CN117578544A - Micro-grid energy storage scheduling method and system - Google Patents
Micro-grid energy storage scheduling method and system Download PDFInfo
- Publication number
- CN117578544A CN117578544A CN202311572767.7A CN202311572767A CN117578544A CN 117578544 A CN117578544 A CN 117578544A CN 202311572767 A CN202311572767 A CN 202311572767A CN 117578544 A CN117578544 A CN 117578544A
- Authority
- CN
- China
- Prior art keywords
- energy storage
- micro
- grid
- scheduling
- storage scheduling
- 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 171
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 14
- 238000003062 neural network model Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 9
- 238000010248 power generation Methods 0.000 claims description 78
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 6
- FFBHFFJDDLITSX-UHFFFAOYSA-N benzyl N-[2-hydroxy-4-(3-oxomorpholin-4-yl)phenyl]carbamate Chemical compound OC1=C(NC(=O)OCC2=CC=CC=C2)C=CC(=C1)N1CCOCC1=O FFBHFFJDDLITSX-UHFFFAOYSA-N 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 30
- 238000010606 normalization Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006854 communication Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 2
- 239000002253 acid Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- 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
- H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
- H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
- H02J3/0075—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source according to economic or energy efficiency considerations, e.g. economic dispatch
-
- 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
- H02J3/381—Dispersed generators
-
- 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
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/00032—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries characterised by data exchange
-
- 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
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/0047—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries with monitoring or indicating devices or circuits
- H02J7/0048—Detection of remaining charge capacity or state of charge [SOC]
-
- 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
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/0047—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries with monitoring or indicating devices or circuits
- H02J7/005—Detection of state of health [SOH]
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a micro-grid energy storage scheduling method, which comprises the following steps: acquiring historical energy storage scheduling data of different micro grid nodes, establishing a sample set according to the historical energy storage scheduling data of the micro grid nodes, and dividing the sample set into a test set and a training set; constructing a convolutional neural network model, and setting a network layer and corresponding initial weight parameters of the convolutional neural network model; setting an objective function, wherein the objective function comprises a power grid fluctuation value, an energy storage scheduling benefit value and an energy storage scheduling efficiency value of the micro-power grid energy storage scheduling; and training the neural network model according to the objective function and the training set, and obtaining the energy storage scheduling model which accords with the objective function condition after adjusting the initial weight parameter. And the final energy storage scheduling model simultaneously accords with the technical effects of economy, stability and efficiency on energy storage scheduling of different micro-grid nodes.
Description
Technical Field
The invention relates to the technical field of energy storage scheduling, in particular to a micro-grid energy storage scheduling method and system.
Background
At present, along with the large-scale installation of wind power, solar energy and various self-generating equipment, the number of power supply ends in a power grid is greatly improved, energy storage equipment is arranged at the power supply ends of the micro-grid respectively, a micro-grid structure with the size is formed on a local power grid, however, the energy storage mode, the electric energy transmission mode and the energy storage distance of the micro-grid can cause fluctuation of the power grid, so that the power supply quality of the micro-grid is affected, and in addition, the energy storage cost and the benefit of the micro-grid are also more.
Disclosure of Invention
One of the purposes of the invention is to provide a micro-grid energy storage scheduling method and system, which are used for constructing a sample micro-grid energy storage scheduling sample set, dividing the sample set into a training set and a testing set, further constructing a convolutional neural network, inputting the sample set into the convolutional neural network for training to obtain a micro-grid energy storage scheduling model which is high in cost and efficiency and stable, and executing energy storage scheduling operation on the micro-grid by using the energy storage scheduling model, so that the energy storage scheduling effect is improved.
The invention further aims to provide a micro-grid energy storage scheduling method and system, which construct a multi-dimensional objective function comprising power grid fluctuation, energy storage efficiency and energy storage benefit, and the training result of the neural network model is enabled to accord with the setting condition of the multi-dimensional objective function by training the sample set in the constructed neural network model, so that the final energy storage scheduling model simultaneously accords with the technical effects of economy, stability and efficiency on energy storage scheduling of different micro-grid nodes.
Another object of the present invention is to provide a micro-grid energy storage scheduling method and system, which uses characteristics of a single sample in a sample set of the neural network model, including each power generation device type of a micro-grid node, a distance between power generation equipment and energy storage equipment, SOC and SOH characteristics of the energy storage equipment itself, output voltage and current of power generation device scheduling, and input voltage and current of receiving energy storage device.
In order to achieve at least one of the above objects, the present invention further provides a micro-grid energy storage scheduling method, the method comprising:
acquiring historical energy storage scheduling data of different micro grid nodes, establishing a sample set according to the historical energy storage scheduling data of the micro grid nodes, and dividing the sample set into a test set and a training set;
constructing a convolutional neural network model, and setting a network layer and corresponding initial weight parameters of the convolutional neural network model;
setting an objective function, wherein the objective function comprises a power grid fluctuation value, an energy storage scheduling benefit value and an energy storage scheduling efficiency value of the micro-power grid energy storage scheduling;
and training the neural network model according to the objective function and the training set, and obtaining the energy storage scheduling model which accords with the objective function condition after adjusting the initial weight parameter.
According to one preferred embodiment of the present invention, the method for constructing the sample set includes: the historical energy storage scheduling scheme of each micro-grid is obtained, the output voltage and the output current of the power generation equipment of each micro-grid node in a single scheduling process, the distance between the micro-grid power generation equipment and the scheduled micro-grid energy storage equipment, the distance between the target micro-grid energy storage device SOC and the SOH and the micro-grid power generation equipment type are obtained according to the historical energy storage scheduling scheme, a feature set is formed by combining the feature sets of different scheduling schemes of different micro-grid nodes into the sample set.
According to another preferred embodiment of the present invention, the sample set construction method includes: and giving a fixed characteristic value according to the type of each power generation device in the micro-grid, constructing a power generation device type characteristic value in a sample set, and directly distributing the power generation device type characteristic value of the current dispatching data scheme after the current power generation device type in the historical energy storage dispatching data is identified.
According to another preferred embodiment of the present invention, the sample set construction method includes: acquiring position data of power generation equipment in a single sample energy storage scheduling scheme, acquiring position data of target energy storage equipment in the energy storage scheduling scheme, calculating the space linear distance between the power generation equipment and the target energy storage equipment according to a space geometric distance calculation method, and taking the space linear distance as an energy storage scheduling distance characteristic value in the sample.
According to another preferred embodiment of the present invention, the sample set construction method includes: acquiring target energy storage device SOC and SOH values to be scheduled by a power generation device of a corresponding micro-grid in a current historical energy storage scheduling data scheme, taking the target energy storage device SOC and SOH values as scheduling result characteristic values of single samples of the current historical energy storage scheduling data scheme, and calculating to obtain energy storage scheduling benefit values of the single samples in the current historical energy storage scheduling data scheme according to total power generation electric energy of the power generation device of the corresponding micro-grid and electric energy received and stored by the scheduled target energy storage device, wherein the energy storage scheduling benefit value delta P calculation method comprises the following steps: calculating total power generation electric energy P of power generation device corresponding to micro-grid 0 And the power P received and stored by the scheduled target energy storage device 1 Is a difference Δp= |p 1 -P 0 |。
According to another preferred embodiment of the present invention, the method for calculating the grid fluctuation in the objective function includes: when the micro-grid power generation equipment is in a power generation scheduling process, acquiring a voltage fluctuation value delta U of a commercial power network connected with the micro-grid, wherein the calculation method of the voltage fluctuation value delta U of the commercial power network comprises the following steps: obtaining an initial voltage U of a commercial power network connected with the micro-grid node before dispatching 0 And detecting the highest voltage or the lowest voltage U of the power generation equipment of the micro-grid in real time in the dispatching process 1 The corresponding voltage fluctuation value Δu=max|u 1 -U 0 I, acquiring voltage fluctuation values delta U of all micro-grids in different energy storage scheduling schemes n 。
According to another preferred embodiment of the present invention, the method for calculating the energy storage scheduling efficiency value Δt in the objective function includes: recording the starting scheduling time t of target power generation equipment in a single scheduling process 0 And recording the energy storage full time t of the scheduled energy storage device 1 The energy storage scheduling efficiency values are respectively deltat= (T) 1 -t 0 )。
According to another preferred embodiment of the present invention, the energy storage scheduling benefit value Δp, the voltage fluctuation value Δu and the energy storage scheduling efficiency value Δt are normalized, and the corresponding adjustment parameters are configured to product the objective function W after the normalization.
In order to achieve at least one of the above objects, the present invention further provides a micro-grid energy storage scheduling system, which performs the above-mentioned micro-grid energy storage scheduling method according to a computer program.
The present invention further provides a computer readable storage medium storing a computer program for execution by a processor to implement a micro grid energy storage scheduling method as described above.
Drawings
Fig. 1 shows a schematic flow chart of a micro-grid energy storage scheduling method of the invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
It will be understood that the terms "a" and "an" should be interpreted as referring to "at least one" or "one or more," i.e., in one embodiment, the number of elements may be one, while in another embodiment, the number of elements may be plural, and the term "a" should not be interpreted as limiting the number.
Referring to fig. 1, the invention discloses a micro-grid energy storage scheduling method and a micro-grid energy storage scheduling system, wherein the method mainly comprises the following steps: firstly, determining power generation equipment and energy storage equipment existing in a micro-grid, wherein the power generation equipment comprises but is not limited to wind power equipment, solar power generation equipment, a diesel generator and the like; and the corresponding energy storage device may be a battery including, but not limited to, lead acid batteries, lithium batteries, nickel-based batteries, and the like. The connection between the different power generation devices and the energy storage devices forms an energy storage grid structure of the micro-grid, the micro-grid node comprises the corresponding power generation device and at least one energy storage device arranged for the power generation device, when the power generation device generates power, electric energy is preferably transmitted and stored to the relevant energy storage device in the micro-grid node, and when the relevant energy storage device in the micro-grid node is fully stored, electric energy scheduling storage among the different micro-grid nodes is executed according to a certain scheduling logic. According to the invention, a convolution neural network model is built, a sample set is built according to energy storage scheduling data of historical micro-grid nodes, the sample set is divided into a training set and a test set, an objective function is built, training of the convolution neural network model is executed according to the objective function, and a micro-grid energy storage scheduling model is obtained, and relevant parameters including power grid fluctuation, scheduling efficiency and scheduling benefit are set in the objective function. In another preferred embodiment of the present invention, the objective function may be used to obtain an energy storage schedule with an optimal adjustment direction, so as to obtain an optimal scheduling scheme with an optimal adjustment direction.
Specifically, after historical energy storage scheduling data of each micro-grid are obtained, output voltage, output current and target micro-grid energy storage device of power generation equipment of each micro-grid node in the historical energy storage scheduling data in a single scheduling process are extractedThe system comprises SOC and SOH, distance between micro-grid power generation equipment and scheduled micro-grid energy storage equipment and micro-grid power generation equipment type, wherein output voltage and output current of the power generation equipment in a single scheduling process can be obtained through related voltage sensors and current sensors, and the target micro-grid energy storage device SOC and SOH can be calculated according to related parameters such as input voltage, input current and rated capacity of the energy storage device. The SOC and SOH of the energy storage device may be calculated corresponding to the lithium battery or the lead-acid battery, and the present invention will not be described in detail because the battery SOC and SOH estimation method is the prior art. The invention defines the output voltage and the output current of different micro-grid power generation equipment to be U respectively out,n And I out,n Where out subscript denotes the output and n denotes the corresponding microgrid node. Further definition U in,n And I in,n For the input voltage and input current of the corresponding energy storage device, n represents the micro-grid node where the corresponding energy storage device is located. SOC and SOH of the energy storage device corresponding to the micro-grid node are further SOC n And SOH n 。
Further, the invention configures a corresponding numerical label for the complaint book micro-grid power generation equipment, and because each micro-grid power generation equipment has a unique identification code, the unique identification code is the factory set identity of each power generation equipment, the unique identification code of the power generation equipment of each micro-grid node can be obtained in the communication process, the corresponding power generation equipment type can be identified according to the unique identification code, for example, in the energy storage scheduling process, the unique identification codes including but not limited to wind power equipment, solar power generation equipment and diesel generator can be obtained, and the unique identification codes of the wind power equipment, the solar power generation equipment and the diesel generator can be a n 、b n 、c n . After the unique identification codes are identified, the numerical labels S of the corresponding types are respectively assigned to the unique identification codes m，n N represents the corresponding micro grid node, and m subscripts represent the corresponding power generation device type, where m is set according to the number of power generation device types. For constructing a type characteristic value of the power generation device.
Further, the methodBecause the positions of the different micro grid nodes are different, a certain space distance can exist, and a scheduling distance feature is also an important reference feature of energy storage scheduling, the scheduling distance feature can have the influence of distance loss related factors of power transmission, and the scheduling distance feature can be used for comprehensive reference features of a scheduling scheme, wherein the calculation method of the scheduling distance feature comprises the following steps: acquiring position data d of power generation equipment in current scheduling scheme 0 The location data may be obtained by means including, but not limited to, GPS, radio frequency location technology, communication base station location technology, etc., and the location data d of the micro-grid node where the target energy storage device of the corresponding scheduled scheme is located is obtained according to the location technology 1 Defining the position data d of the power generation equipment 0 And micro-grid node position data d of the target energy storage device of the scheduled scheme 1 The distance between them is l n，q ＝|d 0 -d 1 And (3) the node of the micro-grid where the target energy storage device to be scheduled is located, and n is the node of the micro-grid where the power generation device to be scheduled is located. The position data d of the power generation equipment is calculated 0 And micro-grid node position data d of the target energy storage device of the scheduled scheme 1 Distance between l n As a dispatch distance feature in the samples. The sample characteristic data of the single scheduling scheme in the historical scheduling data of the micro-grid are as follows: f (F) n ＝(U out,n ；I out,n ；U in,n ；I in,n ；SOC n ；SOH n ；l n，q ；S m，n ) The sample characteristic data of the single scheduling scheme is taken as a single sample in a sample set, and all sample characteristic data in the historical energy storage scheduling data of the micro-grid are further obtained. And preprocessing all the sample characteristic data, and inputting the preprocessed sample characteristic data into the convolutional neural network model for training so as to obtain the micro-grid energy storage scheduling model.
The method for preprocessing the sample data comprises the following steps: element f in each sample data n Performing normalization processing on the sample data element f n Is U (U) out,n ；I out,n ；U in,n ；I in,n ；SOC n ；SOH n ；l n，q ；S m，n The normalization processing method comprises the following steps: obtaining the maximum value f of the sample data corresponding to the same element in the historical data max And a minimum value f min And normalized by the following formula n /|f max -f min |。
After carrying out normalization processing on sample data elements, further dividing the sample data after normalization processing into a training set and a testing set, wherein the training set accounts for 80% of total samples, the testing set accounts for 20% of total samples, training the convolutional neural network by utilizing the training set, optimizing super-parameters such as weight parameters and the like of the convolutional neural network through an objective function in the training process, enabling an output result to meet constraint conditions of the objective function, and further testing the trained convolutional neural network model by utilizing the testing set, thereby obtaining a final micro-grid energy storage scheduling model.
It should be noted that, in the present invention, the number of network layers is preset for the neural network model, where an input layer, a convolution layer, a pooling layer, a full connection layer and an output layer of the convolution neural network are preset. Setting the layer number of the convolution layer and the initial weight parameter of the corresponding layer, and further processing the preprocessed training set sample characteristic data F n ＝(U out,n ；I out,n ；U in,n ；I in,n ；SOC n ；SOH n ；l n，q ；S m，n ) And the optimal energy storage scheduling scheme is predicted at the output layer according to the constrained objective function.
Wherein the constraint parameters of the objective function W in the present invention include: the energy storage scheduling benefit value delta P, the voltage fluctuation value delta U and the energy storage scheduling efficiency value delta T, wherein the calculation method of the energy storage scheduling benefit value delta P comprises the following steps: acquiring target energy storage device SOC and SOH values scheduled by target power generation equipment, and taking the target energy storage device SOC and SOH values as a current historical energy storage scheduling data schemeThe characteristic value of the dispatching result of the single sample is according to the total power generation electric energy P of the power generation device of the corresponding micro-grid 0 And the power P received and stored by the scheduled target energy storage device 1 Calculating to obtain an energy storage scheduling benefit value of a single sample in a current historical energy storage scheduling data scheme, wherein the total power generation electric energy P of the power generation device of the corresponding micro-grid 0 The calculation method of (a) includes, but is not limited to, average voltage u 0 Average current i 0 And the product of the scheduling time t, i.e. P 0 ＝u 0 *i 0 * t. Of course, in other calculation modes of the present invention, the total power generation electric energy of the micro-grid power generation device can be calculated according to the power generation power and the power generation time of the micro-grid power generation device, which is not described in detail in the present invention. Further calculating the electric quantity of the energy storage device before dispatching according to the voltage of the energy storage device before dispatching and the battery capacity, calculating the electric quantity of the energy storage device after dispatching according to the voltage of the energy storage device before dispatching and the battery capacity, calculating the difference value of the electric quantity of the energy storage device after dispatching and the electric quantity before dispatching as the received and stored electric energy P of the dispatching micro-grid energy storage device 1 Therefore, the energy storage scheduling benefit value Δp= |p 1 -P 0 |。
The method for acquiring and calculating the voltage fluctuation value delta U in the constraint parameters of the objective function W comprises the following steps: and a voltage sensor connected with the mains supply is configured on each micro-grid node in advance, the voltage fluctuation value of the mains supply network can be known through the voltage sensor, and the mains supply voltage connected with the power generation equipment micro-grid node and the scheduled energy storage equipment micro-grid node in the scheduling scheme is detected and obtained through the voltage sensor. The invention detects the connected mains voltage before starting the dispatching according to each dispatching scheme to obtain the initial voltage U 0 And detecting the highest voltage or the lowest voltage U of the power generation equipment of the micro-grid in real time in the dispatching process 1 The corresponding voltage fluctuation value Δu=max|u 1 -U 0 When the voltage fluctuation value delta U of all micro grid nodes in different energy storage scheduling schemes is acquired n The above voltage fluctuation value serves as a constraint condition of the objective function W.
The calculation method of the energy storage scheduling efficiency value delta T in the constraint parameters of the objective function W comprises the following steps: recording the starting scheduling time t of target power generation equipment in a single scheduling process 0 And recording the energy storage full time t of the scheduled energy storage device 1 The energy storage scheduling efficiency values are respectively deltat= (T) 1 -t 0 )。
The objective function in the present invention can be expressed as follows: f= (min (Δu) n )；max(ΔP n )；min(ΔT n ) The constraint condition of the objective function is to obtain a scheduling scheme with the best energy storage scheduling efficiency, the lowest voltage fluctuation value and the highest scheduling efficiency in the scheduling scheme. In another preferred embodiment of the present invention, because there is an incompatible technical solution, the present invention can select any constraint parameter in the objective function as an adjustment basis for super parameters of model training, and when different scheduling solutions obtain that the objective function meets the corresponding constraint parameter and the loss function meets the convergence condition, it indicates that the micro-grid energy storage scheduling model is trained. It is worth mentioning that the convolutional neural network adopted by the invention is the prior art, and the method only sets training data and objective functions and does not improve the training process, so that the invention does not describe how to train the convolutional neural network model.
The processes described above with reference to flowcharts may be implemented as computer software programs in accordance with the disclosed embodiments of the invention. Embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via a communication portion, and/or installed from a removable medium. The above-described functions defined in the method of the present application are performed when the computer program is executed by a Central Processing Unit (CPU). It should be noted that the computer readable medium described in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wire segments, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It will be understood by those skilled in the art that the embodiments of the present invention described above and shown in the drawings are merely illustrative and not restrictive of the current invention, and that this invention has been shown and described with respect to the functional and structural principles thereof, without departing from such principles, and that any modifications or adaptations of the embodiments of the invention may be possible and practical.
Claims (10)
1. A micro-grid energy storage scheduling method, the method comprising:
acquiring historical energy storage scheduling data of different micro grid nodes, establishing a sample set according to the historical energy storage scheduling data of the micro grid nodes, and dividing the sample set into a test set and a training set;
constructing a convolutional neural network model, and setting a network layer and corresponding initial weight parameters of the convolutional neural network model;
setting an objective function, wherein the objective function comprises a power grid fluctuation value, an energy storage scheduling benefit value and an energy storage scheduling efficiency value of the micro-power grid energy storage scheduling;
and training the neural network model according to the objective function and the training set, and obtaining the energy storage scheduling model which accords with the objective function condition after adjusting the initial weight parameter.
2. The micro-grid energy storage scheduling method according to claim 1, wherein the method for constructing the sample set comprises the following steps: the historical energy storage scheduling scheme of each micro-grid is obtained, the output voltage and the output current of the power generation equipment of each micro-grid node in a single scheduling process, the distance between the micro-grid power generation equipment and the scheduled micro-grid energy storage equipment, the distance between the target micro-grid energy storage device SOC and the SOH and the micro-grid power generation equipment type are obtained according to the historical energy storage scheduling scheme, a feature set is formed by combining the feature sets of different scheduling schemes of different micro-grid nodes into the sample set.
3. The micro-grid energy storage scheduling method according to claim 2, wherein the sample set construction method comprises: and giving a fixed characteristic value according to the type of each power generation device in the micro-grid, constructing a power generation device type characteristic value in a sample set, and directly distributing the power generation device type characteristic value of the current dispatching data scheme after the current power generation device type in the historical energy storage dispatching data is identified.
4. The micro-grid energy storage scheduling method according to claim 2, wherein the sample set construction method comprises: acquiring position data of power generation equipment in a single sample energy storage scheduling scheme, acquiring position data of target energy storage equipment in the energy storage scheduling scheme, calculating the space linear distance between the power generation equipment and the target energy storage equipment according to a space geometric distance calculation method, and taking the space linear distance as an energy storage scheduling distance characteristic value in the sample.
5. The micro-grid energy storage scheduling method according to claim 2, wherein the sample set construction method comprises: acquiring target energy storage device SOC and SOH values to be scheduled by a power generation device of a corresponding micro-grid in a current historical energy storage scheduling data scheme, taking the target energy storage device SOC and SOH values as scheduling result characteristic values of single samples of the current historical energy storage scheduling data scheme, and calculating to obtain energy storage scheduling benefit values of the single samples in the current historical energy storage scheduling data scheme according to total power generation electric energy of the power generation device of the corresponding micro-grid and electric energy received and stored by the scheduled target energy storage device, wherein the energy storage scheduling benefit value delta P calculation method comprises the following steps: calculating the correspondenceTotal power generation power P of power generation device of micro-grid 0 And the power P received and stored by the scheduled target energy storage device 1 Is a difference Δp= |p 1 -P 0 |。
6. The micro-grid energy storage scheduling method according to claim 5, wherein the method for calculating the grid fluctuation in the objective function comprises: when the micro-grid power generation equipment is in a power generation scheduling process, acquiring a voltage fluctuation value delta U of a commercial power network connected with the micro-grid, wherein the calculation method of the voltage fluctuation value delta U of the commercial power network comprises the following steps: obtaining an initial voltage U of a commercial power network connected with the micro-grid before dispatching 0 And detecting the highest voltage or the lowest voltage U of the power generation equipment of the micro-grid in real time in the dispatching process 1 The corresponding voltage fluctuation value Δu=max|u 1 -U 0 I, acquiring voltage fluctuation values delta U of all micro-grids in different energy storage scheduling schemes n 。
7. The micro-grid energy storage scheduling method according to claim 6, wherein the method for calculating the energy storage scheduling efficiency value in the objective function comprises: recording the starting scheduling time t of target power generation equipment in a single scheduling process 0 And recording the energy storage full time t of the scheduled energy storage device 1 The energy storage scheduling efficiency values are respectively deltat= (T) 1 -t 0 )。
8. The micro-grid energy storage scheduling method according to claim 7, wherein the energy storage scheduling benefit value Δp, the voltage fluctuation value Δu and the energy storage scheduling efficiency value Δt are normalized, and the objective function W is obtained by multiplying the normalized energy storage scheduling benefit value Δp, the normalized energy storage scheduling efficiency value Δu and the normalized energy storage scheduling efficiency value Δt by respectively configuring corresponding adjustment parameters as weights.
9. A micro-grid energy storage scheduling system, characterized in that the system performs a micro-grid energy storage scheduling method according to any one of the preceding claims 1-8 according to a computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, which is executed by a processor to implement a micro grid energy storage scheduling method according to any of the preceding claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311572767.7A CN117578544A (en) | 2023-11-22 | 2023-11-22 | Micro-grid energy storage scheduling method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311572767.7A CN117578544A (en) | 2023-11-22 | 2023-11-22 | Micro-grid energy storage scheduling method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117578544A true CN117578544A (en) | 2024-02-20 |
Family
ID=89860414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311572767.7A Pending CN117578544A (en) | 2023-11-22 | 2023-11-22 | Micro-grid energy storage scheduling method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117578544A (en) |
-
2023
- 2023-11-22 CN CN202311572767.7A patent/CN117578544A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9639642B2 (en) | Time series forecasting ensemble | |
| KR20230122165A (en) | Method and device for optimizing charging and energy supply of charging management system | |
| CN102184453A (en) | Wind power combination predicting method based on fuzzy neural network and support vector machine | |
| CN110659693B (en) | K-nearest neighbor classification-based power distribution network rapid topology identification method, system and medium | |
| CN111722540A (en) | Energy Internet digital twin simulation system and method | |
| CN104348188A (en) | Distributed generation running and monitoring method | |
| CN110380444B (en) | Capacity planning method for distributed wind power orderly access to power grid under multiple scenes based on variable structure Copula | |
| Chobe et al. | Deployment of framework for charging electric vehicle based on various topologies | |
| CN112994097A (en) | High-proportion distributed photovoltaic cooperative control method based on intelligent distribution transformer terminal system | |
| CN103345663A (en) | Combinatorial optimization method of electric power system set considering creep speed constraints | |
| CN111371088B (en) | Method and system for correcting SVG control strategy based on BP neural network | |
| CN116933318A (en) | Power consumption data privacy protection method based on federal learning | |
| Numair et al. | A proposed iot architecture for effective energy management in smart microgrids | |
| CN104537233A (en) | Distribution network pseudo measurement generating method based on kernel density estimation | |
| CN108321801A (en) | A kind of Energy Base system generation schedule formulating method and system a few days ago | |
| CN112819203A (en) | Charging management system and method based on deep learning | |
| CN117578544A (en) | Micro-grid energy storage scheduling method and system | |
| Sun et al. | Prediction-based manufacturing center self-adaptive demand side energy optimization in cyber physical systems | |
| CN116520074A (en) | Active power distribution network fault positioning method and system based on cloud edge cooperation | |
| KR101581684B1 (en) | Apparatus and method for charge and discharge scheduling using Depth of Discharge control in energy storage device | |
| CN116862036A (en) | Load prediction method and device | |
| AlKassem et al. | A topsis model to support smart appliance decision energy management in smart grid | |
| Han et al. | Grid-to-vehicle (G2V) and vehicle-to-grid (V2G) technologies | |
| Lee et al. | Genetic algorithm-based demand response scheme for electric vehicle charging | |
| Mamounakis et al. | Renewable energy prosumers clustering towards target aggregated prosumption profiles based on recursive predictions |
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 |