CN116562685A - Electric power system toughness assessment method and system considering incremental power distribution network support - Google Patents
Electric power system toughness assessment method and system considering incremental power distribution network support Download PDFInfo
- Publication number
- CN116562685A CN116562685A CN202310440227.7A CN202310440227A CN116562685A CN 116562685 A CN116562685 A CN 116562685A CN 202310440227 A CN202310440227 A CN 202310440227A CN 116562685 A CN116562685 A CN 116562685A
- Authority
- CN
- China
- Prior art keywords
- load
- line
- toughness
- power
- fault
- 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 39
- 238000009826 distribution Methods 0.000 title claims abstract description 27
- 238000011084 recovery Methods 0.000 claims abstract description 55
- 238000004088 simulation Methods 0.000 claims abstract description 36
- 238000005070 sampling Methods 0.000 claims abstract description 35
- 238000003062 neural network model Methods 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims description 10
- 230000009194 climbing Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000010521 absorption reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0499—Feedforward 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
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method and a system for evaluating toughness of a power system considering incremental power distribution network support, which relate to the technical field of power systems and comprise the following steps: receiving an IEEE standard node data set, and performing Gaussian sampling near a standard node load of the IEEE standard node data set to generate a node load sample set; receiving power grid related data, inputting the power grid related data into a pre-established cascading failure simulation model added with time sampling to obtain cut load quantity, load recovery quantity and accident chain data, and calculating to obtain toughness indexes by using the cut load quantity, the load recovery quantity and the accident chain data; inputting the obtained node load sample set and the toughness index into a pre-established BP neural network model to obtain a power system toughness evaluation result.
Description
Technical Field
The invention relates to the technical field of power systems, in particular to a method and a system for evaluating toughness of a power system by considering incremental power distribution network support.
Background
The frequency and intensity of natural disasters have increased substantially over the past decades due to the direct impact of climate change, posing a great threat to the safety and stability of incremental power distribution networks. Meanwhile, under the background of new power reform, the power selling side reform is steadily promoted in China, and the power distribution business is gradually released to the market, so that the rapid development of the incremental power distribution network is promoted. But a large number of accesses to the incremental power distribution network can cause great influence on the grid structure and topology of the system, and meanwhile, the intermittence and fluctuation of new energy output in the incremental power distribution network can also influence the trend distribution of the system, so that the toughness of the system is influenced. Therefore, a method for evaluating the toughness of a power system supported by an incremental power distribution network needs to be considered.
The existing research on the toughness improvement method is to adjust the uniformity of power flow distribution by adjusting the operations of generator output, load shedding and the like in the prevention and emergency response stage, so as to improve the toughness of the power system. But in most models the relation between node load and system toughness in the initial state is ignored.
Disclosure of Invention
In order to solve the defects in the background art, the invention aims to provide a method and a system for evaluating toughness of a power system considering incremental power distribution network support.
The aim of the invention can be achieved by the following technical scheme: a toughness evaluation method of a power system considering incremental power distribution network support comprises the following steps:
receiving an IEEE standard node data set, and performing Gaussian sampling near a standard node load of the IEEE standard node data set to generate a node load sample set;
receiving power grid related data, inputting the power grid related data into a pre-established cascading failure simulation model added with time sampling to obtain cut load quantity, load recovery quantity and accident chain data, and calculating to obtain toughness indexes by using the cut load quantity, the load recovery quantity and the accident chain data;
inputting the obtained node load sample set and the toughness index into a pre-established BP neural network model to obtain a power system toughness evaluation result.
Preferably, the grid related data comprises a grid topology, power grid related parameters and constraints.
Preferably, the node load sample set generates a set of N (μ, σ) -compliant nodes by setting each IEEE standard node load to μ 2 ) As a node load sample set.
Preferably, according to the related parameters of the initialized power network, then sampling the line fault caused by bad weather, setting the fault line as the initial fault of the system, detecting whether an island is generated in the initial fault of the system, if not, sampling the fault line again, if one island is generated, calculating the power flow of the fault line, and if the number of the generated islands is greater than or equal to two, calculating the cut load.
Preferably, the process of calculating the power flow of the faulty line is as follows:
calculating power flow according to the new line state, judging whether each line power flow is overloaded, calculating fault probability according to the formula below for an overloaded line, and updating line state information;
wherein ,is the failure probability of line l, p l Is the current load rate of line l, +.>Is the rated load rate of line l, +.>Is the limit load rate of line l; when the current load rate is smaller than the rated load rate, the fault probability is 0; the current load rate is larger than the limit load rate, and the fault probability is 1; when the current load rate is between the rated load rate and the limit load rate, comparing the fault probability with random numbers rho-U (0, 1) which are randomly generated and meet uniform distribution, if the fault probability is larger than rho, considering that the line is overloaded, if a new line is overloaded, judging the island number, if the new line is still one, calculating the power flow of the faulty line again, if the new line is still one, calculating the cut load, and if the new line is not overloaded, sampling the line hidden faults.
Preferably, the process of line hidden fault sampling is as follows:
sampling whether the adjacent lines of the last fault line have hidden faults or not, if a new hidden fault occurs, calculating the power flow of the fault line again, and if no hidden fault occurs, entering an optimal load shedding model, wherein the optimal load shedding model aims at minimizing the total load shedding amount of the system under the constraint that the power balance and the line power flow are not overloaded.
Preferably, the load shedding calculation process is as follows:
judging the type of each island, cutting the load of the number and the type of the nodes in each island, calculating and recording the total load loss, then carrying out recovery sampling on the system, carrying out line recovery and load cutting recovery through a fault development process, ending the chained fault simulation, adding one to the simulation times, if the simulation times are smaller than the maximum simulation times, sampling again the line fault caused by bad weather, if the simulation times are larger than the maximum simulation times, completing the simulation, calculating and recording the accident chain of each simulation, the load loss and the load recovery, drawing a toughness curve according to the recorded data, and finally calculating the toughness index value.
Preferably, the constraint comprises:
the model adopts a direct current power flow model, constraint 1 is the power balance constraint that the total output is the same as the load, and i and j respectively represent an i-th generator and a j-th node in a power grid; constraint 2 is the upper and lower limit constraint of the output of the generator; constraint 3 is a cut load constraint; constraint 4 represents a line flow constraint, LS is a line state matrix, considering that the disconnected line corresponds to 0, i.e. the line flow is 0,the rated load factor multiple which represents the line allowable instantaneous overload is generally set to be 1.3-1.4;
referring to a post-fault recovery mode of a power grid in actual operation, establishing a line fault recovery time model, establishing power grid constraint considering the climbing rate of a motor, and realizing time sampling of load shedding recovery, wherein the climbing constraint of the motor is increased relative to the load shedding model, and the specific constraint is as follows:
constraint 1 is a power balance constraint that the total output is the same as the load; in constraint 2, t re For this reason, the time difference, v, between the restoration of one line to the next re Multiplying the speed of the ith generator climbing to the maximum output percentage and multiplying the speed by the maximum output to represent the allowable output change of the generators in the recovery of the two lines; PD in constraint 3 j,0 The load condition of the jth node before the fault is represented, and the recovery load quantity cannot exceed the original load of the node; constraint 4 does not consider the maximum load flow that can be operated in a short period compared with the load shedding model, because the recovered power grid starts to stably operate, and the model solving target at the moment is the maximum total recovery load quantity.
Preferably, the establishing process of the BP neural network model is as follows:
taking a node load sample set as input and a toughness index as output; according to default 3:1, dividing input and output data into a training set and a testing set in proportion; determining the node number of an input layer, a hidden layer and an output layer; each layer selects a ReLU activation function; and establishing a BP neural network model.
Preferably, a system for evaluating toughness of an electrical power system taking into account incremental power distribution network support, comprises:
the sample set construction module: for receiving an IEEE standard node dataset and performing gaussian sampling around a standard node load of the IEEE standard node dataset, generating a node load sample set;
the toughness index calculation module: the method comprises the steps of receiving power grid related data, inputting the power grid related data into a pre-established cascading failure simulation model added with time sampling to obtain cut load quantity, load recovery quantity and accident chain data, and calculating to obtain toughness indexes by using the cut load quantity, the load recovery quantity and the accident chain data;
and a result generation module: the method is used for inputting the obtained node load sample set and the toughness index into a pre-established BP neural network model to obtain a power system toughness evaluation result.
The invention has the beneficial effects that:
the invention adopts a machine learning method to directly learn the relation between the initial running state of the system and the toughness of the system. Through constructing an initial load sample set, obtaining corresponding toughness index values by adopting a cascading failure simulation model, and learning the relation in the corresponding toughness index values through a BP neural network, an electric power system toughness evaluation model related to an initial operating point of the system is constructed, and the function of directly learning the relation between the initial load and the toughness index is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to those skilled in the art that other drawings can be obtained according to these drawings without inventive effort;
FIG. 1 is a schematic flow chart of the method of the present invention;
FIG. 2 is a flow chart of a cascading failure simulation model of the power system of the present invention;
FIG. 3 is a graph of toughness obtained by cascading failure simulation;
fig. 4 is a training set and test set error plot.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, a method for evaluating toughness of a power system considering incremental power distribution network support, the method comprising the steps of:
receiving an IEEE standard node data set, and performing Gaussian sampling near a standard node load of the IEEE standard node data set to generate a node load sample set;
receiving power grid related data, inputting the power grid related data into a pre-established cascading failure simulation model added with time sampling to obtain cut load quantity, load recovery quantity and accident chain data, and calculating to obtain toughness indexes by using the cut load quantity, the load recovery quantity and the accident chain data;
inputting the obtained node load sample set and the toughness index into a pre-established BP neural network model to obtain a power system toughness evaluation result.
The following describes the technical scheme of the invention in detail:
step one: to improve the training effect of the neural network, a sample set with a certain number and randomness needs to be constructed. The method comprises the following steps:
let the load of each IEEE standard node be μ, generate a set of N (μ, σ) compliant 2 ) As a sample set of node loads.
The aim of the cascading failure simulation model is to obtain the toughness index value corresponding to each initial load. And through cascading failure simulation of adding time samples for multiple times, the obtained result has statistical significance. As shown in fig. 2, the specific steps are as follows:
(21) Initializing network related parameters of the power system.
(22) Line faults caused by bad weather are sampled and set as system initial faults.
(23) Detecting whether an island is generated in the system, and if not, continuing to sample a fault line; if there is one island, then go to step (24); if the island number is greater than or equal to two, step (26) is entered.
(24) And calculating the power flow according to the new line state, and judging whether the power flow of each line is overloaded. And (3) for the overload line, calculating the fault probability of the overload line according to the fault probability model of the formula (1), and updating the line state information.
wherein ,is the failure probability of line l, p l Is the current load rate of line l, +.>Is the rated load rate of line l, +.>Is the ultimate load rate of line l. When the current load rate is smaller than the rated load rate, the fault probability is 0; the current load rate is larger than the limit load rate, and the fault probability is 1; and when the current load rate is between the rated load rate and the limit load rate, comparing the fault probability with random numbers rho-U (0, 1) which are randomly generated and meet uniform distribution, if the fault probability is larger than rho, considering that the line is overloaded, if a new line is overloaded, judging the number of islands, if the new line is still one, repeating the step (24), and if the new line is not less than two, entering the step (26). If no new line is overloaded, step (25) is entered.
(25) And (3) sampling line hidden faults, sampling whether the adjacent lines of the last fault line have hidden faults, if so, entering a step (24), and if not, entering an optimal load shedding model. The model aims at minimizing the total cut load of the system under the constraint of power balance and no overload of line power flow. After the optimum cut load, step (27) is entered.
(26) And judging the island type of each island, carrying out load shedding on the number and the type of the nodes in each island, and calculating and recording the total load loss amount to enter the step (27).
(27) The system resumes sampling. And (5) carrying out line recovery and load shedding recovery through a fault development process. The model aims at maximizing the load recovery amount of the system under the constraint of power balance and no overload of line power flow. And (3) finishing the cascading failure simulation, and adding one to the simulation times to enter the step (28).
(28) If the simulation times are smaller than the maximum simulation times, the step (22) is carried out, otherwise, the simulation is completed, and related data such as accident chains, load loss, load recovery and the like of each simulation are calculated and recorded. A toughness curve was made from the recorded data as shown in fig. 3. And calculating the toughness index value.
In the cascading failure development flow, according to the power grid line and the load data, load shedding constraint aiming at each line breaking condition is established, and load shedding time domain sampling in cascading failure accidents is realized. The constraints include:
the model adopts a direct current power flow model, constraint 1 is the power balance constraint that the total output is the same as the load, and i and j respectively represent an i-th generator and a j-th node in a power grid; constraint 2 is the upper and lower limit constraint of the output of the generator; constraint 3 is a cut load constraint; constraint 4 represents a line flow constraint, LS is a line state matrix, considering that the disconnected line corresponds to 0, i.e. the line flow is 0,the rated load factor multiple representing the line allowable transient overload is generally set to 1.3-1.4. The solution goal of the model is to minimize the total cut load.
And referring to a post-fault recovery mode of the power grid in actual operation, establishing a line fault recovery time model, and establishing power grid constraint considering the climbing rate of the motor to realize time sampling of load shedding recovery. The key of the step is to obtain the related power grid constraint in the cascade fault load recovery process, each line after fault development is overhauled at different time, a plurality of groups of load recovery models are correspondingly arranged, and the motor climbing constraint is increased relative to a load shedding model at the moment, wherein the specific constraint is as follows:
constraint 1 is a power balance constraint that the total output is the same as the load; in constraint 2, t re For this reason, the time difference, v, between the restoration of one line to the next re Multiplying the speed of the ith generator climbing to the maximum output percentage and multiplying the speed by the maximum output to represent the allowable output change of the generators in the recovery of the two lines; PD in constraint 3 j,0 The load condition of the jth node before the fault is represented, and the recovery load quantity cannot exceed the original load of the node; constraint 4 does not consider the maximum power flow that can be operated for a short period of time compared to the cut load model, because the recovered grid begins to operate stably. The model solution target at this time is the maximum total recovery load.
The system toughness index can be classified into an absorbency index and a restorability index. When the system fault enters the propagation phase, the emergency period enters the response phase due to the reduced performance of the power grid. From the initial performance Q (t 1 ) Drop to minimum performance Q (t) 2 ) Maintaining the performance through failure to t 3 The ability to adapt to the negative impact of a failure event by passive adjustment during this period is called absorption capacity. Mainly manifested by the ability to alleviate and arrest performance degradation. The absorption capacity can be characterized by two absorption indicators: firstly, the accumulated performance loss of the power grid system is as follows:
R 13 smaller indicates less power grid performance loss and better toughness; and the second is the relative relation between response time and recovery time, namely:
τ r the value range of (1) is (0, 1)]，τ r =1 represents no performance degradation of the grid, build τ r The method can accurately measure the speed of the effect of the repair measures, and further measure the quality of the adaptability of the system.
The main characteristic of toughness in the recovery stage is recovery capability, which is the capability of the power grid to recover performance by external intervention, and the recovery capability can be characterized by two recovery indexes: first is the performance recovery rate, namely:
higher recovery rate indicates better toughness of the system; secondly, the ratio of the performance of the system after the system is recovered to the performance of the system before the fault occurs is as follows:
in general, the performance after system recovery is not equal to the initial performance of the system before failure, so τ s0 <1。τ s0 The larger the value of (c) is, the better the toughness of the system is.
The value of one or several toughness indicators may generally be optimized during actual power system operation. Therefore, it is considered to integrate the system absorbency and recovery index into the comprehensive toughness evaluation index F:
where C is a constant in order to more clearly present the difference in toughness index at different initial loads. The toughness of the system can be improved by improving the value of the comprehensive toughness index F.
Table 1 below shows the actual and predicted values of the toughness index of the test set
| True value of toughness index | Predicted value of toughness index |
| 146.04495 | 135.6232066 |
| 140.45555 | 154.6831402 |
| 144.15475 | 158.8280096 |
| 138.0176 | 134.845675 |
| 156.43202 | 158.7917356 |
| 127.58846 | 151.0788735 |
| 147.1577 | 151.6577361 |
| 135.5454 | 136.5608242 |
| 143.04819 | 136.111498 |
| 133.93411 | 142.3203048 |
| 131.7631 | 138.40168 |
| 135.60202 | 126.0571275 |
| 152.81941 | 146.3775788 |
| 135.38057 | 135.7906457 |
TABLE 1
Under the condition of knowing input and output, the step 3 adopts BP network to learn the relation between input and output data, specifically:
in the embodiment, IEEE-30 nodes are adopted for simulation verification, an initial load sample set is taken as input, and a comprehensive toughness evaluation index value is taken as output; 56 groups of samples were obtained by simulation and were according to default 3:1, dividing input and output data into a training set and a testing set in proportion; determining that the number of nodes of an input layer is 30, the number of nodes of an output layer is 1, and selecting the number of nodes of an hidden layer to be 11; each layer selects a ReLU activation function; and training trainable parameters of the neural network by using a gradient descent method to establish a BP neural network model by taking the mean square error of the minimum predicted value and the true value as a target. The errors of the model training set and the test set along with the iteration times are shown in fig. 4, and the error result shows that the BP neural network can learn the nonlinear relation between the initial load and the toughness index of the system better.
A power system toughness assessment system that accounts for incremental power distribution network support, comprising:
the sample set construction module: for receiving an IEEE standard node dataset and performing gaussian sampling around a standard node load of the IEEE standard node dataset, generating a node load sample set;
the toughness index calculation module: the method comprises the steps of receiving power grid related data, inputting the power grid related data into a pre-established cascading failure simulation model added with time sampling to obtain cut load quantity, load recovery quantity and accident chain data, and calculating to obtain toughness indexes by using the cut load quantity, the load recovery quantity and the accident chain data;
and a result generation module: the method is used for inputting the obtained node load sample set and the toughness index into a pre-established BP neural network model to obtain a power system toughness evaluation result.
Based on the same inventive concept, the present invention also provides a computer apparatus comprising: one or more processors, and memory for storing one or more computer programs; the program includes program instructions and the processor is configured to execute the program instructions stored in the memory. The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application SpecificIntegrated Circuit, ASIC), field-Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., which are the computational core and control core of the terminal for implementing one or more instructions, in particular for loading and executing one or more instructions within a computer storage medium to implement the methods described above.
It should be further noted that, based on the same inventive concept, the present invention also provides a computer storage medium having a computer program stored thereon, which when executed by a processor performs the above method. The storage media may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing has shown and described the basic principles, principal features, and advantages of the present disclosure. It will be understood by those skilled in the art that the present disclosure is not limited to the embodiments described above, which have been described in the foregoing and description merely illustrates the principles of the disclosure, and that various changes and modifications may be made therein without departing from the spirit and scope of the disclosure, which is defined in the appended claims.
Claims (10)
1. The method for evaluating the toughness of the power system considering the incremental power distribution network support is characterized by comprising the following steps of:
receiving an IEEE standard node data set, and performing Gaussian sampling near a standard node load of the IEEE standard node data set to generate a node load sample set;
receiving power grid related data, inputting the power grid related data into a pre-established cascading failure simulation model added with time sampling to obtain cut load quantity, load recovery quantity and accident chain data, and calculating to obtain toughness indexes by using the cut load quantity, the load recovery quantity and the accident chain data;
inputting the obtained node load sample set and the toughness index into a pre-established BP neural network model to obtain a power system toughness evaluation result.
2. A method of evaluating toughness of a power system in view of incremental power distribution network support according to claim 1, wherein the grid-related data comprises grid topology, power network-related parameters, and constraints.
3. A method of evaluating toughness of a power system in view of incremental power distribution network support according to claim 1, wherein said node load sample set generates a set of N (μ, σ) compliant nodes by setting each IEEE standard node load to μ 2 ) As a node load sample set.
4. The method for evaluating toughness of a power system considering incremental power distribution network support according to claim 2, wherein according to the initialized power network related parameters, then sampling a line fault caused by bad weather, setting the fault line as a system initial fault, detecting whether an island is generated in the system initial fault, if not, sampling the fault line again, if an island is generated, calculating the power flow of the fault line, and if the number of the generated islands is greater than or equal to two, calculating the cut load.
5. The method for evaluating toughness of a power system in consideration of incremental power distribution network support of claim 4, wherein the process of calculating the power flow of the faulty wire is as follows:
calculating power flow according to the new line state, judging whether each line power flow is overloaded, calculating fault probability according to the formula below for an overloaded line, and updating line state information;
wherein ,is the failure probability of line l, p l Is the current load rate of line l, +.>Is the rated load factor of the line i,is the limit load rate of line l; when the current load rate is smaller than the rated load rate, the fault probability is 0; the current load rate is larger than the limit load rate, and the fault probability is 1; when the current load rate is between the rated load rate and the limit load rate, comparing the fault probability with random numbers rho-U (0, 1) which are randomly generated and meet uniform distribution, if the fault probability is larger than rho, considering that the line is overloaded, if a new line is overloaded, judging the island number, if the new line is still one, calculating the power flow of the faulty line again, if the new line is still one, calculating the cut load, and if the new line is not overloaded, sampling the line hidden faults.
6. The method for evaluating toughness of a power system in consideration of incremental power distribution network support of claim 5, wherein the line implicit fault sampling is performed as follows:
sampling whether the adjacent lines of the last fault line have hidden faults or not, if a new hidden fault occurs, calculating the power flow of the fault line again, and if no hidden fault occurs, entering an optimal load shedding model, wherein the optimal load shedding model aims at minimizing the total load shedding amount of the system under the constraint that the power balance and the line power flow are not overloaded.
7. The method for evaluating toughness of a power system in consideration of incremental power distribution network support of claim 6, wherein the process of calculating cut loads is as follows:
judging the type of each island, cutting the load of the number and the type of the nodes in each island, calculating and recording the total load loss, then carrying out recovery sampling on the system, carrying out line recovery and load cutting recovery through a fault development process, ending the chained fault simulation, adding one to the simulation times, if the simulation times are smaller than the maximum simulation times, sampling again the line fault caused by bad weather, if the simulation times are larger than the maximum simulation times, completing the simulation, calculating and recording the accident chain of each simulation, the load loss and the load recovery, drawing a toughness curve according to the recorded data, and finally calculating the toughness index value.
8. A method of evaluating toughness of an electrical power system in view of incremental power distribution network support according to claim 2, wherein said constraints comprise:
the model adopts a direct current power flow model, constraint 1 is the power balance constraint that the total output is the same as the load, and i and j respectively represent an i-th generator and a j-th node in a power grid; constraint 2 is the upper and lower limit constraint of the output of the generator; constraint 3 is a cut load constraint; constraint 4 represents a line flow constraint, LS is a line state matrix, considering that the disconnected line corresponds to 0, i.e. the line flow is 0,the rated load factor multiple which represents the line allowable instantaneous overload is generally set to be 1.3-1.4;
referring to a post-fault recovery mode of a power grid in actual operation, establishing a line fault recovery time model, establishing power grid constraint considering the climbing rate of a motor, and realizing time sampling of load shedding recovery, wherein the climbing constraint of the motor is increased relative to the load shedding model, and the specific constraint is as follows:
constraint 1 is a power balance constraint that the total output is the same as the load; in constraint 2, t re For this reason, the time difference, v, between the restoration of one line to the next re Multiplying the speed of the ith generator climbing to the maximum output percentage and multiplying the speed by the maximum output to represent the allowable output change of the generators in the recovery of the two lines; PD in constraint 3 j,0 The load condition of the jth node before the fault is represented, and the recovery load quantity cannot exceed the original load of the node; constraint 4 does not consider the maximum load flow that can be operated in a short period compared with the load shedding model, because the recovered power grid starts to stably operate, and the model solving target at the moment is the maximum total recovery load quantity.
9. The method for evaluating toughness of a power system considering incremental power distribution network support according to claim 1, wherein the establishing process of the BP neural network model is as follows:
taking a node load sample set as input and a toughness index as output; according to default 3:1, dividing input and output data into a training set and a testing set in proportion; determining the node number of an input layer, a hidden layer and an output layer; each layer selects a ReLU activation function; and establishing a BP neural network model.
10. An electrical power system toughness assessment system that accounts for incremental power distribution network support, comprising:
the sample set construction module: for receiving an IEEE standard node dataset and performing gaussian sampling around a standard node load of the IEEE standard node dataset, generating a node load sample set;
the toughness index calculation module: the method comprises the steps of receiving power grid related data, inputting the power grid related data into a pre-established cascading failure simulation model added with time sampling to obtain cut load quantity, load recovery quantity and accident chain data, and calculating to obtain toughness indexes by using the cut load quantity, the load recovery quantity and the accident chain data;
and a result generation module: the method is used for inputting the obtained node load sample set and the toughness index into a pre-established BP neural network model to obtain a power system toughness evaluation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310440227.7A CN116562685A (en) | 2023-04-23 | 2023-04-23 | Electric power system toughness assessment method and system considering incremental power distribution network support |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310440227.7A CN116562685A (en) | 2023-04-23 | 2023-04-23 | Electric power system toughness assessment method and system considering incremental power distribution network support |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116562685A true CN116562685A (en) | 2023-08-08 |
Family
ID=87487112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310440227.7A Pending CN116562685A (en) | 2023-04-23 | 2023-04-23 | Electric power system toughness assessment method and system considering incremental power distribution network support |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116562685A (en) |
-
2023
- 2023-04-23 CN CN202310440227.7A patent/CN116562685A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018157691A1 (en) | Active distribution network safety quantifying method | |
| CN108537413B (en) | Power grid toughness evaluation method considering typhoon space-time characteristics based on Markov chain | |
| CN107292502A (en) | A kind of distribution network reliability evaluation method | |
| CN109559019B (en) | Power system dynamic security assessment method based on risk index | |
| Wen et al. | Data‐driven transient frequency stability assessment: A deep learning method with combined estimation‐correction framework | |
| CN107305651B (en) | Power transmission system reliability assessment method and system | |
| CN110634082A (en) | Low-frequency load shedding system operation stage prediction method based on deep learning | |
| CN110783964A (en) | Risk assessment method and device for static security of power grid | |
| CN116599050A (en) | Photovoltaic prediction method and related device based on self-attention mechanism | |
| CN113791351B (en) | Lithium battery life prediction method based on transfer learning and difference probability distribution | |
| CN113052473B (en) | Power grid risk analysis method based on fault rate and static safety analysis | |
| CN112287605B (en) | Power flow checking method based on graph convolution network acceleration | |
| CN107563641B (en) | Disaster-resistant multi-scene differentiation planning method for power distribution network considering disaster preference | |
| CN115964951A (en) | Power system operation reliability assessment method and device and electronic equipment | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| CN116307838A (en) | Accurate equivalence method, system and medium for power distribution network in power grid reliability evaluation | |
| CN116562685A (en) | Electric power system toughness assessment method and system considering incremental power distribution network support | |
| CN116565842A (en) | Power distribution network toughness assessment method, system and equipment based on multi-source collaborative strategy | |
| CN116683431A (en) | Rapid power distribution system restoring force assessment index and assessment method and system | |
| CN113627655B (en) | Method and device for simulating and predicting pre-disaster fault scene of power distribution network | |
| CN108616126B (en) | Distribution network reliability calculation method considering power transmission network power supply capacity probability equivalent model | |
| CN113205259A (en) | Power grid scheduling decision evaluation method and device and terminal equipment | |
| CN110797906A (en) | Method and device for determining maximum installed capacity of wind power base and storage medium | |
| CN112434929B (en) | Method for assessing risk resistance of distribution transformer | |
| US11983472B2 (en) | Method for identifying fragile lines in power grids based on electrical betweenness |
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 |