CN115510961A - Community comprehensive energy system operation safety assessment method based on active learning - Google Patents
Community comprehensive energy system operation safety assessment method based on active learning Download PDFInfo
- Publication number
- CN115510961A CN115510961A CN202211134797.5A CN202211134797A CN115510961A CN 115510961 A CN115510961 A CN 115510961A CN 202211134797 A CN202211134797 A CN 202211134797A CN 115510961 A CN115510961 A CN 115510961A
- Authority
- CN
- China
- Prior art keywords
- energy system
- operation safety
- model
- community
- active learning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 54
- 238000011156 evaluation Methods 0.000 claims abstract description 26
- 238000013145 classification model Methods 0.000 claims abstract description 24
- 238000004088 simulation Methods 0.000 claims abstract description 10
- 238000013210 evaluation model Methods 0.000 claims abstract description 6
- 238000012706 support-vector machine Methods 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a community comprehensive energy system operation safety assessment method based on active learning, which comprises the steps of constructing a data set by utilizing historical data; using an active learning strategy to sequentially extract quantitative samples to be added into a training set, gradually increasing the number of the training set, and updating the model at any time in the period; after finite iteration, obtaining a trained SVM classification model, and realizing operation safety evaluation judgment on real-time data of the community comprehensive energy system. The invention has the beneficial effects that: when a training data set is constructed, only sample points near a decision boundary of the SVM are selected for marking, so that the marking work of a large number of useless sample points is avoided, the training task of running a safety evaluation model of the community comprehensive energy system with the least sample amount is realized, the workload of a time domain simulation module is reduced, the integral running speed of off-line module training and updating is greatly improved, and the system has instantaneity, effectiveness and safety.
Description
Technical Field
The invention relates to the field of security assessment of power systems, in particular to an active learning-based operation security assessment method for a community comprehensive energy system.
Background
The comprehensive energy system is a novel regional power system which takes a power system as a core, integrates various energy supply systems such as regional power supply, gas supply, cold supply, heat supply and the like, and organically coordinates and optimizes the distribution, conversion, storage and consumption links of various energy sources such as coal, natural gas, solar energy, electricity, heat and the like. The comprehensive energy system relates to various energy forms such as electricity, heat, gas and the like, and the dynamic time scales have obvious difference; the space-time coupling and complementary substitution exist among different energy supply systems, the system complexity is particularly outstanding, and in such a situation, the traditional power system operation safety evaluation method has the following problems: 1) The operation safety assessment method based on the time domain simulation technology has large calculation amount and serious time consumption, and can not realize real-time and intelligent operation safety assessment of the community comprehensive energy system; 2) The photovoltaic is one of main energy supply systems of a community comprehensive energy system, the power generation of the photovoltaic is random and fluctuating and is influenced by the uncertainty of the environment, and the traditional mechanism model construction method is difficult to effectively measure the uncertainty information. 3) A supervision learning scheme is adopted in a data-driven power system operation safety assessment scheme, a model uses a labeled sample as a training set, a time domain simulation module is required to perform stable states of a long-time simulation labeling system in different characteristic states, and a large amount of time is consumed for data set preparation in a model training stage.
Considering that a large amount of data are needed by a data-driven algorithm for model training and updating, the workload of data set marking is too large, and the model updating speed cannot be guaranteed, the method for evaluating the operation safety of the community comprehensive energy system based on active learning is provided, so that the labeled samples required by model training are greatly reduced, and the method has important significance for realizing the rapid and accurate operation safety evaluation of the community comprehensive energy system.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a community comprehensive energy system operation safety assessment method based on active learning.
In a first aspect, a community integrated energy system operation safety assessment method based on active learning is provided, and includes:
step 1, constructing a data set by utilizing process data generated during the operation of a community integrated energy system and corresponding community integrated energy system operation safety state information;
step 2, sequentially extracting quantitative samples by using an active learning strategy, adding the samples into a training set, gradually increasing the number of the training sets, and updating the model at any time in the period;
and 3, after the finite iteration, obtaining a trained Support Vector Machine (SVM) classification model, and realizing the operation safety evaluation judgment of real-time data of the community comprehensive energy system.
Preferably, step 1 comprises:
step 1.1, acquiring historical process data of relevant equipment of a community comprehensive energy system, including active power, reactive power, node voltage and fault information of each node of the system, and forming an original sample data set:
D i ＝{X i ，y i } i∈1，2，...N
wherein D is i Indicating a sample point representing the ith time instant, X i The characteristic information representing the real-time operation of the community comprehensive energy system at the ith moment comprises system nodes and linesPower, voltage information of y i Based on artificial marking information added in actual simulation, the method indicates whether the current state can maintain the dynamic stability of the system through automatic adjustment when a specific fault occurs in the system at the ith moment;
step 1.2, data preprocessing is carried out on the data set, mean variance normalization processing is carried out on the feature vectors, influences caused by different dimensions of different physical quantities are removed, and the processed data set is processed according to a: b division into pool training sets D p And test set D t 。
Preferably, step 2 comprises:
step 2.1, from pool training set D p Extracting n sample points as a training set D tr Carrying out classification training on the support vector machine based on cross validation to obtain an SVM initial classification model M 0 The two classification decision functions are:
y＝sign(ω T ·X+b)
wherein, ω is T X + b is the SVM initial classification model M 0 ω and b are model parameters, and T is a transposed symbol; sign is a sign function;
step 2.2, using an active learning strategy based on the current SVM initial classification model M 0 Constructing a query function g (M) 0 X), training set D of the pool p Sorting the rest samples based on the return value of the query function, selecting the first M sample points to be added into the training set, and retraining the SVM initial classification model M 0 Obtaining an SVM updating model M j And calculating the SVM updating model M j For test set D t The evaluation accuracy Acc of the sample points.
Preferably, step 3 comprises: and repeating the step 2.2 until the evaluation accuracy Acc of the model is not increased any more, obtaining a community comprehensive energy system operation safety evaluation model M obtained based on minimum sample point training, performing power system operation safety evaluation based on real-time power and voltage information of the power system by using the model M, and predicting system operation safety stability change after a specific fault occurs.
Preferably, in step 2.2, the active learning strategy comprises the following steps:
step 2.2.1, based on the current SVM initial classification model M 0 The Euclidean distance between the sample point and the decision boundary is calculated, the closer the distance is, the higher the possibility that the sample point becomes a support vector point is, and the sample point closest to the decision boundary is selected
Placing at the head of the sorting:
step 2.2.2, mapping decision function return values of the support vector machine to [0,1] using sigmoid function]The interval is used as a probability predicted value output by the classifier, the probability predicted value is used for calculating the probability entropy to evaluate the prediction uncertainty of the sample point under the current model, and the sample point with higher probability entropy is used
Placing at the head of the sorting:
P(y i |X，θ)＝sigmoid(ω T ·X+b)
wherein, P (y) i | X, θ) is the probability prediction value of the sample point X at the output of the classifier, and θ = (ω, b) is a general term of the model parameters.
In a second aspect, an active learning-based operation safety assessment apparatus for a community integrated energy system is provided, which is configured to execute any one of the operation safety assessment methods for the community integrated energy system in the first aspect, and includes:
the system comprises a construction module, a data acquisition module and a data processing module, wherein the construction module is used for constructing a data set by utilizing process data generated during the operation of the community integrated energy system and the corresponding operation safety state information of the community integrated energy system;
the adding module is used for sequentially extracting quantitative samples to be added into a training set by using an active learning strategy, gradually increasing the number of the training sets and updating the model at any time in the period;
and the evaluation module is used for obtaining the trained SVM classification model after finite iteration and realizing the operation safety evaluation judgment of real-time data of the community comprehensive energy system.
In a third aspect, a computer storage medium having a computer program stored therein is provided; when the computer program runs on a computer, the computer is enabled to execute the method for evaluating the operation safety of the community integrated energy system in the first aspect.
In a fourth aspect, a computer program product is provided, which when running on a computer, causes the computer to execute the method for evaluating the operation safety of the community integrated energy system according to any one of the first aspect.
The invention has the beneficial effects that: according to the method, only the sample points near the decision boundary of the SVM are selected for marking when a training data set is constructed, so that the marking work of a large number of useless sample points is avoided, the training task of the community comprehensive energy system operation safety evaluation model is completed with the minimum sample amount, the workload of a time domain simulation module is reduced, the overall operation speed of offline module training and updating is greatly improved, and the system has real-time performance, effectiveness and safety.
Drawings
FIG. 1 is a general framework diagram of a community integrated energy system operation safety assessment method based on active learning;
fig. 2 is a schematic structural diagram of a community integrated energy system operation safety evaluation device based on active learning.
Detailed Description
The present invention will be further described with reference to the following examples. The following examples are set forth merely to aid in the understanding of the invention. It should be noted that, for a person skilled in the art, several modifications can be made to the invention without departing from the principle of the invention, and these modifications and modifications also fall within the protection scope of the claims of the present invention.
Example 1
An active learning-based operation safety assessment method for a community integrated energy system is shown in fig. 1 and comprises the following steps:
step 1, constructing a data set by utilizing process data generated during the operation of a community integrated energy system and the corresponding operation safety state information of the community integrated energy system;
step 2, sequentially extracting quantitative samples by using an active learning strategy, adding the samples into a training set, gradually increasing the number of the training sets, and updating the model at any time in the period;
and 3, obtaining a trained SVM classification model after finite iteration, and realizing operation safety evaluation judgment on real-time data of the community comprehensive energy system.
The step 1 comprises the following steps:
step 1.1, acquiring historical process data of relevant equipment of a community comprehensive energy system, including active power, reactive power, node voltage and fault information of each node of the system, and forming an original sample data set:
D i ＝{X i ，y i } i∈1，2，...N
wherein D is i Indicating a sample point representing the ith time instant, X i The characteristic information representing the real-time operation of the community comprehensive energy system at the ith moment comprises power and voltage information of system nodes and lines, and y i Based on artificial marking information added in actual simulation, the method indicates whether the current state can maintain the dynamic stability of the system through automatic adjustment when a specific fault occurs in the system at the ith moment;
step 1.2, data preprocessing is carried out on the data set, mean variance normalization processing is carried out on the feature vectors, influences caused by different dimensions of different physical quantities are removed, and the processed data set is processed according to a: b division into pool training sets D p And test set D t 。
The step 2 comprises the following steps:
step 2.1, from pool training set D p Extracting n sample points as a training set D tr Carrying out classification training on the support vector machine based on cross validation to obtain an SVM initial classification model M 0 The two classification decision functions are:
y＝sign(ω T ·X+b)
wherein, ω is T X + b is the SVM initial classification model M 0 ω and b are model parameters, and T is a transposed symbol; sign is a sign function;
step 2.2, using an active learning strategy based on the current SVM initial classification model M 0 Constructing a query function g (M) 0 X), pair pool training set D p Sorting the rest samples based on the return value of the query function, selecting the first M sample points to be added into the training set, and retraining the SVM initial classification model M 0 Obtaining the SVM updating model M j And calculating the SVM updating model M j For test set D t The accuracy Acc of the evaluation of the sample points.
The step 3 comprises the following steps: and (3) repeating the step 2.2 until the evaluation accuracy Acc of the model is not increased any more, obtaining a community comprehensive energy system operation safety evaluation model M obtained based on minimum sample point training, carrying out power system operation safety evaluation based on real-time power and voltage information of the power system by using the model M, and predicting system operation safety stability change after a specific fault occurs.
In step 2.2, the active learning strategy comprises the following steps:
step 2.2.1, based on the current SVM initial classification model M 0 The Euclidean distance between the sample points and the decision boundary is calculated, the closer the distance is, the higher the possibility that the sample points become support vector points is, and the sample point closest to the decision boundary is selected
Placing at the head of the sorting:
step 2.2.2, mapping the decision function return value of the support vector machine by using sigmoid functionTo [0,1]]And the interval is used as a probability predicted value output by the classifier, the probability predicted value is used for calculating probability entropy to evaluate the prediction uncertainty of the sample point under the current model, and the sample point with higher probability entropy value is used
Placing at the head of the sorting:
P(y i |X，θ)＝sigmoid(ω T ·X+b)
wherein, P (y) i | X, θ) is the probability prediction value of the sample point X at the output of the classifier, and θ = (ω, b) is a general term of the model parameters.
Example 2
On the basis of the embodiment 1, an experiment based on IEEE 68 node standard calculation example is taken as an example below to illustrate how to realize the operation safety evaluation of the community integrated energy system.
As shown in fig. 1, the present application provides a community integrated energy system operation safety assessment method based on active learning, which includes the following steps:
(1) Obtaining historical process data of the system, wherein the historical process data comprises active power, reactive power, node voltage and dynamic stability marking information of all nodes and connecting lines among the nodes of the system, and forming an original sample data set:
D i ＝{X i ，y i } i∈1，2，...N
wherein D i Sample point, X, representing the ith time instant i The characteristic information which represents the real-time operation of the power system at the ith moment comprises the power and voltage information of system nodes and lines, and 438 characteristics in total, y i The method is based on artificial marking information added in actual simulation, and indicates whether the current state can maintain the dynamic stability of the system through automatic adjustment of a power grid when the system has a specific fault at the ith moment.
(2) Preprocessing the data and performing characteristic vectorAnd (3) performing mean variance normalization treatment, removing influences caused by different dimensions of different physical quantities, and performing treatment on the data set according to a: b division into pool training sets D p And test set D t 。
(3) Slave pool training set D p Extracting n sample points as a training set D tr The SVM is classified and trained based on cross validation, the safety evaluation effect of models based on different kernel functions on a test set is tested, and the result is shown in a table 1:
TABLE 1
According to the table 1, a Gaussian radial basis (Rbf) is selected as a kernel function, and an SVM initial classification model M is finally obtained 0 A two-classification decision function:
y＝sign(ω T ·X+b)
wherein ω is T X + b =0 is the decision boundary of the SVM model, sign () is a sign function, and the return value y ∈ { -1,1}, respectively represents two states of stable and unstable.
(4) Selecting M sample points from the rest samples in the pool training set, adding the M sample points into the training set, retraining the classification model SVM, and obtaining an updated SVM updating model M j Calculating model M j In order to verify the effectiveness of the invention, three selection strategies are tested, namely, the evaluation accuracy Acc of the sample points of the test set and the Recall type Recall of the instability state:
random sampling: an active learning strategy is not adopted, and m unmarked sample points are randomly selected each time to be marked for model updating;
and (3) performing decision boundary distance sampling based on an active learning strategy: based on the current classification model M 0 Constructing a query function, knowing a decision boundary of the current SVM, calculating Euclidean distances from sample points to the decision boundary, wherein the closer the distance is, the higher the possibility that the sample points become support vector points is, selecting the sample point closest to the decision boundary to be placed at the first ranking position, ranking the residual samples of the pool training set in sequence based on the return value of the query function, selecting the first m sample points to be addedTraining set
Probability entropy sampling based on active learning strategy: mapping a decision function return value of a support vector machine to a [0,1] interval by using a sigmoid function to serve as a probability predicted value output by a classifier, calculating the prediction uncertainty of a probability entropy evaluation sample point under a current model by using the probability predicted value, placing the sample point with a higher probability entropy value at the first ranking position, ranking the residual samples of the pool training set in sequence based on the query function return value, selecting the first m sample points and adding the sample points into the training set
P(y i |X，θ)＝sigmoid(ω T ·X+b)。
(5) And (5) repeating the step (4) until the evaluation accuracy Acc of the model is not increased any more, and obtaining a power grid operation safety evaluation model M trained on the minimum sample points.
(6) By using the model M, the operation safety evaluation of the power system can be realized based on the real-time power and voltage information of the power system, and the operation safety and stability change of the system after a specific fault occurs can be predicted.
Aiming at the three embodiments of the selection strategy, the finally obtained sample amount of the training set required by the community comprehensive energy system running safety assessment model and the performance effect of the sample amount in the test set are shown in table 2:
TABLE 2
According to the table 2, the operation safety assessment model of the community comprehensive energy system based on the SVM can be obtained through analysis, under the condition that the model expression effect is consistent, the amount of training set samples required by model training can be greatly reduced by using the construction method based on active learning, in application, the marking workload of a large number of low-quality sample points is avoided, the workload of a time domain simulation module is reduced, the time cost is reduced, and the operation safety assessment work of the community comprehensive energy system is more rapid, effective and safe.
Claims (8)
1. A community comprehensive energy system operation safety assessment method based on active learning is characterized by comprising the following steps:
step 1, constructing a data set by utilizing process data generated during the operation of a community integrated energy system and the corresponding operation safety state information of the community integrated energy system;
step 2, sequentially extracting quantitative samples by using an active learning strategy, adding the samples into a training set, gradually increasing the number of the training set, and updating the model at any time in the period;
and 3, obtaining a trained SVM classification model after finite iteration, and realizing operation safety evaluation judgment on real-time data of the community comprehensive energy system.
2. The active learning-based community integrated energy system operation safety assessment method according to claim 1, wherein step 1 comprises:
step 1.1, acquiring historical process data of relevant equipment of the community comprehensive energy system, including active power, reactive power, node voltage and fault information of each node of the system, and forming an original sample data set:
D i ＝{X i ，y i }i∈1，2，…N
wherein D is i Indicating a sample point representing the ith time instant, X i The characteristic information representing the real-time operation of the community comprehensive energy system at the ith moment comprises power and voltage information of system nodes and lines, and y i Artificial marking information added based on actual simulation indicates whether the system can maintain the dynamic stability of the system through automatic adjustment or not when a specific fault occurs at the ith moment;
step 1.2, data preprocessing is carried out on the data set, and the data set is to be preprocessedThe feature vectors are subjected to mean variance normalization processing to remove influences caused by different dimensions among different physical quantities, and the processed data set is divided into pool training sets D according to a: b p And test set D t 。
3. The active learning-based community integrated energy system operation safety assessment method according to claim 2, wherein the step 2 comprises:
step 2.1, from pool training set D p Extracting n sample points as a training set D tr Carrying out classification training on the support vector machine based on cross validation to obtain an SVM initial classification model M 0 The two classification decision functions are:
y＝sign(ω T ·X+b)
wherein, ω is T X + b is the SVM initial classification model M 0 ω and b are model parameters, and T is a transposed symbol; sign is a sign function;
step 2.2, using an active learning strategy based on the current SVM initial classification model M 0 Constructing a query function g (M) 0 X), training set D of the pool p Sorting the rest samples based on the return value of the query function, selecting the first M sample points to be added into a training set, and retraining the SVM initial classification model M 0 Obtaining an SVM updating model M j And calculating the SVM updating model M j For test set D t The evaluation accuracy Acc of the sample points.
4. The active learning-based community integrated energy system operation safety assessment method according to claim 3, wherein step 3 comprises: and repeating the step 2.2 until the evaluation accuracy Acc of the model is not increased any more, obtaining a community comprehensive energy system operation safety evaluation model M obtained based on minimum sample point training, performing power system operation safety evaluation based on real-time power and voltage information of the power system by using the model M, and predicting system operation safety stability change after a specific fault occurs.
5. The active learning-based community integrated energy system operation safety assessment method according to claim 3, wherein in the step 2.2, the active learning strategy comprises the following steps:
step 2.2.1, based on the current SVM initial classification model M 0 The Euclidean distance between the sample point and the decision boundary is calculated, the closer the distance is, the higher the possibility that the sample point becomes a support vector point is, and the sample point closest to the decision boundary is selected
Placing at the head of the sorting:
step 2.2.2, mapping decision function return values of the support vector machine to [0,1] using sigmoid function]And the interval is used as a probability predicted value output by the classifier, the probability predicted value is used for calculating probability entropy to evaluate the prediction uncertainty of the sample point under the current model, and the sample point with higher probability entropy value is used
Placing at the head of the sorting:
P(y i |X，θ)＝sigmoid(ω T ·X+b)
wherein, P (y) i | X, θ) is the probability prediction value of the sample point X at the output of the classifier, and θ = (ω, b) is the general term of the model parameters.
6. An active learning-based operation safety assessment device for a community integrated energy system, which is used for executing the operation safety assessment method for the community integrated energy system according to any one of claims 1 to 5, and comprises the following steps:
the system comprises a construction module, a data acquisition module and a data processing module, wherein the construction module is used for constructing a data set by utilizing process data generated during the operation of the community integrated energy system and the corresponding operation safety state information of the community integrated energy system;
the adding module is used for sequentially extracting quantitative samples to be added into a training set by using an active learning strategy, gradually increasing the number of the training sets and updating the model at any time in the period;
and the evaluation module is used for obtaining the trained SVM classification model after finite iteration and realizing the operation safety evaluation judgment of the real-time data of the community comprehensive energy system.
7. A computer storage medium, wherein a computer program is stored in the computer storage medium; the computer program, when running on a computer, causes the computer to execute the method for evaluating the operation safety of the community integrated energy system according to any one of claims 1 to 5.
8. A computer program product for causing a computer to perform the method for evaluating the operation safety of the community integrated energy system according to any one of claims 1 to 5 when the computer program product is run on the computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211134797.5A CN115510961A (en) | 2022-09-19 | 2022-09-19 | Community comprehensive energy system operation safety assessment method based on active learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211134797.5A CN115510961A (en) | 2022-09-19 | 2022-09-19 | Community comprehensive energy system operation safety assessment method based on active learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115510961A true CN115510961A (en) | 2022-12-23 |
Family
ID=84503596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211134797.5A Pending CN115510961A (en) | 2022-09-19 | 2022-09-19 | Community comprehensive energy system operation safety assessment method based on active learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115510961A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937616A (en) * | 2023-02-21 | 2023-04-07 | 深圳新视智科技术有限公司 | Training method and system of image classification model and mobile terminal |
-
2022
- 2022-09-19 CN CN202211134797.5A patent/CN115510961A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937616A (en) * | 2023-02-21 | 2023-04-07 | 深圳新视智科技术有限公司 | Training method and system of image classification model and mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102074955B (en) | Method based on knowledge discovery technology for stability assessment and control of electric system | |
| CN110503153B (en) | Photovoltaic system fault diagnosis method based on differential evolution algorithm and support vector machine | |
| CN109412161B (en) | Power system probability load flow calculation method and system | |
| CN111900731A (en) | PMU-based power system state estimation performance evaluation method | |
| CN110705831A (en) | Power angle instability mode pre-judgment model construction method after power system fault and application thereof | |
| CN114330571B (en) | Power system dominant instability mode identification method and system based on transfer learning | |
| CN115510961A (en) | Community comprehensive energy system operation safety assessment method based on active learning | |
| CN116131313A (en) | Explanatory analysis method for association relation between characteristic quantity and transient power angle stability | |
| CN110389268B (en) | Online monitoring system of electric power system | |
| Liang et al. | Status evaluation method for arrays in large-scale photovoltaic power stations based on extreme learning machine and k-means | |
| CN111814394B (en) | Power system safety assessment method based on correlation and redundancy detection | |
| CN116933860A (en) | Transient stability evaluation model updating method and device, electronic equipment and storage medium | |
| CN116127447A (en) | Virtual power plant false data injection attack detection method, device, terminal and medium | |
| CN116204771A (en) | Power system transient stability key feature selection method, device and product | |
| Jing et al. | A data expansion based piecewise regression strategy for incrementally monitoring the wind turbine with power curve | |
| Jianli et al. | Wind power forecasting by using artificial neural networks and Grubbs criterion | |
| Devi et al. | Hybrid Solar Power Generation Prediction Using Support Vector Machines and K-nearest neighbors Optimized by Deep Learning Techniques | |
| CN115374957B (en) | Radial flow type small hydropower station multiscale missing measurement data reconstruction method | |
| CN111798049B (en) | Voltage stability evaluation method based on integrated learning and multi-target planning | |
| CN117688367B (en) | Wind power generation ultra-short term power prediction method and device based on instant learning | |
| Lv et al. | Integrated algorithm evaluation of a scalable digital power management innovation model | |
| Huang et al. | An Ensemble Learning Approach for Wind Power Forecasting | |
| Jia et al. | ML-Based Power System Stability Assessment Considering Network Topology Changes: WECC 20,000+ Bus System Case Study | |
| Tong et al. | Construction of Intelligent Evaluation Model of Power Informatization Monitoring Platform | |
| Jami’in et al. | Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm |
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 |