Verfahren und Vorrichtung zur Bestimmung einer von einer photovoltaischen Anlage abgegebenen Leistung
US8624411B2 (en) * 2011-10-14 2014-01-07 General Electric Company Power generation system including predictive control apparatus to reduce influences of weather-varying factors
CN102521670A (zh) 2011-11-18 2012-06-27 中国电力科学研究院 基于气象要素的光伏电站发电输出功率预测方法
CN102567809B (zh) * 2011-11-18 2015-12-16 中国电力科学研究院 光伏电站发电输出功率预测系统
WO2014075108A2 (fr) * 2012-11-09 2014-05-15 The Trustees Of Columbia University In The City Of New York Système de prévision à l'aide de procédés à base d'ensemble et d'apprentissage machine
US10079317B2 (en) * 2013-07-15 2018-09-18 Constantine Gonatas Device for smoothing fluctuations in renewable energy power production cause by dynamic environmental conditions

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
None *
See also references of WO2014121863A1 *

Also Published As

Publication number Publication date
US9853592B2 (en) 2017-12-26
CN105164593A (zh) 2015-12-16
US20150381103A1 (en) 2015-12-31
WO2014121863A1 (fr) 2014-08-14

Similar Documents

Publication Publication Date Title
WO2014121863A1 (fr) Procédé et dispositif de commande d'une installation de production d'énergie exploitable avec une source d'énergie renouvelable
EP3132317B1 (fr) Procédé permettant l'optimisation assistée par ordinateur de la commande d'une installation au moyen d'un module de simulation
EP2697695B1 (fr) Procédé pour générer, de manière assistée par ordinateur, un modèle piloté par des données d'un système technique, notamment d'une turbine à gaz ou d'une éolienne
EP2724296B1 (fr) Procédé à la modélisation d'un système technique utilisant l'ordinateur
EP3529669B1 (fr) Procédé et dispositif de commande pour commander un système technique
EP2112568B1 (fr) Procédé de commande et/ou réglage assistées par ordinateur d'un système technique
DE102012009502A1 (de) Verfahren zum Trainieren eines künstlichen neuronalen Netzes
DE102007001025A1 (de) Verfahren zur rechnergestützten Steuerung und/oder Regelung eines technischen Systems
WO2014187828A1 (fr) Méthode de détermination d'un modèle d'une grandeur de sortie d'un système technique
EP3429050A1 (fr) Procédé de réglage de la puissance active d'un parc éolien et parc éolien correspondant
DE102017216634A1 (de) Verfahren und Trainingsdatengenerator zum Konfigurieren eines technischen Systems sowie Steuereinrichtung zum Steuern des technischen Systems
WO2021259980A1 (fr) Entraînement d'un réseau de neurones artificiels, réseau de neurones artificiels, utilisation, programme informatique, support de stockage et dispositif
DE102011079433A1 (de) Ansteuerung eines Rotorblatts einer Windturbine
DE102019206541A1 (de) Verfahren zum Durchführen von computerunterstützten XiL-Simulationen
DE102011075337A1 (de) Verfahren und Vorrichtung zur Ansteuerung einer Anlage
WO2023072528A1 (fr) Procédé et dispositif de commande pour commander un système technique
EP3432093A1 (fr) Procédé de modélisation d'un système dynamique par apprentissage assisté par ordinateur de modèles commandés par données
DE102016209721A1 (de) Modellbasierte Ermittlung eines Systemzustandes mittels eines dynamischen Systems
DE102011076969B4 (de) Verfahren zum rechnergestützten Lernen einer Regelung und/oder Steuerung eines technischen Systems
EP3528063B1 (fr) Procédé de création assistée par ordinateur d'un modèle pronostique destiné au pronostic d'une ou plusieurs grandeurs cibles
EP3489773A1 (fr) Procédé de commande assisté par ordinateur d'un système technique, en particulier d'une installation de production d'énergie
DE102012016066A1 (de) Verfahren zur Steuerung einer Anlage
EP3506026A1 (fr) Procédé de prédiction assistée par ordinateur d'au moins une grandeur opérationnelle globale d'un système technique
WO2013182176A1 (fr) Procédé pour entraîner un réseau de neurones artificiels etproduits-programmes informatiques
DE102021119818A1 (de) Computerimplementiertes Verfahren zur Herstellung eines für eine numerische Simulation geeigneten Software-Abbildes zumindest eines Teils eines realen Steuergeräts

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20150703

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

DAX Request for extension of the european patent (deleted)
17Q First examination report despatched

Effective date: 20160804

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: SIEMENS AKTIENGESELLSCHAFT

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

INTG Intention to grant announced

Effective date: 20200807

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20201218