Method for generating available adjusting capacity of light-storage-charging system and related device

Abstract

The embodiment of the invention discloses a light-storage-charging system available regulation capacity generation method and a related device. The method comprises the following steps: acquiring a plurality of preset evaluation indexes and first weights corresponding to the evaluation indexes; based on the multiple evaluation indexes, first index scores of all the subsystems are obtained through calculation; according to a preset subsystem weight, carrying out weighted calculation on the first index score of each subsystem to obtain a second index score of the light-storage-charging system; performing weighted calculation based on the first weight and the second index score to obtain a comprehensive score; determining a target evaluation index corresponding to the lowest score in the second index scores, and obtaining a prediction optimization suggestion; and according to the comprehensive score and the physical adjustment capacity of each subsystem in the light-storage-charging system, generating the available adjustment capacity of the light-storage-charging system. By the adoption of the mode, quantitative analysis is achieved, the optimization direction is given, the available adjusting capacity is generated, and the accuracy of evaluating the adjustable capacity of the combined system is improved.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and in particular to a method and related apparatus for generating the adjustable capacity of a photovoltaic-storage-charging system. Background Technology

[0002] In modern power systems, integrated photovoltaic (PV) power generation systems, energy storage systems, and charging facilities (especially charging piles with vehicle-to-grid functionality) are of great significance for improving grid flexibility and promoting the consumption of new energy sources. Accurately assessing the available regulating capacity of such combined systems is the prerequisite and foundation for achieving efficient and reliable dispatch.

[0003] Existing technologies include several methods for evaluating the performance of power systems or their sub-units. For example, an evaluation system with multiple evaluation indicators is established, and a combined weighting method is used to assign weights to each indicator, ultimately calculating a comprehensive score to quantify the overall system performance. However, applying these methods to complex combined systems like photovoltaic-storage-charging systems still has several shortcomings. First, existing evaluation methods typically analyze individual units such as photovoltaic power generation and charging loads independently, or treat the entire system as a single whole for a general evaluation. This lacks a structured evaluation model that reflects the performance differences between different subsystems (such as the photovoltaic subsystem and the charging subsystem) and their varying importance to the overall system, making it impossible to form a holistic, unified, and refined quantitative assessment of the entire combined system's regulation capacity. Second, while existing technologies propose various evaluation indicators, there is a lack of clear guidance on how to scientifically assign weights based on the differences in the importance of each indicator to the overall system performance, making it difficult for the evaluation results to accurately reflect the true performance state of the system. Finally, and most importantly, existing technologies typically stop at providing one or more abstract evaluation scores or grades, failing to effectively combine these evaluation results with the physical regulation capabilities of the system. This makes it impossible to generate a specific, usable regulation capacity value that can be directly used by the power grid dispatching system, resulting in weak engineering practicality of the evaluation results and making it difficult to bridge the "last mile" from performance evaluation to dispatching applications.

[0004] In summary, there is currently a lack of means to accurately assess the available adjustable capacity of such combined systems. Summary of the Invention

[0005] The main objective of this invention is to provide a method and related apparatus for generating the available adjustable capacity of a light-storage-charging system, which can solve the problem of the lack of means in the prior art to accurately evaluate the available adjustable capacity of such combined systems.

[0006] To achieve the above objectives, the first aspect of the present invention provides a method for generating the available adjustable capacity of a light-storage-charge system, the method comprising: Obtain multiple preset evaluation indicators and their corresponding first weights; the multiple evaluation indicators are used to measure the accuracy of power prediction for each subsystem in the optical-storage-charging system. Based on the multiple evaluation indicators, the first indicator score of each subsystem is calculated; and according to the preset subsystem weights, the first indicator scores of each subsystem are weighted to obtain the second indicator score of the optical-storage-charging system. Based on the first weight and the second index score, a weighted calculation is performed to obtain a comprehensive score, which represents the overall prediction accuracy of the optical-storage-charging system; The target evaluation index corresponding to the lowest score in the second index score is determined, and a prediction optimization suggestion is obtained. The prediction optimization suggestion is used to indicate the optimization direction of the target evaluation index as the power prediction model of the photovoltaic-storage-charging system. Based on the overall score and the physical regulation capacity of each subsystem in the optical-storage-charging system, the available regulation capacity of the optical-storage-charging system is generated.

[0007] To achieve the above objectives, a second aspect of the present invention provides an apparatus for generating adjustable capacity for a light-storage-charge system, the apparatus comprising: The acquisition module is used to acquire multiple preset evaluation indicators and the first weight corresponding to each evaluation indicator; the multiple evaluation indicators are used to measure the accuracy of power prediction of each subsystem in the optical-storage-charging system. The first calculation module is used to calculate the first indicator score of each subsystem based on the multiple evaluation indicators; and to perform a weighted calculation on the first indicator scores of each subsystem according to the preset subsystem weights to obtain the second indicator score of the optical-storage-charging system. The second calculation module is used to perform a weighted calculation based on the first weight and the second index score to obtain a comprehensive score, wherein the comprehensive score characterizes the overall prediction accuracy of the optical-storage-charging system. The direction determination module is used to determine the target evaluation index corresponding to the lowest score in the second index score, and obtain prediction optimization suggestions. The prediction optimization suggestions are used to indicate the optimization direction of the target evaluation index as the power prediction model of the photovoltaic-storage-charging system. The generation module is used to generate the available adjustable capacity of the optical-storage-charging system based on the comprehensive score and the physical adjustable capacity of each subsystem in the optical-storage-charging system.

[0008] To achieve the above objectives, a third aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps shown in the first aspect and any feasible implementation.

[0009] To achieve the above objectives, a fourth aspect of the present invention provides a computer device including a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform the steps shown in the first aspect and any feasible implementation.

[0010] The embodiments of the present invention have the following beneficial effects: This invention provides a method for generating the available adjustable capacity of a photovoltaic-storage-charging system. The method includes: acquiring a plurality of preset evaluation indicators and a first weight corresponding to each evaluation indicator; the plurality of evaluation indicators are used to measure the accuracy of power prediction for each subsystem in the photovoltaic-storage-charging system; calculating a first indicator score for each subsystem based on the plurality of evaluation indicators; and performing a weighted calculation on the first indicator scores of each subsystem according to the preset subsystem weights to obtain a second indicator score for the photovoltaic-storage-charging system; performing a weighted calculation on the first weights and the second indicator scores to obtain a comprehensive score, wherein the comprehensive score characterizes the overall prediction accuracy of the photovoltaic-storage-charging system; determining a target evaluation indicator corresponding to the lowest score in the second indicator scores to obtain a prediction optimization suggestion, wherein the prediction optimization suggestion is used to indicate the optimization direction of the power prediction model of the photovoltaic-storage-charging system using the target evaluation indicator; and generating the available adjustable capacity of the photovoltaic-storage-charging system based on the comprehensive score and the physical adjustable capacity of each subsystem in the photovoltaic-storage-charging system. Compared to existing technologies, this method employs a quantitative analysis approach, providing directions for improved and optimized indicators, which facilitates a clearer assessment of regulation capacity. Finally, this invention combines abstract assessment scores with the physical regulation capacity of each regulation unit and the system's operating mode to generate specific, directly applicable available regulation capacity values ​​for power grid dispatch. This bridges the gap between performance evaluation and engineering applications, demonstrating strong practical value. Consequently, the accuracy of assessing the available regulation capacity of such combined systems is improved. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] in: Figure 1 This is a flowchart of a method for generating the adjustable capacity of a light-storage-charging system according to an embodiment of the present invention; Figure 2This is a structural block diagram of an adjustable capacity generation device for a light-storage-charging system according to an embodiment of the present invention; Figure 3 This is a structural block diagram of a computer device in an embodiment of the present invention. Detailed Implementation

[0013] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0014] This application provides a method for generating the available adjustable capacity of a photovoltaic-storage-charging system, specifically a method based on multi-level weighted evaluation. This method can be executed by a computer program deployed in an energy management system, cloud server, or edge computing device. It interacts with physical subsystems such as photovoltaics, energy storage, and charging to achieve dynamic and quantitative evaluation and generation of the available adjustable capacity of the entire photovoltaic-storage-charging integrated system.

[0015] A typical application environment for this application may include an available adjustable capacity generation system, and photovoltaic subsystems, energy storage subsystems, and charging subsystems connected to this system. The available adjustable capacity generation system serves as the core entity for executing the method provided in this application. Its specific implementation can be a terminal or a server. The terminal can be a desktop terminal or a mobile terminal; the mobile terminal can be at least one of a mobile phone, tablet computer, or laptop computer. The server can be a standalone server or a server cluster composed of multiple servers, or it can be a functional unit integrated into an energy management system. This system can establish bidirectional communication with the inverter or data acquisition unit of the photovoltaic subsystem, the battery management system or energy conversion system of the energy storage subsystem, and the charging pile group controller or a single charging pile with vehicle-to-grid functionality of the charging subsystem via industrial Ethernet, wireless networks (such as 4G / 5G), or other communication buses. This allows it to acquire power prediction data, real-time operating data (e.g., actual power generation, charge / discharge power, battery state of charge, etc.), and rated physical parameters (e.g., rated energy storage capacity, photovoltaic installed capacity, etc.) of each subsystem.

[0016] As an optional implementation, the available adjustable capacity generation system can be internally divided into multiple logical functional modules to collaboratively complete the calculation process of this method. Specifically, it can include a score calculation module, a comprehensive evaluation module, and a capacity generation module. The score calculation module acquires data from each subsystem and calculates the index scores for each subsystem and the system-level index scores. The comprehensive evaluation module receives the calculation results from the score calculation module to calculate the final comprehensive score and identify system performance bottlenecks, thereby determining optimization directions. The capacity generation module, based on the comprehensive score output by the comprehensive evaluation module and combined with the physical capacity information acquired from each subsystem and the current operating mode, generates the final available adjustable capacity value. It can be understood that the data flow between these modules can be sequential, i.e., the output of the score calculation module serves as the input to the comprehensive evaluation module, and the output of the comprehensive evaluation module serves as the input to the capacity generation module.

[0017] Please see Figure 1 , Figure 1 This is a flowchart of a method for generating the adjustable capacity of a light-storage-charging system according to an embodiment of the present invention. The following will be combined with... Figure 1 This method will be explained.

[0018] like Figure 1 The method shown includes the following steps: 101. Obtain multiple preset evaluation indicators and their corresponding first weights; the multiple evaluation indicators are used to measure the accuracy of power prediction for each subsystem in the optical-storage-charging system; The evaluation indicators include at least one of the following: root mean square error, absolute error, average error, pass rate, and correlation coefficient.

[0019] Step 101: Perform indicator classification and weight determination. Specifically, a complete evaluation system can be obtained using the capacity generation system or pre-configured by the system administrator. This system includes multiple evaluation indicators, a first weight corresponding to each evaluation indicator, and the weight of each subsystem. The evaluation indicators are used to measure the power prediction accuracy of the photovoltaic subsystem and the charging subsystem from different dimensions. In one embodiment of this application, to comprehensively evaluate the prediction effect, a set of commonly used and representative evaluation indicators can be selected, which may include, but are not limited to: root mean square error, absolute error, average error, pass rate, and correlation coefficient. It is understood that the root mean square error and absolute error mainly measure the overall deviation between the predicted value and the actual value; the average error is used to determine the overall trend of the prediction result being too high or too low; the pass rate assesses the frequency with which the predicted value falls within the acceptable error band; and the correlation coefficient measures the similarity in shape between the predicted curve and the actual curve.

[0020] To reflect the varying importance of different evaluation indicators in the overall assessment, a corresponding primary weight needs to be assigned to each indicator. For example, if the magnitude of the deviation is considered more important than its direction, a higher weight can be assigned to the root mean square error. In this embodiment, assuming a total weight of 100, the primary weights for the five indicators can be set as follows: root mean square error 30, absolute error 20, average error 15, pass rate 20, and correlation coefficient 15.

[0021] Accordingly, subsystem weights need to be set to reflect the relative importance of the photovoltaic subsystem and the charging subsystem in the entire photovoltaic-storage-charging system, or the difference in their contribution to the system's regulation capability. This importance can be determined comprehensively based on factors such as installed capacity, power volatility, and priority in dispatching. For example, in a power station primarily powered by photovoltaics, the power volatility of the photovoltaic subsystem is a major factor affecting system stability, making its prediction accuracy correspondingly more important. In this embodiment, the weight of the photovoltaic subsystem can be set to 0.6, and the weight of the charging subsystem to 0.4.

[0022] 102. Based on the multiple evaluation indicators, calculate the first indicator score of each subsystem respectively; and according to the preset subsystem weights, perform a weighted calculation on the first indicator scores of each subsystem to obtain the second indicator score of the optical-storage-charging system. After initial configuration is complete, the system enters a periodic calculation process, for example, with a calculation cycle of 15 minutes. At the beginning of each cycle, the index scores of each subsystem can be calculated in parallel or sequentially. For example, if there are photovoltaic subsystems and charging subsystems, then step 102 should include calculating the index scores of the photovoltaic subsystem and the charging subsystem. In one feasible implementation, the step of calculating the first index score of each subsystem based on the multiple evaluation indicators includes: performing a weighted calculation based on the improvement of the current index score in the current calculation cycle compared with the historical index score in the previous calculation cycle, and the current index score in the current calculation cycle to obtain the first index score of each subsystem. The current index score is obtained by substituting the power prediction value and the actual power value in the previous calculation cycle into the algorithm of each evaluation indicator.

[0023] In other words, the scoring calculation module calculates the specific values ​​of the aforementioned five evaluation indicators (root mean square error, absolute error, etc.) for the photovoltaic subsystem and the charging subsystem respectively, based on the power prediction value and actual power value of the previous calculation cycle (e.g., the past 15 minutes).

[0024] After obtaining the specific values ​​for each indicator, they need to be converted into standardized indicator scores. The first indicator score includes the scores of the five evaluation indicators. As an optional implementation, this embodiment adopts a scoring model that combines dynamic trends and static performance. Specifically, the score of each indicator can be composed of two weighted parts: an "improvement status score" and an "indicator value score." The calculation formula can be expressed as: Subsystem indicator score = Second weight × Improvement status score + Third weight × Indicator value score. For example, the second weight can be set to 0.7 and the third weight to 0.3 to focus more on continuous performance improvement.

[0025] In one feasible implementation, the comparison improvement includes: If the current indicator score in the current calculation period is better than the historical indicator score in the previous calculation period, then the score corresponding to the improvement is the first preset score. If the current indicator score in the current calculation period is the same as the historical indicator score in the previous calculation period, then the score corresponding to the improvement in comparison is the second preset score. If the current indicator score in the current calculation period is lower than the historical indicator score in the previous calculation period, then the score corresponding to the improvement in comparison is the third preset score. Among them, the first preset score > the second preset score > the third preset score.

[0026] For example, the "improvement score" is determined based on the trend of indicator value changes, specifically by comparing the current indicator score in the current calculation period with the historical indicator score in the previous calculation period. For indicators such as root mean square error, absolute error, and the absolute value of mean error, where smaller is better, if the indicator value in the current period decreases compared to the previous period (i.e., performance improves), the "improvement score" can be assigned a higher first preset score (e.g., 100 points); if the indicator value remains basically unchanged (e.g., the rate of change is within ±2%), a medium second preset score can be assigned (e.g., 80 points); if the indicator value increases (i.e., performance declines), a lower third preset score can be assigned (e.g., 60 points). For indicators such as pass rate and correlation coefficient, where larger is better, the scoring rules are the opposite.

[0027] The "indicator value score" can be obtained by consulting a pre-defined scoring mapping table based on the magnitude of the indicator value. This table divides the possible value range of different indicators into multiple intervals and assigns a score to each interval. Taking the pass rate of photovoltaic power prediction as an example, the following settings can be made: pass rate ≥ 95% is excellent, scoring 95 points; 90% ≤ pass rate < 95% is good, scoring 85 points; 80% ≤ pass rate < 90% is qualified, scoring 70 points; and pass rate < 80% is unqualified, scoring 50 points.

[0028] Using the above method, the scoring calculation module can calculate five index scores for the photovoltaic subsystem and the charging subsystem respectively, for a total of ten scores.

[0029] After obtaining the subsystem index scores, the system index score (i.e., the second index score) can be calculated. In this step, the score calculation module uses the subsystem weights set in step 101 to perform a weighted average of the obtained subsystem index scores, thereby obtaining the five system index scores for the entire photovoltaic-storage-charging system. For example, the system root mean square error score is calculated as follows: System root mean square error score = (Root mean square error score of photovoltaic subsystem × 0.6) + (Root mean square error score of charging subsystem × 0.4). Similarly, the system absolute error score, system average error score, system pass rate score, and system correlation coefficient score are calculated. It should be noted that this step integrates the dispersed performance evaluations for individual subsystems into a system-level, multi-dimensional performance characterization. Details of the index data can be found in Table 1, which shows the index data for one photovoltaic-storage-charging system.

[0030] Table 1: Performance data of the photovoltaic-storage-charging system

[0031] In Table 1, the index weight refers to the first weight. The photovoltaic prediction index score is the first index score of the photovoltaic subsystem, and the charging prediction index score is the first index score of the charging subsystem. The weighted score is the second index score of the photovoltaic-storage-charging system.

[0032] 103. Based on the first weight and the second index score, a weighted calculation is performed to obtain a comprehensive score, which represents the overall prediction accuracy of the optical-storage-charging system; Step 103 is used to calculate the comprehensive score. The comprehensive evaluation module receives the scores of five system indicators (i.e., the second indicator scores) from the score calculation module, and uses the first weight set in step 101 to perform a weighted sum of these five system indicator scores, finally obtaining a single quantitative indicator that can characterize the overall prediction accuracy of the photovoltaic-storage-charging system—the comprehensive score S. Its calculation formula can be expressed as:

[0033] Where N is the number of evaluation indicators (5 in this example). It is the first weight of the i-th evaluation index. This is the score of the i-th system indicator (i.e., the score of the second indicator). It can be understood that by appropriately normalizing the weights and scores, the range of values ​​for the comprehensive score S can be mapped to a preset interval, such as 0 to 500.

[0034] 104. Determine the target evaluation index corresponding to the lowest score in the second index score, and obtain prediction optimization suggestions. The prediction optimization suggestions are used to indicate the optimization direction of the target evaluation index as the power prediction model of the photovoltaic-storage-charging system. Step 104: Determine the lowest-scoring indicator as the optimization direction. Simultaneously or subsequently, the comprehensive evaluation module compares the scores of the five system indicators to identify the lowest score. The evaluation indicator corresponding to this lowest score is identified as the "weak link" in the current system's predictive performance. For example, if the calculated system pass rate score is 86.438, and the scores of the other four system indicators are all higher than this value, the system can use the "pass rate" indicator as the key area for optimization in the current stage of the predictive model. This optimization direction information, as a predictive optimization suggestion, can be recorded in the system log or pushed to system maintenance personnel or algorithm engineers through the user interface, alarms, etc., thus providing a clear, data-driven basis for subsequent adjustments to model parameters, optimization of feature engineering, or replacement of the predictive algorithm, forming a technical closed loop of "evaluation-feedback-optimization".

[0035] 105. Based on the comprehensive score and the physical regulation capacity of each subsystem in the optical-storage-charging system, generate the available regulation capacity of the optical-storage-charging system.

[0036] In one feasible implementation, step 105 includes the following steps A01 to A03: A01. Based on the comprehensive score, or the preset scheduling strategy, or the real-time status of the power grid, determine the current operating mode of the photovoltaic-storage-charging system; In one feasible implementation, the operating mode includes a normal operating mode and an extreme operating mode.

[0037] A02. Based on the current operating mode and the correspondence between the preset operating mode and the adjustable capacity algorithm, determine the target adjustable capacity algorithm corresponding to the current operating mode; A03. Using the comprehensive score, the physical adjustment capacity, and the target adjustable capacity algorithm, the available adjustment capacity is obtained.

[0038] In one feasible implementation, the subsystem includes an energy storage subsystem, a photovoltaic subsystem, and a charging subsystem. Step A03 may include: if the current operating mode is a normal operating mode, then the physical regulation capacity of the energy storage subsystem in the photovoltaic-storage-charging system is corrected using the comprehensive score to obtain the available regulation capacity; if the current operating mode is an extreme operating mode, then the physical regulation capacity of the energy storage subsystem is corrected using the comprehensive score and combined with the physical regulation capacities of the photovoltaic subsystem and the charging subsystem to obtain the available regulation capacity.

[0039] Specifically, step 105 involves obtaining the physical regulation capacity and operating mode. The capacity generation module obtains the current physical regulation capacity of the energy storage subsystem through a communication interface. P ess (For example, the discharge / chargeable capacity calculated based on the current state of charge and maximum charge / discharge power) to obtain the physical regulation capacity of the photovoltaic subsystem. P pv (This usually refers to the power that can be reduced, i.e., the current generating capacity), and obtains its physical regulation capacity from the charging subsystem. P v2g (This refers to the total power of vehicles participating in the discharge from the vehicle to the grid). Simultaneously, the capacity generation module determines the current operating mode of the system. The determination of the operating mode can be based on various information, such as instructions issued by the grid dispatch center, monitoring of the grid's real-time status (e.g., frequency, voltage), preset dispatch strategies (e.g., time-of-use pricing strategies), or even the comprehensive score S calculated using this method. In this embodiment, for simplicity, two basic operating modes are defined: normal operating mode and extreme operating mode. For example, a comprehensive score threshold can be set. When S is higher than a certain preset value (e.g., 400), it indicates that the system's prediction accuracy is reliable, and it can enter the normal operating mode; when S is lower than this value or the grid issues an emergency support request, it enters the extreme operating mode.

[0040] This process then generates the available adjustable capacity. Based on the determined operating mode, the capacity generation module selects the appropriate calculation method and uses the obtained comprehensive score S to modify or combine the physical adjustable capacity to generate the final available system adjustable capacity. P sys .

[0041] Specifically, the overall score S can first be normalized to a correction coefficient K ranging from 0 to 1. For example, if the maximum overall score is 500, then K = S / 500. This coefficient K can be understood as the "confidence level" of the system's predictive reliability.

[0042] Under normal operating conditions, system regulation is primarily handled by the most flexible energy storage subsystem. In this case, the available regulation capacity can be calculated by adjusting the physical regulation capacity of the energy storage using a correction factor K. The calculation formula is as follows: P sys =K × P ess In other words, when the overall prediction accuracy of the system is high (large K value), there is more confidence in the scheduling of energy storage, and its available adjustable capacity is close to its physical limit; conversely, when the prediction accuracy is low (small K value), the declared available adjustable capacity will be reduced accordingly to ensure safety margin.

[0043] In extreme operating modes, such as when the grid requires emergency power support, the system needs to mobilize all available regulation resources. At this time, the photovoltaic subsystem (through curtailment) and the charging subsystem (through vehicle-to-grid discharge) also participate in regulation. The calculation method for available regulation capacity is adjusted accordingly: first, the physical capacity of the core regulation unit (energy storage) is corrected using a correction factor K, and then it is combined with the physical capacities of other regulation units. The calculation formula is as follows: P sys =K × P ess +P v2g + P pv In this model, the regulation capacity of photovoltaics and charging piles is directly included because, even in extreme cases, it provides "best-effort" support capabilities, even if there are deviations in the prediction.

[0044] To better understand the technical solution of this application, a specific working process example is given below: Assume that at time T1, the system calculates a comprehensive score S of 429.04 (out of 500), then the correction coefficient K = 429.04 / 500 ≈ 0.858. The system determines that it is currently in normal operating mode and obtains its physical adjustable capacity from the energy storage subsystem. P ess The capacity is 10 megawatts. Accordingly, the system's adjustable capacity, calculated and generated by the capacity generation module, is... P sys =0.858 × 10 MW = 8.58 MW. This value will be reported to the higher-level power grid dispatching system as the reliable regulation capacity that the photovoltaic-storage-charging system can provide in the next dispatching cycle.

[0045] This invention provides a method for generating the available adjustable capacity of a photovoltaic-storage-charging system. The method includes: acquiring a plurality of preset evaluation indicators and a first weight corresponding to each evaluation indicator; the plurality of evaluation indicators are used to measure the accuracy of power prediction for each subsystem in the photovoltaic-storage-charging system; calculating a first indicator score for each subsystem based on the plurality of evaluation indicators; and performing a weighted calculation on the first indicator scores of each subsystem according to the preset subsystem weights to obtain a second indicator score for the photovoltaic-storage-charging system; performing a weighted calculation on the first weights and the second indicator scores to obtain a comprehensive score, wherein the comprehensive score characterizes the overall prediction accuracy of the photovoltaic-storage-charging system; determining a target evaluation indicator corresponding to the lowest score in the second indicator scores to obtain a prediction optimization suggestion, wherein the prediction optimization suggestion is used to indicate the optimization direction of the power prediction model of the photovoltaic-storage-charging system using the target evaluation indicator; and generating the available adjustable capacity of the photovoltaic-storage-charging system based on the comprehensive score and the physical adjustable capacity of each subsystem in the photovoltaic-storage-charging system. Compared to existing technologies, this method employs a quantitative analysis approach, providing directions for improved and optimized indicators, which facilitates a clearer assessment of regulation capacity. Finally, this invention combines abstract assessment scores with the physical regulation capacity of each regulation unit and the system's operating mode to generate specific, directly applicable available regulation capacity values ​​for power grid dispatch. This bridges the gap between performance evaluation and engineering applications, demonstrating strong practical value. Consequently, the accuracy of assessing the available regulation capacity of such combined systems is improved.

[0046] This embodiment provides Embodiment 2, a variant of Embodiment 1 described above. The main difference lies in the evaluation index system used in step 101. This variant aims to illustrate that the method framework provided in this application has good scalability and can adapt to different evaluation needs and technical focuses.

[0047] In this embodiment, it is assumed that system operators are more concerned with the distribution of prediction deviations and the ability to control extreme errors. Therefore, in step 101, the capacity generation system can acquire or configure another set of evaluation metrics, which may include: root mean square error, maximum deviation, standard deviation of deviation, and prediction accuracy. The maximum deviation is used to capture extreme values ​​in the prediction error, which is crucial for avoiding system instability caused by extreme prediction errors; the standard deviation of deviation is used to measure the dispersion of the prediction error to reflect the stability of the prediction results; and prediction accuracy is a more intuitive metric.

[0048] Corresponding to the new indicator system, the primary weights also need to be reset. For example, more emphasis can be placed on penalizing extreme cases, setting the weight of maximum deviation to 30, root mean square error to 30, standard deviation of deviation to 20, and prediction accuracy to 20. Subsystem weights (e.g., photovoltaic 0.6, charging 0.4) can remain unchanged or be adjusted according to the new evaluation objectives.

[0049] The subsequent steps, including steps 102 to 105, are completely consistent with those in Example 1.

[0050] For example, during the execution of this embodiment, the system may find that the "system maximum deviation score" is the lowest among all system indicator scores. In this case, the optimization direction output by the system will be "reduce the maximum deviation" to guide algorithm engineers to focus on improving the predictive model's ability to predict extreme scenarios such as sudden weather changes or sudden charging loads.

[0051] As can be seen from this embodiment, the method provided by this application is not limited to the specific evaluation indicators in Embodiment 1, but provides a flexible framework. Users can freely select and combine the most suitable set of evaluation indicators according to actual needs (such as regulatory requirements, technical bottlenecks, economic goals, etc.), which reflects the universality and adaptability of the solution in this application.

[0052] This embodiment provides Embodiment 3, which is another variant of Embodiment 1 described above. The main difference lies in the specific model for calculating the subsystem index score, which is used to illustrate that the technical feature of "calculating index score" can cover multiple implementation methods.

[0053] In Example 1, the subsystem index score is calculated using a linear weighted formula. Alternatively, in another example, the score calculation module may employ a threshold-based nonlinear scoring rule, which may be more intuitive and easier to configure in certain scenarios.

[0054] Specifically, in step 102, for each evaluation indicator, the system no longer uses a weighted formula, but directly determines the score by consulting a multi-level threshold scoring table. Taking the root mean square error (RMSE) of the photovoltaic subsystem as an example, the scoring rules can be set as follows: 1. If the RMSE is less than threshold A (e.g., less than 1% of the rated power), it represents "excellent" performance and directly obtains a base score of 95 points. 2. If the RMSE is between threshold A and threshold B (e.g., between 1% and 3%), it represents "good" performance and obtains a base score of 80 points. 3. If the RMSE is between threshold B and threshold C (e.g., between 3% and 5%), it represents "qualified" performance and obtains a base score of 60 points. 4. If the RMSE is greater than threshold C, it represents "unqualified" performance and obtains a base score of 40 points.

[0055] To further reflect the dynamic trend, this embodiment introduces a dynamic adjustment rule. After obtaining the base score from the table, the system compares the score tier of the current period (e.g., "Excellent," "Good," etc.) with the tier of the previous calculation period: 1. If the current tier has improved compared to the previous period (e.g., from "Good" to "Excellent"), a bonus point (e.g., 5 points) is added to the current base score, resulting in a final score of 95 + 5 = 100 points. 2. If the current tier remains the same as the previous period, the score remains unchanged. 3. If the current tier has decreased compared to the previous period (e.g., from "Excellent" to "Good"), a penalty point (e.g., 5 points) is deducted from the current base score, resulting in a final score of 80 - 5 = 75 points.

[0056] For the charging subsystem and other evaluation indicators, similar nonlinear lookup table scoring rules and dynamic reward and punishment mechanisms based on preset intervals can also be adopted.

[0057] After calculating the index scores of each subsystem in this way, the subsequent steps are consistent with those in Example 1. This example demonstrates that the methods for calculating the index scores of subsystems are flexible and diverse. Whether it is a linear weighted model or a nonlinear threshold model, both fall within the scope of protection claimed in this application. The core lies in transforming the original index values ​​into a standardized score that can be used for subsequent weighted calculations.

[0058] This embodiment discloses Embodiment 4, which is another variant of Embodiment 1. The main difference lies in the introduction of a more refined operating mode and a more complex capacity calculation logic in step 105, which generates the available adjustable capacity. This embodiment aims to demonstrate that the method of this application can be combined with economic factors to generate available adjustable capacity that is closer to actual operational needs.

[0059] In Example 1, only two operating modes, "normal" and "extreme," were defined. In this example, the logic of the capacity generation module is extended to include an "economic operating mode." The triggering conditions for this mode are typically related to electricity market signals. For example, when the system receives real-time electricity price information and is currently in a peak or off-peak electricity price period, the system can automatically switch to the economic operating mode.

[0060] In step 105, once the capacity generation module determines that the system has entered the economic operation mode, it will employ a new calculation method to generate available regulation capacity. In the economic operation mode, the goal of regulation is not only to meet grid demand but also to minimize regulation costs or maximize benefits. At this point, the cost of utilizing different regulation resources (such as energy storage and vehicle-to-grid connections) becomes crucial.

[0061] The formula for calculating the available adjustable capacity can be designed as follows:P sys =K × （α × P ess +β × P v2g ) Unlike Example 1, the available regulation capacity here is primarily provided by the energy storage subsystem and the charging subsystem (via vehicle-to-grid functionality), as they are bidirectionally adjustable and flexible resources, while regulation (curtailment) of photovoltaic power is typically used as a last resort.

[0062] In the formula, K is still the correction coefficient obtained by normalizing the comprehensive score S, which represents the confidence level of the overall predictive reliability of the system.

[0063] The key lies in the introduction of α and β These are two dynamic economic coefficients. These coefficients are functions related to economic factors such as current electricity prices, the discounted cost of energy storage cycle life, and the cost of vehicle-to-grid response compensation. For example, the coefficients... α This can be related to the marginal cost of energy storage. Since each charge-discharge cycle incurs a certain amount of wear and tear on the lifespan of energy storage, this wear and tear can be converted into a cost. When electricity prices are low, and the regulation revenue is insufficient to cover this cost, α The value can be set lower to reduce the use of energy storage. Coefficient β This is related to the economic incentives for vehicles to connect to the grid. During peak electricity demand and when electricity prices are high, the revenue from selling electricity to the grid via vehicles is very high. At this time, the system can... β The value is increased to encourage more qualified electric vehicles to participate in discharge, thereby increasing the available regulation capacity of the system.

[0064] The specific working process is as follows: When the system determines that it has entered the economic operation mode, the capacity generation module will obtain information such as real-time electricity price, energy storage cost per kilowatt-hour, and vehicle-to-grid compensation price from the power market platform or local configuration, and dynamically calculate the current economic coefficient. α and β Then, the correction factor K calculated by the comprehensive evaluation module is combined with the physical regulation capacity obtained from the energy storage subsystem and the charging subsystem. P ess and P v2g， Substituting into the above formula, the available regulating capacity that balances predictive reliability and operational economy can be calculated. P sys .

[0065] This embodiment demonstrates that the two technical features of "selecting the corresponding calculation method according to the operating mode" and "using the comprehensive score to correct or combine the physical adjustment capacity" can cover more complex algorithms that are deeply coupled with the economic scheduling model, and are not limited to the simple mode switching and multiplication correction in Embodiment 1, thereby further expanding the scope of protection and practical application value of this application.

[0066] In summary, the method provided in this application, through a structured two-level weighted evaluation system, can integrate and quantify the multi-dimensional predictive performance indicators of multiple subsystems in a photovoltaic-storage-charging system into a unified comprehensive score. Based on this score, it can not only identify system performance bottlenecks to provide clear optimization directions, but also generate a specific, reliable, and, in some embodiments, economically viable adjustable capacity value by combining the system's physical boundaries and diverse operating modes.

[0067] Compared with existing technologies, the technical solution provided in this application has the following beneficial effects: 1. It realizes the overall quantitative evaluation of the photovoltaic-storage-charging combined system. By constructing a two-level weighted scoring system of "subsystem-system", the dispersed performance indicators of multiple subsystems such as photovoltaic and charging are scientifically integrated into a single, quantifiable system comprehensive score, and based on this, the available regulation capacity of the entire system is generated, solving the problem that existing technologies cannot perform overall, refined quantitative evaluation of complex combined systems. 2. It provides a clear direction for the optimization of the prediction model. By identifying the system indicator with the lowest score during the evaluation process, a clear and quantifiable direction for improvement is provided for the iterative optimization of the prediction model, forming a technical closed loop of "evaluation-optimization", which is conducive to continuously improving the accuracy and reliability of system regulation capacity prediction. 3. It enhances engineering practicality. This invention combines the abstract evaluation score with the physical regulation capacity of each regulation unit and the system operation mode to generate a specific available regulation capacity value that can be directly used for grid dispatch, opening up the conversion path from performance evaluation to engineering application, and has strong practical value.

[0068] Please see Figure 2 , Figure 2 This is a structural block diagram of a usable adjustable capacity generation device for a light-storage-charging system according to an embodiment of the present invention, such as... Figure 2 The apparatus shown includes: The acquisition module 201 is used to acquire multiple preset evaluation indicators and a first weight corresponding to each evaluation indicator; the multiple evaluation indicators are used to measure the accuracy of power prediction of each subsystem in the optical-storage-charging system. The first calculation module 202 is used to calculate the first indicator score of each subsystem based on the multiple evaluation indicators; and to perform a weighted calculation on the first indicator scores of each subsystem according to the preset subsystem weights to obtain the second indicator score of the optical-storage-charging system. The second calculation module 203 is used to perform weighted calculation based on the first weight and the second index score to obtain a comprehensive score, wherein the comprehensive score represents the overall prediction accuracy of the optical-storage-charging system; The direction determination module 204 is used to determine the target evaluation index corresponding to the lowest score in the second index score, and obtain a prediction optimization suggestion. The prediction optimization suggestion is used to indicate the optimization direction of the target evaluation index as the power prediction model of the photovoltaic-storage-charging system. The generation module 205 is used to generate the available adjustable capacity of the optical-storage-charging system based on the comprehensive score and the physical adjustable capacity of each subsystem in the optical-storage-charging system.

[0069] It should be noted that, Figure 2 The functions of each module in the device shown are as follows: Figure 1 The steps in the method shown are similar, and to avoid repetition, they will not be elaborated here. Please refer to the relevant documentation for details. Figure 1 The content of each step in the method shown.

[0070] This invention provides a device for generating the available adjustable capacity of a photovoltaic-storage-charging system. The device includes: an acquisition module for acquiring a plurality of preset evaluation indicators and a first weight corresponding to each evaluation indicator; the plurality of evaluation indicators are used to measure the accuracy of power prediction for each subsystem in the photovoltaic-storage-charging system; a first calculation module for calculating the first indicator score of each subsystem based on the plurality of evaluation indicators; and weighting the first indicator scores of each subsystem according to the preset subsystem weights to obtain a second indicator score for the photovoltaic-storage-charging system; a second calculation module for performing a weighted calculation based on the first weights and the second indicator scores to obtain a comprehensive score, the comprehensive score representing the overall prediction accuracy of the photovoltaic-storage-charging system; a direction determination module for determining the target evaluation indicator corresponding to the lowest score in the second indicator scores and obtaining a prediction optimization suggestion, the prediction optimization suggestion indicating the optimization direction of the power prediction model of the photovoltaic-storage-charging system using the target evaluation indicator; and a generation module for generating the available adjustable capacity of the photovoltaic-storage-charging system based on the comprehensive score and the physical adjustable capacity of each subsystem in the photovoltaic-storage-charging system. Compared with existing technologies, the above method realizes a quantitative analysis method and provides directions for improvement and optimization, which is conducive to the development of a clearer direction for the evaluation of regulation capacity. Finally, the present invention combines the abstract evaluation score with the physical regulation capacity of each regulation unit and the system operation mode to generate specific usable regulation capacity values ​​that can be directly used for power grid dispatch, thus opening up the conversion path from performance evaluation to engineering application and having strong practical value.

[0071] Figure 3 An internal structural diagram of a computer device in one embodiment is shown. This computer device can specifically be a terminal or a server. Figure 3 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program, which, when executed by the processor, causes the processor to perform the aforementioned methods. The internal memory may also store a computer program, which, when executed by the processor, causes the processor to perform the aforementioned methods. Those skilled in the art will understand that… Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0072] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform actions such as... Figure 1 The steps of the method shown.

[0073] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the following actions: Figure 1 The steps of the method shown.

[0074] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0075] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0076] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for adjusting the capacity generation of a light-storage-charge system, characterized in that, The method includes: Obtain multiple preset evaluation indicators and their corresponding first weights; the multiple evaluation indicators are used to measure the accuracy of power prediction for each subsystem in the optical-storage-charging system. Based on the multiple evaluation indicators, the first indicator score of each subsystem is calculated; and according to the preset subsystem weights, the first indicator scores of each subsystem are weighted to obtain the second indicator score of the optical-storage-charging system. Based on the first weight and the second index score, a weighted calculation is performed to obtain a comprehensive score, which represents the overall prediction accuracy of the optical-storage-charging system; The target evaluation index corresponding to the lowest score in the second index score is determined, and a prediction optimization suggestion is obtained. The prediction optimization suggestion is used to indicate the optimization direction of the target evaluation index as the power prediction model of the photovoltaic-storage-charging system. Based on the overall score and the physical regulation capacity of each subsystem in the optical-storage-charging system, the available regulation capacity of the optical-storage-charging system is generated.

2. The method according to claim 1, characterized in that, The step of generating the available adjustable capacity of the optical-storage-charging system based on the comprehensive score and the physical adjustable capacity of each subsystem in the optical-storage-charging system includes: Based on the comprehensive score, or the preset scheduling strategy, or the real-time status of the power grid, determine the current operating mode of the photovoltaic-storage-charging system; Based on the current operating mode and the correspondence between the preset operating mode and the adjustable capacity algorithm, determine the target adjustable capacity algorithm corresponding to the current operating mode; The available adjustable capacity is obtained by using the comprehensive score, the physical adjustment capacity, and the target adjustable capacity algorithm.

3. The method according to claim 1, characterized in that, The multiple evaluation indicators include at least one of the following: root mean square error, absolute error, average error, pass rate, and correlation coefficient.

4. The method according to claim 1, characterized in that, The calculation of the first indicator score for each subsystem based on the multiple evaluation indicators includes: Based on the improvement of the current index score in the current calculation cycle compared with the historical index score in the previous calculation cycle, and the current index score in the current calculation cycle, a weighted calculation is performed to obtain the first index score of each subsystem. The current index score is obtained by substituting the power prediction value and actual power value of the previous calculation cycle into the algorithm of each evaluation index.

5. The method according to claim 4, characterized in that, The improvements mentioned include: If the current indicator score in the current calculation period is better than the historical indicator score in the previous calculation period, then the score corresponding to the improvement is the first preset score. If the current indicator score in the current calculation period is the same as the historical indicator score in the previous calculation period, then the score corresponding to the improvement in comparison is the second preset score. If the current indicator score in the current calculation period is lower than the historical indicator score in the previous calculation period, then the score corresponding to the improvement in comparison is the third preset score. Among them, the first preset score > the second preset score > the third preset score.

6. The method according to claim 2, characterized in that, The operating modes include normal operating mode and extreme operating mode.

7. The method according to claim 6, characterized in that, The subsystem includes an energy storage subsystem, a photovoltaic subsystem, and a charging subsystem. The process of obtaining the available adjustable capacity using the comprehensive score, the physical regulation capacity, and the target adjustable capacity algorithm includes: If the current operating mode is the normal operating mode, the physical regulation capacity of the energy storage subsystem in the photovoltaic-storage-charging system is corrected using the comprehensive score to obtain the available regulation capacity; If the current operating mode is the extreme operating mode, the physical regulation capacity of the energy storage subsystem is corrected using the comprehensive score, and then combined with the physical regulation capacity of the photovoltaic subsystem and the charging subsystem to obtain the available regulation capacity.

8. A variable capacity generation device for a light-storage-charge system, characterized in that, The device includes: The acquisition module is used to acquire multiple preset evaluation indicators and the first weight corresponding to each evaluation indicator; the multiple evaluation indicators are used to measure the accuracy of power prediction of each subsystem in the optical-storage-charging system. The first calculation module is used to calculate the first indicator score of each subsystem based on the multiple evaluation indicators; and to perform a weighted calculation on the first indicator scores of each subsystem according to the preset subsystem weights to obtain the second indicator score of the optical-storage-charging system. The second calculation module is used to perform a weighted calculation based on the first weight and the second index score to obtain a comprehensive score, wherein the comprehensive score characterizes the overall prediction accuracy of the optical-storage-charging system; The direction determination module is used to determine the target evaluation index corresponding to the lowest score in the second index score, and obtain prediction optimization suggestions. The prediction optimization suggestions are used to indicate the optimization direction of the target evaluation index as the power prediction model of the photovoltaic-storage-charging system. The generation module is used to generate the available adjustable capacity of the optical-storage-charging system based on the comprehensive score and the physical adjustable capacity of each subsystem in the optical-storage-charging system.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it causes the processor to perform the steps of the method as described in any one of claims 1 to 7.

10. A computer device, comprising a memory and a processor, characterized in that, The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 7.

Images