CN112421631A - New energy consumption capacity assessment method and system - Google Patents
New energy consumption capacity assessment method and system Download PDFInfo
- Publication number
- CN112421631A CN112421631A CN202110092890.3A CN202110092890A CN112421631A CN 112421631 A CN112421631 A CN 112421631A CN 202110092890 A CN202110092890 A CN 202110092890A CN 112421631 A CN112421631 A CN 112421631A
- Authority
- CN
- China
- Prior art keywords
- new energy
- energy consumption
- power grid
- values
- model
- 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
- 238000005265 energy consumption Methods 0.000 title claims abstract description 150
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 44
- 238000005192 partition Methods 0.000 claims abstract description 37
- 238000011156 evaluation Methods 0.000 claims abstract description 30
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 16
- 238000013210 evaluation model Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 18
- 238000010606 normalization Methods 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 13
- 238000004088 simulation Methods 0.000 claims description 11
- 238000011425 standardization method Methods 0.000 claims description 2
- 238000010521 absorption reaction Methods 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000001186 cumulative effect Effects 0.000 description 5
- 238000013507 mapping Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- HDRXZJPWHTXQRI-BHDTVMLSSA-N diltiazem hydrochloride Chemical compound [Cl-].C1=CC(OC)=CC=C1[C@H]1[C@@H](OC(C)=O)C(=O)N(CC[NH+](C)C)C2=CC=CC=C2S1 HDRXZJPWHTXQRI-BHDTVMLSSA-N 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010206 sensitivity analysis Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
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
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- 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
- H02J3/38—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
- 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
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- 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]
-
- 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
-
- 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
-
- 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
- H02J2300/40—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation wherein a plurality of decentralised, dispersed or local energy generation technologies are operated simultaneously
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Power Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Entrepreneurship & Innovation (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Geometry (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Molecular Biology (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
Abstract
The invention provides a new energy consumption capability assessment method and system, which comprises the following steps: acquiring values of the influence variables of the new energy consumption capacity of the power grid; inputting the value of the new energy absorption capacity influence variable into a pre-established new energy absorption prediction model to obtain a predicted value of the output of each partition in the power grid, and taking the predicted value as a new energy absorption capacity evaluation result; the new energy consumption prediction model comprises the following steps: constructing an input model based on historical values of new energy consumption capacity influence variables of each subarea of the power grid, and training a convolutional neural network by using the input model and a historical output sequence; the new energy consumption prediction model constructed by the invention is trained on the historical values of the new energy consumption capacity influence variables of all the subareas of the power grid, the dynamic association relation between the key influence factors of the multi-area new energy consumption capacity and the actual output of the new energy is established, and the new energy consumption capacity of the multi-area power grid in a period of time in the future can be evaluated.
Description
Technical Field
The invention belongs to the technical field of new energy power generation, and particularly relates to a new energy consumption capacity evaluation method and system.
Background
In recent years, new energy is continuously and rapidly developed, for example, in China, the cumulative installed capacity of photovoltaic power generation reaches 2.04 hundred million kilowatts and the cumulative installed capacity of wind power generation reaches 2.1 hundred million kilowatts after 2019, which are listed at the first position in the world. However, due to the limited peak shaving capability of the system and the influence of the transmission capability constraint of the power grid, the new energy is seriously abandoned, which not only causes the waste of green energy, but also becomes one of the important factors restricting the development of the new energy. Therefore, key factors influencing the new energy consumption capability need to be mined, the new energy acceptance capability and the power abandonment rate of the power grid in the next year/month are accurately evaluated, and a basis is provided for a decision of improving the new energy consumption capability of the power grid.
The conventional method for evaluating the consumption capacity of the new energy is a time sequence production simulation method, and the time sequence simulation method is high in calculation precision and clear in physical significance. However, the time sequence simulation method needs to perform simulation calculation for each time interval, and if the calculation is performed for a large number of multi-region new energy consumption scenes under different operation conditions, the time consumption is large, and the time cost of large-scale case calculation is too high. In fact, the evaluation of the new energy consumption capability can be regarded as a mapping relation between the grid operation key variable and the actual output of the new energy, and in order to learn the mapping relation, a large number of simulation samples need to be obtained through off-line time domain simulation, and then the mapping relation is approximately simulated by using a machine learning algorithm. After the mapping relation is established, aiming at different operation scenes, the learned mapping relation is utilized to quickly obtain the result of evaluating the new energy consumption capability.
In the prior art, a Principal Component Analysis (PCA) method is adopted to obtain wind power theoretical power, photovoltaic theoretical power, load, outgoing connecting line, rotary reserve capacity, installed capacity of various conventional units (thermal power and hydropower), maximum and minimum startup number and maximum and minimum technical outputnReducing the dimension of the dimension data, and selecting the dimension datakA main component of (A)k<n) The data information contained in each principal component is mainly reflected on the variance, and is judged by the cumulative variance contribution ratekThe value of (c). As shown in formula (1) and formula (2). Front sidekCharacteristic valueλ 1,λ 2,…,λ k Corresponding eigenvector Z =(s) ((s))z 1, z 2,…,z k ) As the principal component vector after dimensionality reduction.
In the formulaλ i Is an eigenvalue of the covariance of the data samples and has been sorted by size, i.e.λ 1≥λ 2≥…≥λ n ，η i In order to be the variance contribution rate,η Σ(k) Is frontkThe cumulative variance contribution of the individual principal components,ε=85%, i.e. selecting the value with the cumulative variance contribution rate exceeding 85% as the selected principal component value。
The data samples of the processed year are then divided into training data and test data, with the training rate set to 0.8, i.e. 7000 sets of data are used as training data, and the remaining 1760 sets of data are used as test data. The method comprises the steps of adopting a designed LSTM deep neural network, training data in a Tensorflow deep learning framework, wherein the designed LSTM deep neural network comprises an input layer, a hidden layer and an output layer. Wherein the hidden layer has a two-layer hidden layer structure, and the dimension of the input layer iskI.e. bykThe number of the main components is 10, the time step number of the input layer is 10, the first hidden layer comprises 30 neurons, the second hidden layer comprises 50 neurons, and the dimension of the output layer is 1. In training, some parameters are set as follows: the number of training times was set to 1000, the learning rate was 0.05, and the batch size (batch _ size) was 70.
And finally, performing prediction simulation on the test data by adopting the trained neural network to obtain the simulated actual power of the new energy.
The method has the defects that the calculation cannot be carried out aiming at the multi-region new energy consumption capacity, and only a single-region model without considering section electricity limitation can be calculated.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a new energy consumption capacity evaluation method, which comprises the following steps:
acquiring values of the influence variables of the new energy consumption capacity of the power grid;
inputting the value of the new energy consumption capability influence variable into a pre-established new energy consumption prediction model to obtain a predicted value of the output of each partition in the power grid, and taking the predicted value as a new energy consumption capability evaluation result;
the new energy consumption prediction model comprises: and constructing an input model based on the historical values of the new energy consumption capability influence variables of each subarea of the power grid, and training the convolutional neural network by using the input model and the historical output sequence.
Preferably, the establishing of the new energy consumption evaluation model includes:
processing the values of the new energy consumption capability influence variables of all the partitions of the power grid in the historical period to obtain an input model;
taking the actual sequence of the new energy output based on the input model and the historical time period as a training sample set;
training the convolutional neural network by taking an input model of the training sample set as input and an actual sequence corresponding to the new energy output at the next moment as output to obtain a new energy consumption evaluation model;
the new energy consumption capability influencing variables comprise: wind power theoretical power, photovoltaic theoretical power, power grid load, section quota between partitions and maximum and minimum technical total output of various conventional units.
Preferably, the processing the values of the new energy consumption capability influence variables of each partition of the power grid in the historical period to obtain the input model includes:
dividing values of new energy consumption capacity influence variables of all partitions of the power grid in historical time periods into a plurality of channels according to different partitions;
and dividing the values of the new energy consumption capability influence variables in each channel according to the time and the new energy consumption capability influence variable types to form an input model.
Preferably, after the obtaining of the new energy consumption evaluation model, the method further includes:
acquiring values of new energy consumption capacity influence variables of all the subareas of the power grid in another historical period and actual values of new energy output corresponding to the next moment as a test sample set;
inputting values of the new energy consumption capability influence variables of all the subareas of the power grid in the test sample set into the new energy consumption evaluation model to obtain a simulation value corresponding to the output of the new energy at the next moment;
and evaluating a new energy consumption evaluation model according to the error between the actual value and the simulated value of the new energy output, and optimizing the new energy consumption evaluation model by adopting a self-adaptive moment estimation method until the error meets the requirement.
Preferably, the error includes: power loss deviation, percent mean absolute error, and root mean square error.
Preferably, after obtaining the value of the new energy consumption capability influencing variable of the power grid and before inputting the value of the new energy consumption capability influencing variable into a new energy consumption evaluation model established in advance, the method further includes:
and carrying out normalization processing on the values of the new energy consumption capability influencing variables by adopting a minimum maximum value standardization method.
Based on the same invention concept, the invention also provides a new energy consumption capability evaluation system, which comprises: the system comprises a data acquisition module and an evaluation module;
the data acquisition module is used for acquiring the value of the influence variable of the new energy consumption capacity of the power grid;
the evaluation module is used for inputting the value of the new energy consumption capability influence variable into a pre-established new energy consumption prediction model to obtain a predicted value of the output of each partition in the power grid and taking the predicted value as a new energy consumption capability evaluation result;
the new energy consumption prediction model comprises: and constructing an input model based on the historical values of the new energy consumption capability influence variables of each subarea of the power grid, and training the convolutional neural network by using the input model and the historical output sequence.
Preferably, the system further comprises a modeling module for establishing a new energy consumption evaluation model, wherein the modeling module comprises: the device comprises an input unit, a sample set unit and a training unit;
the input unit is used for processing the values of the new energy consumption capacity influence variables of all the subareas of the power grid in the historical period to obtain an input model;
the sample set unit is used for taking the actual sequence of the new energy output based on the input model and the historical time period as a training sample set;
the training unit is used for training the convolutional neural network by taking the input model of the training sample set as input and taking the actual sequence corresponding to the new energy output at the next moment as output to obtain a new energy consumption evaluation model;
the new energy consumption capability influencing variables comprise: wind power theoretical power, photovoltaic theoretical power, power grid load, section quota between partitions and maximum and minimum technical total output of various conventional units.
Preferably, the input unit includes: a partition sub-unit and a variable partition sub-unit;
the partition sub-unit is used for dividing the values of the new energy consumption capacity influence variables of all the partitions of the power grid in the historical period into a plurality of channels according to different partitions;
and the variable dividing subunit is used for dividing the values of the new energy consumption capacity influence variables in each channel according to time and the new energy consumption capacity influence variable types to form an input model.
Preferably, the device further comprises a normalization module;
and the normalization module is used for performing normalization processing on the value of the new energy consumption capability influence variable by adopting a minimum maximum value normalization method.
Compared with the closest prior art, the invention has the following beneficial effects:
the invention provides a new energy consumption capability assessment method and system, which comprises the following steps: acquiring values of the influence variables of the new energy consumption capacity of the power grid; inputting the value of the new energy absorption capacity influence variable into a pre-established new energy absorption prediction model to obtain a predicted value of the output of each partition in the power grid, and taking the predicted value as a new energy absorption capacity evaluation result; the new energy consumption prediction model comprises the following steps: constructing an input model based on historical values of new energy consumption capacity influence variables of each subarea of the power grid, and training a convolutional neural network by using the input model and a historical output sequence; the new energy consumption prediction model constructed by the invention is trained on the historical values of the new energy consumption capacity influence variables of all the subareas of the power grid, the dynamic association relation between the key influence factors of the multi-area new energy consumption capacity and the actual output of the new energy is established, and the new energy consumption capacity of the multi-area power grid in a period of time in the future can be evaluated.
The method can be applied to sensitivity analysis of new energy consumption calculation, and can be used for quickly simulating to obtain the consumption calculation result when boundary conditions such as resources, loads, link outgoing and the like are changed under the condition that the structure of the power grid is not changed.
Drawings
Fig. 1 is a schematic flow chart of a new energy consumption capability assessment method provided by the present invention;
fig. 2 is a schematic view of a new energy consumption evaluation model establishing process in the new energy consumption capability evaluation method provided by the invention;
FIG. 3 is a schematic diagram of an input data structure of a new energy consumption assessment model according to the present invention;
FIG. 4 is a graph of loss values as a function of iteration number as provided by the present invention;
FIG. 5 is an example of an evaluation provided by the present invention;
fig. 6 is a schematic diagram of a basic structure of a new energy consumption capability evaluation system provided by the present invention;
fig. 7 is a detailed structural diagram of a new energy consumption capability evaluation system provided by the present invention.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
Example 1:
the schematic flow chart of the new energy consumption capability assessment method provided by the invention is shown in fig. 1, and the method comprises the following steps:
step 1: acquiring values of the influence variables of the new energy consumption capacity of the power grid;
step 2: inputting the value of the new energy absorption capacity influence variable into a pre-established new energy absorption prediction model to obtain a predicted value of the output of each partition in the power grid, and taking the predicted value as a new energy absorption capacity evaluation result;
the new energy consumption prediction model comprises the following steps: and constructing an input model based on the historical values of the new energy consumption capability influence variables of each subarea of the power grid, and training the convolutional neural network by using the input model and the historical output sequence.
The new energy consumption capability assessment method provided by the embodiment specifically comprises the following steps:
s1, partitioning the provincial power grid according to the main limited fault of the new energy to obtain different power grid areasm. Collecting different power grid partitions of a provincial power grid respectivelym8760 hours a year, with a time resolution of 1 hour, new energy absorption capacity influencing variables including: wind power theoretical power, photovoltaic theoretical power, power grid load, cross section quota between regions, and total output of maximum and minimum technologies of various conventional units (thermal power and hydropower)nDimensional data, constituting data input samplesX m (t)=( X m,1(t), X m,2(t),…,X m,n (t))（t =1, 2, 3, …, 8760), and the actual power of the new energy in each areaP m N,(t)。
And S2, carrying out normalization processing on the data by adopting minimum and maximum value normalization, wherein the normalization processing is shown as a formula (1).
Whereinx i Is the actual value of the data and,x imin is the minimum value of the data and,x imax is the maximum value of the data and,
is a normalized standard value.
S3, establishing an input data model, wherein the input of the model ismTime of area evaluationtThe new energy consumption capability influence variables with lead and lag for a period of time (generally 2 h) mainly comprise wind power theoretical power, photovoltaic theoretical power, power grid load, section quota between regions, maximum and minimum technical total output of various conventional units (thermal power and hydropower), and the output istAnd the power grid corresponding to the moment receives the actual power of the new energy. Here, an RGB three-channel representation of an analog two-dimensional color image is performed with the model input being dimensionedAnd transforming to establish a three-dimensional input model of channels, rows and columns. Data of each region is input into a corresponding channel, column vectors of the channels are new energy consumption capacity influence elements such as wind power and photovoltaic theoretical power, load, regional discontinuous quota, maximum and minimum technical total output of a conventional unit and the like, and row vectors are time windows with an estimation time advanced and delayed for a period of time (generally 2 h), and are specifically shown in fig. 3.
And S4, designing the structure of the convolutional neural network, optimizing the model parameters, gradually extracting the features and filtering the information through the alternation of a plurality of convolutional layers and pooling layers, and finally obtaining the result output through the feature combination of the full connection layers. Here, a 2-dimensional CNN network structure is adopted, three convolutional layers are adopted to extract features in input data, a pooling layer is adopted to perform maximum pooling on the convolved results, and the features extracted by the convolutional layers are simplified. The specific model parameters are as follows: the number of convolution kernels of the first layer of convolution layers is 30, the size of the convolution kernels is 3 x 2, the number of convolution kernels of the second layer and the third layer of convolution layers is 6, and the size of each convolution layer ism 1, the size of the pooling layer is 2, the activating function adopts a Relu function, and the dropout layer sets the proportion of network weight to be disconnected randomly to be 50%.
And S5, dividing the data samples of the processed year into training data and test data, wherein the training rate is set to be 0.8, namely 7000 groups of data are used as the training data, and the rest 1760 groups of data are used as the test data. The method adopts a designed CNN deep neural network, trains training data in a Keras deep learning framework, and sets part of training parameters as follows: the training times are set to 1000 times, the learning rate is 0.05, the batch size (batch _ size) is 70, and after the training is finished, the trained model structure and parameters are stored to obtain the new energy consumption evaluation model. It should be noted that when the input data is normalized (i.e., normalized), the output data is also denormalized.
S6, carrying out prediction simulation on the test data by adopting the trained new energy consumption evaluation model to obtain the simulated actual power of the new energy
Evaluating an evaluation result by adopting the power curtailment deviation, the average absolute error percentage and the root mean square error, wherein the evaluation error iteration change condition is shown in a graph 4 as shown in a formula (2) to a formula (4), wherein a real line part is a training error, a dotted line part is a verification error, and then optimizing by adopting an adam (Adaptive motion Estimation) optimization method according to the error; it can be seen that the root mean square error converges rapidly as the number of training iterations increases. The results of the evaluation examples are shown in FIG. 5. The whole process of establishing the new energy consumption evaluation model is shown in fig. 2.
Wherein,
，
，
and
（t=1，2，3，…，T) Are respectively the firsttTheoretical output, actual output, simulated output and installed capacity of new energy at any moment,Tthe length of the data representing the test set is,
the deviation of the power rejection rate is shown,
the percentage of the average absolute error is expressed,
the root mean square error is indicated.
The above steps S1-S6 are processes for establishing a new energy consumption evaluation model in advance.
And S7, evaluating the new energy consumption capacity by adopting a new energy consumption evaluation model. The method comprises the steps of obtaining values of new energy consumption capacity influence variables of all the subareas of the power grid, inputting the values into a new energy consumption evaluation model, and obtaining a predicted value of new energy output of the power grid at the next moment as the new energy consumption capacity.
Step S7 is the aforementioned step 1 and step 2.
Example 2:
based on the same invention concept, the invention also provides a new energy consumption capability evaluation system.
The basic structure of the system is shown in fig. 6, and comprises: the system comprises a data acquisition module and an evaluation module;
the data acquisition module is used for acquiring values of the influence variables of the new energy consumption capacity of the power grid;
the evaluation module is used for inputting the value of the new energy consumption capability influence variable into a pre-established new energy consumption prediction model to obtain a predicted value of the output of each partition in the power grid and taking the predicted value as a new energy consumption capability evaluation result;
the new energy consumption prediction model comprises the following steps: and constructing an input model based on the historical values of the new energy consumption capability influence variables of each subarea of the power grid, and training the convolutional neural network by using the input model and the historical output sequence.
A detailed structure of a new energy consumption capability evaluation system is shown in fig. 7.
Wherein, new energy consumption ability evaluation system still includes the modeling module that is used for establishing new energy consumption evaluation model, and the modeling module includes: the device comprises an input unit, a sample set unit and a training unit;
the input unit is used for processing the values of the new energy consumption capacity influence variables of all the subareas of the power grid in the historical period to obtain an input model;
the sample set unit is used for taking an actual sequence of the new energy output based on the input model and the historical time period as a training sample set;
the training unit is used for training the convolutional neural network by taking the input model in the training sample set as input and taking the actual sequence corresponding to the new energy output at the next moment as output to obtain a new energy consumption evaluation model;
the new energy consumption capability influencing variables comprise: wind power theoretical power, photovoltaic theoretical power, power grid load, section quota between partitions and maximum and minimum technical total output of various conventional units.
Wherein, the input unit includes: a partition sub-unit and a variable partition sub-unit;
the partition division subunit is used for dividing the values of the new energy consumption capability influence variables of all the partitions of the power grid in the historical period into a plurality of channels according to different partitions;
and the variable dividing subunit is used for dividing the values of the new energy consumption capacity influence variables in each channel according to the time and the new energy consumption capacity influence variable types to form an input model.
Wherein, the modeling module further comprises an optimization unit;
the optimization unit is used for acquiring the value of the new energy consumption capacity influence variable of each subarea of the power grid in another historical period and the actual value corresponding to the new energy output at the next moment as a test sample set; inputting values of the new energy consumption capability influence variables of all the subareas of the power grid in the test sample set into a new energy consumption evaluation model to obtain a simulation value corresponding to the output of the new energy at the next moment; and evaluating the new energy consumption evaluation model according to the error between the actual value and the simulated value of the new energy output, and optimizing the new energy consumption evaluation model by adopting a self-adaptive moment estimation method until the error meets the requirement.
Wherein the error comprises: power loss deviation, percent mean absolute error, and root mean square error.
Wherein, the system also comprises a normalization module;
and the normalization module is used for performing normalization processing on the value of the new energy consumption capability influence variable by adopting a minimum maximum value normalization method.
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.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting the protection scope thereof, and although the present invention is described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that after reading the present invention, they can make various changes, modifications or equivalents to the specific embodiments of the application, but these changes, modifications or equivalents are all within the protection scope of the claims of the application.
Claims (10)
1. A new energy consumption capability assessment method is characterized by comprising the following steps:
acquiring values of the influence variables of the new energy consumption capacity of the power grid;
inputting the value of the new energy consumption capability influence variable into a pre-established new energy consumption prediction model to obtain a predicted value of the output of each partition in the power grid, and taking the predicted value as a new energy consumption capability evaluation result;
the new energy consumption prediction model comprises: and constructing an input model based on the historical values of the new energy consumption capability influence variables of each subarea of the power grid, and training the convolutional neural network by using the input model and the historical output sequence.
2. The method of claim 1, wherein the establishing of the new energy consumption assessment model comprises:
processing the values of the new energy consumption capability influence variables of all the partitions of the power grid in the historical period to obtain an input model;
taking the actual sequence of the new energy output based on the input model and the historical time period as a training sample set;
training the convolutional neural network by taking an input model of the training sample set as input and an actual sequence corresponding to the new energy output at the next moment as output to obtain a new energy consumption evaluation model;
the new energy consumption capability influencing variables comprise: wind power theoretical power, photovoltaic theoretical power, power grid load, section quota between partitions and maximum and minimum technical total output of various conventional units.
3. The method according to claim 2, wherein the processing of the values of the new energy consumption capability influencing variables of the partitions of the power grid in the historical period to obtain the input model comprises:
dividing values of new energy consumption capacity influence variables of all partitions of the power grid in historical time periods into a plurality of channels according to different partitions;
and dividing the values of the new energy consumption capability influence variables in each channel according to the time and the new energy consumption capability influence variable types to form an input model.
4. The method of claim 2, wherein after obtaining the new energy consumption assessment model, further comprising:
acquiring values of new energy consumption capacity influence variables of all the subareas of the power grid in another historical period and actual values of new energy output corresponding to the next moment as a test sample set;
inputting values of the new energy consumption capability influence variables of all the subareas of the power grid in the test sample set into the new energy consumption evaluation model to obtain a simulation value corresponding to the output of the new energy at the next moment;
and evaluating a new energy consumption evaluation model according to the error between the actual value and the simulated value of the new energy output, and optimizing the new energy consumption evaluation model by adopting a self-adaptive moment estimation method until the error meets the requirement.
5. The method of claim 4, wherein the error comprises: power loss deviation, percent mean absolute error, and root mean square error.
6. The method of claim 1, wherein after obtaining the values of the grid new energy consumption capability influencing variables and before inputting the values of the new energy consumption capability influencing variables into a pre-established new energy consumption evaluation model, the method further comprises:
and carrying out normalization processing on the values of the new energy consumption capability influencing variables by adopting a minimum maximum value standardization method.
7. A new energy consumption capability evaluation system, comprising: the system comprises a data acquisition module and an evaluation module;
the data acquisition module is used for acquiring the value of the influence variable of the new energy consumption capacity of the power grid;
the evaluation module is used for inputting the value of the new energy consumption capability influence variable into a pre-established new energy consumption prediction model to obtain a predicted value of the output of each partition in the power grid and taking the predicted value as a new energy consumption capability evaluation result;
the new energy consumption prediction model comprises: and constructing an input model based on the historical values of the new energy consumption capability influence variables of each subarea of the power grid, and training the convolutional neural network by using the input model and the historical output sequence.
8. The system of claim 7, further comprising a modeling module for building a new energy consumption assessment model, the modeling module comprising: the device comprises an input unit, a sample set unit and a training unit;
the input unit is used for processing the values of the new energy consumption capacity influence variables of all the subareas of the power grid in the historical period to obtain an input model;
the sample set unit is used for taking the actual sequence of the new energy output based on the input model and the historical time period as a training sample set;
the training unit is used for training the convolutional neural network by taking the input model of the training sample set as input and taking the actual sequence corresponding to the new energy output at the next moment as output to obtain a new energy consumption evaluation model;
the new energy consumption capability influencing variables comprise: wind power theoretical power, photovoltaic theoretical power, power grid load, section quota between partitions and maximum and minimum technical total output of various conventional units.
9. The system of claim 8, wherein the input unit comprises: a partition sub-unit and a variable partition sub-unit;
the partition sub-unit is used for dividing the values of the new energy consumption capacity influence variables of all the partitions of the power grid in the historical period into a plurality of channels according to different partitions;
and the variable dividing subunit is used for dividing the values of the new energy consumption capacity influence variables in each channel according to time and the new energy consumption capacity influence variable types to form an input model.
10. The system of claim 7, further comprising a normalization module;
and the normalization module is used for performing normalization processing on the value of the new energy consumption capability influence variable by adopting a minimum maximum value normalization method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110092890.3A CN112421631A (en) | 2021-01-25 | 2021-01-25 | New energy consumption capacity assessment method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110092890.3A CN112421631A (en) | 2021-01-25 | 2021-01-25 | New energy consumption capacity assessment method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112421631A true CN112421631A (en) | 2021-02-26 |
Family
ID=74782524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110092890.3A Pending CN112421631A (en) | 2021-01-25 | 2021-01-25 | New energy consumption capacity assessment method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112421631A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113141008A (en) * | 2021-04-23 | 2021-07-20 | 国网陕西省电力公司电力科学研究院 | Data-driven power distribution network distributed new energy consumption capacity assessment method |
| CN113205279A (en) * | 2021-05-27 | 2021-08-03 | 浙江大学 | Error correction-based power grid new energy consumption capacity improvement amount estimation method and device |
| CN113408193A (en) * | 2021-06-02 | 2021-09-17 | 国网河北省电力有限公司营销服务中心 | New energy consumption capacity evaluation method and device, terminal device and storage medium |
| CN114078062A (en) * | 2021-10-08 | 2022-02-22 | 国电南瑞科技股份有限公司 | Key section identification method and system for new energy absorption blocking factor |
| CN115473283A (en) * | 2022-06-30 | 2022-12-13 | 广东电网有限责任公司佛山供电局 | Power distribution network new energy consumption capacity evaluation method based on load synchronization rate |
| CN117040030A (en) * | 2023-10-10 | 2023-11-10 | 国网浙江宁波市鄞州区供电有限公司 | New energy consumption capacity risk management and control method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480896A (en) * | 2017-08-21 | 2017-12-15 | 国电南瑞科技股份有限公司 | A kind of new energy receiving end power network digestion capability appraisal procedure for supporting multi partition |
| CN109921462A (en) * | 2019-03-07 | 2019-06-21 | 中国电力科学研究院有限公司 | A kind of new energy digestion capability appraisal procedure and system based on LSTM |
| WO2020016808A1 (en) * | 2018-07-17 | 2020-01-23 | Farrokhabadi Mostafa | System and method for fluctuating renewable energy-battery optimization to improve battery life-time |
| CN111030192A (en) * | 2019-12-16 | 2020-04-17 | 国电南瑞科技股份有限公司 | Four-fish section quota optimization method for promoting new energy consumption |
-
2021
- 2021-01-25 CN CN202110092890.3A patent/CN112421631A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480896A (en) * | 2017-08-21 | 2017-12-15 | 国电南瑞科技股份有限公司 | A kind of new energy receiving end power network digestion capability appraisal procedure for supporting multi partition |
| WO2020016808A1 (en) * | 2018-07-17 | 2020-01-23 | Farrokhabadi Mostafa | System and method for fluctuating renewable energy-battery optimization to improve battery life-time |
| CN109921462A (en) * | 2019-03-07 | 2019-06-21 | 中国电力科学研究院有限公司 | A kind of new energy digestion capability appraisal procedure and system based on LSTM |
| CN111030192A (en) * | 2019-12-16 | 2020-04-17 | 国电南瑞科技股份有限公司 | Four-fish section quota optimization method for promoting new energy consumption |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113141008A (en) * | 2021-04-23 | 2021-07-20 | 国网陕西省电力公司电力科学研究院 | Data-driven power distribution network distributed new energy consumption capacity assessment method |
| CN113141008B (en) * | 2021-04-23 | 2023-06-13 | 国网陕西省电力公司电力科学研究院 | Data-driven power distribution network distributed new energy consumption capability assessment method |
| CN113205279A (en) * | 2021-05-27 | 2021-08-03 | 浙江大学 | Error correction-based power grid new energy consumption capacity improvement amount estimation method and device |
| CN113408193A (en) * | 2021-06-02 | 2021-09-17 | 国网河北省电力有限公司营销服务中心 | New energy consumption capacity evaluation method and device, terminal device and storage medium |
| CN114078062A (en) * | 2021-10-08 | 2022-02-22 | 国电南瑞科技股份有限公司 | Key section identification method and system for new energy absorption blocking factor |
| CN115473283A (en) * | 2022-06-30 | 2022-12-13 | 广东电网有限责任公司佛山供电局 | Power distribution network new energy consumption capacity evaluation method based on load synchronization rate |
| CN117040030A (en) * | 2023-10-10 | 2023-11-10 | 国网浙江宁波市鄞州区供电有限公司 | New energy consumption capacity risk management and control method and system |
| CN117040030B (en) * | 2023-10-10 | 2024-04-02 | 国网浙江宁波市鄞州区供电有限公司 | New energy consumption capacity risk management and control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112421631A (en) | New energy consumption capacity assessment method and system | |
| CN112149316B (en) | Aero-engine residual life prediction method based on improved CNN model | |
| CN109255505B (en) | Short-term load prediction method of multi-model fusion neural network | |
| CN110942194A (en) | Wind power prediction error interval evaluation method based on TCN | |
| CN114861533B (en) | Wind power ultra-short-term prediction method based on time convolution network | |
| CN103793887B (en) | Short-term electric load on-line prediction method based on self-adaptive enhancement algorithm | |
| CN107993012B (en) | Time-adaptive online transient stability evaluation method for power system | |
| CN108596242B (en) | Power grid meteorological load prediction method based on wavelet neural network and support vector machine | |
| CN114119273B (en) | Non-invasive load decomposition method and system for park comprehensive energy system | |
| CN110309603A (en) | A kind of short-term wind speed forecasting method and system based on wind speed characteristics | |
| CN111190349A (en) | Method, system and medium for monitoring state and diagnosing fault of ship engine room equipment | |
| CN114006370B (en) | Power system transient stability analysis and evaluation method and system | |
| CN112836604A (en) | Rolling bearing fault diagnosis and classification method, system and equipment based on VMD-SSAE and storage medium thereof | |
| CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
| CN113705897B (en) | Product quality prediction method and system for industrial copper foil production | |
| CN113947182B (en) | Traffic flow prediction model construction method based on dual-stage stacked graph convolution network | |
| CN113837434A (en) | Solar photovoltaic power generation prediction method and device, electronic equipment and storage medium | |
| CN111985845B (en) | Node priority optimization method of heterogeneous Spark cluster | |
| CN111488974B (en) | Ocean wind energy downscaling method based on deep learning neural network | |
| CN108647772B (en) | Method for removing gross errors of slope monitoring data | |
| CN109921462B (en) | New energy consumption capability assessment method and system based on LSTM | |
| CN111723516A (en) | Multi-target seawater intrusion management model based on adaptive DNN (deep dynamic network) substitution model | |
| CN115146718A (en) | Depth representation-based wind turbine generator anomaly detection method | |
| CN114971090A (en) | Electric heating load prediction method, system, equipment and medium | |
| CN114240687A (en) | Energy hosting efficiency analysis method suitable for comprehensive energy system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210226 |