Method and apparatus for generating scenarios with high proportion of photovoltaic power grid integration

Abstract

This application provides a method and apparatus for generating scenarios of high-proportion photovoltaic (PV) grid connection. The method includes: extracting application scenario difference data from PV grid-connected data based on the impact of weather environmental parameters on PV power generation; constructing typical and extreme scenarios of PV grid connection using the application scenario difference data, and generating a sample library based on the typical and extreme scenarios; and generating non-manually constructed random target scenarios based on the probability distribution of different typical and extreme scenarios using a diffusion model based on the sample library. Thus, the above method and apparatus achieve intelligent generation, learning, and comprehensive evaluation of various scenarios of high-proportion PV grid connection. This automated process provides a wider range of more realistic scenario samples for simulation research, helps to deepen the understanding of the performance of PV systems in actual operation, and provides more targeted data support for power system planning and operation.

Description

Technical Field

[0001] This application relates to the field of new energy grid connection technology, and in particular to a method and apparatus for generating scenarios with a high proportion of photovoltaic power grid access. Background Technology

[0002] With the widespread application of photovoltaic (PV) power generation, the architecture of high-proportion PV grid integration is constantly being strengthened. Traditional power system models and simulation methods often fail to fully consider the complexity and dynamics of PV systems. The rapid penetration and complexity of PV systems make traditional scenario generation methods difficult to adapt to diverse operating conditions. This invention provides a more advanced and flexible scenario generation method to better simulate and evaluate the performance of PV systems under different operating conditions, providing more accurate and comprehensive data support for power system planning and operation.

[0003] In existing technologies, scene generation methods can be broadly categorized into two types based on their approaches: probabilistic model-based methods and time series-based methods. Probabilistic model-based methods use parametric or non-parametric estimation methods to fit the probability density function of historical data, and then sample the probability density function to obtain random scenes of new energy output. Time series-based methods generate future scenes based on the changing trends of time series data.

[0004] In probabilistic model-based scene generation methods, parametric estimation methods require prior knowledge of probability distributions, while nonparametric estimation methods require a large amount of historical data. When a high proportion of photovoltaic (PV) systems are integrated into the distribution network, the accuracy of the identified model is low if the probability distribution model is not appropriately chosen or historical data is limited. Scene generation methods based on time series analysis still need improvement in accuracy when facing highly variable PV systems and the influence of external environments. Summary of the Invention

[0005] The purpose of this application is to provide a method and apparatus for generating scenarios with a high proportion of photovoltaic (PV) access to the distribution network. The method generates scenarios with a high proportion of PV access to the distribution network based on diffusion learning, which more accurately simulates the performance of PV systems under different conditions and effectively improves the distribution network's ability to absorb PV.

[0006] To achieve the above objectives, this application provides a method for generating scenarios for high-proportion photovoltaic (PV) grid connection. The method includes: extracting application scenario difference data from PV grid-connected data based on the impact of weather and environmental parameters on PV power generation; constructing typical and extreme scenarios for PV grid connection using the application scenario difference data, and generating a sample library based on the typical and extreme scenarios; and generating non-manually constructed random target scenarios based on the probability distribution of different typical and extreme scenarios using a diffusion model based on the sample library.

[0007] In the above-mentioned method for generating scenarios with a high proportion of photovoltaic power generation connected to the distribution network, optionally, extracting application scenario difference data from photovoltaic grid-connected data based on the impact of weather environmental parameters on photovoltaic power generation includes: constructing a photovoltaic grid-connected characteristic model based on the impact of weather environmental parameters on photovoltaic power generation; and extracting application scenario difference data from photovoltaic grid-connected data through the photovoltaic grid-connected characteristic model.

[0008] In the above-mentioned method for generating scenarios of high-proportion photovoltaic (PV) grid connection, optionally, the construction of typical scenarios of PV grid connection through the application scenario difference data includes: using a simulation system to construct typical scenarios of PV grid connection based on different PV power, PV system access at different locations, solar radiation differences and grid load distribution in different regions, and PV system access time in the PV grid connection characteristic model.

[0009] In the above-mentioned method for generating scenarios with a high proportion of photovoltaic power grid connection, optionally, constructing extreme scenarios of photovoltaic power grid connection through the application scenario difference data includes: using a simulation system to construct extreme scenarios of photovoltaic power grid connection based on the operation of the photovoltaic system under extreme weather conditions and the sudden change data of photovoltaic power in the photovoltaic grid connection characteristic model.

[0010] In the above-mentioned method for generating scenarios with a high proportion of photovoltaic grid connection, optionally, generating non-manually constructed random target scenarios based on the probability distribution of occurrence of different typical and extreme scenarios using a diffusion model according to the sample library includes: constructing a longitudinal historical dataset based on typical and extreme scenarios; and obtaining non-manually constructed random target scenarios by analyzing the probability distribution of occurrence of longitudinal historical datasets with preset periods for different typical and extreme scenarios using the diffusion model.

[0011] In the above-mentioned method for generating scenarios with a high proportion of photovoltaic power grid access, optionally, obtaining a non-manually constructed random target scenario by analyzing the occurrence probability distribution of a preset period of longitudinal historical datasets for different typical and extreme scenarios through the diffusion model includes: extracting feature indicators of the corresponding scenarios based on different access points, power levels, and access times in the typical and extreme scenarios; generating scenario data using a Markov chain based on the occurrence probability distribution of the preset period of longitudinal historical datasets of the feature indicators; and constructing a random target scenario based on the combination of the scenario data.

[0012] In the above-mentioned method for generating scenarios with a high proportion of photovoltaic power generation connected to the distribution network, optionally, the application scenario difference data extracted from the photovoltaic grid-connected data based on the impact of weather environmental parameters on photovoltaic power generation includes: extracting application scenario difference data from historical operation data of photovoltaic grid connection based on the impact of weather environmental parameters on photovoltaic power generation.

[0013] In the above-mentioned method for generating scenarios with a high proportion of photovoltaic power grid integration, the method may optionally further include: analyzing the impact data of the random target scenario on photovoltaic power grid integration based on the operating characteristics of the typical scenario and the extreme scenario; and obtaining the evaluation results of the random target scenario based on the impact data.

[0014] This application also provides a scenario generation device for high-proportion photovoltaic (PV) grid connection, the device comprising: a data extraction module, a sample generation module, and a scenario generation module; the data extraction module is used to extract application scenario difference data from PV grid connection data based on the impact of weather environmental parameters on PV power generation; the sample generation module is used to construct typical and extreme scenarios of PV grid connection based on the application scenario difference data, and generate a sample library based on the typical and extreme scenarios; the scenario generation module is used to generate non-manually constructed random target scenarios based on the probability distribution of different typical and extreme scenarios using a diffusion model based on the sample library.

[0015] In the above-mentioned high-proportion photovoltaic grid connection scenario generation device, optionally, the scenario generation module further includes a generation unit, which is used to construct a longitudinal historical dataset based on typical scenarios and extreme scenarios; extract feature indicators of the corresponding scenarios based on different access points, power levels and access times in the typical scenarios and extreme scenarios; generate scenario data using a Markov chain based on the occurrence probability distribution of the longitudinal historical dataset of the feature indicators within a preset period; and construct random target scenarios by combining the scenario data.

[0016] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method.

[0017] This application also provides a computer-readable storage medium storing a computer program that performs the above-described methods.

[0018] This application also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0019] The beneficial technical effects of this application are as follows: it enables intelligent generation, learning, and comprehensive evaluation of various scenarios involving high-proportion photovoltaic (PV) grid integration. This automated process provides a wider range of more realistic scenario samples for simulation research, helps to deepen the understanding of the performance of PV systems in actual operation, and provides more targeted data support for power system planning and operation. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, do not constitute a limitation thereof. In the drawings:

[0021] Figure 1 This is a flowchart illustrating a method for generating a high-proportion photovoltaic grid connection scenario according to an embodiment of this application.

[0022] Figure 2 This is a schematic diagram illustrating the process of obtaining application scenario difference data according to an embodiment of this application;

[0023] Figure 3 This is a schematic diagram illustrating the process of generating a random target scene according to an embodiment of this application;

[0024] Figure 4 This is a schematic diagram illustrating the application process of the diffusion model provided in an embodiment of this application;

[0025] Figure 5 This is a schematic diagram illustrating the principle of a diffusion learning model provided in an embodiment of this application;

[0026] Figure 6 This is a schematic diagram illustrating the application process of a method for generating scenarios with a high proportion of photovoltaic power grid access, provided in an embodiment of this application.

[0027] Figure 7 This is a schematic diagram illustrating the process of generating a random scene according to an embodiment of this application;

[0028] Figure 8 This is a schematic diagram of the structure of a newly generated scene comprehensive evaluation system provided in an embodiment of this application;

[0029] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0030] The following will describe in detail the implementation methods of this application with reference to the accompanying drawings and embodiments, so as to fully understand how this application uses technical means to solve technical problems and achieve technical effects, and to implement it accordingly. It should be noted that, as long as there is no conflict, the various embodiments and features in each embodiment of this application can be combined with each other, and the resulting technical solutions are all within the protection scope of this application.

[0031] Furthermore, the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0032] Please refer to Figure 1As shown, the method for generating scenarios with a high proportion of photovoltaic power grid integration provided in this application includes:

[0033] S101 extracts application scenario difference data from photovoltaic grid-connected data based on the impact of weather and environmental parameters on photovoltaic power generation;

[0034] S102 constructs typical and extreme scenarios for photovoltaic grid connection using the application scenario difference data, and generates a sample library based on the typical and extreme scenarios;

[0035] S103 generates non-manually constructed random target scenarios based on the sample library and the probability distribution of occurrence of different typical and extreme scenarios using a diffusion model.

[0036] In the above embodiments, the scenario of high-proportion photovoltaic (PV) grid connection can be defined as the various performances of the PV power generation system under different operating conditions, including PV power level, such as the power generation level of the PV system under different illumination conditions, covering various weather conditions such as sunny days, cloudy days, and partly cloudy days; grid connection point distribution, the distribution of PV system grid connection points in the power distribution network, considering different geographical locations and grid connection strategies; power fluctuation, the instantaneous fluctuation of PV system power, simulating power fluctuations caused by changes in cloud cover, etc.; grid connection time, the grid connection status of the PV system in different time periods, including different seasons, day and night changes, etc.; load change, the change of distribution network load, considering the impact of load demand fluctuations on the PV system; and power system topology, the grid connection and impact of the PV system under different power system topologies, including microgrids, ring grids, etc.

[0037] The scenario of high-proportion photovoltaic (PV) grid connection can be extracted using the k-means algorithm. Daily irradiance is measured and recorded every 15 minutes from 6:00 AM to 6:00 PM. The dimensionality of the 48 measured daily irradiance points is reduced to construct a feature index sequence Ai (i = 1, 2, ..., 48) for the PV daily power generation sequence. The mean daily irradiance (AI), standard deviation of daily irradiance (SDi), and maximum daily irradiance (Aimax) are used to replace the daily 48-point irradiance curve, achieving dimensionality reduction of the daily irradiance curve. Then, the historical daily irradiance sequence described by these three feature indices is used to classify typical and extreme scenarios.

[0038] Characteristic indicators for extreme scenarios include: the daily irradiance is significantly greater than the average daily irradiance over a period of time, meaning the daily average irradiance is greater than the expected daily irradiance; the daily average irradiance is significantly less than the average daily irradiance over a period of time, meaning the daily average irradiance is less than the expected daily irradiance; and the daily irradiance fluctuation is much larger than the fluctuation over a period of time, meaning the daily irradiance variance is greater than the expected variance sequence. Under the characteristic indicators of daily irradiance conforming to extreme scenarios, other characteristic indicators in the extreme scenarios, such as voltage, current, and power, are recorded to obtain the photovoltaic power output sequence scenario under the extreme scenario. Dividing by daily irradiance, apart from the above-mentioned extreme scenario characteristic indicators, the remaining indicators are characteristic indicators of typical scenarios. The voltage, current, and power characteristic indicators in typical scenarios are recorded to obtain the photovoltaic power output sequence scenario under the typical scenario.

[0039] Please refer to Figure 2 As shown in one embodiment of this application, the data extracted from the photovoltaic grid-connected data based on the impact of weather environmental parameters on photovoltaic power generation includes:

[0040] S201 constructs a photovoltaic grid-connection characteristic model based on the impact of weather and environmental parameters on photovoltaic power generation;

[0041] S202 extracts application scenario difference data from the photovoltaic grid-connected data through the photovoltaic grid-connected characteristic model.

[0042] The construction of typical photovoltaic (PV) grid connection scenarios using the application scenario difference data can include: constructing typical PV grid connection scenarios using a simulation system based on different PV power outputs, PV system access locations, regional differences in solar radiation and grid load distribution, and PV system access times, as defined in the PV grid connection characteristic model. Furthermore, the construction of extreme PV grid connection scenarios using the application scenario difference data can include: constructing extreme PV grid connection scenarios using a simulation system based on the PV system operation under extreme weather conditions and sudden changes in PV power output, as defined in the PV grid connection characteristic model.

[0043] Specifically, in practical work, the scenario generation method for high-proportion photovoltaic (PV) grid connection provided in this application is mainly based on the analysis of the impact of weather and other factors on PV power generation, and constructs a PV grid connection characteristic model. Based on the PV grid connection characteristic model, typical and extreme scenarios for high-proportion PV grid connection are constructed to form a sample library. Based on a diffusion learning model, considering various factors such as different access points, power levels, and access times, the scenario features in the sample library are learned to generate non-manually constructed random scenarios. Subsequently, based on the operating characteristics of typical and extreme scenarios, the potential impact of new scenarios on grid performance, reliability, and system stability can be considered to establish a comprehensive evaluation system for newly generated scenarios. The specific construction process will be described in detail in subsequent embodiments. In another embodiment, extracting application scenario difference data from PV grid connection data based on the impact of weather and environmental parameters on PV power generation may include: extracting application scenario difference data from historical PV grid connection operating data based on the impact of weather and environmental parameters on PV power generation; this process can adopt the historical data processing method of existing learning algorithms, which will not be described in detail here.

[0044] Please refer to Figure 3 As shown, in one embodiment of this application, generating a non-manually constructed random target scene based on the probability distribution of occurrence of different typical and extreme scenarios using a diffusion model according to the sample library includes:

[0045] S301 constructs a longitudinal historical dataset based on typical and extreme scenarios;

[0046] S302 uses the diffusion model to analyze the probability distribution of the occurrence of longitudinal historical datasets of different typical and extreme scenarios over a preset period to obtain a non-manually constructed random target scenario.

[0047] Please refer to this again. Figure 4 As shown, the above-mentioned method of obtaining a non-manually constructed random target scenario by analyzing the occurrence probability distribution of longitudinal historical datasets of different typical and extreme scenarios over a preset period using the diffusion model can include:

[0048] S401 extracts feature indicators for the corresponding scenarios based on different access points, power levels, and access times in the typical and extreme scenarios.

[0049] S402 generates scene data using Markov chains based on the occurrence probability distribution of the longitudinal historical dataset of the preset period of the feature indicators, and constructs random target scenes based on the combination of the scene data.

[0050] Specifically, in practical work, the diffusion learning model can be referenced. Figure 5 As shown, this process considers various factors such as different access points, power levels, and access times, learns scene features in the sample library, and generates random scenes that are not manually constructed.

[0051] The diffusion process in the power distribution network includes: for the original data of characteristic indicators in the scenario, such as voltage U0~q(U0) and current I0~q(I0), a total of T diffusion steps are included, each step being a diffusion process based on the data U0 obtained in the previous step. t-1 I t-1 Add Gaussian noise as follows:

[0052]

[0053]

[0054] β t The variance used in each step is between 0 and 1.

[0055] For diffusion models, later steps typically use larger variances, i.e., satisfying β1 < β2 < ... < β t If the diffusion step number T is large enough, then the final U obtained will be... t I t This completely loses the original data of the scene's feature indicators, turning it into random noise. This is because each step of the diffusion process generates a noisy data U. t I t :

[0056]

[0057]

[0058] The reverse process involves generating a scenario based on characteristic indicator data from the distribution network scenario:

[0059] If we know the true distribution of the characteristic index data at each step of the reverse process, such as q(U) t-1 |U t ), q(I t-1 |I t ), from a random noise U t ~N(0,I),I t Starting from ~N(0, I), gradually removing noise will generate a real sample, which is the process of generating data. Then, based on the scene data in the sample library, the generated data is combined, which is the process of generating a scene.

[0060] Estimate the distribution q(U) t-1 |U t ), q(I t-1 |I tThis requires the entire training sample, using feature value data from a sample library built based on typical and extreme scenarios, and then using a neural network to estimate these distributions. Here, the reverse process is also defined as a Markov chain, except that it consists of a series of Gaussian distributions parameterized by a neural network:

[0061]

[0062]

[0063] p θ (U t-1 |U t )=N(U t-1 μ θ (U t ,t),∑ θ (U t ,t))

[0064] P θ (I t-1 |I t )=N(I t-1 μ θ (I t ,t),∑ θ (I t ,t))

[0065] Here p(U) T )=N(U t ;0,I),p(I) T )=N(I t ;0,I), while p θ (U t-1 |U t ), p θ (I t-1 |I t The distributions are parameterized Gaussian distributions, and their mean and variance are determined by the trained network μ. θ (I t ,t)μ θ (I t ,t) and ∑ θ The diffusion model aims to obtain these trained networks, considering various factors such as different access points, power levels, and access times, and learn scene features from the sample database. Based on the longitudinal historical datasets constructed from typical and extreme scenarios, horizontally, based on the daily longitudinal historical datasets and probabilities of occurrence of different typical and extreme scenarios, non-manually constructed random scenarios are generated.

[0066] In one embodiment of this application, the method further includes: analyzing the impact data of the random target scenario on photovoltaic grid connection based on the operating characteristics of the typical scenario and the extreme scenario; and obtaining the evaluation result of the random target scenario based on the impact data.

[0067] To facilitate a clearer understanding of the specific application methods and processes of the above embodiments provided in this application, please refer to the following: Figure 6 As shown, the above embodiments are described in general. Those skilled in the art will understand that these embodiments are only for the purpose of understanding the feasible process of each step of this application and do not limit it in any way.

[0068] like Figure 6 As shown, the method for generating scenarios with a high proportion of photovoltaic power grid integration provided in this application may include:

[0069] S601 analyzes the impact of weather and other environmental factors on photovoltaic power generation and constructs a photovoltaic grid-connected characteristic model.

[0070] Based on the photovoltaic grid connection characteristic model, S602 constructs typical and extreme scenarios of high-proportion photovoltaic access to the distribution network to form a sample library.

[0071] Specifically, this includes: considering different photovoltaic (PV) power levels, including low, medium, and high, simulating PV system integration at different locations, taking into account regional differences in solar radiation and grid load distribution, and considering the integration time of PV systems, including integration under different seasons and weather conditions. The simulation system is used to construct typical scenarios of high-proportion PV integration into the distribution network, forming a sample. These typical scenarios also consider different grid topologies, including radial and ring topologies, to simulate PV system integration under different grid configurations. In different typical scenarios, the PV output within a day is simulated to construct a longitudinal historical dataset, recording data including voltage and current fluctuations, frequency fluctuations, and power magnitude.

[0072] The simulation system considers extreme weather conditions, such as extreme high and low temperatures and storms, to simulate its operation under extreme weather conditions. It also simulates the system's operation under extreme sunlight conditions (e.g., sunny days) and cloudy days to account for the photovoltaic system's performance under strong and insufficient sunlight. Furthermore, it considers transient and unconventional photovoltaic power variations, such as drastic power fluctuations caused by rapidly moving clouds. The simulation system is used to construct extreme scenarios with a high proportion of photovoltaic power integrated into the distribution network, forming a sample. In different extreme scenarios, the system simulates the photovoltaic output within a day under various extreme weather conditions, constructing a longitudinal historical dataset that records data including voltage and current fluctuations, frequency fluctuations, and power magnitude.

[0073] The S603 uses a diffusion learning model, considering various factors such as different access points, power levels, and access times, to learn scene features from a sample database and generate random scenes that are not manually constructed. For details, please refer to... Figure 7 As shown, given the historical datasets of relevant typical and extreme scenarios, characteristic indicators such as voltage, current, frequency, and power are extracted for different scenarios based on different access points, power levels, and access times. For each characteristic indicator, a Markov chain is used to generate scenarios horizontally. These generated scenarios are then combined to obtain non-manually constructed random scenarios that conform to each characteristic indicator, simulating photovoltaic power output within a day and recording data such as voltage and current fluctuations, frequency fluctuations, and power magnitude vertically. The principle and application of the diffusion model have been detailed in the preceding embodiments and will not be elaborated upon here.

[0074] Based on the operating characteristics of typical and extreme scenarios, S604 considers the potential impact of new scenarios on power grid performance, reliability, and system stability, and establishes a comprehensive evaluation system for newly generated scenarios.

[0075] One approach involves using a simulation system to generate typical and random scenarios, then using diffusion learning to generate new scenarios. A comprehensive evaluation system for these newly generated scenarios can be constructed based on this learning process. Figure 8 As shown, the newly generated scene comprehensive evaluation system may include:

[0076] Data preprocessing module 801: Preprocesses the scene data generated from the simulation to ensure data consistency and usability. This includes data cleaning, format conversion, and noise reduction.

[0077] Feature extraction and selection module 802: used to extract key features from the generated scene data and select features that are significant for the comprehensive evaluation of the scene.

[0078] Module 803, the comprehensive scenario evaluation module, comprehensively considers multiple evaluation indicators, including the scenario's rationality, completeness, and representativeness. Weights or priorities are used to ensure that each indicator is appropriately considered.

[0079] Performance Analysis Module 804: Performs in-depth analysis of the power system performance of the generated scenario, including voltage stability and power balance. This helps determine the potential impact of the generated scenario on the power grid.

[0080] This application also provides a scenario generation device for high-proportion photovoltaic (PV) grid connection. The device includes a data extraction module, a sample generation module, and a scenario generation module. The data extraction module extracts application scenario difference data from PV grid-connected data based on the impact of weather and environmental parameters on PV power generation. The sample generation module constructs typical and extreme scenarios for PV grid connection using the application scenario difference data, and generates a sample library based on these scenarios. The scenario generation module generates non-manually constructed random target scenarios based on the probability distribution of different typical and extreme scenarios using a diffusion model. The scenario generation module further includes a generation unit, which constructs a longitudinal historical dataset based on the typical and extreme scenarios; extracts feature indicators for corresponding scenarios based on different access points, power levels, and access times in the typical and extreme scenarios; generates scenario data using a Markov chain based on the probability distribution of the longitudinal historical dataset with a preset period for the feature indicators; and constructs random target scenarios by combining the scenario data. The specific implementation logic and operation flow of each module have been described in detail in the foregoing embodiments and will not be elaborated further here.

[0081] The beneficial technical effects of this application are as follows: it realizes the intelligent generation, learning, and comprehensive evaluation of various scenarios of high-proportion photovoltaic (PV) grid integration into distribution networks; this automated process provides a wider range of more realistic scenario samples for simulation research, which helps to deepen the understanding of the performance of PV systems in actual operation and provides more targeted data support for power system planning and operation. Simultaneously, based on scenario models in the sample library, it simulates and generates scenarios of high-proportion PV grid integration under different conditions, especially the operation of PV systems under extreme conditions, better simulating and evaluating the performance of PV systems, avoiding the situation of inappropriate model selection, and achieving high accuracy.

[0082] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method.

[0083] This application also provides a computer-readable storage medium storing a computer program that performs the above-described methods.

[0084] This application also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0085] like Figure 9As shown, the electronic device 600 may also include: a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily need to include these components. Figure 9 All components shown; in addition, the electronic device 600 may also include Figure 9 For components not shown, please refer to existing technologies.

[0086] like Figure 9 As shown, the central processing unit 100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device. The central processing unit 100 receives inputs and controls the operation of various components of the electronic device 600.

[0087] The memory 140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 100 may execute the program stored in the memory 140 to perform information storage or processing, etc.

[0088] Input unit 120 provides input to central processing unit 100. Input unit 120 may be, for example, a keypad or touch input device. Power supply 170 provides power to electronic device 600. Display 160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0089] The memory 140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 140 can also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application / function storage unit 142 for storing application programs and function programs or processes for executing the operation of the electronic device 600 via the central processing unit 100.

[0090] The memory 140 may also include a data storage unit (data 143) for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit (driver 144) of the memory 140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0091] The communication module 110 is a transmitter / receiver 110 that transmits and receives signals via antenna 111. The communication module (transmitter / receiver) 110 is coupled to the central processing unit 100 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0092] Based on different communication technologies, multiple communication modules 110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132, thereby enabling typical telecommunications functions. The audio processor 130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 130 is coupled to a central processing unit 100, enabling on-device recording via the microphone 132 and on-device playback of stored audio via the speaker 131.

[0093] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0094] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0095] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0096] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0097] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for generating scenarios with a high proportion of photovoltaic power grid integration, characterized in that, The method includes: Based on the impact of weather and environmental parameters on photovoltaic power generation, data on differences in application scenarios are extracted from photovoltaic grid-connected data. Typical and extreme scenarios for photovoltaic grid connection are constructed using the application scenario difference data, and a sample library is generated based on the typical and extreme scenarios. Based on the sample library, a non-manually constructed random target scene is generated using a diffusion model based on the probability distribution of occurrence of different typical and extreme scenarios; Based on the aforementioned sample library, a non-manually constructed random target scenario is generated using a diffusion model based on the probability distribution of occurrence of different typical and extreme scenarios. This includes: A longitudinal historical dataset was constructed based on typical and extreme scenarios; By analyzing the probability distribution of occurrence of longitudinal historical datasets with preset periods for different typical and extreme scenarios using the diffusion model, non-manually constructed random target scenarios can be obtained.

2. The method for generating scenarios with a high proportion of photovoltaic power grid integration according to claim 1, characterized in that, Based on the impact of weather and environmental parameters on photovoltaic power generation, the application scenario differences data extracted from photovoltaic grid-connected data include: A photovoltaic grid-connection characteristic model is constructed based on the impact of weather and environmental parameters on photovoltaic power generation. The application scenario difference data in the photovoltaic grid connection data are extracted using the photovoltaic grid connection characteristic model.

3. The method for generating scenarios with a high proportion of photovoltaic power grid integration according to claim 2, characterized in that, Typical scenarios for photovoltaic grid connection were constructed using the application scenario difference data, including: Based on the photovoltaic grid connection characteristic model, a simulation system is used to construct typical scenarios of photovoltaic grid connection, including different photovoltaic power, photovoltaic system access at different locations, differences in solar radiation and grid load distribution in different regions, and photovoltaic system access time.

4. The method for generating scenarios with a high proportion of photovoltaic power grid integration according to claim 2, characterized in that, The extreme scenarios for photovoltaic grid connection constructed using the application scenario difference data include: Based on the photovoltaic system's operation under extreme weather conditions and the sudden change data of photovoltaic power in the photovoltaic grid-connected characteristic model, an extreme scenario of photovoltaic access to the distribution network is constructed using a simulation system.

5. The method for generating scenarios with a high proportion of photovoltaic power grid integration according to claim 1, characterized in that, By analyzing the occurrence probability distribution of longitudinal historical datasets with preset periods for different typical and extreme scenarios using the diffusion model, non-manually constructed random target scenarios are obtained, including: Based on the different access points, power levels, and access times in the typical and extreme scenarios, feature indicators for the corresponding scenarios are extracted. Based on the probability distribution of the occurrence of the longitudinal historical dataset with the preset period of the feature indicators, scene data is generated using Markov chains, and random target scenes are constructed by combining the scene data.

6. The method for generating scenarios with a high proportion of photovoltaic power grid integration according to claim 1, characterized in that, Based on the impact of weather and environmental parameters on photovoltaic power generation, the application scenario differences data extracted from photovoltaic grid-connected data include: Based on the impact of weather and environmental parameters on photovoltaic power generation, application scenario difference data is extracted from historical operation data of photovoltaic grid connection.

7. The method for generating scenarios with a high proportion of photovoltaic power grid integration according to claim 1, characterized in that, The method further includes: Based on the operational characteristics of the typical and extreme scenarios, the impact data of the random target scenario on photovoltaic grid connection are analyzed. The evaluation results of the random target scenario are obtained based on the impact data.

8. A scenario generation device for high-proportion photovoltaic grid integration, characterized in that, The device includes: a data extraction module, a sample generation module, and a scene generation module; The data extraction module is used to extract application scenario difference data from photovoltaic grid-connected data based on the impact of weather and environmental parameters on photovoltaic power generation. The sample generation module is used to construct typical and extreme scenarios of photovoltaic grid connection through the application scenario difference data, and generate a sample library based on the typical and extreme scenarios. The scene generation module is used to generate non-manually constructed random target scenes based on the sample library and the probability distribution of the occurrence of different typical and extreme scenes using a diffusion model. The scene generation module further includes a generation unit, which is used to construct a longitudinal historical dataset based on typical and extreme scenarios; extract feature indicators of the corresponding scenarios based on different access points, power levels and access times in the typical and extreme scenarios; generate scene data using a Markov chain based on the occurrence probability distribution of the longitudinal historical dataset with a preset period of the feature indicators; and construct random target scenarios by combining the scene data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that enables a computer to execute the method of any one of claims 1 to 7.

11. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 7.

Images