A Distributed Energy Storage Inverter Optimization Method and System Based on Big Data Analysis

Abstract

The present invention relates to the technical field of energy storage inverters, and particularly to an optimization method and system for a distributed energy storage inverter based on big data analysis. By combining meteorological and load historical data, the present invention can more accurately predict load fluctuations. According to the obtained load fluctuation influence rate, the control parameters of the energy storage inverter can be dynamically adjusted to adapt to load changes. According to real-time energy conversion efficiency data, the control parameters can be dynamically adjusted under different operating conditions to ensure that the system operates within the optimal efficiency range. By comprehensively considering the energy conversion efficiency, the error of load prediction can be reduced and the response ability of the system can be improved. By real-time monitoring the load value and demand response gain and adjusting the charge and discharge strategy of the distributed energy storage inverter accordingly, not only the dynamic response ability and stability of the system are improved, but also it helps to improve the energy use efficiency. By dynamically adjusting the charging amount, it helps to optimize the use of energy storage and improve the overall economy and stability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage converters, and particularly to an optimization method and system for a distributed energy storage converter based on big data analysis. Background Technique

[0002] A distributed energy storage converter is a power electronic device used to connect and manage distributed energy and energy storage systems. Its main function is to achieve the conversion, control, and optimization of electrical energy for efficient storage and release of electrical energy. Its main functions include electrical energy conversion, energy management, power regulation, and intelligent control, and it can be used in energy storage systems for homes or commercial buildings. Combined with solar power generation, it can increase the proportion of self-use electricity. The distributed energy storage converter plays a key role in realizing the efficient utilization of renewable energy and enhancing the flexibility and stability of the power system. With the popularization of distributed energy, its importance has become increasingly prominent.

[0003] Existing distributed energy storage converters adopt a control strategy based on fixed rules. For example, according to the priorities of different loads, when the power supply is insufficient, the demand of important loads is preferentially met, and corresponding charging and discharging are carried out. However, the above method fails to dynamically adjust according to real-time data and environmental changes, lacks an effective demand response strategy, and may cause the energy storage converter to be unable to quickly adjust the charging and discharging strategy to maintain system balance during peak loads or rapid fluctuations. Summary of the Invention

[0004] The main object of the present invention is to provide an optimization method for a distributed energy storage converter based on big data analysis, aiming to solve the technical problems in the prior art.

[0005] The present invention proposes an optimization method for a distributed energy storage converter based on big data analysis, including:

[0006] Obtain the historical environmental characteristic information and historical operating state characteristic information of the distributed energy storage converter, where the historical operating state characteristic information includes historical electrical characteristic information and historical energy storage characteristic information;

[0007] Obtain the historical meteorological characteristic information and historical load characteristic information of the historical environmental characteristic information, and obtain the load fluctuation influence rate according to the historical meteorological characteristic information and the historical load characteristic information;

[0008] Obtain the energy conversion efficiency according to the historical electrical characteristic information and the historical energy storage characteristic information, and obtain the load prediction value according to the energy conversion efficiency and the load fluctuation influence rate;

[0009] Obtain the demand response gain according to the load prediction value;

[0010] Obtain the adjusted real-time environmental characteristic information and real-time operating status characteristic information of the distributed energy storage converter, and obtain the real-time load value according to the real-time environmental characteristic information and the real-time operating status characteristic information;

[0011] Adjust the charge and discharge strategy of the distributed energy storage converter according to the real-time load value and the demand response gain until the distributed energy storage converter system is balanced.

[0012] Preferably, the step of obtaining the load fluctuation influence rate according to the historical meteorological characteristic information and the historical load characteristic information includes:

[0013] Obtain multiple temperature characteristics, multiple humidity characteristics, and multiple wind speed characteristics of the historical meteorological characteristic information;

[0014] Obtain the total meteorological variable according to multiple temperature characteristics, multiple humidity characteristics, and multiple wind speed characteristics, and obtain the corresponding temperature influence coefficient, humidity influence coefficient, and wind speed influence coefficient according to each temperature characteristic, humidity characteristic, and wind speed characteristic and the total meteorological variable;

[0015] Obtain multiple power loads and multiple load change rates of the historical load characteristic information;

[0016] Obtain the total load variable according to multiple power loads and multiple load change rates, and obtain the corresponding power influence coefficient and load change influence coefficient according to each power load and load change rate and the total load variable;

[0017] Obtain the load fluctuation influence rate according to multiple temperature influence coefficients, multiple humidity influence coefficients, multiple wind speed influence coefficients, multiple power influence coefficients, and multiple load change influence coefficients.

[0018] Preferably, the step of obtaining the energy conversion efficiency according to the historical electrical characteristic information and the historical energy storage characteristic information includes:

[0019] Obtain the charge and discharge rate and discharge depth of the historical energy storage characteristic information;

[0020] Obtain the rated capacity of the distributed energy storage converter, and obtain the charge duration and discharge duration according to the rated capacity, charge and discharge rate, and discharge depth;

[0021] Obtain the harmonics, frequency, output power, and input power of the historical electrical characteristic information;

[0022] Obtain the input energy value according to the charge duration, input power, harmonics, and frequency;

[0023] Calculate the output energy value according to the discharge duration, discharge depth, output power, harmonics, and frequency, where the calculation formula is:

[0024] ;

[0025] Among them, represents the output energy value, represents the output power, represents the discharge duration, represents the frequency, represents the harmonic, represents the depth of discharge;

[0026] Calculate the energy conversion efficiency according to the output energy value and the input energy value. Among them, the calculation formula is:

[0027] ;

[0028] Among them, represents the energy conversion efficiency, represents the output energy value, represents the input energy value.

[0029] Preferably, the step of obtaining the demand response gain according to the energy conversion efficiency and the load fluctuation influence rate includes:

[0030] Obtain multiple load data of the distributed energy storage converter within a preset time period, and obtain the initial load average value according to the multiple load data;

[0031] Obtain the first weight factor of the energy conversion efficiency;

[0032] Obtain the second weight factor of the load fluctuation influence rate;

[0033] Input the initial load average value, the energy conversion efficiency, the load fluctuation influence rate, the first weight factor and the second weight factor into the load prediction model to obtain the load prediction value. Among them, the load prediction model is:

[0034] ;

[0035] Among them, represents the load prediction value, represents the initial load average value, represents the energy conversion efficiency, represents the load fluctuation influence rate, represents the first weight factor, represents the second weight factor.

[0036] Preferably, the step of obtaining the demand response gain according to the reference load value and the load prediction value includes:

[0037] Obtain the reference load value of the distributed energy storage converter;

[0038] Obtain a reference gain based on the reference load value and the load prediction value;

[0039] Obtain a demand response gain based on the reference gain, the reference load value, and the load prediction value.

[0040] Preferably, the step of adjusting the charge and discharge strategy of the distributed energy storage converter according to the real-time load value and the demand response gain until the distributed energy storage converter system is balanced includes:

[0041] Obtain the real-time load value and the load prediction value, and determine whether the real-time load value is greater than the load prediction value;

[0042] If the real-time load value is greater than the load prediction value, obtain the discharge efficiency coefficient of the distributed energy storage converter, and obtain the discharge amount according to the discharge efficiency coefficient and the demand response gain;

[0043] Adjust the discharge of the distributed energy storage converter according to the discharge amount until the distributed energy storage converter system responds in balance;

[0044] If the real-time load value is not less than the load prediction value, obtain the charge efficiency coefficient of the distributed energy storage converter, and obtain the charge amount according to the charge efficiency coefficient and the demand response gain;

[0045] Adjust the charge of the distributed energy storage converter according to the charge amount until the distributed energy storage converter system responds in balance.

[0046] The present invention also provides an optimized system for a distributed energy storage converter based on big data analysis, including:

[0047] A first acquisition module for acquiring the historical environmental characteristic information and the historical operation state characteristic information of the distributed energy storage converter, wherein the historical operation state characteristic information includes historical electrical characteristic information and historical energy storage characteristic information;

[0048] A second acquisition module for acquiring the historical meteorological characteristic information and the historical load characteristic information of the historical environmental characteristic information, and obtaining a load fluctuation influence rate according to the historical meteorological characteristic information and the historical load characteristic information;

[0049] A third acquisition module for obtaining an energy conversion efficiency according to the historical electrical characteristic information and the historical energy storage characteristic information, and obtaining a load prediction value according to the energy conversion efficiency and the load fluctuation influence rate;

[0050] A fourth acquisition module for obtaining a demand response gain according to the load prediction value;

[0051] A fifth acquisition module, configured to acquire the adjusted real-time environmental characteristic information and real-time operating state characteristic information of the distributed energy storage converter, and acquire a real-time load value according to the real-time environmental characteristic information and the real-time operating state characteristic information;

[0052] An adjustment module, configured to adjust the charge and discharge strategy of the distributed energy storage converter according to the real-time load value and the demand response gain until the distributed energy storage converter system reaches balance.

[0053] Preferably, the second acquisition module includes:

[0054] A first acquisition unit, configured to acquire multiple temperature characteristics, multiple humidity characteristics, and multiple wind speed characteristics of the historical meteorological characteristic information;

[0055] A second acquisition unit, configured to acquire a total meteorological variable according to the multiple temperature characteristics, multiple humidity characteristics, and multiple wind speed characteristics, and acquire corresponding temperature influence coefficients, humidity influence coefficients, and wind speed influence coefficients according to each temperature characteristic, humidity characteristic, and wind speed characteristic and the total meteorological variable;

[0056] A third acquisition unit, configured to acquire multiple power loads and multiple load change rates of the historical load characteristic information;

[0057] A fourth acquisition unit, configured to acquire a total load variable according to the multiple power loads and multiple load change rates, and acquire corresponding power influence coefficients and load change influence coefficients according to each power load and load change rate and the total load variable;

[0058] A fifth acquisition unit, configured to acquire a load fluctuation influence rate according to the multiple temperature influence coefficients, multiple humidity influence coefficients, multiple wind speed influence coefficients, multiple power influence coefficients, and multiple load change influence coefficients.

[0059] The present invention further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned distributed energy storage converter optimization method based on big data analysis are implemented.

[0060] The present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned distributed energy storage converter optimization method based on big data analysis are implemented.

[0061] The beneficial effects of the present invention are as follows: By combining meteorological and load historical data, the present invention can more accurately predict load fluctuations. According to the obtained load fluctuation influence rate, the control parameters of the energy storage converter can be dynamically adjusted to adapt to load changes. By analyzing the historical operating state, the key factors affecting the energy conversion efficiency can be identified, the charge-discharge strategy can be optimized, and the overall efficiency of the energy storage system can be improved. According to the real-time energy conversion efficiency data, the control parameters can be dynamically adjusted under different operating conditions to ensure that the system operates within the optimal efficiency range. By real-time monitoring the load value and demand response gain and adjusting the charge-discharge strategy of the distributed energy storage converter accordingly, not only the dynamic response ability and stability of the system are improved, but also it helps to improve the energy use efficiency and reduce costs. Dynamically adjusting the charging amount helps to optimize the use of energy storage and improve the overall economy and stability of the system. Description of the Drawings

[0062] Figure 1 It is a schematic flowchart of the method according to an embodiment of the present invention.

[0063] Figure 2 It is a schematic structural diagram of the device according to an embodiment of the present invention.

[0064] Figure 3 It is a schematic internal structure diagram of a computer device according to an embodiment of the present invention.

[0065] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0066] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0067] As Figure 1 shown, the present invention provides an optimization method for a distributed energy storage converter based on big data analysis, including:

[0068] S1. Obtain the historical environmental characteristic information and historical operating state characteristic information of the distributed energy storage converter, wherein the historical operating state characteristic information includes historical electrical characteristic information and historical energy storage characteristic information;

[0069] S2. Obtain the historical meteorological characteristic information and historical load characteristic information of the historical environmental characteristic information, and obtain the load fluctuation influence rate according to the historical meteorological characteristic information and the historical load characteristic information;

[0070] S3. Obtain the energy conversion efficiency according to the historical electrical characteristic information and the historical energy storage characteristic information, and obtain the load prediction value according to the energy conversion efficiency and the load fluctuation influence rate;

[0071] S4. Obtain the demand response gain according to the load prediction value;

[0072] S5. Obtain the adjusted real-time environmental characteristic information and real-time operating status characteristic information of the distributed energy storage converter, and obtain the real-time load value according to the real-time environmental characteristic information and the real-time operating status characteristic information;

[0073] S6. Adjust the charge and discharge strategy of the distributed energy storage converter according to the real-time load value and the demand response gain until the distributed energy storage converter system is balanced.

[0074] As described in the above steps S1 - S6, a distributed energy storage converter is a power electronic device used to connect and manage distributed energy sources (such as solar energy, wind energy, etc.) and energy storage systems (such as batteries). Its main function is to achieve the conversion, control, and optimization of electrical energy for efficient storage and release of electrical energy. Its main functions include electrical energy conversion, energy management, power regulation, and intelligent control. It can be used in energy storage systems for households or commercial buildings, combined with solar power generation, to increase the proportion of self - used electricity. The distributed energy storage converter plays a key role in realizing the efficient utilization of renewable energy, enhancing the flexibility and stability of the power system. With the popularization of distributed energy sources, its importance has become increasingly prominent. Existing distributed energy storage converters adopt control strategies based on fixed rules. For example, according to the priorities of different loads (such as important loads and non - important loads), when the power supply is insufficient, the demand of important loads is preferentially met, and corresponding charge - discharge operations are carried out. However, the above - mentioned method fails to dynamically adjust according to real - time data and environmental changes, lacking an effective demand response strategy. It may lead to the situation that when the load peak or rapid fluctuations occur, the energy storage converter cannot quickly adjust the charge - discharge strategy to maintain system balance. In the present invention, by obtaining the historical environmental characteristic information of the distributed energy storage converter, and obtaining the load fluctuation influence rate according to the historical meteorological characteristic information and historical load characteristic information in the historical environmental characteristic information. Among them, the load fluctuation influence rate refers to the degree of influence of load changes on system performance or stability, and is used to evaluate the impact of the change range of the load on the operating state of the power system, equipment, or energy storage system. By combining meteorological and load historical data, load fluctuations can be predicted more accurately. This multi - variable analysis can better capture the dynamic relationship between load and meteorological changes. Analyzing historical data helps to identify the patterns of load fluctuations, and can foresee future possible load changes, so as to better carry out regulation. According to the obtained load fluctuation influence rate, the control parameters of the energy storage converter can be dynamically adjusted to adapt to load changes. For example, when the load fluctuation is large, the response sensitivity is increased to improve the adaptability of the system. Understanding the load fluctuation characteristics can help avoid over - reaction, reduce frequent charge - discharge operations, and improve the stability and efficiency of the system. By obtaining the historical operating state characteristic information of the distributed energy storage converter, and obtaining the energy conversion efficiency according to the historical electrical characteristic information and historical energy storage characteristic information in the historical operating state characteristic information, and obtaining the load prediction value according to the energy conversion efficiency and the load fluctuation influence rate. Among them, the energy conversion efficiency refers to the ratio between the input energy and the output energy during the energy conversion process, reflecting the effectiveness of the system in converting one form of energy (such as electrical energy, thermal energy) into another form. By analyzing the historical operating state, the key factors affecting the energy conversion efficiency can be identified, the charge - discharge strategy can be optimized, and the overall efficiency of the energy storage system can be improved. According to the real - time energy conversion efficiency data, the control parameters can be dynamically adjusted under different operating conditions to ensure that the system operates within the optimal efficiency range. Using the relationship between the energy conversion efficiency and the load fluctuation influence rate,It is possible to more accurately predict load fluctuations, thereby making timely responses under different load conditions. By comprehensively considering the energy conversion efficiency, the error of load prediction can be reduced, and the response ability of the system can be improved. According to different operating states and energy conversion efficiencies, customized control strategies can be designed to cope with various load situations and improve response sensitivity. The combination of accurate load prediction and energy efficiency monitoring helps to better balance power supply and load demand, reduce the unstable factors caused by power supply fluctuations, reduce the risk of over-discharge or over-charging, ensure the stable operation of the energy storage system when the load changes, and avoid impacting the power grid. By obtaining the demand response gain and the real-time load value of the distributed energy storage converter through the load prediction value, and then adjusting the charge and discharge strategy of the distributed energy storage converter according to the real-time load value and the demand response gain until the distributed energy storage converter system is balanced. Among them, the demand response gain refers to the additional benefits or benefits that can be achieved by adjusting the power demand of users (for example, reducing electricity consumption during peak hours) in demand response activities. By real-time monitoring the load changes, the charge and discharge strategy can be quickly adjusted to cope with load fluctuations, improve the flexibility and adaptability of the system. According to the real-time calculation of the demand response gain, the operating state of the energy storage system can be adjusted more precisely to ensure the balance between power supply and demand. By optimizing the charge and discharge strategy, the impact of load fluctuations on the system can be effectively reduced, maintaining the stability of power supply, avoiding power supply interruptions or overloads. By dynamically adjusting the charge and discharge strategy according to the demand response gain, unnecessary charge and discharge cycles can be reduced, the energy use efficiency can be improved, and the energy loss can be reduced. Make full use of the energy storage system to charge during low load and discharge during high load to achieve the optimal allocation of resources. By real-time monitoring the load value and the demand response gain and adjusting the charge and discharge strategy of the distributed energy storage converter accordingly, not only the dynamic response ability and stability of the system are improved, but also it helps to improve the energy use efficiency and reduce costs. Dynamically adjusting the charging amount helps to optimize the use of energy storage and improve the overall economy and stability of the system.

[0075] In one embodiment, step S2 of obtaining the load fluctuation influence rate according to the historical meteorological characteristic information and the historical load characteristic information includes:

[0076] S21. Obtain multiple temperature characteristics, multiple humidity characteristics, and multiple wind speed characteristics of the historical meteorological characteristic information;

[0077] S22. Obtain the total meteorological variable according to the multiple temperature characteristics, multiple humidity characteristics, and multiple wind speed characteristics, and obtain the corresponding temperature influence coefficient, humidity influence coefficient, and wind speed influence coefficient according to each temperature characteristic, humidity characteristic, and wind speed characteristic and the total meteorological variable. The calculation formula of the temperature influence coefficient is: ; where represents the temperature influence coefficient, represents the a temperature feature, representing the total meteorological variable, representing the serial number of the temperature feature; wherein the calculation methods of the humidity influence coefficient and the wind speed influence coefficient are the same as those of the temperature influence coefficient;

[0078] S23. Obtain multiple electric loads and multiple load change rates of the historical load feature information;

[0079] S24. Obtain the total load variable according to the multiple electric loads and the multiple load change rates, and obtain the corresponding electric influence coefficient and load change influence coefficient according to each electric load and load change rate and the total load variable. Similarly, the calculation methods of the electric influence coefficient and the load change influence coefficient here are the same as those of the temperature influence coefficient;

[0080] S25. Obtain the load fluctuation influence rate according to the multiple temperature influence coefficients, the multiple humidity influence coefficients, the multiple wind speed influence coefficients, the multiple electric influence coefficients and the multiple load change influence coefficients.

[0081] As described in the above steps S21 - S25, the present invention obtains the total meteorological variable through multiple temperature characteristics, multiple humidity characteristics, and multiple wind speed characteristics of historical meteorological characteristic information, and obtains the corresponding temperature influence coefficient, humidity influence coefficient, and wind speed influence coefficient according to each temperature characteristic, humidity characteristic, and wind speed characteristic and the total meteorological variable. Among them, the total meteorological variable generally refers to a more comprehensive meteorological index or parameter obtained by integrating multiple meteorological characteristics (such as temperature, humidity, wind speed, etc.). By analyzing multiple meteorological characteristics, the impact of environmental factors on power demand and supply can be understood more comprehensively, which helps to formulate a more scientific operation strategy. By understanding the impact of each meteorological characteristic on the total meteorological variable, it can help identify which characteristics have the greatest impact on the performance of the load and energy storage system under specific conditions, thus achieving refined management. Meteorological factors such as temperature, humidity, and wind speed are closely related to power demand. Using the influence coefficient can improve the load prediction model and enhance its accuracy. According to the changes in meteorological factors, the charge and discharge strategy of the energy storage converter can be adjusted in real time to enhance the response ability to load fluctuations and maintain the balance of power supply. By accurately predicting the load and optimizing the response, the fluctuations of the power grid caused by meteorological factors can be reduced, and the overall stability of the system can be improved. Through the analysis of historical meteorological characteristic information, the influence coefficients of temperature, humidity, and wind speed, etc. can be obtained, which can optimize the control parameters of the distributed energy storage converter in multiple aspects. This not only improves the accuracy and dynamic response ability of load prediction, but also enhances the stability and economic benefits of the system. The total load variable is obtained through multiple power loads and multiple load change rates of historical load characteristic information, and the corresponding power influence coefficient and load change influence coefficient are obtained according to each power load and load change rate and the total load variable. By using the data of multiple power loads and load change rates, the future load demand can be predicted more accurately, the error can be reduced, and the scheduling strategy can be optimized. By analyzing the historical load change rate, the seasonal or temporal patterns of the load can be identified, so as to make more reasonable predictions in different time periods or climate conditions. According to the power influence coefficient and load change influence coefficient, the charge and discharge strategy of the energy storage converter is adjusted in real time, enabling it to respond flexibly to load changes. Precise load information and change rate analysis can help identify potential load fluctuations, adjust the energy storage strategy in a timely manner, reduce the impact on the power grid, accurately control the charge and discharge process of the energy storage device, reduce unnecessary energy losses, and improve the overall efficiency. Among them, the load change rate is the ratio of the increase or decrease of the load within a certain time period to the load at the beginning of that time period. The load fluctuation influence rate is obtained by summing up multiple temperature influence coefficients, multiple humidity influence coefficients, multiple wind speed influence coefficients, multiple power influence coefficients, and multiple load change influence coefficients. In this way, by combining the influences of temperature, humidity, wind speed, power, and load change, the impact of the external environment on load fluctuations can be comprehensively understood, and the prediction accuracy can be enhanced. Based on the load fluctuation influence rate, the charge and discharge strategy of the energy storage converter is dynamically adjusted, so as to flexibly respond to load changes and maintain system balance.By accurately identifying load fluctuations, the impact on the power grid can be more effectively reduced, enhancing the overall stability of the system. In summary, using the load fluctuation influence rate to optimize the control parameters of the distributed energy storage converter can not only improve the dynamic response ability and stability of the system, but also provide strong support for the intelligent management of the power system and the integration of renewable energy.

[0082] In one embodiment, the step S3 of obtaining the energy conversion efficiency according to the historical electrical characteristic information and the historical energy storage characteristic information includes:

[0083] S31. Obtain the charge-discharge rate and discharge depth of the historical energy storage characteristic information;

[0084] S32. Obtain the rated capacity of the distributed energy storage converter, and obtain the charge duration and discharge duration according to the rated capacity, charge-discharge rate, and discharge depth;

[0085] S33. Obtain the harmonics, frequency, output power, and input power of the historical electrical characteristic information;

[0086] S34. Obtain the input energy value according to the charge duration, input power, harmonics, and frequency;

[0087] S35. Calculate the output energy value according to the discharge duration, discharge depth, output power, harmonics, and frequency, where the calculation formula is:

[0088] ;

[0089] Wherein, represents the output energy value, represents the output power, represents the discharge duration, represents the frequency, represents the harmonics, represents the discharge depth;

[0090] S36. Calculate the energy conversion efficiency according to the output energy value and the input energy value, where the calculation formula is:

[0091] ;

[0092] Wherein, represents the energy conversion efficiency, represents the output energy value, represents the input energy value.

[0093] As described in the above steps S31 - S36, the present invention obtains the rated capacity of the distributed energy storage converter, and obtains the charging duration and the discharging duration according to the rated capacity, the charge - discharge rate and the depth of discharge of the historical energy storage characteristic information. Among them, the charge - discharge rate generally refers to the rate of battery charging or discharging, and the depth of discharge refers to the proportion of the discharged electricity in the total battery capacity during the battery discharging process. The calculation method of the charging duration is the ratio of the product value between the charge - discharge rate and the depth of discharge to the charge - discharge rate. The discharging duration is the ratio of the product value between the difference obtained by calculating 1 minus the depth of discharge and the charge - discharge rate to the charge - discharge rate. By accurately calculating the charging and discharging durations in this way, the operation plan of the energy storage device can be arranged more effectively, ensuring that the energy storage system can respond quickly when needed. Understanding the charging and discharging durations helps to predict the availability of the energy storage system, reducing the response time affected by delays. In the case of load fluctuations, the operation state of the energy storage device can be adjusted in a timely manner according to the calculated charging and discharging durations, effectively maintaining the load balance of the power grid and enhancing the stability of the system. By obtaining the harmonics, frequency, output power and input power of the historical electrical characteristic information, and obtaining the input energy value according to the charging duration, input power, harmonics and frequency, calculating the output energy value according to the discharging duration, depth of discharge, output power, harmonics and frequency, and then calculating the energy conversion efficiency according to the output energy value and the input energy value. By calculating the input and output energy values and the energy conversion efficiency, the performance of the energy storage system can be effectively evaluated, thereby identifying potential points for efficiency improvement. By understanding the energy conversion efficiency, the charging and discharging durations and strategies can be adjusted specifically to improve the overall energy utilization rate of the system. According to the real - time input and output energy data, the control parameters of the energy storage converter can be dynamically adjusted to quickly respond to load changes and maintain the stability of the power grid. By monitoring harmonics and frequency, optimizing the control parameters can reduce the impact of harmonics on the system stability and maintain the power quality. Precise energy calculation and adjustment can effectively balance the power grid load, reduce the fluctuations caused by uneven load, and optimizing the energy conversion efficiency can reduce energy losses and operating costs, thereby improving the overall economic benefits. Therefore, by systematically obtaining and analyzing the historical electrical characteristic information and optimizing the control parameters of the distributed energy storage converter accordingly, the dynamic response balance stability can be significantly improved.

[0094] In one embodiment, step S3 of obtaining the load prediction value according to the energy conversion efficiency and the load fluctuation influence rate includes:

[0095] S37. Obtain multiple load data of the distributed energy storage converter within a preset time period, and obtain the initial load average value according to the multiple load data;

[0096] S38. Obtain the first weight factor of the energy conversion efficiency;

[0097] S39. Obtain the second weight factor of the load fluctuation influence rate;

[0098] S310. Input the initial load mean value, energy conversion efficiency, load fluctuation influence rate, first weight factor, and second weight factor into the load prediction model to obtain a load prediction value, where the load prediction model is:

[0099] ;

[0100] Wherein, represents the load prediction value, represents the initial load mean value, represents the energy conversion efficiency, represents the load fluctuation influence rate, represents the first weight factor, represents the second weight factor.

[0101] As described in the above steps S37 - S310, the present invention obtains multiple load data of the distributed energy storage converter within a preset time period, obtains the initial load mean value according to the multiple load data, obtains the first weight factor of the energy conversion efficiency and the second weight factor of the load fluctuation influence rate, and inputs the initial load mean value, energy conversion efficiency, load fluctuation influence rate, first weight factor, and second weight factor into the load prediction model to obtain a load prediction value. By analyzing the multiple load data, a more accurate initial load mean value can be obtained, enhancing the reliability and accuracy of load prediction. Using the energy conversion efficiency and the load fluctuation influence rate as weight factors, the prediction model can be dynamically adjusted according to the actual situation, thereby improving the flexibility of load prediction. Through the load prediction value, the control parameters of the energy storage converter can be adjusted more accurately to achieve more efficient charge and discharge management, optimize energy use. Precise load prediction helps to quickly respond to changes in grid demand, maintain dynamic balance, and reduce system instability caused by load fluctuations. By considering the load fluctuation influence rate, it is possible to better cope with load changes and ensure the stable operation of the system under various load conditions. The load prediction value can help the energy storage system better balance the load and reduce fluctuations in the power grid caused by uneven load. Therefore, by obtaining and analyzing load data and related factors, the control parameter optimization ability of the distributed energy storage converter can be significantly improved by using the load prediction model, thereby enhancing the dynamic response balance stability of the system, improving the overall efficiency, reducing costs, and supporting the efficient utilization of renewable energy.

[0102] In one embodiment, the step S4 of obtaining the demand response gain according to the reference load value and the load prediction value includes:

[0103] S41. Obtain the reference load value of the distributed energy storage converter;

[0104] S42. Obtain a reference gain based on the reference load value and the load prediction value;

[0105] S43. Obtain a demand response gain based on the reference gain, the reference load value, and the load prediction value. The calculation formula is: ; where represents the demand response gain, represents the reference gain, represents the load prediction value, represents the reference load value.

[0106] As described in the above steps S41 - S43, the present invention obtains the reference load value of the distributed energy storage converter, obtains the reference gain according to the reference load value and the load prediction value, and obtains the demand response gain according to the reference gain, the reference load value, and the load prediction value. Since the reference load value provides a reference point, by comparing it with the load prediction value, the load state of the system can be better evaluated, ensuring the effectiveness of the control strategy. By calculating the reference gain, the control strategy can be dynamically adjusted according to the actual load change, enabling the system to respond more flexibly to load fluctuations. The calculation of the reference gain and the demand response gain helps to formulate more accurate control parameters, enabling the converter to achieve the best performance under different load conditions. The accurate gain value enables the control system to quickly respond to load changes, reduce the hysteresis phenomenon, and maintain the stability of the power grid. By analyzing the reference gain and the demand response gain, the charging and discharging processes of the energy storage system can be more reasonably allocated, improving the overall energy utilization rate.

[0107] In one embodiment, step S6 of adjusting the charging and discharging strategy of the distributed energy storage converter according to the real - time load value and the demand response gain until the distributed energy storage converter system reaches balance includes:

[0108] S61. Obtain the real - time load value and the load prediction value, and determine whether the real - time load value is greater than the load prediction value;

[0109] S62. If the real - time load value is greater than the load prediction value, obtain the discharge efficiency coefficient of the distributed energy storage converter, and obtain the discharge amount according to the discharge efficiency coefficient and the demand response gain;

[0110] S63. Adjust the discharge of the distributed energy storage converter according to the discharge amount until the distributed energy storage converter system responds to balance;

[0111] S64. If the real - time load value is not less than the load prediction value, obtain the charge efficiency coefficient of the distributed energy storage converter, and obtain the charge amount according to the charge efficiency coefficient and the demand response gain;

[0112] S65. Adjust the charging of the distributed energy storage converter according to the charging amount until the response of the distributed energy storage converter system is balanced.

[0113] As described in the above steps S101 - S103, the present invention obtains the real - time load value and the load prediction value, and judges whether the real - time load value is greater than the load prediction value. If the real - time load value is greater than the load prediction value, it obtains the discharge efficiency coefficient of the distributed energy storage converter, and obtains the discharge amount according to the discharge efficiency coefficient and the demand response gain, and adjusts the discharge of the distributed energy storage converter according to the discharge amount until the response of the distributed energy storage converter system is balanced. If the real - time load value is not less than the load prediction value, it obtains the charging efficiency coefficient of the distributed energy storage converter, and obtains the charging amount according to the charging efficiency coefficient and the demand response gain, and then adjusts the charging of the distributed energy storage converter according to the charging amount until the response of the distributed energy storage converter system is balanced. According to the comparison between the real - time load and the predicted load, the system can quickly judge whether discharging or charging is needed, ensuring timely response to changes in grid demand. By combining the discharge efficiency coefficient and the charging efficiency coefficient, charging and discharging operations can be carried out under optimal conditions, improving the overall utilization rate of energy. The charging and discharging amounts calculated according to the efficiency coefficients ensure that the energy storage system operates in the most effective state, thereby reducing unnecessary energy losses. Dynamically adjusting the discharge or charging amount can effectively balance the grid load, avoiding grid fluctuations and potential failures caused by uneven loads. Discharging during high loads helps reduce peak load pressure, relieve the grid burden, and improve power supply reliability.

[0114] As Figure 2 shown, the present invention also provides an optimized system for a distributed energy storage converter based on big data analysis, including:

[0115] A first acquisition module for acquiring the historical environmental characteristic information and historical operating state characteristic information of the distributed energy storage converter, wherein the historical operating state characteristic information includes historical electrical characteristic information and historical energy storage characteristic information;

[0116] A second acquisition module for acquiring the historical meteorological characteristic information and historical load characteristic information of the historical environmental characteristic information, and obtaining the load fluctuation influence rate according to the historical meteorological characteristic information and the historical load characteristic information;

[0117] A third acquisition module for obtaining the energy conversion efficiency according to the historical electrical characteristic information and the historical energy storage characteristic information, and obtaining the load prediction value according to the energy conversion efficiency and the load fluctuation influence rate;

[0118] A fourth acquisition module for obtaining the demand response gain according to the load prediction value;

[0119] A fifth acquisition module, configured to acquire the adjusted real-time environmental characteristic information and real-time operation state characteristic information of the distributed energy storage converter, and acquire a real-time load value according to the real-time environmental characteristic information and the real-time operation state characteristic information;

[0120] An adjustment module, configured to adjust the charge and discharge strategy of the distributed energy storage converter according to the real-time load value and the demand response gain until the distributed energy storage converter system reaches balance.

[0121] In one embodiment, the second acquisition module includes:

[0122] A first acquisition unit, configured to acquire a plurality of temperature characteristics, a plurality of humidity characteristics, and a plurality of wind speed characteristics of the historical meteorological characteristic information;

[0123] A second acquisition unit, configured to acquire a total meteorological variable according to the plurality of temperature characteristics, the plurality of humidity characteristics, and the plurality of wind speed characteristics, and acquire a corresponding temperature influence coefficient, humidity influence coefficient, and wind speed influence coefficient according to each temperature characteristic, humidity characteristic, and wind speed characteristic and the total meteorological variable;

[0124] A third acquisition unit, configured to acquire a plurality of electric loads and a plurality of load change rates of the historical load characteristic information;

[0125] A fourth acquisition unit, configured to acquire a total load variable according to the plurality of electric loads and the plurality of load change rates, and acquire a corresponding electric influence coefficient and load change influence coefficient according to each electric load and load change rate and the total load variable;

[0126] A fifth acquisition unit, configured to acquire a load fluctuation influence rate according to the plurality of temperature influence coefficients, the plurality of humidity influence coefficients, the plurality of wind speed influence coefficients, the plurality of electric influence coefficients, and the plurality of load change influence coefficients.

[0127] As Figure 3 shown, the present invention further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned distributed energy storage converter optimization method based on big data analysis are implemented.

[0128] The present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned distributed energy storage converter optimization method based on big data analysis are implemented.

[0129] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, storage, database, or other medium provided by the present invention and used in the embodiments can include non-volatile and / or volatile memories. 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), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0130] It should be noted that in this document, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, apparatus, article or method comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article or method. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, apparatus, article or method comprising the element.

[0131] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A distributed energy storage converter optimization method based on big data analysis, characterized in that: include: Acquire historical environmental characteristic information and historical operating state characteristic information of the distributed energy storage converter, wherein the historical operating state characteristic information includes historical electrical characteristic information and historical energy storage characteristic information; Acquire historical meteorological characteristic information and historical load characteristic information of the historical environmental characteristic information, and acquire a load fluctuation impact rate according to the historical meteorological characteristic information and the historical load characteristic information; Obtaining energy conversion efficiency according to the historical electrical characteristic information and the historical energy storage characteristic information, and obtaining a load forecast value according to the energy conversion efficiency and the load fluctuation impact rate; Obtaining a demand response gain according to the load forecast value; Acquire the real-time environmental characteristic information and the real-time operating state characteristic information of the distributed energy storage converter after adjustment, and acquire the real-time load value according to the real-time environmental characteristic information and the real-time operating state characteristic information; Adjusting the charging and discharging strategy of the distributed energy storage converter according to the real-time load value and the demand response gain until the distributed energy storage converter system is balanced; The step of obtaining the demand response gain according to the load prediction value comprises: Obtaining a benchmark load value of a distributed energy storage converter; Obtaining a reference gain according to the reference load value and the load prediction value; The demand response gain is obtained according to the reference gain, the reference load value and the load prediction value.

2. The distributed energy storage converter optimization method based on big data analysis according to claim 1 is characterized in that: The step of obtaining the load fluctuation impact rate according to the historical meteorological characteristic information and the historical load characteristic information comprises: Acquire multiple temperature characteristics, multiple humidity characteristics, and multiple wind speed characteristics of the historical meteorological characteristic information; Obtaining a total meteorological variable according to a plurality of temperature characteristics, a plurality of humidity characteristics, and a plurality of wind speed characteristics, and obtaining a corresponding temperature influence coefficient, humidity influence coefficient, and wind speed influence coefficient according to each temperature characteristic, humidity characteristic, and wind speed characteristic and the total meteorological variable; Acquire multiple power loads and multiple load change rates of the historical load characteristic information; Obtaining a total load variable according to a plurality of power loads and a plurality of load change rates, and obtaining a corresponding power influence coefficient and a load change influence coefficient according to each power load, load change rate and the total load variable; The load fluctuation influence rate is obtained according to multiple temperature influence coefficients, multiple humidity influence coefficients, multiple wind speed influence coefficients, multiple power influence coefficients and multiple load change influence coefficients.

3. The distributed energy storage converter optimization method based on big data analysis according to claim 1 is characterized in that: The step of acquiring energy conversion efficiency according to the historical electrical characteristic information and the historical energy storage characteristic information comprises: Obtaining the charge and discharge rate and discharge depth of the historical energy storage characteristic information; Obtaining the rated capacity of the distributed energy storage converter, and obtaining the charging time and the discharging time according to the rated capacity, the charging and discharging rate, and the discharge depth; Obtaining harmonics, frequency, output power and input power of the historical electrical characteristic information; Acquire input energy value according to the charging time, input power, harmonics and frequency; The output energy value is calculated according to the discharge duration, discharge depth, output power, harmonics and frequency, wherein the calculation formula is: ； in, Represents the output energy value, Indicates the output power, Indicates the discharge time. Indicates frequency, represents harmonics, Indicates the depth of discharge; The energy conversion efficiency is calculated according to the output energy value and the input energy value, wherein the calculation formula is: ； in, represents the energy conversion efficiency, Represents the output energy value, Indicates the input energy value.

4. The distributed energy storage converter optimization method based on big data analysis according to claim 1 is characterized in that: The step of obtaining a load prediction value according to the energy conversion efficiency and the load fluctuation influence rate comprises: Acquire multiple load data of the distributed energy storage converter within a preset time period, and acquire an initial load average value according to the multiple load data; Obtaining a first weight factor of the energy conversion efficiency; Obtaining a second weight factor of the load fluctuation impact rate; The initial load mean value, energy conversion efficiency, load fluctuation impact rate, first weight factor and second weight factor are input into the load forecasting model to obtain the load forecast value, wherein the load forecasting model is: ； in, represents the load forecast value, represents the initial load mean, represents the energy conversion efficiency, represents the load fluctuation impact rate, represents the first weight factor, represents the second weighting factor.

5. The distributed energy storage converter optimization method based on big data analysis according to claim 1 is characterized in that: The step of adjusting the charging and discharging strategy of the distributed energy storage converter according to the real-time load value and the demand response gain until the distributed energy storage converter system is balanced includes: Obtaining a real-time load value and a load forecast value, and determining whether the real-time load value is greater than the load forecast value; If the real-time load value is greater than the load prediction value, the discharge efficiency coefficient of the distributed energy storage converter is obtained, and the discharge amount is obtained according to the discharge efficiency coefficient and the demand response gain; Discharging and adjusting the distributed energy storage converter according to the discharge amount until the distributed energy storage converter system responds in a balanced manner; If the real-time load value is not less than the load prediction value, the charging efficiency coefficient of the distributed energy storage converter is obtained, and the charging amount is obtained according to the charging efficiency coefficient and the demand response gain; The charging of the distributed energy storage converter is adjusted according to the charging amount until the distributed energy storage converter system responds in a balanced manner.

6. A distributed energy storage converter optimization system based on big data analysis, characterized in that: include: A first acquisition module is used to acquire historical environmental characteristic information and historical operating state characteristic information of the distributed energy storage converter, wherein the historical operating state characteristic information includes historical electrical characteristic information and historical energy storage characteristic information; A second acquisition module is used to acquire historical meteorological characteristic information and historical load characteristic information of the historical environmental characteristic information, and acquire a load fluctuation impact rate according to the historical meteorological characteristic information and the historical load characteristic information; A third acquisition module is used to acquire energy conversion efficiency according to the historical electrical characteristic information and the historical energy storage characteristic information, and to acquire a load prediction value according to the energy conversion efficiency and the load fluctuation influence rate; A fourth acquisition module, configured to acquire a demand response gain according to the load prediction value; A fifth acquisition module, used to acquire the real-time environmental characteristic information and the real-time operating state characteristic information of the distributed energy storage converter after adjustment, and acquire the real-time load value according to the real-time environmental characteristic information and the real-time operating state characteristic information; An adjustment module, used to adjust the charging and discharging strategy of the distributed energy storage converter according to the real-time load value and the demand response gain until the distributed energy storage converter system is balanced; The step of obtaining the demand response gain according to the load prediction value comprises: Obtaining a benchmark load value of a distributed energy storage converter; Obtaining a reference gain according to the reference load value and the load prediction value; The demand response gain is obtained according to the reference gain, the reference load value and the load prediction value.

7. The distributed energy storage converter optimization system based on big data analysis according to claim 6 is characterized in that: The second acquisition module includes: A first acquisition unit, used to acquire a plurality of temperature characteristics, a plurality of humidity characteristics and a plurality of wind speed characteristics of the historical meteorological characteristic information; A second acquisition unit is used to acquire a total meteorological variable according to a plurality of temperature characteristics, a plurality of humidity characteristics and a plurality of wind speed characteristics, and acquire a corresponding temperature influence coefficient, humidity influence coefficient and wind speed influence coefficient according to each temperature characteristic, humidity characteristic and wind speed characteristic and the total meteorological variable; A third acquisition unit, configured to acquire a plurality of power loads and a plurality of load change rates of the historical load characteristic information; A fourth acquisition unit, configured to acquire a total load variable according to a plurality of power loads and a plurality of load change rates, and acquire a corresponding power influence coefficient and a load change influence coefficient according to each power load, load change rate and the total load variable; The fifth acquisition unit is used to acquire the load fluctuation influence rate according to multiple temperature influence coefficients, multiple humidity influence coefficients, multiple wind speed influence coefficients, multiple power influence coefficients and multiple load change influence coefficients.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. 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 method according to any one of claims 1 to 5 are implemented.

Images