Generation method and device of power grid operation scene, terminal equipment and storage medium

Abstract

The invention discloses a power grid operation scene generation method and device, terminal equipment and a storage medium, and the method comprises the steps: obtaining a plurality of source load data samples and a power grid topological structure, and constructing a plurality of first source load distribution scenes containing the output of a new energy unit and the power utilization of a load; then randomly generating a second source load distribution scene, a third source load distribution scene and a fourth source load distribution scene, calculating target output power of thermal power generation nodes in each source load distribution scene, and further verifying whether each source load distribution scene can operate normally or not in combination with a power grid topological structure; and finally, according to the source load distribution scene capable of normally operating and the corresponding target output power, generating a plurality of power grid operation scenes capable of normally operating under the power grid topological structure. Therefore, the problem that the diversity and flexibility of the current power grid scene generation method are insufficient is solved, and the defect that the scene generated by the current power grid scene generation method cannot be suitable for the actual power system is overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method, device, terminal equipment and storage medium for generating a power grid operation scenario. Background Art

[0002] With the continuous expansion of renewable energy in the power system, the operation of the power grid has become more complex. The uncertainty of renewable energy generation, especially the volatility and intermittency of output, is significantly different from the relatively stable characteristics of traditional power resources. This difference increases the difficulty of balanced grid dispatching. At the same time, the dynamic changes in power demand and the flexible adjustment of the grid structure also put higher demands on the safety and operation efficiency of the system. In order to effectively meet these challenges, it is key to generate diversified grid scenarios that can reflect different operating states. These scenarios can not only help predict the performance of the power grid under different conditions, but also provide a rich data basis for large-scale model training, thereby improving the scientificity and accuracy of dispatch strategy optimization.

[0003] Existing power grid scenario generation technologies can be mainly divided into two categories: statistical methods and machine learning. Scenario generation based on statistical methods relies on in-depth analysis of historical data, and generates representative power grid operation status through Monte Carlo simulation, scenario clustering and other technologies. These methods capture typical patterns through statistical analysis of historical data such as renewable energy generation and load fluctuations, and help simulate typical scenarios under different power grid operation conditions. Scenario generation methods based on machine learning have been widely used in recent years. This type of method generates more diverse and adaptive power grid scenarios by training large-scale data sets and using deep learning technologies such as generative adversarial networks and variational autoencoders.

[0004] Although the existing power grid scenario generation methods have made some progress in simulating power grid operation, they still have obvious limitations. First, the scenario generation methods based on statistical methods lack diversity and flexibility and cannot fully reflect the complexity of the power grid. Second, although the generation method based on deep learning can capture the complex nonlinear relationships in power grid operation and generate richer data scenarios, due to the lack of constraints in this method, the generated scenarios are not applicable to the actual power system situation and have poor practicality. Summary of the invention

[0005] The embodiments of the present invention provide a method, apparatus, terminal device and storage medium for generating power grid operation scenarios. By generating diversified source-load distribution scenarios, a data basis is provided for the subsequent generation of diversified power grid operation scenarios, thereby overcoming the problem of insufficient diversity and flexibility of current power grid scenario generation methods. Secondly, by verifying the feasibility of each source-load distribution scenario before finally generating the scenario, the defect that the scenarios generated by the current power grid scenario generation method are not applicable to the actual power system is overcome.

[0006] An embodiment of the present invention provides a method for generating a power grid operation scenario, comprising:

[0007] Acquire a power grid topology structure and a plurality of source-load data samples of a power grid; wherein the source-load data samples include: power generation data samples of a plurality of new energy power generation units, and a plurality of load demand data samples; the power grid topology structure includes: a plurality of new energy power generation nodes, a plurality of thermal power generation nodes, and a plurality of load nodes;

[0008] Generate the power generation data of the new energy power generation node in the power grid topology structure according to the power generation data samples in the source-load data samples, and generate the load demand data of the load node in the power grid topology structure according to the load demand data samples in the source-load data samples, and then generate several first source-load distribution scenarios including the output of the new energy unit and the power consumption of the load under the power grid topology structure;

[0009] According to the first source-load distribution scenario, randomly generate several second source-load distribution scenarios in which a generator is shut down, several third source-load distribution scenarios in which an N-1 fault occurs, and several fourth source-load distribution scenarios in which a generator is shut down and an N-1 fault occurs simultaneously;

[0010] Constructing a source-load distribution scenario set, and taking the first source-load distribution scenario, the second source-load distribution scenario, the third source-load distribution scenario, and the fourth source-load distribution scenario as source-load distribution scenarios in the source-load distribution scenario set;

[0011] Using a preset power flow algorithm, calculate the target output power of a number of the thermal power generation nodes under each source-load distribution scenario in the source-load distribution scenario set;

[0012] Traversing each source-load distribution scenario in the source-load distribution scenario set, and determining whether the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid, and recording the target source-load distribution scenario and the corresponding target output power that can enable the normal operation of the power grid;

[0013] When it is determined that the traversal of the source-load distribution scenario set is completed, a number of power grid operation scenarios are generated according to the target source-load distribution scenario and the corresponding target output power.

[0014] Furthermore, several source load data samples are obtained, including:

[0015] Acquire a number of actual source-load data samples of the power grid;

[0016] Inputting the actual source load data sample into a preset generative adversarial network, so that the generator in the generative adversarial network learns the distribution of the actual source load data sample and generates a number of simulated source load data samples similar to the actual source load data sample, and then the discriminator in the generative adversarial network discriminates the simulated source load data sample, and finally outputs the simulated source load data sample determined by the discriminator as a real sample;

[0017] A plurality of the simulated source load data samples and a plurality of the actual source load data samples are used as the source load data samples.

[0018] Further, the using the plurality of simulated source-load data samples and the plurality of actual source-load data samples as the source-load data samples includes:

[0019] Performing type identification on the simulated source-load data sample and a plurality of the actual source-load data samples, and assigning corresponding type labels;

[0020] Count the number of samples under each type of label, and determine a number of target type labels that do not meet the preset number threshold;

[0021] Repeatedly randomly extracting source load data samples under the target type label and inputting them into the generative adversarial network, so that the generative adversarial network repeatedly generates a number of initial source load data under the target type label until the number of samples under the target type label meets the preset number threshold;

[0022] When it is determined that the number of samples under each type label meets the preset number threshold, a number of the simulated source load data samples and a number of the actual source load data samples under the type labels are used as the source load data samples.

[0023] Further, the power generation data of the new energy power generation node in the power grid topology is generated according to the power generation data sample in the source-load data sample, and the load demand data of the load node in the power grid topology is generated according to the load demand data sample in the source-load data sample, and then several first source-load distribution scenarios containing the output of the new energy unit and the power consumption of the load are generated under the power grid topology, including:

[0024] Randomly extract a power generation data sample from the source-load data sample as the power generation data of any new energy power generation node in the power grid topology structure, and randomly extract a load demand data sample from the source-load data sample as the load demand data of any load node in the power grid topology structure, to generate several random source-load distribution scenarios;

[0025] Randomly extracting several target new energy power generation nodes and several target load nodes from several initial source-load distribution scenarios, and adding disturbances to the power generation data of several target new energy power generation nodes, and adding disturbances to the load data of several target load nodes, to generate several disturbed source-load distribution scenarios;

[0026] A plurality of the random source-load distribution scenarios and a plurality of the disturbance source-load distribution scenarios are used as the first source-load distribution scenarios.

[0027] Furthermore, the power grid topology structure further includes: a number of transformers and transmission lines;

[0028] The method randomly generates, according to the first source-load distribution scenario, a plurality of second source-load distribution scenarios in which a generator is shut down, a plurality of third source-load distribution scenarios in which an N-1 fault occurs, and a plurality of fourth source-load distribution scenarios in which a generator is shut down and an N-1 fault occurs simultaneously, including:

[0029] According to the first source-load distribution scenario, randomly setting any number of renewable energy power generation nodes and power generation units in the power grid topology structure to be shut down to generate a number of initial second source-load distribution scenarios;

[0030] According to the first source-load distribution scenario, randomly setting any number of transformers and transmission line faults in the power grid topology structure to generate a number of initial third source-load distribution scenarios;

[0031] According to the first source-load distribution scenario, randomly setting any number of renewable energy power generation nodes and power generation nodes in the power grid topology structure to shut down the generator sets, and causing several transformers and transmission lines to fail, so as to generate several initial fourth source-load distribution scenarios;

[0032] Determine whether the difference between the sum of the load demand data of all load nodes and the sum of the power generation data of the normally operating new energy power generation nodes in each of the initial second source-load distribution scenario, the initial third source-load distribution scenario, and the initial fourth source-load distribution scenario is not greater than the sum of the maximum output powers of the normally operating thermal power generation nodes;

[0033] If so, a corresponding second source load distribution scenario, a third source load distribution scenario, or a fourth source load distribution scenario is generated.

[0034] Furthermore, the use of a preset power flow algorithm to calculate the target output power of a number of the thermal power generation nodes in each source-load distribution scenario in the source-load distribution scenario set includes:

[0035] Constructing an objective function for minimizing thermal power generation cost, a line capacity constraint function, a first power balance constraint function of a thermal power generation node, and a first output constraint function;

[0036] According to the objective function, the line capacity constraint function, the first power balance constraint function, and the first output constraint function, the power flow algorithm is used to solve the target output power of several thermal power generation nodes in each source-load distribution scenario.

[0037] Further, traversing each source-load distribution scenario in the source-load distribution scenario set, and determining whether the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid, includes:

[0038] Constructing a second power balance constraint function and a voltage constraint of the load node;

[0039] The preset AC power flow algorithm is used to calculate the active power and reactive power injected into each load node according to the currently traversed source-load distribution scenario and the corresponding target output power;

[0040] Determine whether the active power and reactive power of each of the load nodes satisfy the second power balance constraint function, the voltage constraint, and the line capacity constraint function;

[0041] When it is confirmed that the active power and reactive power of all load nodes satisfy the second power balance constraint function, the voltage constraint, and the line capacity constraint function, it is determined that the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid.

[0042] Another embodiment of the present invention provides a device for generating a power grid operation scenario, including:

[0043] A data acquisition module is used to acquire the power grid topology structure and a number of source-load data samples of the power grid; wherein the source-load data samples include: power generation data samples of a number of new energy power generation units, and a number of load demand data samples; the power grid topology structure includes: a number of new energy power generation nodes, a number of thermal power generation nodes, and a number of load nodes;

[0044] A source-load scenario generation module, used to generate power generation data of new energy power generation nodes in the power grid topology structure according to power generation data samples in the source-load data samples, and to generate load demand data of load nodes in the power grid topology structure according to load demand data samples in the source-load data samples, and then generate a plurality of first source-load distribution scenarios including output of new energy units and power consumption of loads under the power grid topology structure;

[0045] A source-load scenario optimization module, configured to randomly generate, based on the first source-load distribution scenario, a plurality of second source-load distribution scenarios in which a generator is shut down, a plurality of third source-load distribution scenarios in which an N-1 fault occurs, and a plurality of fourth source-load distribution scenarios in which a generator is shut down and an N-1 fault occurs simultaneously;

[0046] A scenario set generation module, used to construct a source-load distribution scenario set, and use the first source-load distribution scenario, the second source-load distribution scenario, the third source-load distribution scenario, and the fourth source-load distribution scenario as source-load distribution scenarios in the source-load distribution scenario set;

[0047] An output power calculation module, used to calculate the target output power of a number of the thermal power generation nodes in each source-load distribution scenario in the source-load distribution scenario set by using a preset power flow algorithm;

[0048] A source-load scenario analysis module is used to traverse each source-load distribution scenario in the source-load distribution scenario set, and determine whether the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid, and record the target source-load distribution scenario and the corresponding target output power that can enable the normal operation of the power grid;

[0049] The operation scenario generation module is used to generate a number of power grid operation scenarios according to the target source-load distribution scenario and the corresponding target output power when it is determined that the traversal of the source-load distribution scenario set is completed.

[0050] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a method for generating a power grid operation scenario as described in any one of the embodiments.

[0051] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a method for generating a power grid operation scenario as described in any one of the above embodiments.

[0052] The following beneficial effects are achieved by implementing the present invention:

[0053] The present invention discloses a method, device, terminal equipment and storage medium for generating a power grid operation scenario. The method acquires a number of source-load data samples and a power grid topology structure, constructs a number of first source-load distribution scenarios including the output of a new energy unit and the power consumption of a load, and then randomly generates a second source-load distribution scenario, a third source-load distribution scenario, and a fourth source-load distribution scenario, generates a variety of source-load distribution scenarios, and then calculates the target output power of the thermal power generation node in each source-load distribution scenario according to the DC optimal power flow algorithm, and finally verifies whether each source-load distribution scenario can operate normally in combination with the power grid topology structure and the corresponding target output power, and finally generates a number of power grid operation scenarios that can operate normally under the power grid topology structure according to the source-load distribution scenarios that can operate normally and the corresponding target output power. Therefore, the present invention provides a data basis for the subsequent generation of a variety of power grid operation scenarios by generating a variety of source-load distribution scenarios, overcomes the problem of insufficient diversity and flexibility of the current power grid scenario generation method, and secondly, by verifying the feasibility of each source-load distribution scenario before finally generating the scenario, overcomes the defect that the scenario generated by the current power grid scenario generation method cannot be applied to the actual power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flowchart of a method for generating a power grid operation scenario provided by an embodiment of the present invention.

[0055] Figure 2 It is a structural schematic diagram of a device for generating a power grid operation scenario provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0058] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0059] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0060] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0061] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0062] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0063] See also Figure 1 , is a flow chart of a method for generating a power grid operation scenario provided by an embodiment of the present invention, comprising:

[0064] S1. Obtaining a power grid topology structure and a plurality of source-load data samples of a power grid; wherein the source-load data samples include: power generation data samples of a plurality of new energy power generation units, and a plurality of load demand data samples; the power grid topology structure includes: a plurality of new energy power generation nodes, a plurality of thermal power generation nodes, and a plurality of load nodes;

[0065] In a preferred embodiment of the present invention, the grid topology refers to the connection and layout between different nodes in the grid, involving multiple links such as power generation, transmission, distribution and consumption. The grid topology includes source nodes (such as photovoltaic power stations, wind farms, etc.) and load nodes (such as residential users, industrial users, etc.).

[0066] Preferably, obtaining a number of source-load data samples includes:

[0067] S11, obtaining a number of actual source-load data samples of the power grid;

[0068] In a preferred embodiment of the present invention, the power generation data samples refer to the power generation data of renewable energy sources such as wind power and photovoltaic power, the sampling period is T', and the sampling duration of each sample curve is T. The load demand data samples refer to the power demand data of each node in the power grid, including different types of power demand such as residential, commercial, and industrial, the sampling period is T', and the sampling duration of each sample curve is T.

[0069] Furthermore, in order to ensure the quality of data samples, in this embodiment, data preprocessing is performed on the actual source load data samples. Specifically, data preprocessing refers to data completion and data cleaning. Data completion uses interpolation methods such as linear interpolation, polynomial interpolation, or collaborative filtering models to fill in the missing data caused by equipment failure or transmission problems to restore the integrity of the data and avoid affecting the model performance. Data cleaning identifies outliers through box plot analysis and uses distribution-based anomaly detection methods to exclude abnormal data to improve data quality and consistency.

[0070] S12, inputting the actual source load data sample into a preset generative adversarial network, so that the generator in the generative adversarial network learns the distribution of the actual source load data sample, and generates a number of simulated source load data samples similar to the actual source load data sample, and then the discriminator in the generative adversarial network discriminates the simulated source load data sample, and finally outputs the simulated source load data sample determined by the discriminator as a real sample;

[0071] In a preferred embodiment of the present invention, the generative adversarial network is a conditional generative adversarial network (CGAN) composed of a generator G and a discriminator D. The core idea is to guide the output of the generative model by introducing conditional variables so that it generates data of a specific category or meets specific conditions. First, the generator takes random noise z and condition y as input, learns the distribution determined by the conditional variable y, and generates samples G(z|y) that conform to the characteristics of real samples as realistically as possible. Then, the discriminator accepts the real sample x, generates the sample G(z|y), and the condition y, outputs the probability of whether the generated sample is a real sample, and judges whether the generated sample meets the condition y.

[0072] The objective function of CGAN is essentially an optimization problem. It uses game theory to train the generator and discriminator. Its objective function is as follows:

[0073]

[0074] The task of the discriminator D is to distinguish between the real sample x and the generated sample G(z|y) as much as possible. It represents the probability that the real sample x is judged as real by the discriminator under condition y. The discriminator hopes to maximize this term to improve the ability to distinguish real samples. It represents the probability that the generated sample G(z|y) is judged as not a real sample under condition y. The discriminator hopes to maximize this term to improve the recognition accuracy of the generated samples. The goal of the generator is to generate sufficiently realistic samples to deceive the discriminator so that it cannot distinguish between real data and generated data. The generator hopes to minimize the second term Try to make D(G(z|y)|y) close to 1, that is, let the discriminator think that the generated data is consistent with the real data. During the entire training process, the generator and the discriminator are constantly updated through this adversarial goal, and eventually the generator can generate samples that are highly similar to the real data, while the discriminator continuously improves its ability to distinguish between generated data and real data.

[0075] S13: taking a number of the simulated source load data samples and a number of the actual source load data samples as the source load data samples.

[0076] Preferably, the using the plurality of simulated source-load data samples and the plurality of actual source-load data samples as the source-load data samples comprises:

[0077] S131, performing type identification on the simulated source-load data sample and a plurality of the actual source-load data samples, and assigning corresponding type labels;

[0078] S132, counting the number of samples under each type of label, and determining a number of target type labels that do not meet a preset number threshold;

[0079] S133, repeatedly randomly extracting source load data samples under the target type label and inputting them into the generative adversarial network, so that the generative adversarial network repeatedly generates a number of initial source load data under the target type label, until the number of samples under the target type label meets the preset number threshold;

[0080] S134. When it is determined that the number of samples under each type label meets the preset number threshold, a number of the simulated source load data samples and a number of the actual source load data samples under the type labels are used as the source load data samples.

[0081] In a preferred embodiment of the present invention, a closed-loop mechanism for source-load data generation is based on CGAN. In this structure, source-load data samples are first generated by CGAN, and these samples undergo a type recognition process. Next, by analyzing the distribution of samples of different categories, source-load categories with a small number of samples are identified. For these unbalanced categories, they are re-input into the CGAN model as new conditions to further generate samples of the corresponding categories. Through this cyclic iterative process, the number of samples of each source-load category is gradually balanced, thereby improving the overall distribution balance of the source-load data. Assume that the final generated source sample set is S = {S1, S2, ..., S m}, the load sample set is L = {L1,L2,...,L n}.

[0082] It should be noted that, in this embodiment, the type of the sample is identified through the following steps:

[0083] First, calculate the average output of each new energy sample curve (power generation data)

[0084]

[0085] Then, set the high output and medium output thresholds P by analyzing historical data or using empirical values. high and P med , then for the i-th renewable energy output curve, if If If It is low output.

[0086] For load classification, first calculate the peak-to-valley difference rate R of each load j,peak-valley :

[0087]

[0088]

[0089] Assume R high and R med are the thresholds of high and medium peak-to-valley difference rates, respectively. For the jth load curve, if R j,peak-valley >R high , then it is the peak-to-valley difference rate; if R med ≤R j,peak-valley ≤R hig , h is the peak-to-valley difference rate; if R j,peak-valley <R med , then it is a low peak-to-valley rate.

[0090] Then, calculate the load factor R for each load j,load :

[0091]

[0092] Among them, P j,max is the maximum power value in the jth load curve. Assume that R′ high and R′ med are the thresholds of high and medium load rates respectively. For the jth load curve, if R j,load >R′ high , then it is a high load rate; if R′ med ≤R j,load ≤R′ high , then it is the medium load rate; if R j,load <R′ med , it is a low load rate.

[0093] By performing multi-scale characteristic analysis on renewable energy output and load data, labels can be automatically generated for each source-load curve according to the above process. This automated labeling process can improve the efficiency of data processing, reduce manual intervention, and ensure the systematicness and consistency of labels.

[0094] S2. Generate power generation data of new energy power generation nodes in the power grid topology structure according to the power generation data samples in the source-load data samples, and generate load demand data of load nodes in the power grid topology structure according to the load demand data samples in the source-load data samples, and then generate several first source-load distribution scenarios including the output of new energy units and the power consumption of loads under the power grid topology structure;

[0095] Preferably, the power generation data of the new energy power generation node in the power grid topology is generated according to the power generation data sample in the source-load data sample, and the load demand data of the load node in the power grid topology is generated according to the load demand data sample in the source-load data sample, and then several first source-load distribution scenarios containing the output of the new energy unit and the power consumption of the load are generated under the power grid topology, including:

[0096] S21, randomly extracting a power generation data sample from the source-load data sample as the power generation data of any new energy power generation node in the power grid topology structure, and randomly extracting a load demand data sample from the source-load data sample as the load demand data of any load node in the power grid topology structure, to generate several random source-load distribution scenarios;

[0097] S22, randomly selecting a number of target new energy power generation nodes and a number of target load nodes in a number of initial source-load distribution scenarios, and adding disturbances to the power generation data of the target new energy power generation nodes, and adding disturbances to the load data of the target load nodes, to generate a number of disturbed source-load distribution scenarios;

[0098] S23: Use a plurality of the random source-load distribution scenarios and a plurality of the disturbance source-load distribution scenarios as the first source-load distribution scenarios.

[0099] In a preferred embodiment of the present invention, it is assumed that there are N s source nodes and N l load nodes.

[0100] A two-stage Monte Carlo sampling method is used with random superposition of disturbances to generate source load data for each node;

[0101] Monte Carlo sampling is divided into two parts: the initial random sampling stage and the sampling stage based on probability distribution. First, the initial random sampling stage refers to randomly assigning a sample curve to each source load node from the corresponding sample sets S and L. Specifically, for the i-th source node node s,i , randomly select a curve S from the source sample set S k To make an allocation:

[0102]

[0103] Among them, k = random (m) is a randomly selected index from {1, 2, ..., m}, representing the kth source sample curve. Similarly, for the load node node l,j , randomly select a curve L from the load sample set L h To make an allocation:

[0104]

[0105] Wherein, h=random(n) is an index randomly selected from {1,2,...,n}, representing the hth load sample curve.

[0106] After the above random allocation is completed, a source-load distribution scenario including renewable energy output and load power consumption is obtained. Repeat the initial random sampling process to obtain a large number of source-load distribution scenarios and form a set

[0107] In the sampling stage based on probability distribution, we first screen out source-load distribution scenarios that can meet the normal operation of the power grid through steps 6) and 7) based on the large number of source-load distribution scenarios generated in the preliminary random sampling stage. On the basis of these feasible scenarios, the power probability distribution of each source-load node is further analyzed. Next, according to the probability distribution of each node, sampling is performed from the corresponding source-load data sample set, and the curve that conforms to the power probability distribution of the corresponding node is selected. In this way, we can generate a large number of source-load distribution scenarios that are more in line with the actual operating status of the power grid. Finally, through this two-stage sampling method, the generated scenarios not only meet the requirements of power grid operation, but also better reflect the actual operating characteristics of the source-load nodes, ensuring that the generated data has more practical application value.

[0108] The random superposition interference refers to superimposing a small random interference on the source-load curve sampled in the above steps to increase the diversity and authenticity of the source-load curve:

[0109]

[0110] Among them, ε s and ε l is a random interference term.

[0111] S3. According to the first source-load distribution scenario, randomly generate several second source-load distribution scenarios in which a generator is shut down, several third source-load distribution scenarios in which an N-1 fault occurs, and several fourth source-load distribution scenarios in which a generator is shut down and an N-1 fault occurs simultaneously;

[0112] Preferably, the power grid topology structure further includes: a number of transformers and transmission lines;

[0113] The method randomly generates, according to the first source-load distribution scenario, a plurality of second source-load distribution scenarios in which a generator is shut down, a plurality of third source-load distribution scenarios in which an N-1 fault occurs, and a plurality of fourth source-load distribution scenarios in which a generator is shut down and an N-1 fault occurs simultaneously, including:

[0114] S31. According to the first source-load distribution scenario, randomly shut down the generator sets in any number of new energy power generation nodes and a number of thermal power generation nodes in the power grid topology structure to generate a number of initial second source-load distribution scenarios;

[0115] S32. According to the first source-load distribution scenario, randomly set any number of transformers and transmission line faults in the power grid topology structure to generate a number of initial third source-load distribution scenarios;

[0116] S33, according to the first source-load distribution scenario, randomly setting any number of renewable energy power generation nodes and several thermal power generation nodes in the power grid topology structure to shut down the generator sets, and several transformers and transmission lines to fail, so as to generate several initial fourth source-load distribution scenarios;

[0117] S34, judging whether the difference between the sum of the load demand data of all load nodes and the sum of the power generation data of the normally operating new energy power generation nodes in each of the initial second source-load distribution scenario, the initial third source-load distribution scenario, and the initial fourth source-load distribution scenario is not greater than the sum of the maximum output powers of the normally operating thermal power generation nodes;

[0118] S35. If yes, generate a corresponding second source load distribution scenario, a third source load distribution scenario, or a fourth source load distribution scenario.

[0119] In a preferred embodiment of the present invention, the random simulation of generator shutdown is to reflect that in actual power grid operation, some generators G are shut down due to maintenance, failure or demand changes. i The N-1 fault is used to simulate the operating state of key equipment in the power grid, such as transformers or transmission lines, when they fail or are disconnected. By introducing random simulation of generator shutdown and N-1 fault, a more diverse network topology can be generated, showing the state changes of the power grid under different fault or operating conditions.

[0120] Network topology Γ when only the generator is shut down G for:

[0121]

[0122] Network topology Γ when only N-1 fault state exists N-1 for:

[0123]

[0124] Network topology Γ when both generator shutdown and N-1 fault occur G for:

[0125] Γ G,N-1 =Γ({Gi},{E j});

[0126] Normal operation means that all generators G i And key equipment E i (such as transformers and transmission lines) are all in normal working condition. At this time, the network topology Γ normal for:

[0127]

[0128] Among them, G i =1 and E j =1 indicates that the generator and key equipment are operating normally.

[0129] In order to ensure that the supply and demand of the power grid can be balanced when calculating the output of thermal power units in the subsequent steps, a source-load balance condition is set to screen the source-load distribution scenarios. Specifically: The source-load balance condition refers to the total output of new energy. The total power load demand The difference between the two values ​​shall not be higher than the maximum output value of the thermal power unit. That is, the following conditions are met:

[0130]

[0131] S4: construct a source-load distribution scenario set, and use the first source-load distribution scenario, the second source-load distribution scenario, the third source-load distribution scenario, and the fourth source-load distribution scenario as source-load distribution scenarios in the source-load distribution scenario set;

[0132] S5. Using a preset power flow algorithm, calculate the target output power of a number of the thermal power generation nodes in each source-load distribution scenario in the source-load distribution scenario set;

[0133] Preferably, the use of a preset power flow algorithm to calculate the target output power of a number of the thermal power generation nodes in each source-load distribution scenario in the source-load distribution scenario set includes:

[0134] S51, constructing an objective function for minimizing thermal power generation cost, a line capacity constraint function, a first power balance constraint function of a thermal power generation node, and a first output constraint function;

[0135] S52. According to the objective function, the line capacity constraint function, the first power balance constraint function, and the first output constraint function, the power flow algorithm is used to solve the target output power of several thermal power generation nodes in each source-load distribution scenario.

[0136] In a preferred embodiment of the present invention, the preset power flow algorithm is a DC optimal power flow algorithm that determines the output of the thermal power generation unit by minimizing the power generation cost of the thermal power generation unit while satisfying the power grid supply and demand balance and physical constraints. Assuming a certain network topology Γ k There are N TG There are thermal power generating units, and the power generation cost of the i-th unit is C i (P i ), its power generation is P i , then to minimize the total power generation cost, the objective function can be expressed as:

[0137]

[0138] Among them, a i ,b i ,c i is the cost coefficient associated with the i-th thermal power unit.

[0139] At the same time, the output of the thermal power generating unit must also meet the following constraints:

[0140] (1) Power balance constraints

[0141] In the operation of the power grid, the power generation must meet the load demand. Therefore, the power generation of thermal power units must meet:

[0142]

[0143] (2) Generator power output constraints

[0144] The output of each thermal power unit is subject to upper and lower limits, that is, the output of each generator P i It must be at its minimum output P i min and maximum output P i max between:

[0145] P i min ≤P i ≤P i max ;

[0146] (3) Transmission line capacity constraints:

[0147] The power transmission lines of the power grid have capacity limitations. Assume that the power flow from node m to node n is F mn , then the power flow cannot exceed the maximum transmission capacity of the line

[0148]

[0149] Then, in the DC power flow model, the line power flow F mn There is a linear relationship with the node voltage phase angle θ, and the power flow calculation formula is as follows:

[0150]

[0151] Among them, X mn is the reactance of line mn.

[0152] By combining the objective function with the constraints, we can transform this problem into a linear programming or quadratic programming problem. By solving this optimization problem, we can determine the optimal output P of each thermal power unit. i Finally, the optimal output of the thermal power unit can be obtained by solving this optimization problem. When solving it with the standard optimization algorithm, the optimal solution can be found under the conditions of satisfying power balance, generator output limit and line capacity constraints, thereby determining the economic optimal output of the thermal power unit.

[0153] S6. Traverse each source-load distribution scenario in the source-load distribution scenario set, and determine whether the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid, and record the target source-load distribution scenario and the corresponding target output power that can enable the normal operation of the power grid;

[0154] Preferably, traversing each source-load distribution scenario in the source-load distribution scenario set, and determining whether the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid, includes:

[0155] S61, constructing a second power balance constraint function and a voltage constraint for the load node;

[0156] S62, using a preset AC power flow algorithm, according to the currently traversed source-load distribution scenario and the corresponding target output power, calculate the active power and reactive power injected into each load node;

[0157] S63, judging whether the active power and reactive power of each of the load nodes satisfy the second power balance constraint function, the voltage constraint, and the line capacity constraint function;

[0158] S64. When it is confirmed that the active power and reactive power of all load nodes satisfy the second power balance constraint function, the voltage constraint, and the line capacity constraint function, it is determined that the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid.

[0159] In a preferred embodiment of the present invention, the basic equation of AC power flow is:

[0160]

[0161] Among them, P i and Q i are the active power and reactive power injected into node i respectively; V i and V j is the voltage amplitude of nodes i and j; G ij and B ij are the real and imaginary parts of the admittance between nodes i and j, respectively; θ ij is the voltage phase angle difference between nodes i and j.

[0162] At the same time, each node must also meet the following constraints:

[0163] (1) Power balance constraints

[0164] For each node, its power output P G Subtract load demand P D Equal to the power passing through the node in the network Right now:

[0165]

[0166] (2) Voltage Constraint

[0167] The voltage amplitude of all nodes is V i Need to be kept within a certain range, namely:

[0168] V i,min ≤V i ≤V i,max ;

[0169] Among them, V i,min and V i,max are the minimum and maximum voltage amplitudes of the i-th node respectively.

[0170] (3) Line power constraints

[0171] Power flow per line F ij The maximum transmission capacity of the line cannot be exceeded Right now:

[0172]

[0173] After establishing the basic equations and constraints of the power grid, AC power flow calculation usually uses numerical iteration methods to solve node voltage and power distribution. A common method is the Newton-Raphson iteration method, which can effectively handle nonlinear equations. First, use the node admittance matrix Y busThe grid topology and impedance relationship are expressed, and the nonlinear equations of the system are constructed by combining the power balance equation of each node. The voltage amplitude and phase angle are adjusted iteratively until the power balance conditions of all nodes are met, thus obtaining the voltage and power distribution of each node and the power flow of the line.

[0174] Finally, if the calculation results meet all constraints, the scenario is a feasible grid operation state. The source and load data, thermal power generation unit output data and grid topology are output to generate the final grid scenario sample.

[0175] S7. When it is determined that the traversal of the source-load distribution scenario set is completed, a plurality of power grid operation scenarios are generated according to the target source-load distribution scenario and the corresponding target output power.

[0176] The present embodiment provides a method for generating a power grid operation scenario, by acquiring a number of source-load data samples and a power grid topology, constructing a number of first source-load distribution scenarios including the output of new energy units and load power consumption, and then randomly generating a second source-load distribution scenario, a third source-load distribution scenario, and a fourth source-load distribution scenario, generating a variety of source-load distribution scenarios, and then calculating the target output power of the thermal power generation node in each source-load distribution scenario according to the DC optimal power flow algorithm, and finally combining the power grid topology and the corresponding target output power to verify whether each source-load distribution scenario can operate normally, and finally generating a number of power grid operation scenarios that can operate normally under the power grid topology according to the source-load distribution scenarios that can operate normally and the corresponding target output power. Therefore, the present invention provides a data basis for the subsequent generation of a variety of power grid operation scenarios by generating a variety of source-load distribution scenarios, thereby overcoming the problem of insufficient diversity and flexibility of the current power grid scenario generation method, and secondly, by verifying the feasibility of each source-load distribution scenario before finally generating the scenario, overcoming the defect that the scenario generated by the current power grid scenario generation method cannot be applied to the actual power system.

[0177] See also Figure 2 , is a schematic diagram of a structure of a device for generating a power grid operation scenario provided by an embodiment of the present invention, comprising:

[0178] A data acquisition module is used to acquire the power grid topology structure and a number of source-load data samples of the power grid; wherein the source-load data samples include: power generation data samples of a number of new energy power generation units, and a number of load demand data samples; the power grid topology structure includes: a number of new energy power generation nodes, a number of thermal power generation nodes, and a number of load nodes;

[0179] A source-load scenario generation module, used to generate power generation data of new energy power generation nodes in the power grid topology structure according to power generation data samples in the source-load data samples, and to generate load demand data of load nodes in the power grid topology structure according to load demand data samples in the source-load data samples, and then generate a plurality of first source-load distribution scenarios including output of new energy units and power consumption of loads under the power grid topology structure;

[0180] A source-load scenario optimization module, configured to randomly generate, based on the first source-load distribution scenario, a plurality of second source-load distribution scenarios in which a generator is shut down, a plurality of third source-load distribution scenarios in which an N-1 fault occurs, and a plurality of fourth source-load distribution scenarios in which a generator is shut down and an N-1 fault occurs simultaneously;

[0181] A scenario set generation module, used to construct a source-load distribution scenario set, and use the first source-load distribution scenario, the second source-load distribution scenario, the third source-load distribution scenario, and the fourth source-load distribution scenario as source-load distribution scenarios in the source-load distribution scenario set;

[0182] An output power calculation module, used to calculate the target output power of a number of the thermal power generation nodes in each source-load distribution scenario in the source-load distribution scenario set by using a preset power flow algorithm;

[0183] A source-load scenario analysis module is used to traverse each source-load distribution scenario in the source-load distribution scenario set, and determine whether the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid, and record the target source-load distribution scenario and the corresponding target output power that can enable the normal operation of the power grid;

[0184] The operation scenario generation module is used to generate a number of power grid operation scenarios according to the target source-load distribution scenario and the corresponding target output power when it is determined that the traversal of the source-load distribution scenario set is completed.

[0185] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0186] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0187] Another preferred embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a method for generating a power grid operation scenario as described in any one of the above embodiments.

[0188] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0189] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0190] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0191] Another preferred embodiment of the present invention provides a storage medium, the storage medium is a computer-readable storage medium, the computer program is stored in the computer-readable storage medium, and the computer program, when executed by the processor, can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0192] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for generating a power grid operation scenario, characterized in that: include: Acquire a power grid topology structure and a plurality of source-load data samples of a power grid; wherein the source-load data samples include: power generation data samples of a plurality of new energy power generation units, and a plurality of load demand data samples; the power grid topology structure includes: a plurality of new energy power generation nodes, a plurality of thermal power generation nodes, and a plurality of load nodes; Generate the power generation data of the new energy power generation node in the power grid topology structure according to the power generation data samples in the source-load data samples, and generate the load demand data of the load node in the power grid topology structure according to the load demand data samples in the source-load data samples, and then generate several first source-load distribution scenarios including the output of the new energy unit and the power consumption of the load under the power grid topology structure; According to the first source-load distribution scenario, randomly generate several second source-load distribution scenarios in which a generator is shut down, several third source-load distribution scenarios in which an N-1 fault occurs, and several fourth source-load distribution scenarios in which a generator is shut down and an N-1 fault occurs simultaneously; Constructing a source-load distribution scenario set, and taking the first source-load distribution scenario, the second source-load distribution scenario, the third source-load distribution scenario, and the fourth source-load distribution scenario as source-load distribution scenarios in the source-load distribution scenario set; Using a preset power flow algorithm, calculate the target output power of a number of the thermal power generation nodes under each source-load distribution scenario in the source-load distribution scenario set; Traversing each source-load distribution scenario in the source-load distribution scenario set, and determining whether the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid, and recording the target source-load distribution scenario and the corresponding target output power that can enable the normal operation of the power grid; When it is determined that the traversal of the source-load distribution scenario set is completed, a number of power grid operation scenarios are generated according to the target source-load distribution scenario and the corresponding target output power.

2. A method for generating a power grid operation scenario according to claim 1, characterized in that: Get several source load data samples, including: Acquire a number of actual source-load data samples of the power grid; Inputting the actual source load data sample into a preset generative adversarial network, so that the generator in the generative adversarial network learns the distribution of the actual source load data sample and generates a number of simulated source load data samples similar to the actual source load data sample, and then the discriminator in the generative adversarial network discriminates the simulated source load data sample, and finally outputs the simulated source load data sample determined by the discriminator as a real sample; A plurality of the simulated source load data samples and a plurality of the actual source load data samples are used as the source load data samples.

3. A method for generating a power grid operation scenario according to claim 2, characterized in that: The using the plurality of simulated source load data samples and the plurality of actual source load data samples as the source load data samples comprises: Performing type identification on the simulated source-load data sample and a plurality of the actual source-load data samples, and assigning corresponding type labels; Count the number of samples under each type of label, and determine a number of target type labels that do not meet the preset number threshold; Repeatedly randomly extracting source load data samples under the target type label and inputting them into the generative adversarial network, so that the generative adversarial network repeatedly generates a number of initial source load data under the target type label until the number of samples under the target type label meets the preset number threshold; When it is determined that the number of samples under each type label meets the preset number threshold, a number of the simulated source load data samples and a number of the actual source load data samples under the type labels are used as the source load data samples.

4. A method for generating a power grid operation scenario according to claim 3, characterized in that: The generating data of the new energy power generation node in the power grid topology is generated according to the power generation data sample in the source-load data sample, and the load demand data of the load node in the power grid topology is generated according to the load demand data sample in the source-load data sample, and then the first source-load distribution scenarios containing the output of the new energy unit and the power consumption of the load are generated under the power grid topology, including: Randomly extract a power generation data sample from the source-load data sample as the power generation data of any new energy power generation node in the power grid topology structure, and randomly extract a load demand data sample from the source-load data sample as the load demand data of any load node in the power grid topology structure, to generate several random source-load distribution scenarios; Randomly extracting several target new energy power generation nodes and several target load nodes from several initial source-load distribution scenarios, and adding disturbances to the power generation data of several target new energy power generation nodes, and adding disturbances to the load data of several target load nodes, to generate several disturbed source-load distribution scenarios; A plurality of the random source-load distribution scenarios and a plurality of the disturbance source-load distribution scenarios are used as the first source-load distribution scenarios.

5. A method for generating a power grid operation scenario according to claim 4, characterized in that: The grid topology structure also includes: a number of transformers and transmission lines; The method randomly generates, according to the first source-load distribution scenario, a plurality of second source-load distribution scenarios in which a generator is shut down, a plurality of third source-load distribution scenarios in which an N-1 fault occurs, and a plurality of fourth source-load distribution scenarios in which a generator is shut down and an N-1 fault occurs simultaneously, including: According to the first source-load distribution scenario, randomly setting any number of renewable energy power generation nodes and power generation units in the power grid topology structure to be shut down to generate a number of initial second source-load distribution scenarios; According to the first source-load distribution scenario, randomly setting any number of transformers and transmission line faults in the power grid topology structure to generate a number of initial third source-load distribution scenarios; According to the first source-load distribution scenario, randomly setting any number of renewable energy power generation nodes and power generation nodes in the power grid topology structure to shut down the generator sets, and causing several transformers and transmission lines to fail, so as to generate several initial fourth source-load distribution scenarios; Determine whether the difference between the sum of the load demand data of all load nodes and the sum of the power generation data of the normally operating new energy power generation nodes in each of the initial second source-load distribution scenario, the initial third source-load distribution scenario, and the initial fourth source-load distribution scenario is not greater than the sum of the maximum output powers of the normally operating thermal power generation nodes; If so, a corresponding second source load distribution scenario, a third source load distribution scenario, or a fourth source load distribution scenario is generated.

6. A method for generating a power grid operation scenario according to claim 5, characterized in that: The using of a preset power flow algorithm to calculate the target output power of a plurality of the thermal power generation nodes in each source-load distribution scenario in the source-load distribution scenario set includes: Constructing an objective function for minimizing thermal power generation cost, a line capacity constraint function, a first power balance constraint function of a thermal power generation node, and a first output constraint function; According to the objective function, the line capacity constraint function, the first power balance constraint function, and the first output constraint function, the power flow algorithm is used to solve the target output power of several thermal power generation nodes in each source-load distribution scenario.

7. A method for generating a power grid operation scenario according to claim 6, characterized in that: The traversing each source-load distribution scenario in the source-load distribution scenario set, and determining whether the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid, includes: Constructing a second power balance constraint function and a voltage constraint of the load node; The preset AC power flow algorithm is used to calculate the active power and reactive power injected into each load node according to the currently traversed source-load distribution scenario and the corresponding target output power; Determine whether the active power and reactive power of each of the load nodes satisfy the second power balance constraint function, the voltage constraint, and the line capacity constraint function; When it is confirmed that the active power and reactive power of all load nodes satisfy the second power balance constraint function, the voltage constraint, and the line capacity constraint function, it is determined that the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid.

8. A device for generating a power grid operation scenario, characterized in that: include: A data acquisition module is used to acquire the power grid topology structure and a number of source-load data samples of the power grid; wherein the source-load data samples include: power generation data samples of a number of new energy power generation units, and a number of load demand data samples; the power grid topology structure includes: a number of new energy power generation nodes, a number of thermal power generation nodes, and a number of load nodes; A source-load scenario generation module, used to generate power generation data of new energy power generation nodes in the power grid topology structure according to power generation data samples in the source-load data samples, and to generate load demand data of load nodes in the power grid topology structure according to load demand data samples in the source-load data samples, and then generate a plurality of first source-load distribution scenarios including output of new energy units and power consumption of loads under the power grid topology structure; A source-load scenario optimization module, configured to randomly generate, based on the first source-load distribution scenario, a plurality of second source-load distribution scenarios in which a generator is shut down, a plurality of third source-load distribution scenarios in which an N-1 fault occurs, and a plurality of fourth source-load distribution scenarios in which a generator is shut down and an N-1 fault occurs simultaneously; A scenario set generation module, used to construct a source-load distribution scenario set, and use the first source-load distribution scenario, the second source-load distribution scenario, the third source-load distribution scenario, and the fourth source-load distribution scenario as source-load distribution scenarios in the source-load distribution scenario set; An output power calculation module, used to calculate the target output power of a number of the thermal power generation nodes in each source-load distribution scenario in the source-load distribution scenario set by using a preset power flow algorithm; A source-load scenario analysis module is used to traverse each source-load distribution scenario in the source-load distribution scenario set, and determine whether the currently traversed source-load distribution scenario and the corresponding target output power can enable the normal operation of the power grid, and record the target source-load distribution scenario and the corresponding target output power that can enable the normal operation of the power grid; The operation scenario generation module is used to generate a number of power grid operation scenarios according to the target source-load distribution scenario and the corresponding target output power when it is determined that the traversal of the source-load distribution scenario set is completed.

9. A terminal device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a method for generating a power grid operation scenario as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute a method for generating a power grid operation scenario as described in any one of claims 1 to 7.

Images