Method and device for determining output power of new energy equipment, and electronic device

Abstract

The application discloses a new energy equipment output power determination method and device and electronic equipment. The method comprises the following steps: receiving a power determination request; in response to the power determination request, determining the influence parameter value of the influence parameter item corresponding to the target new energy equipment according to the equipment identifier; determining the target output scene in a plurality of predetermined output scenes according to the influence parameter value; and determining the target output power of the target new energy equipment according to the target output scene. The application solves the technical problem that the model constructed in the related art cannot reflect the new energy output characteristics, and the prediction of the new energy output power is inaccurate.

Description

Technical Field

[0001] This invention relates to the field of data processing, and more specifically, to a method, apparatus, and electronic device for determining the output power of a new energy device. Background Technology

[0002] Determining the output power of renewable energy equipment is crucial for optimizing energy allocation, ensuring power supply and demand balance, and improving energy efficiency. Currently, methods such as historical data backtesting, probabilistic statistical analysis, and time series forecasting are mainly used to generate renewable energy output scenarios to determine the output power of renewable energy equipment. However, the models constructed using this method cannot reflect the characteristics of renewable energy output, resulting in technical problems with inaccurate predictions of renewable energy output power.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, and electronic device for determining the output power of new energy equipment, in order to at least solve the technical problem in related technologies that the constructed models cannot reflect the power output characteristics of new energy and the prediction of the output power of new energy is inaccurate.

[0005] According to one aspect of the present invention, a method for determining the output power of a new energy device is provided, comprising: receiving a power determination request, wherein the power determination request is used to determine the output power of a target energy device, and the power determination request carries a device identifier of the target energy device; responding to the power determination request, determining an influence parameter value of an influence parameter item corresponding to the target energy device based on the device identifier, wherein the influence parameter item is a parameter item whose influence index on the output power of the target energy device is greater than a predetermined threshold; determining a target output scenario among a plurality of predetermined output scenarios based on the influence parameter value, wherein the plurality of predetermined output scenarios are determined based on a plurality of predetermined parameter values, the predetermined parameter values ​​are determined based on target distribution data corresponding to the influence parameter item, and the target distribution data are determined based on historical parameter values ​​corresponding to the influence parameter item; and determining the target output power of the target energy device based on the target output scenario.

[0006] Optionally, before determining the target output scenario among multiple predetermined output scenarios based on the influencing parameter values, the method further includes: obtaining historical parameter values ​​corresponding to the influencing parameter item at multiple historical time points; determining first distribution data based on the variance values ​​corresponding to the multiple historical parameter values, the first parameter average value corresponding to the multiple historical parameter values, and the multiple historical parameter values, wherein the first distribution data is used to determine the parameter value fluctuation range of the influencing parameter item; determining second distribution data based on the first parameter average value corresponding to the multiple historical parameter values, wherein the second distribution data is used to determine the average parameter value of the influencing parameter item; determining target distribution data corresponding to the influencing parameter item based on the first distribution data and the second distribution data; determining multiple predetermined parameter values ​​of the influencing parameter item within a predetermined time period based on the target distribution data; and determining the multiple predetermined output scenarios based on the multiple predetermined parameter values.

[0007] Optionally, determining the plurality of predetermined output scenarios based on the plurality of predetermined parameter values ​​includes: determining the initial output scenarios corresponding to the plurality of predetermined parameter values ​​respectively; determining the plurality of first clustering spaces based on the plurality of initial output scenarios, wherein a first distance between the plurality of first output scenarios corresponding to the first clustering spaces is less than a first threshold; determining the distances between the plurality of first cluster centers and the plurality of first remaining scenarios respectively, to obtain the plurality of second distances, wherein the first remaining scenarios are the remaining output scenarios among the plurality of initial output scenarios, excluding the plurality of first clustering spaces each including the plurality of first processing scenarios, and the plurality of first cluster centers are... The plurality of first cluster spaces are distributed with corresponding cluster centers; based on the plurality of second distances, N clustering operations are performed on the plurality of first cluster spaces and the plurality of first remaining scenarios until a plurality of Nth cluster spaces corresponding to the Nth clustering operation are obtained, wherein the distance change value of the Nth cluster center corresponding to the Nth cluster space is less than the second threshold, and the distance change value is the distance difference between the corresponding Nth cluster center and the corresponding N-1th cluster center obtained by the N-1th clustering operation, where N is a positive integer greater than 1; based on the plurality of Nth cluster spaces and the plurality of predetermined parameter values, the plurality of predetermined output scenarios are determined.

[0008] Optionally, based on the plurality of second distances, N clustering operations are performed on the plurality of first clustering spaces and the plurality of first remaining scenarios until a plurality of Nth clustering spaces corresponding to the Nth clustering operation are obtained, including: determining the target output scenarios corresponding to the plurality of Mth clustering spaces obtained by the Mth clustering operation, wherein the target output scenario is the other output scenario among the plurality of Mth output scenarios included in the corresponding Mth clustering space, excluding the output scenario corresponding to the Mth cluster center, where M is a positive integer greater than 1 and less than N; determining the sum of first distances corresponding to the plurality of target output scenarios, wherein the corresponding sum of first distances is the sum of the distances between the plurality of Mth output scenarios included in the corresponding Mth clustering space and the corresponding target output scenario; and determining the first difference corresponding to the plurality of target output scenarios. The first difference is the difference between the first distance sum and the second distance sum, where the second distance sum is the sum of the distances between the multiple Mth output scenarios included in the Mth cluster space and the corresponding Mth cluster center. When the first difference is less than the third threshold, the corresponding target output scenario is determined as the cluster center of the corresponding Mth cluster space, and the corresponding updated cluster center is obtained. Based on the third distance between the multiple second remaining scenarios and the corresponding updated cluster center, clustering operations are performed on the multiple Mth cluster spaces and the multiple second remaining scenarios until multiple Nth cluster spaces corresponding to the Nth clustering operation are obtained. The second remaining scenarios are the remaining output scenarios among the multiple initial output scenarios, excluding the multiple Mth processing scenarios included in the multiple Mth cluster spaces.

[0009] Optionally, determining the plurality of predetermined output scenarios based on the plurality of Nth cluster spaces and the plurality of predetermined parameter values ​​includes: determining a first predetermined scenario corresponding to each of the plurality of Nth cluster spaces, wherein the corresponding first predetermined scenario is an output scenario in which the frequency of occurrence of the target energy device is greater than a predetermined threshold among the plurality of output scenarios existing within the predetermined time; determining a target parameter value based on the plurality of predetermined parameter values, wherein a second difference corresponding to the target parameter value is greater than a fourth threshold, the second difference being the difference between the target parameter value and a second parameter average, the second parameter average being the parameter average corresponding to the plurality of predetermined parameter values; determining a second predetermined scenario corresponding to the target parameter value; and determining the plurality of predetermined output scenarios based on the plurality of first predetermined scenarios and second predetermined scenarios.

[0010] Optionally, determining multiple predetermined parameter values ​​for the influencing parameter item within a predetermined time period based on the target distribution data includes: determining multiple initial parameter values ​​for the influencing parameter item within the predetermined time period based on the target distribution data; determining an environmental correction coefficient for the influencing parameter item within the predetermined time period; and determining the multiple predetermined parameter values ​​based on the environmental correction coefficient and the multiple initial parameter values.

[0011] Optionally, after determining the target output power of the target energy device based on the target output scenario, the method further includes: determining the power loss coefficient corresponding to the target energy device; and determining the actual output power corresponding to the target energy device based on the target output power and the power loss coefficient.

[0012] According to one aspect of the present invention, an apparatus for determining the output power of a new energy device is provided, comprising: a receiving module, configured to receive a power determination request, wherein the power determination request is used to determine the output power of a target energy device, and the power determination request carries a device identifier of the target energy device; a responding module, configured to, in response to the power determination request, determine an influence parameter value of an influence parameter item corresponding to the target energy device based on the device identifier, wherein the influence parameter item is a parameter item whose influence index on the output power of the target energy device is greater than a predetermined threshold; a first determining module, configured to determine a target output scenario among multiple predetermined output scenarios based on the influence parameter value, wherein the multiple predetermined output scenarios are determined based on multiple predetermined parameter values, the predetermined parameter values ​​are determined based on target distribution data corresponding to the influence parameter item, and the target distribution data is determined based on historical parameter values ​​corresponding to the influence parameter item; and a second determining module, configured to determine the target output power of the target energy device based on the target output scenario.

[0013] According to one aspect of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement any of the above-described methods for determining the output power of a new energy device.

[0014] According to one aspect of the present invention, a computer-readable storage medium is provided, which, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the method for determining the output power of a new energy device as described above.

[0015] In this embodiment of the invention, a power determination request is received, wherein the power determination request is used to determine the output power of the target energy device, and the power determination request carries a device identifier of the target energy device; in response to the power determination request, based on the device identifier, the influence parameter value of the influence parameter item corresponding to the target energy device is determined, wherein the influence parameter item is a parameter item whose influence index on the output power of the target energy device is greater than a predetermined threshold; based on the influence parameter value, a target output scenario is determined among multiple predetermined output scenarios, wherein the multiple predetermined output scenarios are determined based on multiple predetermined parameter values, the predetermined parameter values ​​are determined based on the target distribution data corresponding to the influence parameter item, and the target distribution data is determined based on the historical parameter values ​​corresponding to the influence parameter item; The method of determining the target output power of a target energy device based on the target output scenario achieves the goal of determining the target output power of the target energy device based on the target output scenario by identifying the target output scenario among multiple predetermined output scenarios based on the influencing parameter values. Since the influencing parameter is a parameter that can affect the output power of the device, and the predetermined output scenario is a simulated output scenario of the target device under predetermined influencing parameter values, it can accurately reflect the output power of the target device under those parameter values. Therefore, by obtaining the target output scenario corresponding to the influencing parameter values, an accurate output power can be determined, thereby solving the technical problem in related technologies where the constructed model cannot reflect the characteristics of new energy output and the prediction of new energy output power is inaccurate. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a method for determining the output power of new energy equipment according to an embodiment of the present invention;

[0018] Figure 2 This is a flowchart of a new energy power output scenario generation method provided by an optional embodiment of the present invention;

[0019] Figure 3 This is a flowchart of a predetermined output scenario generation method provided by an optional embodiment of the present invention;

[0020] Figure 4 This is a flowchart of the clustering method provided by an optional embodiment of the present invention;

[0021] Figure 5 This is a structural block diagram of a device for determining the output power of new energy equipment according to an embodiment of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] Example 1

[0025] According to an embodiment of the present invention, an embodiment of a method for determining the output power of a new energy device is provided. It should be noted that 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. Furthermore, 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.

[0026] Figure 1 This is a flowchart of a method for determining the output power of new energy equipment according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0027] Step S102: Receive a power determination request, wherein the power determination request is used to determine the output power of the target energy device, and the power determination request carries the device identifier of the target energy device.

[0028] In step S102 of this application, a power determination request is received.

[0029] This involves power determination requests, which are instructions used to determine the expected output power of energy equipment.

[0030] This involves target energy equipment, which refers to new energy production or conversion devices whose expected output power is being queried, such as wind turbines and solar photovoltaic panels.

[0031] This involves device identification, which refers to a unique identifier or tag for each energy device. It enables the precise location and differentiation of different devices within a system composed of multiple similar devices. Examples include device serial numbers, media access control addresses, or any other information that can uniquely identify a device.

[0032] In this step, a power determination request is received to determine the output power of the target energy device. The power determination request contains the device identifier of the target energy device. Receiving the power determination request is a fundamental step in determining the output power of the target device. It helps to quickly identify equipment failures or performance degradation, optimize the device's operating status, reduce energy consumption, and improve energy utilization efficiency.

[0033] Step S104: In response to the power determination request, based on the device identifier, determine the influence parameter value of the influence parameter item corresponding to the target energy device, wherein the influence parameter item is the parameter item whose influence index on the output power of the target energy device is greater than a predetermined threshold.

[0034] In step S104 of this application, the influence parameter value of the influence parameter item corresponding to the target energy equipment is determined.

[0035] This involves influencing parameters, which refer to parameters that significantly affect the output power of energy equipment, such as wind speed, light intensity, temperature, and humidity. In the field of new energy, weather conditions and equipment status are key factors affecting these parameters.

[0036] This involves influencing parameter values, which refer to the specific values ​​of the influencing parameters, such as wind speed, light intensity, and temperature.

[0037] This involves the impact index, which is a quantitative indicator that measures the degree of influence of a parameter on the output power of a target energy device.

[0038] This involves a predetermined threshold, which refers to a pre-set standard value used to filter out parameters that have a significant impact on the output power of the target device.

[0039] In this step, when a power determination request for a target energy device is received, the device identifier is used to identify which device is the target energy device. Further analysis is conducted to determine which parameters have a significant impact on the output power of the device, thus identifying the influencing parameters. This process is accomplished by filtering out parameters whose influence index is greater than a predetermined threshold, thereby ensuring that the system only focuses on those parameters that truly have a significant impact on the device performance.

[0040] This step involves setting a predetermined threshold to filter out key influencing parameters, which improves the accuracy of the subsequently determined output power. At the same time, setting a predetermined threshold to filter out key influencing parameters helps simplify the power prediction model, reduce the demand for computing resources, and improve analysis efficiency.

[0041] Step S106: Based on the influence parameter values, determine the target output scenario among multiple predetermined output scenarios. The multiple predetermined output scenarios are determined based on multiple predetermined parameter values. The predetermined parameter values ​​are determined based on the target distribution data corresponding to the influence parameter items. The target distribution data are determined based on the historical parameter values ​​corresponding to the influence parameter items.

[0042] In step S106 provided in this application, a target output scenario is determined among multiple predetermined output scenarios.

[0043] This involves predetermined output scenarios, which refer to possible scenarios for renewable energy power generation simulated using a series of pre-set parameter values. Each scenario represents the renewable energy output under a specific combination of parameters.

[0044] This involves target output scenarios, which refer to one or more scenarios selected from multiple predetermined output scenarios based on the values ​​of influencing parameters.

[0045] This involves predetermined parameter values, which refer to pre-set influencing parameter values ​​used to simulate new energy power generation scenarios.

[0046] This involves target distribution data, which refers to data derived from historical parameter value analysis, representing the probability distribution or time series characteristics of influencing parameters (such as wind speed and light intensity). Target distribution data is used to guide the setting of predetermined parameter values, ensuring that the generated power output scenario reflects the statistical characteristics of new energy power output in the real world.

[0047] This involves historical parameter values, which refer to various parameters that have been recorded in the past and affect the output of new energy sources, such as wind speed data and solar radiation intensity over the past few years. Historical parameter values ​​are a key data source for analyzing and estimating the characteristics of new energy output.

[0048] In this step, a statistical distribution model (target distribution data) of key parameters affecting renewable energy power generation (such as wind speed and solar irradiance) is first constructed based on historical data (historical parameter values). Next, based on this distribution model, a series of possible renewable energy output scenarios (predicted output scenarios) are generated. Finally, among these scenarios, using the set influencing parameter values, one or more output scenarios that best meet expectations or have specific significance are selected as the target output scenarios.

[0049] Step S108: Determine the target output power of the target energy equipment based on the target output scenario.

[0050] In step S108 provided in this application, the target output power of the target energy device is determined.

[0051] This involves the target output power, which refers to the expected power output value of the target energy equipment under the target output scenario corresponding to the influencing parameter values.

[0052] Through the above steps S102-S108, a power determination request can be received, wherein the power determination request is used to determine the output power of the target energy device, and the power determination request carries the device identifier of the target energy device; in response to the power determination request, based on the device identifier, the influence parameter value of the influence parameter item corresponding to the target energy device is determined, wherein the influence parameter item is a parameter item whose influence index on the output power of the target energy device is greater than a predetermined threshold; based on the influence parameter value, the target output scenario is determined among multiple predetermined output scenarios, wherein the multiple predetermined output scenarios are determined based on multiple predetermined parameter values, the predetermined parameter values ​​are determined based on the target distribution data corresponding to the influence parameter item, and the target distribution data are determined based on the historical parameter values ​​corresponding to the influence parameter item. The method of determining the target output power of a target energy device based on the target output scenario is achieved by identifying the target output scenario among multiple predetermined output scenarios based on the influence parameter values. Since the influence parameter is a parameter that can affect the output power of the device, and the predetermined output scenario is a simulated output scenario of the target device under the predetermined influence parameter values, it can accurately reflect the output power of the target device under those parameter values. Therefore, by obtaining the target output scenario corresponding to the influence parameter values, an accurate output power can be determined, thereby solving the technical problem in related technologies where the constructed model cannot reflect the characteristics of new energy output and the prediction of new energy output power is inaccurate.

[0053] As an optional embodiment, before determining the target output scenario among multiple predetermined output scenarios based on the influencing parameter values, the method further includes: obtaining historical parameter values ​​corresponding to the influencing parameter item at multiple historical time points; determining first distribution data based on the variance values ​​corresponding to the multiple historical parameter values, the first parameter average value corresponding to the multiple historical parameter values, and the multiple historical parameter values, wherein the first distribution data is used to determine the fluctuation range of the parameter value of the influencing parameter item; determining second distribution data based on the first parameter average value corresponding to the multiple historical parameter values, wherein the second distribution data is used to determine the average parameter value of the influencing parameter item; determining target distribution data corresponding to the influencing parameter item based on the first distribution data and the second distribution data; determining multiple predetermined parameter values ​​of the influencing parameter item within a predetermined time period based on the target distribution data; and determining multiple predetermined output scenarios based on the multiple predetermined parameter values.

[0054] In this embodiment, the specific steps for determining multiple predetermined output scenarios are described.

[0055] This involves the average value of the first parameter, which is the arithmetic mean of all historical parameter values ​​and is used to reflect the average level of the parameter in historical data.

[0056] This involves first-distribution data, which refers to data used to describe the fluctuation range of the influencing parameters, such as the linear correlation coefficient (autocorrelation function coefficient) between the time series and the parameter values ​​corresponding to the influencing parameter items.

[0057] This involves secondary distribution data, which refers to data used to describe the average parameter value that affects the parameter, such as the coefficient of the probability density function.

[0058] This step begins by collecting and analyzing historical data on key parameters affecting the output power of energy equipment to obtain their fluctuation range (first distribution data) and average state (second distribution data). Then, target distribution data is established based on these analyses. This distribution data integrates historical fluctuations and average levels, reflecting the possible future states of the influencing parameters. Next, using the target distribution data, multiple possible values ​​(predicted parameter values) for these influencing parameters are predicted for a future time period. Finally, based on these predetermined parameter values, predetermined output scenarios for the target energy equipment under different conditions are determined, providing decision support for power dispatch, system planning, and market transactions. This step, through in-depth analysis of historical parameter fluctuations and average states, and the determination of target distribution data, more accurately reflects the future behavior of the influencing parameters, thereby improving the reliability of output scenario predictions.

[0059] As an optional embodiment, determining multiple predetermined output scenarios based on multiple predetermined parameter values ​​includes: determining initial output scenarios corresponding to the multiple predetermined parameter values ​​respectively; determining multiple first clustering spaces based on the multiple initial output scenarios, wherein a first distance between the multiple first output scenarios corresponding to the first clustering spaces is less than a first threshold; determining the distances between the multiple first cluster centers and the multiple first remaining scenarios respectively to obtain multiple second distances, wherein the first remaining scenarios are the remaining output scenarios among the multiple initial output scenarios, excluding the multiple first clustering spaces which each include multiple first processing scenarios, and the multiple first clustering spaces... A cluster center is the cluster center corresponding to multiple first cluster spaces. Based on multiple second distances, N clustering operations are performed on multiple first cluster spaces and multiple first remaining scenarios until multiple Nth cluster spaces corresponding to the Nth clustering operation are obtained. The distance change value of the Nth cluster center corresponding to the Nth cluster space is less than the second threshold. The distance change value is the distance difference between the corresponding Nth cluster center and the corresponding N-1th cluster center obtained by the N-1th clustering operation, where N is a positive integer greater than 1. Based on multiple Nth cluster spaces and multiple predetermined parameter values, multiple predetermined output scenarios are determined.

[0060] This embodiment describes the specific steps for determining multiple predetermined output scenarios based on multiple predetermined parameter values.

[0061] This involves the initial output scenario, which refers to the output scenario generated based on each predetermined parameter value. It reflects the output power status of the target energy device under the corresponding predetermined parameter value.

[0062] This involves the first cluster space, which refers to the spatial set formed by performing the first cluster analysis on multiple initial output scenarios.

[0063] This involves the first output scenario, which refers to the output scenario in the first cluster space.

[0064] This involves the concept of the first distance, which refers to the distance between two output scenarios used to measure the degree of difference between them, such as Euclidean distance, Mahalanobis distance, or other suitable statistical distances.

[0065] This involves a first threshold, which is a threshold index set to measure the similarity between power output scenarios. When the distance between two initial power output scenarios is less than the first threshold, they can be clustered into the first power output scenario.

[0066] This involves a second distance, which refers to the distance between the first cluster center and the first remaining scene, used to assess the degree of association between these remaining scenes and the already formed cluster space.

[0067] This involves the Nth cluster space, which refers to the cluster space obtained after N clustering operations between the initial cluster space and the first remaining scenario.

[0068] This involves the Nth cluster center, which refers to the center point of each Nth cluster space after the Nth clustering operation.

[0069] This involves a second threshold, which is a threshold index set to measure whether the clustering process has converged and whether the cluster centers are stable.

[0070] In this step, an initial power output scenario is first generated based on multiple predetermined parameter values. Then, through multiple rounds of clustering operations, similar scenarios are gradually filtered and aggregated to form a series of cluster spaces. In each clustering operation, the initial cluster space is updated, and the cluster space and cluster centers are adjusted to obtain multiple cluster spaces corresponding to the number of clustering operations, i.e., the Nth cluster space, until the convergence condition is met, i.e., the change in distance between the Nth cluster center of the Nth cluster space is less than a second threshold. Finally, these stable Nth cluster spaces and their corresponding scenarios constitute multiple predetermined power output scenarios, which can be used for power system planning and operation strategy formulation to cope with the uncertainties of new energy power generation.

[0071] This step filters out the most representative scenarios from a large initial set of scenarios, covering most of the possibilities for new energy power generation. Meanwhile, the iterative algorithm with N clustering operations ensures analytical accuracy while significantly reducing the demand for computing resources through gradual filtering and optimization, avoiding the computational complexity of processing all scenarios, and improving the execution efficiency of the algorithm.

[0072] As an optional embodiment, based on multiple second distances, N clustering operations are performed on multiple first clustering spaces and multiple first residual scenarios until multiple Nth clustering spaces corresponding to the Nth clustering operation are obtained, including: determining the target output scenarios corresponding to the multiple Mth clustering spaces obtained by the Mth clustering operation, wherein the target output scenario is the other output scenario among the multiple Mth output scenarios included in the corresponding Mth clustering space, excluding the output scenario corresponding to the Mth cluster center, where M is a positive integer greater than 1 and less than N; determining the first distance sum corresponding to the multiple target output scenarios, wherein the corresponding first distance sum is the sum of the distances between the multiple Mth output scenarios included in the corresponding Mth clustering space and the corresponding target output scenario; determining the first distance sum corresponding to the multiple target output scenarios. The difference is defined as follows: the first difference is the difference between the first distance sum and the second distance sum, where the second distance sum is the sum of the distances between the multiple Mth output scenarios included in the Mth cluster space and the corresponding Mth cluster center; when the first difference is less than the third threshold, the corresponding target output scenario is determined as the cluster center of the corresponding Mth cluster space, and the corresponding updated cluster center is obtained; based on the third distance between the multiple second remaining scenarios and the corresponding updated cluster center, clustering operations are performed on the multiple Mth cluster spaces and the multiple second remaining scenarios until multiple Nth cluster spaces corresponding to the Nth clustering operation are obtained, where the second remaining scenarios are the remaining output scenarios among the multiple initial output scenarios, excluding the multiple Mth cluster spaces which each include multiple Mth processing scenarios.

[0073] This embodiment describes the specific steps of performing N clustering operations on multiple first clustering spaces and multiple first residual scenarios based on multiple second distances until multiple Nth clustering spaces corresponding to the Nth clustering operation are obtained.

[0074] This involves the first distance sum, which refers to the sum of distances between the target output scenario and all other scenarios in the Mth cluster space, used to evaluate the representativeness of the scenario.

[0075] This involves the second distance sum, which refers to the sum of distances between the output scenario corresponding to the Mth cluster center and all other scenarios within the Mth cluster space.

[0076] This involves the first difference, which refers to the difference between the first distance sum and the second distance sum, used to determine whether the target scene is suitable as a new cluster center.

[0077] This involves a third threshold, which is a standard value set in cluster analysis to determine whether the target output scenario can replace the current cluster center.

[0078] In this step, during each clustering operation, the output scenarios excluding the Mth cluster center are examined, and the sum of their distances to the Mth cluster center and other peripheral scenarios is determined, i.e., the first distance sum. The difference between the first distance sum and the second distance sum corresponding to the Mth cluster center is compared, i.e., the first difference. If the first difference is lower than a third threshold, it means that the target output scenario better represents the characteristics of the output scenarios in the current clustering space. Therefore, the target output scenario is identified as the new cluster center, realizing the update of the cluster center. Finally, clustering continues based on the second remaining scenarios and the updated cluster center until N iterations are completed or other termination conditions are met.

[0079] This step continuously optimizes the cluster centers and reduces the distance between scenes within the cluster space, thereby improving the accuracy and representativeness of clustering and obtaining a more granular and accurate cluster space that reflects the characteristics of new energy output.

[0080] As an optional embodiment, multiple predetermined output scenarios are determined based on multiple Nth cluster spaces and multiple predetermined parameter values, including: determining a first predetermined scenario corresponding to each of the multiple Nth cluster spaces, wherein the corresponding first predetermined scenario is an output scenario whose frequency of occurrence is greater than a predetermined threshold among multiple output scenarios existing in the target energy device within a predetermined time; determining a target parameter value based on the multiple predetermined parameter values, wherein a second difference corresponding to the target parameter value is greater than a fourth threshold, the second difference being the difference between the target parameter value and the average value of the second parameter, the average value of the second parameter being the average value of the parameters corresponding to the multiple predetermined parameter values; determining a second predetermined scenario corresponding to the target parameter value; and determining multiple predetermined output scenarios based on the multiple first predetermined scenarios and the second predetermined scenarios.

[0081] This embodiment describes the specific steps for determining multiple predetermined output scenarios based on multiple first predetermined scenarios and second predetermined scenarios.

[0082] This involves the first predetermined scenario, which refers to the output scenario corresponding to the Nth cluster space, and can reflect the average output level of the target energy equipment within a predetermined time.

[0083] This involves target parameter values, which are parameter values ​​determined from multiple predetermined parameter values. These target parameter values ​​correspond to more extreme or deviating-from-average conditions, and the resulting power output scenarios may have a more significant impact on power system planning and operation.

[0084] This involves a fourth threshold, which is a pre-set threshold used to determine the parameter values ​​corresponding to extreme output scenarios.

[0085] This involves a second predetermined scenario, which refers to the output scenario associated with the target parameter value. These scenarios often correspond to atypical or extreme impact parameter values.

[0086] In this step, firstly, a first predetermined scenario is identified, where the frequency of occurrence in the Nth cluster space exceeds a predetermined threshold. These scenarios represent the most common output states of power equipment within a predetermined time period. Next, target parameter values ​​are selected from all predetermined parameter values, with a difference from the average of the second parameter values ​​exceeding a fourth threshold. These values ​​correspond to more extreme or special operating conditions, such as extremely low or high wind speeds, or strong or weak sunlight. Then, second predetermined scenarios are generated based on these target parameter values, representing possible output states of power equipment under extreme conditions. Finally, by combining the first and second predetermined scenarios, multiple predetermined output scenarios covering both normal operating conditions and extreme events are obtained. These scenarios will be used in the decision-making process for power system planning and operation to ensure the system can cope with various possible power generation conditions and maintain stability and safety.

[0087] This step identifies multiple predetermined output scenarios, including the first and second predetermined scenarios, enabling a better understanding and preparation for changes in power supply and demand under both normal and extreme conditions. This improves the adaptability and flexibility of overall operation and enhances the robustness of power system planning and operation strategies.

[0088] As an optional embodiment, determining multiple predetermined parameter values ​​for an influencing parameter item within a predetermined time period based on target distribution data includes: determining multiple initial parameter values ​​for an influencing parameter item within a predetermined time period based on target distribution data; determining an environmental correction coefficient for an influencing parameter item within a predetermined time period; and determining multiple predetermined parameter values ​​based on the environmental correction coefficient and the multiple initial parameter values.

[0089] This embodiment describes the specific steps for determining multiple predetermined parameter values ​​of an influencing parameter item within a predetermined time period based on target distribution data.

[0090] This involves initial parameter values, which refer to the set of basic numerical values ​​of the influencing parameters generated within a predetermined time period based on the target distribution data through random sampling or deterministic algorithms.

[0091] This involves the environmental correction factor, which is a quantitative indicator that takes into account the possible deviation of the actual value of the parameter due to changes in environmental factors (such as seasons and weather conditions) within a predetermined time. It is used to adjust the initial parameter value to make it closer to the actual possible state.

[0092] In this step, firstly, the target distribution data affecting the parameter terms is determined, providing a probabilistic framework for subsequent numerical generation. Next, multiple initial parameter values ​​are generated to simulate the possible changes in the parameter terms over a predetermined time period. Considering the potential impact of external environmental factors (such as seasonal variations and weather forecasts) on the parameter values, environmental correction coefficients are introduced to adjust these initial parameter values, making them more consistent with reality. Through weighted averaging of the environmental correction coefficients, multiple initial parameter values ​​are corrected, resulting in multiple predetermined parameter values. These predetermined parameter values ​​are key inputs for subsequently constructing new energy output scenarios. By combining the target distribution data and environmental correction coefficients, this step enables more accurate prediction of new energy output within a specific time period, reducing uncertainty and improving the accuracy of power system planning and operation.

[0093] As an optional embodiment, after determining the target output power of the target energy device based on the target output scenario, the method further includes: determining the power loss coefficient corresponding to the target energy device; and determining the actual output power corresponding to the target energy device based on the target output power and the power loss coefficient.

[0094] In this embodiment, the specific steps for determining the actual output power of the target energy device are described.

[0095] This involves the power loss factor, which is an indicator that reflects the efficiency loss of energy equipment during the energy conversion process.

[0096] This involves actual output power, which refers to the power that the target energy device can actually output under a given power output scenario after taking efficiency losses into account.

[0097] In this step, the efficiency loss of the target energy equipment during actual operation is considered due to various reasons, such as power transmission loss, equipment aging, maintenance conditions, and the influence of external environmental factors (such as temperature and humidity). By multiplying the target output power by the power loss coefficient, the actual output power of the energy equipment under the target output scenario can be obtained. This value is closer to the actual power output level that the equipment can achieve under specific conditions.

[0098] This step introduces a power loss factor, taking into account the actual limitations of equipment efficiency, avoiding setting unrealistic power output targets in the operation plan, and reducing the risk of system instability or equipment failure caused by equipment overload.

[0099] Based on the above embodiments and optional embodiments, an optional implementation method is provided, which is described in detail below.

[0100] In related technologies, the generation of new energy output scenarios mainly employs methods such as historical data backtracking, probabilistic statistical analysis, and time series forecasting. However, these methods typically have the following shortcomings: First, backtracking methods based solely on historical data are insufficient to depict future trends in new energy output; second, traditional probabilistic statistical methods have limitations when dealing with non-Gaussian distributed and strongly spatiotemporally correlated new energy output data; and third, time series forecasting methods rely on model parameter settings, which may be insufficient to effectively capture the complex fluctuation characteristics of new energy output. Therefore, how to construct typical-extreme scenarios that accurately reflect the characteristics of new energy output while meeting the needs of power planning and operation remains one of the current research challenges.

[0101] In view of this, an optional embodiment of the present invention provides a technology for generating typical and extreme scenarios of new energy output suitable for power planning and operation. Figure 2 This is a flowchart of a new energy output scenario generation method provided by an optional embodiment of the present invention, such as... Figure 2 As shown, the probability distribution and temporal characteristics of power output are analyzed to extract key parameters that can effectively characterize the power output variation. Then, based on the key parameters, random simulations of new energy power output are performed to generate a large-scale power output scenario set. Subsequently, cluster analysis is used to reduce the dimensionality of the scenario set and extract typical scenarios that can represent the overall distribution characteristics of new energy power output. Finally, to improve the robustness of the system, extreme scenarios with significant power output deviations from the center are selected from the scenario set to ensure that the power system planning and operation scheme has strong adaptability under various possible new energy power output conditions.

[0102] The specific steps of the method provided by the optional embodiments of the present invention are described in detail below.

[0103] S1, Receive power determination request.

[0104] S2. In response to the power determination request, determine the influence parameter value of the influence parameter item corresponding to the target energy device based on the device identifier.

[0105] S3. Based on the influence parameter values, determine the target output scenario among multiple predetermined output scenarios.

[0106] Before proceeding, it is necessary to identify multiple planned output scenarios. The steps for identifying multiple planned output scenarios are described in detail below.

[0107] A1. Determine the target distribution data corresponding to the influencing parameters: By analyzing the probability distribution and time characteristics, key parameters that can reflect the characteristics of new energy output are obtained.

[0108] The following explanation uses wind power output as an example.

[0109] The prerequisite for generating wind power output scenarios is to conduct effective operational simulations of wind power output. The volatility of wind power stems from the volatility of wind speed, and an effective way to characterize wind speed volatility is by using the autocorrelation function. The autocorrelation function is the linear correlation coefficient between a time series and its sequences at different time shifts, reflecting the magnitude of the time series volatility. Let v... t It is a time series. With σ 2 Let v be its mean and variance, respectively. t The autocorrelation function ρ(k) is:

[0110]

[0111] Where T is the period length of the time series, t is the time point, and k is the number of lag times.

[0112] The value of the autocorrelation function decays as time difference increases; the more volatile the time series, the faster the autocorrelation function decays. The autocorrelation function of wind speed can be numerically represented by a negative exponential function:

[0113] ρ(k)=e -θk θ>0, k=1,2,3

[0114] The magnitude of θ (same as the first distribution data mentioned above) determines the rate of decay of the autocorrelation function, and e is a constant with a value of 2.71828. This reflects the severity of wind speed fluctuations.

[0115] The wind power operation simulation method employs a stochastic differential equation model. This model can simulate and generate stochastic processes that follow a given marginal distribution and whose autocorrelation function decays exponentially.

[0116] To establish a stochastic process, it is necessary to satisfy the following conditions: if the probability density function f(x) is greater than zero, continuous, and has finite variance in its domain (l, u), and its expected value E(x) = μ, then the stochastic process X... t It satisfies the following stochastic differential equation:

[0117]

[0118] Where: θ≥0, W t For standard Brownian motion, v(X) t ) is a non-negative function defined on (l,u) to represent the intensity of random wind speed fluctuations, and v(x) is:

[0119]

[0120] Where y is the integral value of the function (μ-y)f(y) on the interval (l,u), and f(y) is the probability density function of y.

[0121] When the above theorem is satisfied, the following conclusion will occur:

[0122] (1) The stochastic process X is ergodic and the marginal probability density function of its state at each time step is f(x).

[0123] (2) The stochastic process X is mean-reverting and its autocorrelation function conforms to the following formula:

[0124] corr(X s+t ,X s ) = e -θt ,s,t≥0

[0125] Where s is a time series point, X s+t and X s These are the random sequence values ​​at time points s+t and s, respectively.

[0126] Using the above theorem, a stochastic process model can be established, in which the probability distribution of the state at each time step of the stochastic process follows a Weibull distribution, and its autocorrelation function follows an exponential decay.

[0127] A2. Based on the target distribution data, determine the values ​​of multiple predetermined parameters affecting the parameter items within a predetermined time period.

[0128] By generating samples of the random process at fixed time intervals as wind speed time series, and combining them with the standard power characteristic curve of the wind turbine, the reliability model, the wake effect of the wind farm, and external factors such as season and date, the operation simulation of a single wind farm can be achieved.

[0129] The commonly used two-parameter Weibull distribution for wind speed probability distribution is f W(c,k) (x) is represented as:

[0130]

[0131] Where c and k represent the scale parameter and shape parameter of the Weibull distribution, respectively (same as the second distribution data mentioned above). Assuming the wind speed conforms to a Weibull distribution with scale and shape parameters c and k, respectively, then the average wind speed μ is:

[0132]

[0133] According to the function v(X) t The initial wind speed sequence v(x) should be defined as follows:

[0134]

[0135] Where F(x) is the distribution function corresponding to f(x), and Γ(a) is the gamma function, whose expression is:

[0136] Γ(a)=∫0 +∞ y a-1 e -y dy

[0137] Γ(x,a), x≥0 is an incomplete gamma function, and its expression is:

[0138] Γ(x,a)=∫0 x y a-1 e -y dy

[0139] In summary, the power output time series of wind farms for:

[0140]

[0141] The wind speed sequence of a wind farm is not a completely random process. Due to climatic reasons, the wind speed level in the area where the wind farm is located varies in different seasons and exhibits certain patterns (e.g., lower in winter and higher in summer). Within a day, the average wind speed varies at different times of the day due to differences in the surface temperature of the area where the wind farm is located (e.g., higher at night and lower during the day). To account for the seasonal and intra-day regularity of wind speed in wind farms, the generated wind speed sequence v... t After correction, the wind speed sequence v t for:

[0142]

[0143] Where, k m (m=1,2,...,12) is the seasonal wind speed factor, k h (h=1,2,...,24) is the daily characteristic factor of wind speed.

[0144] A3. Based on multiple predetermined parameter values, determine multiple predetermined output scenarios.

[0145] Using the corrected wind speed sequence v t Considering the wind turbine output characteristic curve, the wake effect of the wind farm, and the output reliability of the wind turbines in the wind farm, the time-series output curve of the wind farm is as follows:

[0146] P t =n t (1-η)C(v t k h k m )

[0147] Where C(x) is the power output characteristic curve of the wind turbine, η is the wake effect coefficient of the wind farm, representing the power loss of the wind farm due to the wake effect, usually taken as 5% to 10%, and n t Let be the number of available wind turbines in the wind farm, a random variable representing the number of available wind turbines within the wind farm. If we assume that the turbine failures within the wind farm follow an independent exponential distribution, then for any time t, the number of available wind turbines in the wind farm follows a Bernoulli distribution, which can be obtained through random sampling.

[0148] The following can be used to determine multiple predetermined output scenarios based on the wind turbine output characteristic curve.

[0149] Scene reduction mainly involves two steps: clustering and selection. Commonly used clustering techniques include k-means, hierarchical clustering, and fuzzy clustering, the aim of which is to select the scenes with the highest probability. Furthermore, considering the intermittent and fluctuating nature of wind power, extreme cases should also be considered. For representative scene selection, current methods include choosing existing scenes and combining most solutions.

[0150] Since both statistical simulation data on wind power output and predicted load data exist, and neither of these data sets considers the spatiotemporal correlation between them, this invention employs a parallel clustering method. Figure 3 This is a flowchart of a predetermined output scenario generation method provided by an optional embodiment of the present invention, such as... Figure 3 As shown, using a typical day as a reference, the wind power output of each day in the month containing the typical day is selected as the dataset to be clustered, and these approximately 30 output samples are clustered. Since the selection of the typical day already takes into account the differences in load and wind power output between seasons, this clustering method using the month to which the typical day belongs as the interval can reflect the fluctuation of wind power output within a certain time interval, which is both economical and detailed. In addition, in order to preserve the authenticity of the simulated wind power output curve, an optional embodiment of this invention uses the simulated output curve directly as the representative scenario for clustering.

[0151] For a typical day, the program not only identifies representative scenarios for each category but also records the number of elements in each category, i.e., the number of days belonging to each scenario. Dividing the number of days in each scenario by the total number of days in the month gives the probability of each scenario occurring; this probability value will appear as a coefficient in the total cost calculation. The program categorizes all wind power output data for each month and identifies representatives for each category. The general approach is to minimize intra-category differences and maximize inter-category differences—this is the purpose of clustering. The most commonly used clustering methods are K-means and K-center methods.

[0152] The K-means algorithm is simple, efficient, and widely used. Given a set of data points and the number of clusters K, the algorithm assigns data to clusters based on the mean of the attribute of each cluster element. The algorithm flow is as follows:

[0153] (1) Randomly select K representative elements from N objects as the initial centroids;

[0154] (2) Measure the distance of the remaining elements to each cluster centroid and assign them to the cluster containing the nearest centroid;

[0155] (3) Recalculate the centroids of each cluster that have been obtained;

[0156] (4) Repeat steps 2-3 until a new centroid is reached, until the K centroids no longer change.

[0157] The K-center method is an improvement on the K-means method. It directly selects the element in the cluster that is closest to the mean as the cluster center. This method reduces the sensitivity of the results to outliers. The algorithm flow is as follows:

[0158] (1) Randomly select K representative objects from N objects as the initial center points;

[0159] (2) Measure the distance of the remaining elements to each cluster center and assign them to the cluster containing the nearest cluster center;

[0160] (3) Randomly select a non-central element Y from each cluster;

[0161] (4) Calculate the total cost S of replacing the center point X with Y;

[0162] (5) If S is negative, then Y can be used to replace X to form a new center point;

[0163] (6) Repeat steps 2 to 5 until the K center points no longer change.

[0164] Because the K-means method is sensitive to outliers and initial values, and the K-center method involves a large computational cost in calculating the cost function, this invention proposes a K-means center algorithm that combines the advantages of both algorithms in its optional implementation. Figure 4 This is a flowchart of the clustering method provided by an optional embodiment of the present invention, such as... Figure 4 As shown, on the one hand, the algorithm's calculation steps are similar to those of the K-means method, and the amount of computation is on the same order of magnitude; on the other hand, the algorithm uses real objects as representatives of each cluster after clustering, transforming the continuous into the discrete, reducing the impact of outliers and abnormal values ​​on the results, while preserving the authenticity of the representative scene.

[0165] After identifying the representative scenario, the predetermined output power is determined based on the wind power output model. The details of this step are described below.

[0166] The output power of a wind turbine generator set is determined by factors such as the on-site wind speed, the physical characteristics of the equipment, the hub height, and the surrounding terrain. Its output can generally be calculated in two ways: one is by interpolation based on the wind speed-power characteristic curve provided by the wind turbine manufacturer; the other is by extrapolation based on the relationship between the wind turbine's output power and wind speed.

[0167] 1) Calculation based on the fan speed-power characteristic curve:

[0168] The wind speed-power characteristic curve of a wind turbine describes the change in the turbine's output power under different wind speed conditions. It is usually measured by the manufacturer under standard test conditions, but appropriate adjustments need to be made based on the actual geographical environment during actual use. When the wind speed is low, the turbine basically does not work; as the wind speed increases, the turbine's output power gradually increases until it maintains the rated power; when the wind speed is too high, the turbine will shut down to protect the equipment.

[0169] 2) Calculate according to the fan speed-power relationship:

[0170] Currently, most wind turbines use asynchronous generators. Besides these, there are also doubly-fed induction generators and synchronous induction generators. However, the relationship between wind turbine output and wind speed generally follows a functional relationship. The wind turbine output power P... W The functional relationship between wind speed v and wind speed v is as follows:

[0171]

[0172] Where A, B, and C are the parameters of the wind turbine power characteristic curve, and their expressions are shown below:

[0173]

[0174] Among them, v ci v r and v co These are the wind turbine's cut-in velocity, rated velocity, and cut-out velocity, respectively. r This refers to the rated power of the wind turbine.

[0175] A wind farm consists of dozens or even hundreds of wind turbines installed in parallel at the same location. Due to the wake effect, the wind speed of wind turbines located downwind will be lower than that of wind turbines located upwind, a phenomenon known as the wake effect. Wind turbines in flat terrain are analyzed using the Jensen model, while those in complex terrain can be simulated using the Lissaman wake model. For wind farms in the planning stage, it can be assumed that all wind turbines within the same wind farm have the same wind speed and direction. The total output power of all wind turbines multiplied by a coefficient representing the wake effect gives the output power of the wind farm. Operational experience of wind farms shows that the typical value of wake-induced losses is 10%. The actual output power of the wind farm is represented by multiplying the total output power of the wind turbines by a typical coefficient of 0.9.

[0176] An optional embodiment of the present invention also provides a stochastic model for the output of a photovoltaic power plant based on the characteristics of solar radiation intensity variation:

[0177] The intensity of solar radiation received by the Earth's surface depends on the relative position of the sun and the Earth, the elevation of the Earth's surface, and the local atmospheric composition and weather conditions.

[0178] Annual Variation Characteristics of Solar Radiation Intensity. For observation points at a specific latitude, the annual variation characteristics of solar radiation intensity are described by the change in the total daily solar radiation on a horizontal surface. The total daily solar radiation primarily depends on the solar declination angle η. m Therefore, the total daily solar radiation exhibits obvious seasonal (monthly) variation characteristics. Approximately calculated using the Cooper equation, the total daily solar radiation ξ is:

[0179]

[0180] Where n represents the accumulated days, that is, the number of days in a year starting from New Year's Day, n = 1, 2...365 (366 in leap years), for example, January 5th, n = 5.

[0181] The variation in solar radiation intensity throughout the day is primarily influenced by the solar altitude. Solar altitude is characterized by the angle at which the sun is above the horizon. The expression for the solar altitude angle h is:

[0182] sinh=sinфsinσ+cosσcosфcosω

[0183] Where ф is latitude, σ is solar declination angle, and ω is solar hour angle, which is 0 at noon and changes by 15° every hour, being positive in the morning and negative in the afternoon.

[0184] The output power of a photovoltaic array depends on the solar radiation intensity, the array area, and the photoelectric conversion efficiency. For a photovoltaic array with M cell modules, the area and photoelectric conversion efficiency of each module are Am and η, respectively. m (m=1,2,…,M), then the output power P of the photovoltaic array solar for:

[0185] P solar =IAη

[0186]

[0187] Where A is the total power generation area of ​​the photovoltaic array, η is the efficiency of the photovoltaic array in converting solar energy into electrical energy, and I is the light intensity during the current operation of the system.

[0188] An optional embodiment of the present invention also provides a formula for the output power of distributed photovoltaic power generation.

[0189] The output of distributed photovoltaic (PV) systems is determined by factors such as the irradiance on the PV array surface, the physical parameters of the components, the operating mode, and the surrounding environmental conditions. When operating in maximum power point tracking mode, its output characteristics can be described by the following formula:

[0190]

[0191] Among them, I STC P represents the light intensity under standard test conditions. PV and P PV,R These represent the output power and rated power of distributed photovoltaic systems, respectively; f PV This is a derating factor for distributed photovoltaic systems, used to account for the reduction in system output caused by factors such as photovoltaic cell aging and array surface contamination.

[0192] An optional embodiment of the present invention also provides a formula for the output power of distributed natural gas (biomass) power generation.

[0193] The output power of a distributed natural gas (biomass) power generation system mainly depends on the equipment's operating strategy and the user's energy demand. The output characteristics of a distributed natural gas (biomass) power generation system can be described by a fuel consumption characteristic curve. The following equation gives the linear relationship between fuel consumption and output power of a distributed natural gas (biomass) power generation system:

[0194] F G =f0·P G,R +f1·P G

[0195] Among them, F G This indicates that the unit's output power is P. G Fuel consumption; P G,RThis represents the rated output power of the unit; f0 and f1 are both fitting coefficients for the fuel consumption characteristic curve.

[0196] S4. Determine the target output power of the target energy equipment based on the target output scenario.

[0197] The above optional implementation methods can achieve at least the following beneficial effects:

[0198] (1) It overcomes the problem that traditional new energy power output scenario generation methods do not adequately describe the power output uncertainty. It comprehensively considers the probability distribution and time characteristics of new energy power output, extracts key parameters to accurately characterize the power output fluctuation characteristics, and improves the scientificity and rationality of scenario generation.

[0199] (2) Typical scenarios are extracted through cluster analysis, and extreme scenarios that deviate significantly from the center are selected. This ensures accurate characterization of the overall characteristics of new energy output in power planning and operation, and enhances the system's adaptability to new energy fluctuations under extreme conditions.

[0200] (3) It can not only generate more accurate typical new energy output scenarios, but also identify potential extreme output situations, providing more comprehensive scenario data support for power system dispatch and optimization, which helps to improve the stability and security of the power system under the condition of high proportion of new energy access.

[0201] (4) It can be applied to the generation of power output scenarios in different regions and different types of new energy (such as wind power, photovoltaic, etc.), and has strong versatility. It can provide a flexible and applicable new energy uncertainty modeling tool for power planning and operation.

[0202] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0203] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0204] Example 2

[0205] According to an embodiment of the present invention, an apparatus for implementing the above-described method for determining the output power of new energy equipment is also provided. Figure 5 This is a structural block diagram of the device for determining the output power of new energy equipment according to an embodiment of the present invention, as shown below. Figure 5 As shown, the device includes: a receiving module 502, a response module 504, a first determining module 506, and a second determining module 508. The device will be described in detail below.

[0206] A receiving module 502 is used to receive a power determination request, wherein the power determination request is used to determine the output power of a target energy device, and the power determination request carries a device identifier of the target energy device; a response module 504, connected to the receiving module 502, is used to respond to the power determination request and, based on the device identifier, determine the influence parameter value of the influence parameter item corresponding to the target energy device, wherein the influence parameter item is a parameter item whose influence index on the output power of the target energy device is greater than a predetermined threshold; a first determining module 506, connected to the response module 504, is used to determine a target output scenario among multiple predetermined output scenarios based on the influence parameter value, wherein the multiple predetermined output scenarios are determined based on multiple predetermined parameter values, the predetermined parameter values ​​are determined based on the target distribution data corresponding to the influence parameter item, and the target distribution data is determined based on the historical parameter values ​​corresponding to the influence parameter item; a second determining module 508, connected to the first determining module 506, is used to determine the target output power of the target energy device based on the target output scenario.

[0207] It should be noted here that the above-mentioned receiving module 502, response module 504, first determining module 506 and second determining module 508 correspond to steps S102 to S108 in the method for determining the output power of new energy equipment. The multiple modules and the corresponding steps are the same in terms of implementation examples and application scenarios, but are not limited to the content disclosed in the above embodiment 1.

[0208] Example 3

[0209] According to another aspect of the present invention, an electronic device is also provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute instructions to implement the method for determining the output power of a new energy device as described above.

[0210] Example 4

[0211] According to another aspect of the present invention, a computer-readable storage medium is also provided, which, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the method for determining the output power of a new energy device as described above.

[0212] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0213] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0214] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0215] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0216] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0217] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0218] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining the output power of a new energy device, characterized in that, include: Receive a power determination request, wherein the power determination request is used to determine the output power of a target energy device, and the power determination request carries a device identifier of the target energy device; In response to the power determination request, based on the device identifier, the influence parameter value of the influence parameter item corresponding to the target energy device is determined, wherein the influence parameter item is a parameter item whose influence index on the output power of the target energy device is greater than a predetermined threshold; Based on the aforementioned influencing parameter values, a target output scenario is determined among multiple predetermined output scenarios. The multiple predetermined output scenarios are determined based on multiple predetermined parameter values, which are determined based on the target distribution data corresponding to the influencing parameter items. The target distribution data are determined based on the historical parameter values ​​corresponding to the influencing parameter items. Based on the target output scenario, the target output power of the target energy equipment is determined.

2. The method according to claim 1, characterized in that, Before determining the target output scenario among multiple predetermined output scenarios based on the influence parameter values, the method further includes: Obtain the historical parameter values ​​of the influencing parameter items at multiple historical time points; Based on the variance values ​​corresponding to multiple historical parameter values, the average value of the first parameter corresponding to the multiple historical parameter values, and the multiple historical parameter values, a first distribution data is determined, wherein the first distribution data is used to determine the fluctuation range of the parameter value of the influencing parameter item; Based on the average value of the first parameter corresponding to the plurality of historical parameter values, a second distribution data is determined, wherein the second distribution data is used to determine the average parameter value of the influencing parameter item; Based on the first distribution data and the second distribution data, determine the target distribution data corresponding to the influencing parameter item; Based on the target distribution data, determine multiple predetermined parameter values ​​for the influencing parameter item within a predetermined time period; Based on the multiple predetermined parameter values, the multiple predetermined output scenarios are determined.

3. The method according to claim 2, characterized in that, The determination of the multiple predetermined output scenarios based on the multiple predetermined parameter values ​​includes: Determine the initial output scenarios corresponding to the plurality of predetermined parameter values; Based on multiple initial output scenarios, multiple first clustering spaces are determined, wherein the first distance between the multiple first output scenarios corresponding to the first clustering space is less than a first threshold. The distances between multiple first cluster centers and multiple first remaining scenarios are determined to obtain multiple second distances. The first remaining scenarios are the remaining output scenarios among the multiple initial output scenarios, excluding the multiple first cluster spaces which each include multiple first processing scenarios. The multiple first cluster centers are the cluster centers corresponding to the distribution of the multiple first cluster spaces. Based on the plurality of second distances, N clustering operations are performed on the plurality of first clustering spaces and the plurality of first residual scenarios until a plurality of Nth clustering spaces corresponding to the Nth clustering operation are obtained. The distance change value of the Nth clustering center corresponding to the Nth clustering space is less than the second threshold. The distance change value is the distance difference between the corresponding Nth clustering center and the corresponding N-1 clustering center obtained by the N-1th clustering operation, where N is a positive integer greater than 1. Based on the plurality of Nth cluster spaces and the plurality of predetermined parameter values, the plurality of predetermined output scenarios are determined.

4. The method according to claim 3, characterized in that, The step of performing N clustering operations on the multiple first clustering spaces and the multiple first residual scenarios based on the multiple second distances, until multiple Nth clustering spaces corresponding to the Nth clustering operation are obtained, includes: Determine the target output scenarios corresponding to the multiple Mth cluster spaces obtained by the Mth clustering operation, wherein the target output scenario is the other output scenario among the multiple Mth output scenarios included in the corresponding Mth cluster space, excluding the output scenario corresponding to the Mth cluster center, and M is a positive integer greater than 1 and less than N. Determine the first distance sum corresponding to multiple target output scenarios, wherein the corresponding first distance sum is the sum of the distances between the multiple Mth output scenarios included in the corresponding Mth cluster space and the corresponding target output scenario; Determine the first difference corresponding to each of the plurality of target output scenarios, wherein the corresponding first difference is the difference between the corresponding first distance sum and the corresponding second distance sum, and the corresponding second distance sum is the sum of the distances between each of the plurality of Mth output scenarios included in the corresponding Mth cluster space and the corresponding Mth cluster center; If the first difference is less than the third threshold, the corresponding target output scenario is determined as the cluster center of the corresponding M-th cluster space, and the corresponding updated cluster center is obtained. Based on the third distance between the multiple second remaining scenarios and their corresponding updated cluster centers, clustering operations are performed on the multiple Mth cluster spaces and the multiple second remaining scenarios until multiple Nth cluster spaces corresponding to the Nth clustering operation are obtained. The second remaining scenarios are the remaining output scenarios among the multiple initial output scenarios, excluding the multiple Mth cluster spaces which each include multiple Mth processing scenarios.

5. The method according to claim 3, characterized in that, The step of determining the multiple predetermined output scenarios based on the multiple Nth cluster spaces and the multiple predetermined parameter values ​​includes: Determine a first predetermined scenario corresponding to each of the plurality of Nth cluster spaces, wherein the corresponding first predetermined scenario is an output scenario in which the frequency of occurrence of the target energy device is greater than a predetermined threshold among the plurality of output scenarios existing within the predetermined time. Based on the plurality of predetermined parameter values, a target parameter value is determined, wherein the second difference corresponding to the target parameter value is greater than a fourth threshold, the second difference is the difference between the target parameter value and the average value of the second parameter, and the average value of the second parameter is the average value of the parameters corresponding to the plurality of predetermined parameter values; Determine the second predetermined scenario corresponding to the target parameter value; Based on multiple first predetermined scenarios and second predetermined scenarios, the multiple predetermined output scenarios are determined.

6. The method according to claim 2, characterized in that, The step of determining multiple predetermined parameter values ​​for the influencing parameter item within a predetermined time period based on the target distribution data includes: Based on the target distribution data, determine multiple initial parameter values ​​for the influencing parameter item within the predetermined time period; Determine the environmental correction coefficient for the influencing parameter within the predetermined time period; The predetermined parameter values ​​are determined based on the environmental correction coefficient and the plurality of initial parameter values.

7. The method according to any one of claims 1 to 6, characterized in that, After determining the target output power of the target energy device based on the target output scenario, the method further includes: Determine the power loss coefficient corresponding to the target energy equipment; The actual output power of the target energy device is determined based on the target output power and the power loss coefficient.

8. A device for determining the output power of a new energy device, characterized in that, include: A receiving module is configured to receive a power determination request, wherein the power determination request is used to determine the output power of a target energy device, and the power determination request carries a device identifier of the target energy device; A response module is configured to respond to the power determination request and, based on the device identifier, determine the influence parameter value of the influence parameter item corresponding to the target energy device, wherein the influence parameter item is a parameter item whose influence index on the output power of the target energy device is greater than a predetermined threshold. The first determining module is used to determine a target output scenario among multiple predetermined output scenarios based on the influence parameter values, wherein the multiple predetermined output scenarios are determined based on multiple predetermined parameter values, the predetermined parameter values ​​are determined based on the target distribution data corresponding to the influence parameter items, and the target distribution data are determined based on the historical parameter values ​​corresponding to the influence parameter items. The second determining module is used to determine the target output power of the target energy device based on the target output scenario.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the method for determining the output power of the new energy equipment as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the method for determining the output power of the new energy device as described in any one of claims 1 to 7.

Images