Photovoltaic energy storage converging segmented voltage transformation method and system

Abstract

The present invention discloses a photovoltaic energy storage confluence segmented voltage transformation method and system, which relates to the field of photovoltaic technology, including: obtaining historical operation data of a target photovoltaic energy storage system; selecting and judging indicators based on preset indicator selection criteria for the historical operation data of the target photovoltaic energy storage system; establishing a confluence segmented voltage transformation evaluation model, using the selected indicators as input variables of the confluence segmented voltage transformation evaluation model, training the confluence segmented voltage transformation evaluation model, and evaluating the performance of the photovoltaic energy storage system; generating several confluence segmented voltage transformation schemes, calculating performance indicators, selecting the optimal confluence segmented voltage transformation scheme and implementing it. The present invention realizes quantitative evaluation of the performance of the photovoltaic energy storage system by using preset indicator selection judgment criteria and using the selected indicators as input variables, and realizes hierarchical processing of prediction accuracy requirements by calculating thresholds, generating a confluence segmented voltage transformation scheme, and formulating a more reasonable voltage transformation scheme based on actual performance prediction results.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic technology, and in particular to a photovoltaic energy storage confluence segmented voltage transformation method and system. Background Art

[0002] With the transformation of the global energy structure and the rapid development of renewable energy, photovoltaic energy storage technology has become one of the key technologies to promote sustainable energy development. Photovoltaic power generation has become the main form of solar energy utilization due to its clean and renewable characteristics. However, due to the intermittent and instability of photovoltaic power generation, energy storage technology has become an effective means to solve this problem. In recent years, energy storage technology has made significant progress in improving the stability of photovoltaic power generation systems and optimizing the operation of power systems. The energy storage system effectively balances the contradiction between supply and demand and improves energy utilization efficiency by storing energy during the peak period of photovoltaic power generation and releasing energy during peak demand or low power generation.

[0003] Despite this, existing photovoltaic energy storage technologies still have many shortcomings in practical applications. First, the operating efficiency of photovoltaic power generation systems is affected by many factors, including sunshine intensity, photovoltaic panel efficiency, battery performance, etc. The uncertainty of these factors increases the complexity of the system. Secondly, the energy storage system lacks intelligence and flexibility in capacity configuration, charging and discharging strategies, etc., and it is difficult to adapt to changing electricity demand. In addition, existing technologies often rely on experience judgment in evaluating and optimizing the performance of photovoltaic energy storage systems, and lack systematicity and scientificity. These problems limit the further improvement and widespread application of the performance of photovoltaic energy storage systems. Summary of the invention

[0004] In view of the fact that the threshold determination methods of the above-mentioned existing photovoltaic energy storage technologies are often based on experience or simple statistical analysis, and the lack of effective evaluation and decision support in the face of complex and changeable operating environments, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: by calculating the standard deviation and maximum fluctuation range of each performance indicator, combining the importance of the performance indicator, using a weighted method to comprehensively consider the impact of each indicator, and dynamically adjusting the threshold to adapt to the accuracy and response speed of system performance evaluation, thereby enhancing the adaptability and flexibility of the photovoltaic energy storage system under different operating conditions.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a photovoltaic energy storage confluence segmented voltage transformation method, comprising: obtaining historical operation data of a target photovoltaic energy storage system; performing indicator selection and judgment on the historical operation data of the target photovoltaic energy storage system according to preset indicator selection and judgment criteria; establishing a confluence segmented voltage transformation evaluation model, using the selected indicators as input variables of the confluence segmented voltage transformation evaluation model, training the confluence segmented voltage transformation evaluation model, and evaluating the performance of the photovoltaic energy storage system; based on the evaluation results of the current photovoltaic energy storage system performance, generating several confluence segmented voltage transformation schemes, calculating performance indicators, selecting the optimal confluence segmented voltage transformation scheme and implementing it.

[0007] As a preferred scheme of the photovoltaic energy storage confluence segmented transformation method of the present invention, wherein: historical operation data includes factors affecting photovoltaic power generation, factors affecting energy storage capacity, factors affecting load demand, factors affecting grid voltage and transformer related parameters; factors affecting photovoltaic power generation include sunshine intensity, photovoltaic panel efficiency, photovoltaic panel layout, photovoltaic panel aging degree and photovoltaic array output power; factors affecting energy storage capacity include battery type, battery cycle life, battery pack charge state, charge and discharge efficiency and maximum charge and discharge power; factors affecting load demand include power load curve, peak-to-valley difference, load power factor and load type; factors affecting grid voltage include grid frequency, grid power quality, voltage fluctuation range, voltage stability and harmonic content; transformer related parameters include rated power, rated voltage, impedance, loss, no-load current and transformation ratio.

[0008] As a preferred solution of the photovoltaic energy storage confluence segmented transformation method of the present invention, wherein: according to the preset indicator selection and judgment criteria, the historical operation data of the target photovoltaic energy storage system is subjected to indicator selection and judgment, including: when the prediction accuracy requirement is less than the first threshold, at least three photovoltaic power generation influencing factors are selected as evaluation indicators, at least two energy storage capacity influencing factors are selected as evaluation indicators, at least two load demand influencing factors are selected as evaluation indicators, at least two grid voltage influencing factors are selected as evaluation indicators, and at least two transformer related parameters are selected as evaluation indicators; when the prediction accuracy requirement is not less than the first threshold and not greater than the second threshold, at least four photovoltaic power generation influencing factors are selected as evaluation indicators, at least three energy storage capacity influencing factors are selected as evaluation indicators, at least three load demand influencing factors are selected as evaluation indicators, at least three grid voltage influencing factors are selected as evaluation indicators, and at least three transformer related parameters are selected as evaluation indicators; when the prediction accuracy requirement is greater than the second threshold, at least five photovoltaic power generation influencing factors are selected as evaluation indicators, at least four energy storage capacity influencing factors are selected as evaluation indicators, at least four load demand influencing factors are selected as evaluation indicators, at least four grid voltage influencing factors are selected as evaluation indicators, and at least four transformer related parameters are selected as evaluation indicators.

[0009] As a preferred solution of the photovoltaic energy storage busbar transformer method of the present invention, the calculation steps of the first threshold and the second threshold are as follows: Calculate the standard deviation of the data of each performance indicator , assign weights to the first threshold according to the importance of each performance indicator ; Calculate weighted standard deviation using weights , select the risk adjustment coefficient k1 based on expert experience; multiply the weighted standard deviation by The risk adjustment factor k1 is added to the total average of the averages of all performance indicators. Get the first threshold T1; calculate the maximum fluctuation range of each performance indicator , assign weights to the second threshold according to the importance of each performance indicator ; Calculate the weighted maximum fluctuation range , select the sensitivity coefficient k2 based on expert experience; the weighted maximum fluctuation range Multiply by the sensitivity factor k2, plus the total average of all performance index averages The second threshold T2 is obtained.

[0010] As a preferred solution of the photovoltaic energy storage busbar voltage transformation method of the present invention, the weighted standard deviation The calculation formula is as follows:

[0011] ,

[0012] in, represents the weighted standard deviation, Indicates the first threshold , m represents the total number of performance indicators, i represents the index of the performance indicator, represents the standard deviation; the grand average of all performance indicator averages The calculation formula is as follows:

[0013] ,

[0014] in, represents the grand average of all performance indicator averages, represents the average value of the i-th performance indicator, m represents the total number of performance indicators, and i represents the index of the performance indicator; the calculation formula of the first threshold T1 is as follows:

[0015] ,

[0016] Wherein, T1 represents the first threshold, represents the total average of all performance indicators, k1 represents the risk adjustment coefficient, Represents weighted standard deviation; weighted maximum fluctuation range The calculation formula is as follows:

[0017] ,

[0018] in, represents the weighted maximum fluctuation range, m represents the total number of performance indicators, i represents the index of the performance indicator, represents the second threshold allocation weight, Indicates the maximum fluctuation range of each performance indicator; the calculation formula of the second threshold T2 is as follows:

[0019] ,

[0020] Wherein, T2 represents the second threshold value, represents the total average value of all performance indexes, k2 represents the sensitivity coefficient, represents the weighted standard deviation, Indicates the weighted maximum fluctuation range.

[0021] As a preferred solution of the photovoltaic energy storage confluence segmented transformation method of the present invention, wherein: evaluating the performance of the photovoltaic energy storage system includes using a machine learning model, selecting and judging based on indicators, inputting the selected indicators into the machine learning model, and outputting several indicators reflecting the performance of the photovoltaic energy storage system; preprocessing historical operation data, dividing the data set, and training the machine learning model; using a cross-validation method to verify the stability and reliability of the trained machine learning model; using the trained machine learning model to predict the performance of the photovoltaic energy storage system; determining the threshold range corresponding to the current prediction accuracy requirement based on preset indicator selection judgment criteria; and classifying and evaluating the photovoltaic energy storage system performance prediction results based on the determined threshold range.

[0022] As a preferred scheme of the photovoltaic energy storage bus segmented transformation method of the present invention, wherein: based on the evaluation results, several bus segmented transformation schemes are generated, performance indicators are calculated, the optimal bus segmented transformation scheme is selected and implemented, including: according to the evaluation results of the photovoltaic energy storage system performance prediction results, an intelligent optimization algorithm is used to generate a bus segmented transformation scheme; using a trained machine learning model to predict the performance of the generated bus segmented transformation scheme, calculate key performance indicators, and use a multi-objective optimization method to sort all bus segmented transformation schemes; selecting the optimal bus segmented transformation scheme, formulating an implementation plan, and implementing the optimal bus segmented transformation scheme.

[0023] Another object of the present invention is to provide a photovoltaic energy storage confluence segmented transformer system, comprising: a data acquisition module for acquiring historical operating data of a target photovoltaic energy storage system; an indicator selection and judgment module for performing indicator selection and judgment on the historical operating data of the target photovoltaic energy storage system according to preset indicator selection and judgment criteria; an evaluation module for establishing a confluence segmented transformer evaluation model, using the selected indicators as input variables of the confluence segmented transformer evaluation model, training the confluence segmented transformer evaluation model, and evaluating the performance of the current photovoltaic energy storage system; a scheme selection module for generating a number of confluence segmented transformer schemes based on the evaluation results of the current photovoltaic energy storage system performance, calculating performance indicators, selecting the optimal confluence segmented transformer scheme and implementing it.

[0024] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the photovoltaic energy storage current segmented transformation method are implemented.

[0025] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the above photovoltaic energy storage busbar segmented voltage transformation method are implemented.

[0026] The beneficial effects of the present invention are as follows: by selecting judgment criteria through preset indicators, the historical operation data is screened, which helps to identify the factors that have the greatest impact on system performance, thereby achieving the purpose of optimizing the input of the evaluation model, establishing a convergence segmented transformer evaluation model, and using the selected indicators as input variables to achieve a quantitative evaluation of the performance of the photovoltaic energy storage system, training the evaluation model, and improving the accuracy and reliability of the evaluation through machine learning technology, so that the system performance can be predicted and evaluated more accurately. By calculating the first threshold and the second threshold, the hierarchical processing of the prediction accuracy requirements is achieved, and the precision of the evaluation model can be adjusted according to different requirements to adapt to different application scenarios. The system performance is predicted using the trained machine learning model, and the future performance of the photovoltaic energy storage system is predicted, which provides a basis for decision-making. Based on the evaluation results, a convergence segmented transformer scheme is generated, and a more reasonable transformer scheme can be formulated based on the actual performance prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0028] Figure 1 This is a schematic diagram of the structure of a terminal in the first embodiment of the present invention;

[0029] Figure 2 It is a schematic diagram of a flow chart in the first embodiment of the present invention;

[0030] Figure 3 FIG. 4 is a schematic diagram of the structure of a computer device in a third embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0032] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0033] Example 1

[0034] Reference Figure 1 , as an embodiment of the present invention, provides a photovoltaic energy storage bus segmented transformation method.

[0035] First, the photovoltaic energy storage bus segmented voltage transformation method provided in this application can be applied to Figure 1 In the terminal shown. Figure 1 As shown, the terminal may include one or two ( Figure 1 Only one is shown in the figure) processor and memory for storing data, wherein the processor may include but is not limited to a processing system such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device and an input and output device for communication functions. It can be understood by ordinary technicians in this field that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0036] The memory can be used to store computer programs, such as the computer program corresponding to the photovoltaic energy storage busbar segmented transformation method in this embodiment. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, implementing the above method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely located relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0037] The transmission device is used to receive or send data via a network. The above-mentioned network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0038] like Figure 2 As shown, the embodiment of the present invention provides a photovoltaic energy storage bus segmented voltage transformation method, which is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0039] S1: Obtain historical operating data of the target photovoltaic energy storage system.

[0040] Specifically, the historical operation data of the target photovoltaic energy storage system is obtained, and the operation data includes but is not limited to the factors affecting photovoltaic power generation, factors affecting energy storage capacity, factors affecting load demand, factors affecting grid voltage, and transformer-related parameters. Factors affecting photovoltaic power generation include sunshine intensity, photovoltaic panel efficiency, photovoltaic panel layout, photovoltaic panel aging, photovoltaic array output power, and external factors that may affect power generation, such as seasonal changes, geographical location, climate conditions, etc.; factors affecting energy storage capacity include battery type, battery cycle life, battery pack charge state, charge and discharge efficiency, and maximum charge and discharge power, as well as the performance of the battery management system and battery health status; factors affecting load demand include power load curve, peak-to-valley difference, load power factor, load type, and power demand forecasts and historical power consumption pattern analysis for different time periods; grid voltage includes factors affecting grid frequency, grid power quality, voltage fluctuation range, voltage stability, harmonic content, and load characteristics and power supply reliability of the grid; transformer-related parameters include rated power, rated voltage, impedance, loss, no-load current, and transformation ratio, and the maintenance record and operation status of the transformer can also be added.

[0041] S2: According to the preset indicator selection and judgment criteria, the historical operation data of the target photovoltaic energy storage system is selected and judged.

[0042] When the prediction accuracy requirement is less than the first threshold, at least three factors affecting photovoltaic power generation are selected as evaluation indicators, such as sunshine intensity, photovoltaic panel temperature, and photovoltaic array output power; at least two factors affecting energy storage capacity are selected as evaluation indicators, such as battery pack charge state and charging and discharging efficiency; at least two factors affecting load demand are selected as evaluation indicators, such as power load curve and peak-to-valley difference; at least two factors affecting grid voltage are selected as evaluation indicators, such as voltage fluctuation range and voltage stability; at least two transformer-related parameters are selected as evaluation indicators, such as transformer capacity and impedance;

[0043] When the prediction accuracy requirement is not less than the first threshold and not greater than the second threshold, at least four factors affecting photovoltaic power generation are selected as evaluation indicators to improve the efficiency of photovoltaic panels; at least three factors affecting energy storage capacity are selected as evaluation indicators to increase the maximum charging and discharging power; at least three factors affecting load demand are selected as evaluation indicators to increase the load type; at least three factors affecting grid voltage are selected as evaluation indicators to increase the harmonic content; at least three transformer-related parameters are selected as evaluation indicators to increase transformer losses.

[0044] When the prediction accuracy requirement is greater than the second threshold, at least five factors affecting photovoltaic power generation are selected as evaluation indicators, and the inclination and azimuth of the photovoltaic array are further increased; at least four factors affecting energy storage capacity are selected as evaluation indicators, and the battery health status is further increased; at least four factors affecting load demand are selected as evaluation indicators, and the load prediction error is further increased; at least four factors affecting grid voltage are selected as evaluation indicators, and the power factor is further increased; at least four transformer-related parameters are selected as evaluation indicators, and the transformer temperature is further increased.

[0045] Furthermore, the combination of evaluation indicators is not fixed, and the prediction accuracy requirements can be flexibly adjusted according to the specific needs of the system and the operating environment, so as to select the most suitable combination of evaluation indicators.

[0046] In summary, different numbers of evaluation indicators are selected according to different accuracy requirements. While ensuring the prediction accuracy, unnecessary waste of computing resources is avoided. By setting different thresholds, hierarchical evaluation is achieved, which can provide evaluation results of corresponding accuracy for decisions of different importance. When low precision is required, fewer indicators are selected to reduce the workload of data collection and processing and improve the system response speed. When high precision is required, more indicators are selected to provide more comprehensive and accurate information support for important decisions. By dynamically adjusting the evaluation indicators, the prediction model can be continuously optimized to improve its accuracy and robustness. By precisely controlling the number of evaluation indicators, the monitoring and computing costs can be minimized while ensuring performance.

[0047] Furthermore, the calculation steps of the first threshold and the second threshold are as follows: Calculate the standard deviation of the data of each performance indicator , assign weights to the first threshold according to the importance of each performance indicator ; Calculate weighted standard deviation using weights , select the risk adjustment coefficient k1 based on expert experience; multiply the weighted standard deviation by The risk adjustment factor k1 is added to the total average of the averages of all performance indicators. Get the first threshold T1; calculate the maximum fluctuation range of each performance indicator , assign weights to the second threshold according to the importance of each performance indicator ; Calculate the weighted maximum fluctuation range , select the sensitivity coefficient k2 based on expert experience; the weighted maximum fluctuation range Multiply by the sensitivity factor k2, plus the total average of all performance index averages The second threshold T2 is obtained.

[0048] Furthermore, the average value of the i-th performance indicator The calculation formula is as follows:

[0049] ,

[0050] in, represents the average value of the i-th performance indicator, represents the total number of observed data points for the ith performance indicator, represents the j-th observation value of the i-th performance indicator.

[0051] Calculate the standard deviation of the data for each performance metric , assign weights to the first threshold according to the importance of each performance indicator .

[0052] Standard Deviation The calculation formula is as follows:

[0053] ,

[0054] in, represents the standard deviation, represents the total number of observed data points for the ith performance indicator, represents the jth observation value of the ith performance indicator, represents the average value of the i-th performance indicator, and j represents the index of the observed data point.

[0055] Weighted standard deviation The calculation formula is as follows:

[0056] ,

[0057] in, represents the weighted standard deviation, Indicates the first threshold , m represents the total number of performance indicators, i represents the index of the performance indicator, Represents standard deviation.

[0058] The total average of all performance indicator averages The calculation formula is as follows:

[0059] ,

[0060] in, represents the grand average of all performance indicator averages, represents the average value of the i-th performance indicator, m represents the total number of performance indicators, and i represents the index of the performance indicator.

[0061] The calculation formula of the first threshold T1 is as follows:

[0062] ,

[0063] Wherein, T1 represents the first threshold, represents the total average of all performance indicators, k1 represents the risk adjustment coefficient, represents the weighted standard deviation.

[0064] The maximum fluctuation range of each performance indicator The calculation formula is as follows:

[0065] ,

[0066] in, Indicates the maximum fluctuation range of each performance indicator. Represents the observed values ​​of all i-th performance indicators The maximum value in indicates the highest value reached by the indicator during the observation period; Represents the observed values ​​of all i-th performance indicators The minimum value in indicates the lowest value reached by the indicator during the observation period.

[0067] Weighted Maximum Volatility The calculation formula is as follows:

[0068] ,

[0069] in, represents the weighted maximum fluctuation range, m represents the total number of performance indicators, i represents the index of the performance indicator, represents the second threshold allocation weight, Indicates the maximum fluctuation range of each performance indicator.

[0070] The calculation formula of the second threshold T2 is as follows:

[0071] ,

[0072] Wherein, T2 represents the second threshold value, represents the total average value of all performance indexes, k2 represents the sensitivity coefficient, represents the weighted standard deviation, Indicates the weighted maximum fluctuation range.

[0073] In summary, by calculating the statistical characteristics of key performance indicators, T1 and T2 are set for classified evaluation of system performance. By calculating the mean and standard deviation of each performance indicator, the normal operating status of the system can be described more accurately, and the accuracy of performance evaluation can be improved. By dynamically calculating the threshold, the system can automatically adjust the evaluation criteria according to historical operating data to adapt to different operating environments and conditions. Multiple performance indicators are considered and weights are assigned according to their importance to ensure the comprehensiveness and rationality of the evaluation. By setting two thresholds (T1 and T2), the normal, warning and abnormal states of the system can be more finely distinguished, and the sensitivity of anomaly detection can be improved. By introducing the risk adjustment coefficient (k1) and the sensitivity coefficient (k2), the risk tolerance and sensitivity to fluctuations of the system can be adjusted according to actual needs. These statistical indicators and thresholds provide important input parameters for the subsequent performance prediction model and improve the accuracy of the prediction.

[0074] S3: Establish a busbar segmented transformer evaluation model, use the selected indicators as input variables of the busbar segmented transformer evaluation model, train the busbar segmented transformer evaluation model, and evaluate the performance of the photovoltaic energy storage system.

[0075] Specifically, considering the complexity of the problem and multiple input variables, we choose to use machine learning models such as Random Forest or Gradient Boosting Trees to process multiple input variables, capture the nonlinear relationship between variables, and establish a confluence segment transformer assessment model.

[0076] Furthermore, based on the previous indicator selection and judgment, the selected indicators are used as input variables of the busbar segmented transformer evaluation model, including: photovoltaic power generation related parameters, energy storage capacity related parameters, load demand related parameters, grid voltage related parameters and transformer related parameters.

[0077] Furthermore, the historical operation data was cleaned, outliers and missing values ​​were removed, and the data was standardized or normalized. The processed data set was divided into a training set (70%), a validation set (15%), and a test set (15%). The training set was used to train the convergence segment transformer assessment model, the validation set was used to adjust the model hyperparameters, such as the depth of the decision tree and the number of trees, etc., and the test set was used to assess the generalization ability of the convergence segment transformer assessment model; the cross-validation method was used to verify the stability and reliability of the trained convergence segment transformer assessment model.

[0078] Furthermore, real-time data of the current system is collected, including all selected input variables, and the performance of the current system is predicted using the trained bus-section transformer evaluation model. The collected real-time data is input into the trained bus-section transformer evaluation model to obtain the overall performance prediction result of the current system output by the bus-section transformer evaluation model.

[0079] Furthermore, according to the previously set indicators, the judgment criteria are selected to determine the threshold range corresponding to the current prediction accuracy requirement. Based on the threshold range, the overall performance prediction results of the current system are classified and evaluated:

[0080] If the prediction result is lower than the first threshold value T1, the system performance is rated as "needs optimization", and specific improvement measures are provided for the "needs optimization" situation;

[0081] If the prediction result is between the first threshold T1 and the second threshold T2, the system performance is rated as "normal", and suggestions for maintenance and slight improvement are provided for the "normal" situation;

[0082] If the prediction result is higher than the second threshold value T2, the system performance is rated as "excellent", and a maintenance strategy is provided for the "excellent" situation.

[0083] Furthermore, key performance indicators are calculated, including but not limited to: overall system efficiency = actual output power / theoretical maximum output power; energy storage utilization rate = actually used energy storage capacity / total energy storage capacity; load matching degree = the degree of fit between the system output power curve and the load demand curve; grid stability index = 1-(voltage fluctuation range / maximum allowable voltage fluctuation range); transformer efficiency = 1-(transformer loss / transformer input power).

[0084] Furthermore, for each key performance indicator, the deviation from the historical average is calculated to identify indicators with abnormal performance. Taking into account the model prediction results, performance ratings and key indicators, a detailed performance evaluation report is generated, including: overall performance rating, specific values ​​of each key indicator and historical comparison, parts of the system that perform well and need improvement, and potential performance bottlenecks and optimization directions.

[0085] S4: Based on the evaluation results of the current photovoltaic energy storage system performance, generate several bus segmented transformation schemes, calculate the performance indicators, select the optimal bus segmented transformation scheme and implement it.

[0086] Specifically, based on the performance evaluation results, key aspects that need to be optimized (such as efficiency, stability, etc.) are determined, and multiple candidate solutions are generated using intelligent optimization algorithms (such as genetic algorithms, particle swarm optimization algorithms, or simulated annealing algorithms). Each solution includes but is not limited to: confluence mode (such as centralized, string, or multi-level confluence); segmentation strategy (such as voltage level division, capacity allocation); transformer configuration (such as capacity, connection method); system constraints (such as total capacity requirements, voltage level restrictions, power factor requirements, and power factor requirements); safety design (such as electrical safety and fire safety).

[0087] Furthermore, for each generated solution, the trained bus-section transformer evaluation model is used to input solution parameters and predict its performance. Key performance indicators are calculated, including but not limited to: overall system efficiency, energy storage utilization, load matching, grid stability index, transformer efficiency, expected annual power generation, expected economic benefits (such as return on investment, cost per kilowatt-hour), and environmental benefits (such as carbon emission reduction).

[0088] Furthermore, the implementation cost and technical feasibility are taken into account, and the initial investment cost, operation and maintenance cost, and technical complexity index are calculated.

[0089] Furthermore, a multi-objective optimization function is established, taking into account the above performance indicators, costs and feasibility. For example: F = w1*system overall efficiency + w2* energy storage utilization + w3* energy storage utilization + w4* energy storage utilization + w5 * transformer efficiency + w6 * expected economic benefits. Including but not limited to the above performance indicators, costs and feasibility, you can choose to add or delete as appropriate.

[0090] Furthermore, a multi-objective optimization method, such as Pareto optimization (used to describe a situation where, when weighing multiple objectives, the improvement of any one objective will inevitably lead to the deterioration of at least one other objective), is used to rank all the schemes. The scheme with the highest comprehensive score is selected as the optimal busbar segmentation transformation scheme and implemented.

[0091] Example 2

[0092] Reference Figure 1-2 , which is an embodiment of the present invention, provides a photovoltaic energy storage busbar segmented transformer system, comprising:

[0093] A data acquisition module is used to obtain historical operating data of the target photovoltaic energy storage system;

[0094] An indicator selection and judgment module is used to select and judge indicators for the historical operation data of the target photovoltaic energy storage system according to preset indicator selection and judgment criteria;

[0095] An evaluation module is used to establish a busbar segmented transformer evaluation model, use the selected indicators as input variables of the busbar segmented transformer evaluation model, train the busbar segmented transformer evaluation model, and evaluate the performance of the current photovoltaic energy storage system;

[0096] The scheme selection module is used to generate several bus segmentation transformation schemes based on the evaluation results of the current photovoltaic energy storage system performance, calculate the performance indicators, select the optimal bus segmentation transformation scheme and implement it.

[0097] For the specific definition of the photovoltaic energy storage convergence segmented transformer system, please refer to the definition of the photovoltaic energy storage convergence segmented transformer method above, which will not be repeated here. Each module in the above photovoltaic energy storage convergence segmented transformer system can be implemented in whole or in part through software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0098] Example 3

[0099] Reference Figure 3 , which is the third embodiment of the present invention. Based on the first two embodiments, the embodiment of the present invention provides a computer device, which may be a server, and its internal structure diagram may be as shown in FIG. Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium.

[0100] The database of the computer device is used to store action detection data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in any of the above-mentioned sparse tensor operation acceleration method embodiments are implemented.

[0101] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0102] In one embodiment, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above-mentioned sparse tensor operation acceleration method embodiments are implemented.

[0103] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0104] Example 4

[0105] As an embodiment of the present invention, a photovoltaic energy storage busbar segmented voltage transformation method is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0106] Specifically, in order to verify the effectiveness of the photovoltaic energy storage converging segmented transformation method proposed in the present invention, the research team selected a large (100MW) and a medium (50MW) photovoltaic power station in a certain province for a three-month experiment. Both power stations were equipped with energy storage systems of corresponding scales.

[0107] The detailed operation data of the two photovoltaic energy storage systems in the past two years were collected, including factors affecting photovoltaic power generation, factors affecting energy storage capacity, load demand, grid voltage, and transformer-related parameters. The raw data were preprocessed using data cleaning and outlier processing techniques.

[0108] According to the indicator selection judgment criteria proposed in the method of the present invention, the historical operation data is analyzed. The prediction accuracy requirement of a large power station (100MW) is set to be greater than the second threshold, and the prediction accuracy requirement of a medium-sized power station (50MW) is set to be between the first threshold and the second threshold.

[0109] The optimal solution was compared with the traditional method and the unoptimized system. The experiment lasted for 3 months, and the key performance indicators of the system were recorded every day. The experimental results are shown in the following table:

[0110] Table 1: Comparison of performance indicators of large power plants (100MW)

[0111] ,

[0112] Table 2: Performance index comparison of medium-sized power plants (50MW)

[0113] ,

[0114] By analyzing the data in Table 1 and Table 2, the following conclusions can be drawn: the method of the present invention shows significant advantages in photovoltaic energy storage systems of different scales, proving its good applicability.

[0115] Furthermore, the utilization rate of photovoltaic power generation increased by 11.4 percentage points in large power plants and by 11.3 percentage points in medium-sized power plants, indicating that this method can effectively improve the utilization efficiency of photovoltaic resources.

[0116] Furthermore, in terms of energy storage, large power stations improved by 7.2 percentage points and medium-sized power stations improved by 7.1 percentage points, reflecting the superiority of this method in coordinating the charging and discharging process of energy storage systems.

[0117] Furthermore, after adopting the method of the present invention, the overall efficiency of the system of power stations of all sizes has been significantly improved. Large power stations have increased by 11.8 percentage points, and medium-sized power stations have increased by 11.5 percentage points, which fully proves the effectiveness of the method in optimizing the performance of the entire photovoltaic energy storage system.

[0118] Furthermore, in terms of reducing the peak-to-valley difference of the power grid, the reduction rate of large power stations increased by 10.4 percentage points, and that of medium-sized power stations increased by 9.3 percentage points, indicating that this method can effectively smooth out load fluctuations and improve power grid stability.

[0119] Furthermore, in terms of reducing transformer losses, large power plants reduced losses by 0.9 percentage points, and medium-sized power plants reduced losses by 0.9 percentage points, indicating that this method can effectively improve the operating efficiency of transformers.

[0120] Furthermore, after adopting the method of the present invention, the system reliability index of power stations of all sizes has been improved. Large power stations have increased by about 2.27%, and medium-sized power stations have increased by about 2.45%, which fully proves that the method can effectively improve the reliability and stability of the entire photovoltaic energy storage system.

[0121] In summary, the photovoltaic energy storage busbar segmented transformation method proposed in the present invention shows significant advantages in multiple key performance indicators and performs well in photovoltaic energy storage systems of different scales.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A photovoltaic energy storage busbar voltage conversion method, characterized in that: include: Obtain historical operating data of the target photovoltaic energy storage system; According to the preset indicator selection and judgment criteria, the historical operation data of the target photovoltaic energy storage system is subjected to indicator selection and judgment; Establish a busbar segmented transformer evaluation model, use the selected indicators as input variables of the busbar segmented transformer evaluation model, train the busbar segmented transformer evaluation model, and evaluate the performance of the photovoltaic energy storage system; Based on the evaluation results of the current photovoltaic energy storage system performance, generate several bus segmentation transformation schemes, calculate performance indicators, select the optimal bus segmentation transformation scheme and implement it; The step of selecting and judging the indicators for the historical operation data of the target photovoltaic energy storage system according to the preset indicator selection and judgment criteria includes: When the prediction accuracy requirement is less than the first threshold, at least three photovoltaic power generation influencing factors are selected as evaluation indicators, at least two energy storage capacity influencing factors are selected as evaluation indicators, at least two load demand influencing factors are selected as evaluation indicators, at least two grid voltage influencing factors are selected as evaluation indicators, and at least two transformer related parameters are selected as evaluation indicators; When the prediction accuracy requirement is not less than the first threshold and not greater than the second threshold, at least four photovoltaic power generation influencing factors are selected as evaluation indicators, at least three energy storage capacity influencing factors are selected as evaluation indicators, at least three load demand influencing factors are selected as evaluation indicators, at least three grid voltage influencing factors are selected as evaluation indicators, and at least three transformer related parameters are selected as evaluation indicators; When the prediction accuracy requirement is greater than the second threshold, at least five photovoltaic power generation influencing factors are selected as evaluation indicators, at least four energy storage capacity influencing factors are selected as evaluation indicators, at least four load demand influencing factors are selected as evaluation indicators, at least four grid voltage influencing factors are selected as evaluation indicators, and at least four transformer related parameters are selected as evaluation indicators; The calculation steps of the first threshold and the second threshold are as follows: Calculate the standard deviation σ of the data for each performance indicator i , assign a weight w to the first threshold according to the importance of each performance indicator 1i ; Calculate the weighted standard deviation σ using the weights w1 , select the risk adjustment coefficient k1 based on expert experience; The weighted standard deviation σ w1 Multiply by the risk adjustment factor k1, plus the grand average of all performance indicator averages Obtain a first threshold value T1; Calculate the maximum fluctuation range V of each performance indicator i , assign a weight w to the second threshold according to the importance of each performance indicator 2i ; Calculate the weighted maximum fluctuation range V W2 , select the sensitivity coefficient k2 based on expert experience; The weighted maximum fluctuation range V W2 Multiply by the sensitivity factor k2, plus the total average of all performance index averages Obtain a second threshold value T2; The weighted standard deviation σ w1 The calculation formula is as follows: Among them, σ w1 represents the weighted standard deviation, w 1i represents the first threshold, m represents the total number of performance indicators, i represents the index of the performance indicator, σ i represents standard deviation; The total average of all performance indicator averages mentioned The calculation formula is as follows: in, represents the grand average of all performance indicator averages, represents the average value of the i-th performance indicator, m represents the total number of performance indicators, and i represents the index of the performance indicator; The calculation formula of the first threshold T1 is as follows: Wherein, T1 represents the first threshold, represents the total average of all performance indicators, k1 represents the risk adjustment coefficient, σ w1 represents the weighted standard deviation; The weighted maximum fluctuation range V W2 The calculation formula is as follows: Among them, V W2 represents the weighted maximum fluctuation range, m represents the total number of performance indicators, i represents the index of the performance indicator, and w 2i represents the second threshold allocation weight, V i Indicates the maximum fluctuation range of each performance indicator; The calculation formula of the second threshold T2 is as follows: Wherein, T2 represents the second threshold value, represents the total average of all performance indexes, k2 represents the sensitivity coefficient, σ w1 represents the weighted standard deviation, V W2 Indicates the weighted maximum fluctuation range.

2. The photovoltaic energy storage busbar voltage conversion method according to claim 1, characterized in that: The historical operation data includes factors affecting photovoltaic power generation, factors affecting energy storage capacity, factors affecting load demand, factors affecting grid voltage, and transformer related parameters; The factors affecting photovoltaic power generation include sunshine intensity, photovoltaic panel efficiency, photovoltaic panel layout, photovoltaic panel aging degree and photovoltaic array output power; The energy storage capacity influencing factors include battery type, battery cycle life, battery pack charge state, charge and discharge efficiency, and maximum charge and discharge power; The load demand influencing factors include power load curve, peak-to-valley difference, load power factor and load type; The grid voltage influencing factors include grid frequency, grid power quality, voltage fluctuation range, voltage stability and harmonic content; The transformer related parameters include rated power, rated voltage, impedance, loss, no-load current and transformation ratio.

3. The photovoltaic energy storage busbar voltage conversion method according to claim 2, characterized in that: The evaluation of photovoltaic energy storage system performance includes: Using a machine learning model, based on the index selection and judgment, the selected index is input into the machine learning model, and several indexes reflecting the performance of the photovoltaic energy storage system are output; Preprocess historical operation data, divide data sets, and train machine learning models; Use cross-validation to verify the stability and reliability of trained machine learning models; Use the trained machine learning model to predict the performance of the photovoltaic energy storage system; Select the judgment criteria based on the preset indicators and determine the threshold range corresponding to the current prediction accuracy requirement; The performance prediction results of the photovoltaic energy storage system are evaluated based on the determined threshold range classification.

4. The photovoltaic energy storage busbar voltage conversion method according to claim 3, characterized in that: Based on the evaluation results, several bus-section transformation schemes are generated, performance indicators are calculated, the optimal bus-section transformation scheme is selected and implemented, including: Based on the evaluation results of the photovoltaic energy storage system performance prediction results, an intelligent optimization algorithm is used to generate a busbar segmented voltage transformation plan; Use the trained machine learning model to predict the performance of the generated bus-section transformer schemes, calculate key performance indicators, and use a multi-objective optimization method to rank all bus-section transformer schemes; Select the optimal bus-section transformation scheme, develop an implementation plan, and implement the optimal bus-section transformation scheme.

5. A system using the photovoltaic energy storage busbar segmented voltage transformation method as described in any one of claims 1 to 4, characterized in that: include: A data acquisition module is used to obtain historical operating data of the target photovoltaic energy storage system; An indicator selection and judgment module is used to perform indicator selection and judgment on the historical operation data of the target photovoltaic energy storage system according to a preset indicator selection and judgment criterion; An evaluation module is used to establish a busbar segmented transformer evaluation model, use the selected indicators as input variables of the busbar segmented transformer evaluation model, train the busbar segmented transformer evaluation model, and evaluate the performance of the current photovoltaic energy storage system; The scheme selection module is used to generate several bus segmentation transformation schemes based on the evaluation results of the current photovoltaic energy storage system performance, calculate the performance indicators, select the optimal bus segmentation transformation scheme and implement it.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the photovoltaic energy storage bus segmented voltage transformation method described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the photovoltaic energy storage bus segmented voltage transformation method described in any one of claims 1 to 4 are implemented.

Images