CN114997566A - Power grid blocking risk assessment method and system considering node connectivity loss - Google Patents
Power grid blocking risk assessment method and system considering node connectivity loss Download PDFInfo
- Publication number
- CN114997566A CN114997566A CN202210406215.8A CN202210406215A CN114997566A CN 114997566 A CN114997566 A CN 114997566A CN 202210406215 A CN202210406215 A CN 202210406215A CN 114997566 A CN114997566 A CN 114997566A
- Authority
- CN
- China
- Prior art keywords
- data
- power grid
- grid
- risk assessment
- blocking
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses a power grid blocking risk assessment method and system considering node connectivity loss, wherein a grid structure of a target power grid and given operation mode data are utilized, simulation data generated by an electric power system analysis calculation model and historical data of actual operation of the power grid are combined, the data are calibrated according to a data preprocessing technology and indexes considering node connectivity loss, and then a multi-source blocking risk assessment sample set is generated; then, using a feature extraction technology to perform data dimension reduction processing; and forming a power grid blocking risk assessment method by combining a machine learning algorithm. According to the method, an accurate power grid mathematical model is not needed, mining is performed only based on simulation data and historical operation data, accuracy of machine learning power grid blocking risk assessment is continuously improved, decision support is provided for power grid static operation risk prevention and scheduling control, and safety of actual operation of the power grid is remarkably improved.
Description
Technical Field
The invention belongs to the field of steady state analysis of power systems, and particularly relates to a power grid blocking risk assessment method and system considering node connectivity loss.
Background
The traditional power grid safety early warning field mainly aims at some off-line methods based on model driving. Such as: the early safety early warning concept is based on a power grid safety early warning technology of a diagnosis-consultation mode, the potential safety hazard of a power grid is searched in a multidimensional way in the diagnosis, the safety level of the power grid is determined, comprehensive early warning is made in the diagnosis, and high automation is realized. In the prior art, a power grid safety early warning and decision support system is designed from three levels of time dimension, space dimension and object dimension. According to the prior art, a major power failure defense system is designed according to three defense lines of a power system, the safety early warning of a power grid is the basis of the system, and the three defense lines are mainly used for protection control after a fault and cannot early warn in advance. In the prior art, a power grid safety early warning system is constructed by comprehensively considering static safety problems, transient safety problems, voltage safety problems, relay protection fixed value checking and other problems based on an energy management system data platform. The online dynamic safety assessment and early warning system of the power system is also technically constructed, and the system can realize various types of online safety and stability analysis such as static stability, transient stability, voltage stability, small interference stability and the like. Some students developed a safety analysis, early warning and control system for a large power grid, and can preliminarily preview, analyze, early warn and pre-control various power grid faults and accidents.
With the continuous development of the smart power grid, on one hand, the scale of the power grid is larger and larger, and the operation mode of the power grid tends to be complicated and close to a stable operation boundary due to the fact that high-proportion new energy and alternating current and direct current are in series-parallel connection; on the other hand, a large amount of measurement means and accumulation of multi-space-time scale data also bring new challenges to operation analysis and evaluation of the power grid, and the traditional power grid risk evaluation technology based on the model driving type has the following problems: the method is characterized in that a key line or a power transmission section is an important means for scheduling operators to perform 'dimensionality reduction monitoring' on a power grid, and in the traditional 'model driving type' power grid safety early warning, the power transmission section is established off line, cannot be updated on line, and is difficult to adapt to the current complex and changeable operation mode of the power grid. Secondly, the section limit transmission capacity is an important basis for a dispatcher to monitor the section, and the section flow needs to be controlled below the section limit transmission capacity. However, in the traditional model-driven type power grid safety early warning, the operation rule is relatively extensive, the selection of the safety characteristics of the power grid is lacked, the key factors influencing the power grid safety cannot be clearly expressed, and the early warning and pre-control of the power grid according to the key factors are more difficult to perform. Due to the limitation of computing power, the model-driven power grid safety early warning is difficult to realize real-time early warning and real-time or advanced early warning.
Therefore, research on problems such as data generation and preprocessing technology, blocking risk early warning and the like related to data-driven power grid blocking risk assessment in the smart power grid information physical environment is urgently needed.
Disclosure of Invention
The invention aims to provide a power grid blocking risk assessment method and system considering node connectivity loss, and aims to overcome the defect that the prior art cannot quantitatively assess the risk of real-time operation of a power grid in real time on line.
In order to achieve the purpose, the invention adopts the following technical scheme:
the power grid blocking risk assessment method considering node connectivity loss comprises the following steps:
forming data to be processed by utilizing the grid structure of the target power grid and the operation mode data of the target power grid and combining simulation data generated by an analysis and calculation model of the power system and historical data of actual operation of the power grid;
preprocessing data to be processed;
adding an index considering node connectivity loss to the preprocessed data as a data attribute, establishing a power grid blocking risk index by using the data considering the node connectivity loss index to calibrate the preprocessed data, and generating a blocking risk assessment sample set;
performing dimension reduction processing on the blocking risk assessment sample set by using a feature extraction technology;
and aiming at the blocking risk assessment sample set subjected to the dimensionality reduction, a power grid blocking risk assessment neural network model is built, the power grid blocking risk assessment neural network model is trained, and the power grid blocking risk is assessed by adopting the trained power grid blocking risk assessment neural network model.
Further, the grid structure of the target power grid refers to all grid structures under various normal, overhaul and new commissioning lines and main transformers and under the condition of operation scheduling considering topology control;
the operation mode data of the target power grid comprise a conventional generator set, a new energy source set, and various tide operation modes under the parameters of load and direct current transmission power.
Further, the simulation data generated by the power system analysis and calculation model refers to steady-state calculation simulation data generated by various analysis software capable of performing power system steady-state load flow calculation;
the historical data of the actual operation of the power grid refers to historical steady-state power flow data recorded by actual operation under various grid structures and various operation modes.
Further, the specific process of preprocessing the data to be processed is as follows: and sequentially carrying out data denoising, abnormal data cleaning, missing data completion and data normalization processing on the data to be processed.
Further, the index considering the node connectivity loss refers to the loss of the system node connectivity at two consecutive operation times:
represents the loss of connectivity of the node of the system at time t, C t 、C t-1 Respectively represents the node communication degrees of the system at the time t and the time t-1.
Further, the establishing of the grid blocking risk indicator to calibrate the preprocessed data specifically includes: defining a power grid blocking risk label under the preprocessed data as a line power overload index R, namely:
wherein:
k denotes the number of the network bus lines, rho k The influence of k power overload on the line; p is a radical of k For the transmission of power for the line k,
rating the maximum transmission power, mu, for line k k Representing the line k importance factor.
Furthermore, the blocking risk assessment sample set refers to a machine learning training sample set subjected to data calibration under different grid structures and different operation modes.
Further, the performing of the dimension reduction processing on the occlusion risk assessment sample set by using the feature extraction technology specifically comprises: and (3) performing data feature dimension reduction by using a feature extraction algorithm, wherein the feature extraction algorithm adopts a minimum redundancy maximum correlation method or a principal component analysis method.
Further, the grid blocking risk assessment neural network model adopts a composite model comprising a long-term and short-term memory neural network and a back propagation neural network.
The power grid blocking risk assessment system considering node connectivity loss comprises:
a to-be-processed data acquisition module: the system comprises a grid structure, a grid model analysis and calculation model, a grid history data acquisition module, a grid management module and a grid management module, wherein the grid structure is used for generating grid operation mode data;
a preprocessing module: the data preprocessing module is used for preprocessing data to be processed;
a blockage risk assessment sample set generation module: the method comprises the steps of adding an index considering node connectivity loss to preprocessed data as a data attribute, establishing a power grid blocking risk index to calibrate the preprocessed data by using the data considering node connectivity loss index, and generating a blocking risk evaluation sample set;
a dimension reduction module: the method is used for performing dimension reduction processing on the blocking risk assessment sample set by utilizing a feature extraction technology;
an evaluation module: and the method is used for building a power grid blocking risk assessment neural network model aiming at the blocking risk assessment sample set subjected to dimensionality reduction, training the power grid blocking risk assessment neural network model, and assessing the power grid blocking risk by adopting the trained power grid blocking risk assessment neural network model.
Compared with the prior art, the invention has the following beneficial technical effects:
according to the method, an accurate power grid mathematical model is not needed, only mining is carried out based on simulation data and historical operation data, offline learning and online learning can be carried out simultaneously, and the accuracy of the machine learning power grid blocking risk assessment method is continuously improved, so that the defect that the traditional N-1 static safety analysis cannot carry out online rapid and accurate early warning on system safety is overcome; and after the node connectivity loss index is additionally considered as a data attribute, the incidence relation between the power grid topological information and the operation risk can be more fully excavated, the power grid blocking risk early warning precision is improved, meanwhile, decision support is provided for operation scheduling aiming at the power grid risk, the actual operation safety of the power grid can be obviously improved, and the expected economic and social benefits are obvious.
Drawings
The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention, and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a schematic flow chart of a power grid blocking risk assessment method considering node connectivity loss.
FIG. 2 is a schematic diagram illustrating node connectivity calculation.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Referring to fig. 1, in the method for evaluating the risk of blocking the power grid in consideration of the loss of the node connectivity, a grid structure of a target power grid and given operation mode data are utilized, simulation data generated by a power system analysis and calculation model and historical data of actual operation of the power grid are combined, the data are calibrated according to a data preprocessing technology and an index in consideration of the loss of the node connectivity, and a sample set for evaluating the risk of blocking is generated; then, using a feature extraction technology to perform data dimension reduction processing; and forming a power grid blocking risk assessment method by combining a machine learning algorithm.
The grid structure of the target power grid refers to all grid structure information of various normal, overhaul and new operation lines and main transformers and under the condition of operation scheduling considering topological control; the operation mode data of the target power grid refers to various tidal current operation modes under different parameters of conventional generator sets, new energy source sets, loads and direct-current transmission power, such as large winter, small winter, large summer, small summer, early year modes and the like; simulation data generated by the electric power system analysis and calculation model refers to steady-state calculation simulation data which are performed according to various analysis software capable of performing electric power system steady-state load flow calculation, such as PSASP, PSD-BPA, PSS/E and the like; the historical data of the actual operation of the power grid refers to historical steady-state power flow data which are recorded by actual operation under various grid structures and various operation modes.
The data preprocessing technology refers to data processing operations such as data denoising, abnormal data cleaning, missing data completion, data normalization and the like; the index considering the node connectivity loss refers to the loss of the system node connectivity at two continuous operation moments:
represents the loss of connectivity of the node of the system at time t, C t 、C t-1 Respectively representing the node communication degrees of the system at t and t-1 moments; the data calibration means that a power grid blocking risk label under the data is defined as a line power overload index R, namely:
wherein:
k denotes the number of the network bus lines, rho k The influence of k power overload of the line; p is a radical of k Power is transmitted for line k.
The line k is rated for maximum transmission power. Mu.s k And the factor represents the importance degree of the line k, and the influence factors comprise the aspects of line topology, voltage level, supplied load level and the like.
The generated blocking risk assessment sample set is a machine learning training sample set subjected to data calibration under different grid structures and different operation modes; the data dimension reduction processing by the feature extraction technology is to reduce the dimension of the data features by using feature extraction algorithms such as minimum redundancy maximum correlation, principal component analysis and the like; the method for forming the power grid blocking risk assessment by combining the machine learning algorithm is machine learning modeling training and testing for power grid blocking risk assessment by utilizing machine learning algorithms such as a back propagation neural network, a long-term and short-term memory neural network and the like.
Example two
The invention also provides a power grid blocking risk assessment system considering node connectivity loss, which comprises:
a to-be-processed data acquisition module: the system comprises a grid structure, a grid model analysis and calculation model, a grid history data acquisition module, a grid management module and a grid management module, wherein the grid structure is used for generating grid operation mode data;
a pretreatment module: the data preprocessing module is used for preprocessing data to be processed;
an occlusion risk assessment sample set generation module: the method comprises the steps of adding an index considering node connectivity loss to preprocessed data as a data attribute, establishing a power grid blocking risk index by using the data considering the node connectivity loss index, calibrating the preprocessed data, and generating a blocking risk assessment sample set;
a dimension reduction module: the method is used for performing dimension reduction processing on the blocking risk assessment sample set by utilizing a feature extraction technology;
an evaluation module: and aiming at the blocking risk evaluation sample set after the dimensionality reduction, a power grid blocking risk evaluation neural network model is built, the power grid blocking risk evaluation neural network model is trained, and the trained power grid blocking risk evaluation neural network model is adopted to evaluate the power grid blocking risk.
EXAMPLE III
The source-load node connectivity is a quantification of the level of connectivity between generator nodes and load nodes in the power system. It can be divided into two types of power supply side and load side. The specific definition is as follows:
1) node connectivity-load side definition:
wherein C is load Represents the node connectivity-load side overall index,
source to load connectivity, Gen, representing load i j Representing the active output, Load, of generator j i Representing the active demand of load i, α ij Indicating the communication coefficient between the load i and the generator j. d ij The electrical distance between the buses connected with the load i and the generator j is represented by adding one to the number of the shortest transmission lines between the two buses.
2) Node connectivity-power side definition:
wherein C is gen Represents the system node connectivity-power supply side overall index, wherein
Representing source-to-charge connectivity, Gen, of generator j j Representing the active output, Load, of generator j i Representing the active demand of load i, α ij And represents the communication coefficient of the load i and the generator j. d ij Indicates the load i and the hairThe electrical distance between the buses connected to each motor j is represented by the number of the shortest transmission lines between two buses plus one.
3) System node connectivity definition:
C＝λ load C load +λ gen C gen
wherein C represents the system node connectivity, λ load ，λ gen The node connectivity load factor and the generator weight are respectively expressed and set to 1.0 and 1.0, respectively.
Taking the schematic diagram of fig. 2 as an example, the actual calculation of the system node connectivity is as follows:
node connectivity-load side calculation:
node connectivity-power side calculation:
calculating the connectivity of the system nodes:
C＝λ load C load +λ gen C gen ＝1.0*C load +1.0*C gen
after the transmission line L3 is broken, the electrical distance d between the buses of the system ij And when the system source load connectivity index changes, the change of the topological structure of the system can be reflected, and the blocking risk of the power system can be identified in an auxiliary manner.
Further, the examination of the method of the present invention was carried out according to the following steps:
the method comprises the following steps: a set of occlusion risk assessment samples is generated. And (3) collecting the history information of the IEEE-118 node standard test system, wherein the history information comprises information such as a network topology structure, active and reactive power of a generator, active and reactive requirements of a load, the voltage of each bus node, the load rate of each power transmission line, the load rate of the generator and the like. And (3) establishing an IEEE-118 node system simulation model by using power system simulation calculation software such as PSASP (Power System analysis software Package) and the like, and simulating and calculating the operation data of different grid structures and different operation modes. And combining the historical data and the simulation data to form data to be processed. And performing multi-source data preprocessing on the data to be processed, wherein the preprocessing comprises the steps of data denoising, abnormal data cleaning, missing data completion, data normalization processing and the like. And calculating the power overload indexes of the lines at all times, and storing the calculation results of the power overload indexes of all transmission lines. And calculating the difference value of the node connectivity of the current moment and the previous moment according to the time sequence, and storing the system node connectivity loss and the calculation results of the connectivity loss of each load and the generator node. And generating a blocking risk assessment sample set according to the calculation result. Note that the method of the present invention does not depend on an accurate power grid mathematical model, so that under the condition of insufficient historical data or less operation modes, simulation data can be generated by using any power system simulation platform to expand a data set. The initial time system node connectivity indexes are shown in tables 1 and 2.
TABLE 1 node connectivity-Power side
TABLE 2 node connectivity-load side
Step two: and performing feature extraction and data dimension reduction by using a minimum redundancy maximum correlation method. First, a sufficiently large integer n is given, based on the mutual information I (S) n Y), successively selecting features to generate n sets of sequence features
Mutual information I (S) n And Y) is defined as follows:
wherein: y denotes the grid blocking risk label, p (x) 1 ,x 2 ,…,x n ) Representing a joint probability density function. Then, respectively training the models according to the n feature sets for prediction to obtain a prediction error sequence E ═ E { (E) 1 ,e 2 ,…,e n Selecting adjacent k error components with smaller mean and varianceA set of errors Ω; and finally, searching the minimum value in omega, wherein the corresponding feature set is the optimal feature set.
Step three: and training a machine learning model. Since the node connectivity loss is time-dependent and the power system is continuously running, its risk profile is related to historical operating conditions. The method constructs a composite model comprising a long-short term memory neural network (LSTM) and a Back Propagation (BP) neural network. The LSTM inputs historical information to mine the operation rule of the power grid, and the BP neural network inputs information at the current moment to correct. And (4) arranging the data set according to the LSTM input parameters, and training a power grid blocking risk assessment neural network model.
According to the method, a similar neural network model is established according to the sample set without using the node connectivity for comparison experiments, and the results are shown in table 3.
TABLE 3 occlusion Risk assessment model comparison results
It can be seen that the prediction accuracy is improved from 92.35% to 98.56% by using the method of the invention. Although the characteristic dimension of the sample is increased and the training time of a single round is increased after the source-load connectivity is used, the iterative convergence is greatly improved, the total training time is shortened from 416 seconds to 176 seconds, and the performance is improved by 57.69%. This will be more significant for the promotion of large power systems.
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 has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, those skilled in the art will appreciate that various changes, modifications and equivalents can be made to the embodiments of the invention without departing from the scope of the invention as defined by the appended claims.
Claims (10)
1. The power grid blocking risk assessment method considering node connectivity loss is characterized by comprising the following steps of:
forming data to be processed by utilizing the grid structure of the target power grid and the operation mode data of the target power grid and combining simulation data generated by the power system analysis calculation model and historical data of actual operation of the power grid;
preprocessing data to be processed;
adding an index considering node connectivity loss to the preprocessed data as a data attribute, establishing a power grid blocking risk index by using the data considering the node connectivity loss index to calibrate the preprocessed data, and generating a blocking risk assessment sample set;
performing dimension reduction processing on the blocking risk assessment sample set by using a feature extraction technology;
and aiming at the blocking risk assessment sample set subjected to the dimensionality reduction, a power grid blocking risk assessment neural network model is built, the power grid blocking risk assessment neural network model is trained, and the power grid blocking risk is assessed by adopting the trained power grid blocking risk assessment neural network model.
2. The method according to claim 1, wherein the grid structure of the target grid refers to all grid structures under various normal, overhaul, new commissioning lines and main transformers, and operation scheduling situations considering topology control;
the operation mode data of the target power grid comprise a conventional generator set, a new energy source set, and various tide operation modes under the parameters of load and direct current transmission power.
3. The method for evaluating the risk of blocking the power grid in consideration of the node connectivity loss according to claim 2, wherein the simulation data generated by the power system analysis and calculation model is steady-state calculation simulation data generated by various analysis software capable of performing power system steady-state power flow calculation;
the historical data of the actual operation of the power grid refers to historical steady-state power flow data recorded by actual operation under various grid structures and various operation modes.
4. The method for evaluating the risk of the grid blocking considering the node connectivity loss according to claim 1, wherein the specific process of preprocessing the data to be processed is as follows: and sequentially carrying out data denoising, abnormal data cleaning, missing data completion and data normalization processing on the data to be processed.
5. The method for evaluating the risk of blocking the power grid by considering the loss of the node connectivity according to claim 1, wherein the index considering the loss of the node connectivity refers to the loss of the connectivity of the system nodes at two consecutive operating moments:
represents the node connectivity loss of the system at time t, C t 、C t-1 Respectively represents the node communication degrees of the system at the time t and the time t-1.
6. The method for evaluating the risk of blocking the power grid in consideration of the node connectivity loss according to claim 5, wherein the establishing of the risk index of blocking the power grid to calibrate the preprocessed data specifically comprises: defining a power grid blocking risk label under the preprocessed data as a line power overload index R, namely:
wherein:
k denotes the number of the bus lines of the network, p k The influence of k power overload of the line is taken; p is a radical of k For the transmission of power for the line k,
rating the maximum transmission power, mu, for line k k Representing the line k importance factor.
7. The method for evaluating the risk of blocking the power grid in consideration of the node connectivity loss according to claim 1, wherein the blocking risk evaluation sample set refers to a machine learning training sample set after data calibration under different grid structures and different operation modes.
8. The method for evaluating the risk of blocking the power grid in consideration of the node connectivity loss according to claim 1, wherein the performing the dimensionality reduction on the blocking risk evaluation sample set by using the feature extraction technology specifically comprises: and (3) performing data feature dimension reduction by using a feature extraction algorithm, wherein the feature extraction algorithm adopts a minimum redundancy maximum correlation method or a principal component analysis method.
9. The grid blockage risk assessment method considering node connectivity loss according to claim 1, wherein the grid blockage risk assessment neural network model adopts a composite model comprising a long-short term memory neural network and a back propagation neural network.
10. Power grid blocking risk assessment system considering node connectivity loss is characterized by comprising:
a to-be-processed data acquisition module: the system comprises a grid structure, a grid model analysis and calculation model, a grid operation mode data acquisition module and a grid operation mode data acquisition module, wherein the grid structure is used for utilizing a grid structure of a target grid and the operation mode data of the target grid, and simulation data generated by the power system analysis and calculation model and historical data of actual operation of the grid are combined to form data to be processed;
a preprocessing module: the data preprocessing module is used for preprocessing data to be processed;
an occlusion risk assessment sample set generation module: the method comprises the steps of adding an index considering node connectivity loss to preprocessed data as a data attribute, establishing a power grid blocking risk index by using the data considering the node connectivity loss index, calibrating the preprocessed data, and generating a blocking risk assessment sample set;
a dimension reduction module: the method is used for utilizing a feature extraction technology to perform dimension reduction processing on the blocking risk assessment sample set;
an evaluation module: and the method is used for building a power grid blocking risk assessment neural network model aiming at the blocking risk assessment sample set subjected to dimensionality reduction, training the power grid blocking risk assessment neural network model, and assessing the power grid blocking risk by adopting the trained power grid blocking risk assessment neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210406215.8A CN114997566A (en) | 2022-04-18 | 2022-04-18 | Power grid blocking risk assessment method and system considering node connectivity loss |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210406215.8A CN114997566A (en) | 2022-04-18 | 2022-04-18 | Power grid blocking risk assessment method and system considering node connectivity loss |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114997566A true CN114997566A (en) | 2022-09-02 |
Family
ID=83023907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210406215.8A Pending CN114997566A (en) | 2022-04-18 | 2022-04-18 | Power grid blocking risk assessment method and system considering node connectivity loss |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114997566A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115545477A (en) * | 2022-10-08 | 2022-12-30 | 广东电力交易中心有限责任公司 | Power transmission line blocking risk probability assessment method and product based on incremental interpolation |
| CN116167527A (en) * | 2023-04-21 | 2023-05-26 | 南方电网数字电网研究院有限公司 | Pure data-driven power system static safety operation risk online assessment method |
| CN116317110B (en) * | 2023-01-17 | 2023-11-14 | 中国电力科学研究院有限公司 | Power grid dispatching operation previewing method and system considering source load bilateral fluctuation |
-
2022
- 2022-04-18 CN CN202210406215.8A patent/CN114997566A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115545477A (en) * | 2022-10-08 | 2022-12-30 | 广东电力交易中心有限责任公司 | Power transmission line blocking risk probability assessment method and product based on incremental interpolation |
| CN116317110B (en) * | 2023-01-17 | 2023-11-14 | 中国电力科学研究院有限公司 | Power grid dispatching operation previewing method and system considering source load bilateral fluctuation |
| CN116167527A (en) * | 2023-04-21 | 2023-05-26 | 南方电网数字电网研究院有限公司 | Pure data-driven power system static safety operation risk online assessment method |
| CN116167527B (en) * | 2023-04-21 | 2023-09-12 | 南方电网数字电网研究院有限公司 | Pure data-driven power system static safety operation risk online assessment method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | A novel equivalent model of active distribution networks based on LSTM | |
| Bahmanyar et al. | Power system voltage stability monitoring using artificial neural networks with a reduced set of inputs | |
| CN114997566A (en) | Power grid blocking risk assessment method and system considering node connectivity loss | |
| CN110417011A (en) | A kind of online dynamic secure estimation method based on mutual information Yu iteration random forest | |
| CN110659443A (en) | Detecting state estimation network model data errors | |
| CN110363334B (en) | Grid line loss prediction method of photovoltaic grid connection based on gray neural network model | |
| Kamalasadan et al. | A new intelligent algorithm for online voltage stability assessment and monitoring | |
| CN111401749A (en) | Dynamic safety assessment method based on random forest and extreme learning regression | |
| CN109993665B (en) | Online safety and stability assessment method, device and system for power system | |
| Makasa et al. | On-line voltage stability load index estimation based on PMU measurements | |
| CN109657913B (en) | Transmission and distribution network joint risk assessment method considering distributed power supply | |
| LU500551B1 (en) | Virtual load dominant parameter identification method based on incremental learning | |
| CN112330488B (en) | Power grid frequency situation prediction method based on transfer learning | |
| CN114006413A (en) | Transient stability control method and system for power system based on graph neural network | |
| CN112821424A (en) | Power system frequency response analysis method based on data-model fusion drive | |
| CN112070413A (en) | Reliability research method of traction power supply system based on small sample condition | |
| CN111025041A (en) | Electric vehicle charging pile monitoring method and system, computer equipment and medium | |
| CN112332420B (en) | Device and method for determining hierarchical load reduction in power system risk assessment | |
| Morison et al. | Identification of voltage control areas and reactive power reserve; an advancement in on-line voltage security assessment | |
| CN116245033A (en) | Artificial intelligent driven power system analysis method and intelligent software platform | |
| CN115563786A (en) | Electrochemical energy storage power station fault scene reconstruction method | |
| Sawhney et al. | On-line transient stability assessment using artificial neural network | |
| Sun et al. | Reliability prediction of distribution network based on PCA-GA-BP neural network | |
| CN111797919A (en) | Dynamic security assessment method based on principal component analysis and convolutional neural network | |
| CN112800674A (en) | Power system element reliability parameter calculation method based on extreme learning machine |
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 |