CN113743674A - Energy storage output prediction method, system, equipment and medium based on deep learning - Google Patents
Energy storage output prediction method, system, equipment and medium based on deep learning Download PDFInfo
- Publication number
- CN113743674A CN113743674A CN202111063012.5A CN202111063012A CN113743674A CN 113743674 A CN113743674 A CN 113743674A CN 202111063012 A CN202111063012 A CN 202111063012A CN 113743674 A CN113743674 A CN 113743674A
- Authority
- CN
- China
- Prior art keywords
- historical
- energy storage
- output
- predicted
- storage output
- 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.)
- Pending
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000013135 deep learning Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 49
- 210000002569 neuron Anatomy 0.000 claims abstract description 40
- 238000012360 testing method Methods 0.000 claims description 55
- 239000011159 matrix material Substances 0.000 claims description 54
- 238000012545 processing Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000013102 re-test Methods 0.000 claims description 3
- 238000012022 requirements testing Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind 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
- 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
- Y02E10/56—Power conversion systems, e.g. maximum power point trackers
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system, equipment and a medium for predicting energy storage output based on deep learning, wherein predicted power grid data are firstly obtained; then inputting the predicted power grid data serving as predicted input data into an energy storage output prediction model to obtain predicted energy storage output; the energy storage output prediction model is obtained by training a multilayer neuron network model, and when the multilayer neuron network model is trained, historical power grid data are used as historical input data, and historical energy storage output is used as historical output data. The method can predict the behavior of the energy storage facility in the power grid from the energy storage history participation performance and the known part of the power grid from an objective angle, has small main effect and reduces the workload of personnel.
Description
Technical Field
The invention belongs to the field of behavior analysis and prediction of energy storage facilities in a power grid, and particularly relates to a method, a system, equipment and a medium for predicting energy storage output based on deep learning.
Background
With the development of the electric power market, the behaviors of market members are full of autonomy, and different from the operation of a power grid in a planning mode, the power grid cannot accurately know the real-time power generation or how to provide auxiliary services of all the market members in each period in advance. Thus, safety regulations for electrical grids present some challenges. With the development of energy storage technology, particularly distributed energy storage technology, and the modification of admission thresholds and organization forms of an electric energy market, an auxiliary service market and a capacity market, uncertainty is brought to the behavior prediction of energy storage participating in the market in a power grid.
Disclosure of Invention
The invention provides an energy storage output prediction method, an energy storage output prediction system, energy storage output prediction equipment and an energy storage output prediction medium based on deep learning, which are used for overcoming the defects of the prior art, can support the prediction of the behavior of an energy storage facility in a power grid from the aspects of objective under the condition that operators of the energy storage facility have different participation market schemes and established strategies, or under different scenes or under different market rules and organization forms, and have less subjective influence, reduce the workload of personnel and provide reference for power market planning operators.
In order to achieve the purpose, the invention adopts the following technical scheme:
the energy storage output prediction method based on deep learning comprises the following steps:
acquiring predicted power grid data;
inputting the predicted power grid data serving as predicted input data into an energy storage output prediction model to obtain predicted energy storage output; the energy storage output prediction model is obtained by training a multilayer neuron network model, and when the multilayer neuron network model is trained, historical power grid data are used as historical input data, and historical energy storage output is used as historical output data.
Further, the historical power grid data comprises historical load values, historical network topological structures and historical output values of hydropower, wind power and photovoltaic, and when the historical network topological structures are used as historical input data, the historical network topological structures at a certain historical time point are constructed into historical incidence matrixes corresponding to the historical time point;
the historical energy storage output is a set of energy storage outputs of a plurality of energy storage facilities at historical time points.
Further, taking historical power grid data as historical input data, taking historical energy storage output as historical output data, and training the multilayer neuron network model in the specific process that:
constructing historical input data into a historical input matrix; each row of the historical input matrix corresponds to a historical load value of a historical time point, historical output values of different hydropower, wind power and photovoltaic and different elements of a historical incidence matrix, and the different elements of the historical incidence matrix represent the connection relation between different devices in a historical network topology structure;
constructing historical output data into a historical output matrix; each row of the historical output matrix corresponds to the energy storage output of different energy storage facilities at a historical time point;
connecting the historical input matrix and the historical output matrix through the corresponding relation of historical time points to form a historical matrix, and carrying out normalization processing on the historical matrix;
splitting the history matrix after the normalization processing according to a preset proportion to obtain a training set and a test set, decomposing the training set into a history input training set and a history output training set, and decomposing the test set into a history input test set and a history output test set;
training a multi-layer neuron network model by adopting a historical input training set and a historical output training set, testing the trained multi-layer neuron network model by adopting a historical input testing set and a historical output testing set, obtaining an energy storage output prediction model if a testing result meets requirements, re-training the trained multi-layer neuron network model by adopting the historical input training set and the historical output training set after adjusting model parameters of the trained multi-layer neuron network model if the testing result does not meet the requirements, and re-testing by adopting the historical input testing set and the historical output testing set until the testing result meets the requirements.
Further, the specific process of testing the trained multi-layer neuron network model by using the historical input test set and the historical output test set is as follows:
and inputting the historical input test set into the trained multilayer neuron network model to obtain an output result, comparing the output result with the historical output test set, wherein when the accuracy is more than or equal to a preset threshold value, the test result meets the requirement, and otherwise, the test result does not meet the requirement.
Further, the model parameters include the construction form and training times of the multilayer neuron network model.
Further, the predicted power grid data adopts a predicted value under a time scale corresponding to the predicted energy storage output, and specifically comprises a load predicted value, a future network topology structure constructed by the current topology superposition maintenance plan, and predicted values of water, electricity, wind electricity and photovoltaic, wherein the future network topology structure at a certain future time point is constructed into a predicted incidence matrix corresponding to the future time point before the prediction model of the energy storage output is input into the future network topology structure.
Further, the process of inputting the predicted power grid data as the predicted input data into the energy storage output prediction model to obtain the predicted energy storage output specifically comprises the following steps:
constructing the prediction input data into a prediction input matrix;
normalizing the prediction input matrix;
inputting the prediction input matrix subjected to normalization processing into an energy storage output prediction model to obtain a prediction output matrix;
and carrying out inverse normalization processing on the prediction output matrix to obtain the predicted energy storage output.
Energy storage output prediction system based on deep learning includes: the device comprises a data acquisition module and an energy storage output prediction module, wherein:
a data acquisition module: the system is used for acquiring predicted power grid data;
the energy storage output prediction module: the energy storage output prediction model is used for inputting the predicted power grid data as predicted input data into the energy storage output prediction model to obtain predicted energy storage output; the energy storage output prediction model is obtained by training a multilayer neuron network model, and when the multilayer neuron network model is trained, historical power grid data are used as historical input data, and historical energy storage output is used as historical output data.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the deep learning based energy storage contribution prediction method when executing the computer program.
A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the deep learning-based energy storage contribution prediction method.
Compared with the prior art, the invention has the following beneficial technical effects:
the method utilizes the historical power grid data and the historical energy storage output to carry out deep learning training on the neuron network model, and utilizes the energy storage output prediction model obtained by training to predict the energy storage output under the market environment, thereby providing help for the safe operation of the power mechanism, and can make measures for guaranteeing the operation safety of the power grid in advance according to the energy storage output prediction.
Compared with the traditional method for predicting the energy storage output by utilizing similar days and utilizing a linear extrapolation method, the method has the advantages of a multi-layer neuron network, better processes the relation between the input power grid data and the predicted energy storage output, reasonably associates the strong association variable and the weak association variable, and has the advantages of processing the nonlinear relation.
Drawings
The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic flow chart of the training process of the present invention;
FIG. 3 is a schematic diagram of an energy storage output acquisition process according to the present invention;
FIG. 4 is a schematic diagram of the system of the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples.
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
An energy storage output prediction method based on deep learning is disclosed, and with reference to fig. 1, the method specifically includes:
acquiring predicted power grid data; the method comprises the steps that predicted values of predicted energy storage output under corresponding time scales are adopted for predicting power grid data, and specifically the predicted values comprise a load predicted value, a future network topological structure constructed by a current topological superposition maintenance plan and distributed hydropower, wind power and photovoltaic predicted values, and the future network topological structure is constructed into a predicted incidence matrix before an energy storage output prediction model is input into the future network topological structure.
Inputting the predicted power grid data serving as predicted input data into an energy storage output prediction model to obtain predicted energy storage output; the energy storage output prediction model is obtained by training a multilayer neuron network model, and the multilayer neuron network model adopts RNN (recurrent neural network) or LSTM (long-short term memory neural network).
The method comprises the steps of training a multi-layer neuron network model by using historical data, wherein the historical data comprises historical power grid data and historical energy storage output, in the training process, the historical power grid data is used as historical input data of the multi-layer neuron network model, the historical energy storage output is used as historical output data of the multi-layer neuron network model, and after training is finished, an energy storage output prediction model is obtained.
The historical power grid data comprises historical load values, historical network topological structures and historical output values of hydropower, wind power and photovoltaic, and when the historical network topological structures are used as historical input data, the historical network topological structures at a certain historical time point are constructed into historical association matrixes corresponding to the historical time point; the historical energy storage output is a set of energy storage outputs of a plurality of energy storage facilities at historical time points.
During training, referring to fig. 2, historical input data is constructed into a historical input matrix; each row of the historical input matrix corresponds to a historical load value of a historical time point, historical output values of different hydropower, wind power and photovoltaic and different elements of a historical incidence matrix, and the different elements of the historical incidence matrix represent the connection relation between different devices in a historical network topology structure; constructing historical output data into a historical output matrix; each row of the historical output matrix corresponds to the energy storage output of different energy storage facilities at a historical time point; connecting the historical input matrix and the historical output matrix through the corresponding relation of historical time points to form a historical matrix, and carrying out normalization processing on the historical matrix; splitting the history matrix after the normalization processing according to a preset proportion (in the embodiment, the preset proportion is 7:3) to obtain a training set and a test set, decomposing the training set into a history input training set and a history output training set, and decomposing the test set into a history input test set and a history output test set; training a multilayer neuron network model by adopting a historical input training set and a historical output training set, and testing the trained multilayer neuron network model by adopting a historical input testing set and a historical output testing set, wherein the testing process comprises the following specific steps: inputting a historical input test set into the trained multilayer neuron network model to obtain an output result, comparing the output result with the historical output test set, wherein when the accuracy is greater than or equal to a preset threshold (in the embodiment, the preset threshold is 90%), the test result meets the requirement, and otherwise, the test result does not meet the requirement; if the test result meets the requirement, obtaining an energy storage output prediction model, if the test result does not meet the requirement, adjusting model parameters (the construction form and the training times of the neuron network model) of the trained multilayer neuron network model, then adopting a historical input training set and a historical output training set to retrain again, adopting a historical input test set and a historical output test set to retest, and circulating the process until the test result meets the requirement.
Referring to fig. 3, after training is completed, inputting predicted power grid data as predicted input data into an energy storage output prediction model, wherein the predicted input data is constructed into a predicted input matrix before being input into the energy storage output prediction model, each row of the predicted input matrix corresponds to a load prediction value of a future time point, different hydropower, wind power and photovoltaic prediction values and different elements of a predicted incidence matrix, and the different elements of the predicted incidence matrix represent the connection relationship between different devices in a future network topology; then, normalizing the prediction input matrix; and inputting the normalized prediction input matrix into the energy storage output prediction model to obtain a prediction output matrix, and performing inverse normalization processing on the prediction output matrix to obtain the predicted energy storage output.
The invention also provides a system for predicting energy storage output based on deep learning, referring to fig. 4, including: the device comprises a data acquisition module and an energy storage output prediction module, wherein:
a data acquisition module: the system is used for acquiring predicted power grid data;
the energy storage output prediction module: the energy storage output prediction model is used for inputting the predicted power grid data as predicted input data into the energy storage output prediction model to obtain predicted energy storage output; the energy storage output prediction model is obtained by training a multilayer neuron network model, and when the multilayer neuron network model is trained, historical power grid data are used as historical input data, and historical energy storage output is used as historical output data.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, those skilled in the art will appreciate that various changes, modifications and equivalents can be made in the embodiments of the invention without departing from the scope of the invention as defined by the appended claims.
Claims (10)
1. The energy storage output prediction method based on deep learning is characterized by comprising the following steps:
acquiring predicted power grid data;
inputting the predicted power grid data serving as predicted input data into an energy storage output prediction model to obtain predicted energy storage output; the energy storage output prediction model is obtained by training a multilayer neuron network model, and when the multilayer neuron network model is trained, historical power grid data are used as historical input data, and historical energy storage output is used as historical output data.
2. The energy storage output prediction method based on deep learning of claim 1 is characterized in that the historical power grid data comprises historical load values, historical network topology structures and historical output values of hydropower, wind power and photovoltaic, and when the historical network topology structures are used as historical input data, the historical network topology structures at a certain historical time point are constructed into historical association matrixes corresponding to the historical time point;
the historical energy storage output is a set of energy storage outputs of a plurality of energy storage facilities at historical time points.
3. The energy storage output prediction method based on deep learning of claim 2, wherein the specific process of training the multi-layer neuron network model by using historical power grid data as historical input data and historical energy storage output data as historical output data is as follows:
constructing historical input data into a historical input matrix; each row of the historical input matrix corresponds to a historical load value of a historical time point, historical output values of different hydropower, wind power and photovoltaic and different elements of a historical incidence matrix, and the different elements of the historical incidence matrix represent the connection relation between different devices in a historical network topology structure;
constructing historical output data into a historical output matrix; each row of the historical output matrix corresponds to the energy storage output of different energy storage facilities at a historical time point;
connecting the historical input matrix and the historical output matrix through the corresponding relation of historical time points to form a historical matrix, and carrying out normalization processing on the historical matrix;
splitting the history matrix after the normalization processing according to a preset proportion to obtain a training set and a test set, decomposing the training set into a history input training set and a history output training set, and decomposing the test set into a history input test set and a history output test set;
training a multi-layer neuron network model by adopting a historical input training set and a historical output training set, testing the trained multi-layer neuron network model by adopting a historical input testing set and a historical output testing set, obtaining an energy storage output prediction model if a testing result meets requirements, re-training the trained multi-layer neuron network model by adopting the historical input training set and the historical output training set after adjusting model parameters of the trained multi-layer neuron network model if the testing result does not meet the requirements, and re-testing by adopting the historical input testing set and the historical output testing set until the testing result meets the requirements.
4. The energy storage output prediction method based on deep learning of claim 3, wherein the specific process of testing the trained multi-layer neuron network model by using the historical input test set and the historical output test set is as follows:
and inputting the historical input test set into the trained multilayer neuron network model to obtain an output result, comparing the output result with the historical output test set, wherein when the accuracy is more than or equal to a preset threshold value, the test result meets the requirement, and otherwise, the test result does not meet the requirement.
5. The deep learning-based energy storage capacity contribution prediction method of claim 3, wherein the model parameters comprise a construction form and training times of a multilayer neuron network model.
6. The energy storage output prediction method based on deep learning of claim 1, wherein the predicted power grid data adopts a predicted value under a time scale corresponding to the predicted energy storage output, and specifically comprises a load predicted value, a future network topology structure constructed by a current topology superposition maintenance plan, and predicted values of hydropower, wind power and photovoltaic, and the future network topology structure constructs the future network topology structure at a future time point as a predicted association matrix corresponding to the future time point before the energy storage output prediction model is input.
7. The energy storage output prediction method based on deep learning of claim 1, wherein the process of inputting the predicted power grid data as the prediction input data into the energy storage output prediction model to obtain the predicted energy storage output specifically comprises:
constructing the prediction input data into a prediction input matrix;
normalizing the prediction input matrix;
inputting the prediction input matrix subjected to normalization processing into an energy storage output prediction model to obtain a prediction output matrix;
and carrying out inverse normalization processing on the prediction output matrix to obtain the predicted energy storage output.
8. Energy storage output prediction system based on deep learning is characterized by comprising: the device comprises a data acquisition module and an energy storage output prediction module, wherein:
a data acquisition module: the system is used for acquiring predicted power grid data;
the energy storage output prediction module: the energy storage output prediction model is used for inputting the predicted power grid data as predicted input data into the energy storage output prediction model to obtain predicted energy storage output; the energy storage output prediction model is obtained by training a multilayer neuron network model, and when the multilayer neuron network model is trained, historical power grid data are used as historical input data, and historical energy storage output is used as historical output data.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the deep learning based energy storage contribution prediction method of any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for predicting a deep learning-based energy storage contribution according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111063012.5A CN113743674A (en) | 2021-09-10 | 2021-09-10 | Energy storage output prediction method, system, equipment and medium based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111063012.5A CN113743674A (en) | 2021-09-10 | 2021-09-10 | Energy storage output prediction method, system, equipment and medium based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113743674A true CN113743674A (en) | 2021-12-03 |
Family
ID=78737996
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111063012.5A Pending CN113743674A (en) | 2021-09-10 | 2021-09-10 | Energy storage output prediction method, system, equipment and medium based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113743674A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114548549A (en) * | 2022-02-20 | 2022-05-27 | 国网河北省电力有限公司邢台供电分公司 | Power consumption prediction method and prediction system based on Koalas |
CN116388279A (en) * | 2023-05-23 | 2023-07-04 | 安徽中超光电科技有限公司 | Grid-connected control method and control system for solar photovoltaic power generation system |
CN117454121A (en) * | 2023-12-22 | 2024-01-26 | 华能济南黄台发电有限公司 | Data analysis processing method and system based on power plant safety precaution |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108009673A (en) * | 2017-11-24 | 2018-05-08 | 国网北京市电力公司 | Novel load Forecasting Methodology and device based on deep learning |
CN111861039A (en) * | 2020-07-31 | 2020-10-30 | 广东电网有限责任公司广州供电局 | Power load prediction method, system, equipment and storage medium based on LSTM and generalized predictive control algorithm |
CN112215442A (en) * | 2020-11-27 | 2021-01-12 | 中国电力科学研究院有限公司 | Method, system, device and medium for predicting short-term load of power system |
CN113240187A (en) * | 2021-05-26 | 2021-08-10 | 合肥工业大学 | Prediction model generation method, system, device, storage medium and prediction method |
-
2021
- 2021-09-10 CN CN202111063012.5A patent/CN113743674A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108009673A (en) * | 2017-11-24 | 2018-05-08 | 国网北京市电力公司 | Novel load Forecasting Methodology and device based on deep learning |
CN111861039A (en) * | 2020-07-31 | 2020-10-30 | 广东电网有限责任公司广州供电局 | Power load prediction method, system, equipment and storage medium based on LSTM and generalized predictive control algorithm |
CN112215442A (en) * | 2020-11-27 | 2021-01-12 | 中国电力科学研究院有限公司 | Method, system, device and medium for predicting short-term load of power system |
CN113240187A (en) * | 2021-05-26 | 2021-08-10 | 合肥工业大学 | Prediction model generation method, system, device, storage medium and prediction method |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114548549A (en) * | 2022-02-20 | 2022-05-27 | 国网河北省电力有限公司邢台供电分公司 | Power consumption prediction method and prediction system based on Koalas |
CN116388279A (en) * | 2023-05-23 | 2023-07-04 | 安徽中超光电科技有限公司 | Grid-connected control method and control system for solar photovoltaic power generation system |
CN116388279B (en) * | 2023-05-23 | 2024-01-23 | 安徽中超光电科技有限公司 | Grid-connected control method and control system for solar photovoltaic power generation system |
CN117454121A (en) * | 2023-12-22 | 2024-01-26 | 华能济南黄台发电有限公司 | Data analysis processing method and system based on power plant safety precaution |
CN117454121B (en) * | 2023-12-22 | 2024-04-05 | 华能济南黄台发电有限公司 | Data analysis processing method and system based on power plant safety precaution |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113743674A (en) | Energy storage output prediction method, system, equipment and medium based on deep learning | |
CN109324291B (en) | Prediction method for predicting service life of proton exchange membrane fuel cell | |
CN102707256B (en) | Fault diagnosis method based on BP-Ada Boost nerve network for electric energy meter | |
CN112651290A (en) | Hydroelectric generating set vibration trend prediction method and system | |
CN109782124B (en) | Main distribution integrated fault positioning method and system based on gradient descent algorithm | |
CN106126944B (en) | A kind of power transformer top-oil temperature interval prediction method and system | |
CN112069727B (en) | Intelligent transient stability evaluation system and method with high reliability for power system | |
CN105547730A (en) | Fault detection system of water-wheel generator set | |
CN111062170A (en) | Transformer top layer oil temperature prediction method | |
CN105320987A (en) | Satellite telemetry data intelligent interpretation method based on BP neural network | |
CN110532314A (en) | The method and terminal device of High-Voltage Electrical Appliances quality testing | |
Hu et al. | A hybrid model for predicting the degradation trend of hydropower units based on deep learning | |
CN109061391A (en) | A kind of electric network failure diagnosis method and system based on computer vision tidal current chart | |
CN108767987A (en) | A kind of power distribution network and its micro-capacitance sensor protection and control system | |
CN109921462B (en) | New energy consumption capability assessment method and system based on LSTM | |
CN111371088A (en) | Method and system for correcting SVG control strategy based on BP neural network | |
CN113240217A (en) | Photovoltaic power generation prediction method and device based on integrated prediction model | |
CN117236380A (en) | Power system fault prediction method, system, electronic equipment and medium | |
CN105741184A (en) | Transformer state evaluation method and apparatus | |
CN112465136A (en) | Hydroelectric generating set degradation prediction method and system | |
CN115496234A (en) | Fault diagnosis method and device for direct current charger and storage medium | |
CN115184734A (en) | Power grid line fault detection method and system | |
CN107124003A (en) | Wind power plant wind energy Forecasting Methodology and equipment | |
Liu et al. | Intelligent voltage prediction of active distribution network with high proportion of distributed photovoltaics | |
CN114320773A (en) | Wind turbine generator fault early warning method based on power curve analysis and neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |