Modularized energy storage battery charging and discharging scheduling management method

Abstract

The invention relates to a modular energy storage battery charging and discharging scheduling management method, and relates to the field of energy storage battery management, and the method comprises the steps: carrying out scheduling scheme enumeration by taking the expected operation power as the constraint, and obtaining a plurality of initial battery scheduling schemes; executing simulation operation, and constructing a plurality of simulated working battery temperature distributions; performing temperature diffusion prediction to generate a plurality of predicted battery temperature distributions; carrying out screening by taking the rigid temperature index as a constraint, and if a screening result is not 0, obtaining a plurality of first battery scheduling schemes; and optimizing the plurality of first battery scheduling schemes to obtain an optimal scheduling scheme for scheduling management. According to the invention, the problems of unbalanced charging and discharging among battery units and easy occurrence of local overheating of batteries due to the fact that an adaptive charging and discharging scheduling strategy cannot be set according to the battery state and the scheduling requirement in the charging and discharging process of a traditional battery pack can be solved; the heat dissipation problem generated in the charging and discharging process can be effectively controlled, and the stability and reliability of operation of the battery pack are ensured.

Description

Technical Field

[0001] The present invention relates to the field of energy storage battery management, and in particular to a modular energy storage battery charging and discharging scheduling management method. Background Art

[0002] Energy storage battery packs are energy storage systems composed of multiple battery cells, designed to store electrical energy and provide it to loads or grids when needed. With the rapid development of renewable energy and the transformation of energy structure, energy storage systems play an increasingly important role in power dispatching, load balancing, and efficient use of renewable energy such as wind and solar energy. As a core component, energy storage battery packs play a key role, especially in large-scale energy storage and dispatching.

[0003] However, with the continuous advancement of energy storage technology, the charging and discharging management methods of traditional energy storage battery packs have exposed some technical difficulties. At present, the traditional charging and discharging management methods are unable to set a corresponding charging and discharging scheduling strategy according to the battery status and scheduling requirements, resulting in unbalanced charging and discharging between battery cells, and prone to local overheating of the battery. Summary of the invention

[0004] The present invention provides a modular energy storage battery charging and discharging scheduling management method to solve the technical problem that during the charging and discharging process of traditional energy storage battery packs, a corresponding charging and discharging scheduling strategy cannot be set according to the battery status and scheduling requirements, resulting in unbalanced charging and discharging between battery cells and prone to local overheating of the battery.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, the present invention provides a modular energy storage battery charging and discharging scheduling management method, which is applied to an energy storage battery group, wherein the energy storage battery group includes a plurality of battery cells, and comprises: obtaining an expected operating power of the energy storage battery group, enumerating scheduling schemes based on a plurality of battery cells with the expected operating power being satisfied as a constraint, and obtaining a plurality of initial battery scheduling schemes; performing simulated operation of the plurality of initial battery scheduling schemes respectively through an energy storage battery simulation model, obtaining a plurality of simulated working battery temperature sets at the end of the operation, and constructing a plurality of simulated working battery temperature distributions; performing temperature diffusion superposition prediction on the plurality of simulated working battery temperature distributions respectively, and generating a plurality of predicted battery temperature distributions; screening the plurality of predicted battery temperature distributions with the preset rigid temperature index being satisfied as a constraint, and obtaining a plurality of first battery temperature distributions and a plurality of first battery scheduling schemes if the screening result is not 0; optimizing the plurality of first battery temperature distributions based on a heat dissipation evaluation function, setting the first battery scheduling scheme corresponding to the first battery temperature distribution with the largest heat dissipation adaptability as the optimal scheduling scheme, and performing operation scheduling of the energy storage battery group according to the optimal scheduling scheme.

[0007] In a second aspect, the present invention further provides an electronic device, comprising:

[0008] At least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can perform the steps of any one of the methods described in the first aspect above.

[0009] In a third aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed, the steps of the method described in any one of the first aspects are implemented.

[0010] The beneficial effects of the present invention are as follows: by obtaining the expected operating power of the energy storage battery group, taking the expected operating power as a constraint, enumerating the scheduling schemes based on a number of battery cells, and obtaining a plurality of initial battery scheduling schemes; then, through the energy storage battery simulation model, respectively executing the simulation operation of the plurality of initial battery scheduling schemes, obtaining a plurality of simulated working battery temperature sets at the end of the operation, and constructing a plurality of simulated working battery temperature distributions; then respectively performing temperature diffusion superposition prediction on the plurality of simulated working battery temperature distributions, and generating a plurality of predicted battery temperature distributions; further, taking the preset rigid temperature index as a constraint, screening the plurality of predicted battery temperature distributions, if the screening results is not 0, obtaining multiple first battery temperature distributions and multiple first battery scheduling plans; finally, based on the heat dissipation evaluation function, optimizing the multiple first battery temperature distributions, setting the first battery scheduling plan corresponding to the first battery temperature distribution with the largest heat dissipation adaptability as the optimal scheduling plan, and performing operation scheduling of the energy storage battery group according to the optimal scheduling plan; through the above method, on the premise of meeting the scheduling requirements, the scientificity and accuracy of the setting of the charging and discharging scheduling strategy can be improved, the heat dissipation problems generated during the battery charging and discharging process can be effectively controlled, the battery overheating can be avoided, and the stability and reliability of the battery group operation can be ensured; at the same time, the consumption of heat dissipation resources can be saved and the overall energy efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of a flow chart of a modular energy storage battery charging and discharging scheduling management method provided by the present invention;

[0012] Figure 2 A schematic diagram of the structure of an electronic device provided by the present invention;

[0013] Figure 3 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0014] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0015] Electronic device 500 , memory 510 , processor 520 , first computer program 511 , computer-readable storage medium 600 , second computer program 611 . DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0018] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0019] Embodiment 1, as Figure 1 As shown, an embodiment of the present invention provides a modular energy storage battery charging and discharging scheduling management method, which is applied to an energy storage battery pack, wherein the energy storage battery pack includes a plurality of battery cells, and specifically includes the following steps:

[0020] S100: Obtaining the expected operating power of the energy storage battery group, enumerating scheduling plans based on a number of battery units based on the expected operating power as a constraint, and obtaining multiple initial battery scheduling plans.

[0021] Furthermore, step S100 of the present invention further includes:

[0022] Obtain an expected operating power of an energy storage battery pack, wherein the expected operating power is an expected charging power or an expected discharging power, and the energy storage battery pack includes a plurality of battery cells, each of which is identified by a unique position coordinate; and based on satisfying the expected operating power as a constraint, enumerate battery scheduling schemes using the plurality of battery cells to obtain a plurality of initial battery scheduling schemes, wherein the number of working batteries and the battery position coordinates in each initial battery scheduling scheme are not exactly the same.

[0023] Specifically, the energy storage battery pack is composed of multiple battery cells, each battery cell has a unique location coordinate, and the working status of each battery cell will affect the overall performance of the battery pack. Among them, the physical location coordinates of the battery cell are very important for charge and discharge scheduling and temperature management, because battery cells in different positions may be affected by different heat dissipation, which in turn affects their charge and discharge capabilities.

[0024] First, the expected operating power of the energy storage battery pack is obtained, where the expected operating power is the expected charging power or the expected discharging power, which can be set according to the actual charging and discharging scenarios. When the battery pack is charging, the expected charging power refers to the power required to be input by the system within a given time; when the battery pack is used as a power source to provide electricity, the expected discharge power is the power output by the battery pack to meet the load demand or grid scheduling goals.

[0025] Next, the expected operating power is taken as a constraint condition, and the battery scheduling scheme is enumerated using the several battery cells, that is, the appropriate number and type of battery cells are selected to perform the task, and the battery scheduling scheme is generated according to the selection and position coordinates of the battery cells. Each scheduling scheme should meet the constraint conditions of the expected operating power. The main goal of the enumeration process is to generate multiple valid scheduling schemes and flexibly schedule them according to factors such as the number, location and state of the battery cells. Multiple battery scheduling schemes can be enumerated through various scheduling algorithms (such as heuristic algorithms, greedy algorithms, genetic algorithms, etc.), each scheme corresponds to a different battery cell combination, a different number of working batteries, and a different battery cell position allocation; multiple initial battery scheduling schemes are obtained, and the number of working batteries and the battery position coordinates in each initial battery scheduling scheme are not exactly the same, wherein batteries at different positions may have different effects on the charging and discharging strategies due to heat dissipation and other reasons.

[0026] S200: Using the energy storage battery simulation model, respectively executing simulation runs of the multiple initial battery scheduling schemes, obtaining multiple simulated working battery temperature sets at the end of the runs, and constructing multiple simulated working battery temperature distributions.

[0027] Furthermore, step S200 of the present invention further includes:

[0028] Acquire the expected operation target, and calculate the operation end time according to the expected operation target and the expected operation power; simulate and model the energy storage battery group, build an energy storage battery simulation model, and collect a sample battery scheduling plan set, a sample ambient temperature set, multiple sample initial battery temperature sets, and multiple sample working battery temperature sets at the end of historical operation as training data to train the energy storage battery simulation model until the expected convergence accuracy is met; monitor and acquire the real-time ambient temperature and several initial battery temperatures, and use the number of working batteries and battery position coordinates in the multiple initial battery scheduling plans to screen the several initial battery temperatures respectively to obtain multiple initial working battery temperature sets; integrate the multiple initial battery scheduling plans, real-time ambient temperature and multiple initial working battery temperature sets to obtain multiple input data, and input the multiple input data into the energy storage battery simulation model for simulation operation, and output multiple simulated working battery temperature sets at the end of operation; construct the multiple simulated working battery temperature distributions based on the working battery position coordinates and the multiple simulated working battery temperature sets.

[0029] Specifically, first, obtain the expected operation target, which is the expected charging target or the expected discharging target. The expected charging target refers to the final charging state of the battery pack, such as increasing the SOC of the battery pack from the current value to a specific value (such as 100%); the expected discharging target refers to the battery pack providing a certain power during the discharge process, and the discharge process involves extracting energy from the battery pack to meet the load demand until the SOC of the battery pack drops to a certain minimum value (such as 10%). Then, calculate the operation duration according to the expected operation target and the expected operation power, obtain the operation duration, and determine the end time of the operation, which is the current time plus the operation duration.

[0030] Next, the purpose of constructing the energy storage battery simulation model is to predict the performance and behavior of the battery pack by simulating the battery charging and discharging process, temperature changes and other key characteristics, such as simulating the temperature change of the battery. The energy storage battery pack is simulated and modeled in a three-dimensional simulation platform, that is, a three-dimensional geometric model of the energy storage battery pack is established, including the physical size of the battery pack, the layout of the battery cells, the battery connection method (such as series-parallel connection), and the distribution method of the battery module, etc., to generate an energy storage battery simulation model. Then, the historical operation log of the energy storage battery pack is queried, and a sample battery scheduling plan set, a sample ambient temperature set, a plurality of sample initial battery temperature sets, and a plurality of sample working battery temperature sets at the end of the historical operation are collected; further, the sample battery scheduling plan, the sample ambient temperature and the plurality of sample initial battery temperatures are used as input training data, and the corresponding sample working battery temperature is used as output training data to train the energy storage battery simulation model. For example, the relationship between the temperature change of the battery and the battery scheduling and the ambient temperature can be learned through a regression model until the model output result reaches the expected convergence accuracy, such as the loss function is less than the expected index, etc., to obtain a trained energy storage battery simulation model.

[0031] Then, the real-time ambient temperature and several initial battery temperatures at the current time node are monitored and acquired. The real-time ambient temperature data can be usually acquired through sensors or temperature control systems. The initial battery temperature can be measured by temperature sensors installed in each battery cell. The several initial battery temperatures are further screened using the number of working batteries and the battery position coordinates in the multiple initial battery scheduling schemes, that is, the battery cells that need to participate in the simulation calculation are screened out according to the number of working batteries and the battery position coordinates in each scheduling scheme. These batteries will be used as working battery cells to obtain multiple initial working battery temperature sets.

[0032] Next, the multiple initial battery scheduling schemes, real-time ambient temperature and multiple initial working battery temperature sets are integrated to obtain multiple input data, wherein each set of input data includes the initial battery scheduling scheme, the real-time ambient temperature and the corresponding initial working battery temperature set. The multiple input data are then respectively input into the energy storage battery simulation model for simulation operation. The simulation model will simulate the battery charging and discharging process and temperature change according to different input conditions, and output the temperature distribution result at the end of the operation to obtain multiple simulated working battery temperature sets at the end of the operation.

[0033] Finally, based on the working battery position coordinates and multiple simulated working battery temperature sets, the temperature data of the battery cell is combined with its physical position, and a temperature distribution diagram is drawn within the spatial range of the battery pack to obtain multiple simulated working battery temperature distributions.

[0034] S300: Perform temperature diffusion superposition prediction on the multiple simulated working battery temperature distributions respectively to generate multiple predicted battery temperature distributions.

[0035] Furthermore, step S300 of the present invention further includes:

[0036] The working operation log of the energy storage battery pack is queried to collect a sample working battery temperature distribution set and a sample all-battery temperature distribution set at the end of historical operation; the sample working battery temperature distribution is used as input and the sample all-battery temperature distribution is used as supervision, and the sample working battery temperature distribution set and the sample all-battery temperature distribution set are used to perform supervised training on the BP neural network until convergence to obtain a temperature diffusion superposition predictor; the temperature diffusion superposition predictor is used to perform temperature diffusion superposition prediction on the multiple simulated working battery temperature distributions respectively, and the multiple predicted battery temperature distributions are output.

[0037] Specifically, the working operation log of the energy storage battery pack records various data of the battery pack during operation, including charging and discharging records, temperature changes, etc. By querying these logs, valuable historical data can be obtained to help analyze the temperature performance of the battery pack under different working conditions. Then query the working operation log of the energy storage battery pack, collect multiple sample working battery temperature distributions, construct a sample working battery temperature distribution set, and collect the temperature distribution of all batteries (including working battery cells and non-working battery cells) of the samples of different sample working battery temperature distributions at the end of the historical operation to obtain the sample all battery temperature distribution set.

[0038] Next, the sample working battery temperature distribution is used as input data, the sample all battery temperature distribution is used as supervision data, and the sample working battery temperature distribution set and the sample all battery temperature distribution set are used as training data to supervise the BP neural network training. First, the input layer receives the sample working battery temperature distribution as input data, and the data is processed by the hidden layer. The neurons in each hidden layer perform weighted summation on the input, and apply the activation function (such as sigmoid or ReLU) to obtain the output. The output layer generates the prediction result of the model, that is, the predicted battery temperature distribution; then, the error between the prediction result and the actual supervision data (the sample all battery temperature distribution set) is calculated. The error refers to the gap between the network output and the actual target, which is usually measured by the mean square error; then, the gradient of the error relative to the weight of each layer is calculated layer by layer through the gradient descent method of the error, and the weight of each connection is updated using the gradient descent algorithm; iterative training is performed, and each iteration network adjusts the weight according to the feedback error, gradually reducing the prediction error, until the error converges to a smaller value or reaches the set maximum number of iterations, and a trained temperature diffusion superposition predictor is obtained.

[0039] Finally, the multiple simulated working battery temperature distributions are input into the temperature diffusion superposition predictor for temperature diffusion superposition prediction, and multiple predicted battery temperature distributions are output. By constructing a temperature diffusion superposition predictor based on the BP neural network for temperature diffusion superposition prediction, accurate battery temperature distribution prediction can be achieved, thereby providing reliable data support for subsequent scheduling scheme screening and evaluation.

[0040] S400: The plurality of predicted battery temperature distributions are screened based on a constraint of satisfying a preset rigid temperature index, and if the screening result is not 0, a plurality of first battery temperature distributions and a plurality of first battery scheduling schemes are obtained.

[0041] Furthermore, step S400 of the present invention further includes:

[0042] Obtain a preset rigid temperature index, wherein the preset rigid temperature index includes an expected temperature difference index of the energy storage battery pack and an expected threshold temperature of the battery cell; based on the expected temperature difference index and the expected threshold temperature, screen the multiple predicted battery temperature distributions, and set the predicted battery temperature distribution that meets the expected temperature difference index and the expected threshold temperature as a first battery temperature distribution, and if the first battery temperature distribution is not 0, obtain multiple first battery temperature distributions; set the initial battery scheduling plan corresponding to the first battery temperature distribution as a first battery scheduling plan, and obtain multiple first battery scheduling plans.

[0043] Specifically, a preset rigid temperature index is obtained, wherein the preset rigid temperature index includes an expected temperature difference index of the energy storage battery pack and an expected threshold temperature of the battery cell. The expected temperature difference index refers to the maximum temperature difference between different battery cells in the energy storage battery pack (e.g., the maximum temperature difference is 3 degrees Celsius). It is crucial to control the temperature difference between the battery cells in the battery pack, because excessive temperature difference will lead to inconsistent performance of the battery cells, affecting the overall efficiency and increasing the risk of overheating. The expected threshold temperature refers to the maximum temperature value allowed to be reached by the battery cell during the charging and discharging process, which can be set according to the thermal stability of the battery material, the heat generation characteristics during the charging and discharging process, and the safety specifications of the battery, such as the threshold temperature of 50 degrees Celsius.

[0044] Next, according to the expected temperature difference index and the expected threshold temperature, the multiple predicted battery temperature distributions are screened. First, the temperature difference data of the multiple predicted battery temperature distributions are calculated respectively to obtain multiple temperature difference data and obtain multiple maximum temperature values; then, according to the expected temperature difference index and the expected threshold temperature, the multiple temperature difference data and the multiple maximum temperature values ​​are screened respectively, and the predicted battery temperature distribution whose temperature difference data is less than the expected temperature difference index and whose maximum temperature value is less than the expected threshold temperature is set as the first battery temperature distribution. If the first battery temperature distribution is not 0, that is, the screening result is not empty, multiple first battery temperature distributions (usually multiple, or possibly 1) are obtained.

[0045] The initial battery scheduling scheme corresponding to the first battery temperature distribution is further set as a first battery scheduling scheme to obtain a plurality of first battery scheduling schemes.

[0046] S500: Based on the heat dissipation evaluation function, the plurality of first battery temperature distributions are optimized, a first battery scheduling scheme corresponding to a first battery temperature distribution with the greatest heat dissipation adaptability is set as an optimal scheduling scheme, and operation scheduling of the energy storage battery group is performed according to the optimal scheduling scheme.

[0047] Furthermore, step S500 of the present invention further includes:

[0048] According to a predetermined high temperature threshold, the multiple first battery temperature distributions are respectively divided into regions to obtain multiple first high temperature regional distributions, and the multiple first high temperature regional distributions are respectively evaluated for distribution discreteness to obtain multiple high temperature regional distribution discreteness; the temperature variance of the multiple first battery temperature distributions is calculated respectively, and the inverse of the variance calculation result is set as the temperature consistency coefficient to obtain multiple temperature consistency coefficients; based on the heat dissipation evaluation function, multiple first heat dissipation fitnesses are calculated according to the multiple high temperature regional distribution discreteness and the multiple temperature consistency coefficients; the first battery scheduling plan corresponding to the first battery temperature distribution with the largest heat dissipation fitness among the multiple first heat dissipation fitnesses is set as the optimal scheduling plan; wherein the expression of the heat dissipation evaluation function is: P=v1·Y+v2·S; wherein P is the heat dissipation fitness, v1 is the temperature consistency weight, v2 is the local high temperature weight, Y is the temperature consistency coefficient, and S is the high temperature regional distribution discreteness.

[0049] Specifically, first, a predetermined high temperature threshold is obtained. The predetermined high temperature threshold is used to identify whether the battery cell is in a high temperature state, and can be set according to the actual scenario. For example, setting the high temperature threshold to 42°C means that all battery cells with a temperature higher than 42°C will be regarded as high temperature areas; then, the multiple first battery temperature distributions are divided into regions according to the predetermined high temperature threshold, and the battery cells with a temperature higher than the high temperature threshold are marked as high temperature areas, and multiple first high temperature area distributions are obtained. The multiple first high temperature area distributions are further evaluated for distribution discreteness, and the distribution discreteness refers to the breadth or concentration of the high temperature area in the battery pack. The higher the discreteness, the more dispersed the distribution of the high temperature area. Conversely, a low discreteness means that the high temperature area is more concentrated, and multiple high temperature area distribution discreteness is obtained.

[0050] On the other hand, the temperature variance is calculated for each of the multiple first battery temperature distributions. The variance is calculated by squaring the difference between the temperature of each battery cell and the average temperature of the battery pack, and then averaging the square differences of all battery cells. The larger the temperature variance, the greater the temperature difference in the battery pack and the worse the temperature consistency. The inverse of the variance calculation result is then set as the temperature consistency coefficient to obtain multiple temperature consistency coefficients.

[0051] Next, a heat dissipation evaluation function is constructed: P = v1·Y+v2·S; in the heat dissipation evaluation function, P is the heat dissipation fitness, v1 is the temperature consistency weight, and v2 is the local high temperature weight, where the sum of v1 and v2 is 1, which can be set according to the index influence. The greater the influence of the index on the heat dissipation of the energy storage battery pack, the greater the corresponding weight, Y is the temperature consistency coefficient, and S is the high temperature area distribution discreteness. Then, based on the heat dissipation evaluation function, multiple first heat dissipation fitnesses are calculated according to the multiple high temperature area distribution discretenesses and multiple temperature consistency coefficients.

[0052] Finally, the first battery scheduling scheme corresponding to the first battery temperature distribution with the largest heat dissipation fitness among the multiple first heat dissipation fitness is selected as the optimal scheduling scheme, and the operation scheduling (charging scheduling or discharging scheduling) of the energy storage battery group is performed according to the optimal scheduling scheme. Through this process, the efficient operation of the energy storage battery group can be achieved, while meeting the charging and discharging requirements, maintaining temperature balance, and improving the reliability and service life of the battery group.

[0053] Furthermore, the present invention further comprises the following steps:

[0054] If the screening result is 0, the heat dissipation system and heat dissipation operating parameters of the energy storage battery pack are obtained, and the heat dissipation system and heat dissipation operating parameters are rendered to the energy storage battery simulation model to generate a battery heat dissipation simulation model; the minimum heat dissipation parameters corresponding to the minimum heat dissipation performance are determined according to the heat dissipation operating parameters, and based on the battery heat dissipation simulation model, the multiple predicted battery temperature distributions are compensated once according to the minimum heat dissipation parameters to obtain multiple once-compensated battery temperature distributions.

[0055] Specifically, the multiple predicted battery temperature distributions are screened based on the constraint of meeting the preset rigid temperature index. If the screening result is 0, it indicates that all predicted battery temperature distributions do not meet the preset temperature requirements. At this time, the heat dissipation system needs to provide additional heat dissipation services. Next, the heat dissipation system (such as air cooling system, liquid cooling system) and heat dissipation operation parameters (flow rate, etc.) of the energy storage battery pack are obtained; then the heat dissipation system and heat dissipation operation parameters are rendered to the energy storage battery simulation model to generate a battery heat dissipation simulation model, wherein the battery heat dissipation simulation model is used to predict the impact of heat dissipation parameters on battery cell temperature changes.

[0056] Next, the minimum heat dissipation parameters (such as minimum flow rate) corresponding to the minimum heat dissipation performance are determined according to the heat dissipation operation parameters; the battery heat dissipation simulation model is further used to perform a single compensation on the multiple predicted battery temperature distributions according to the minimum heat dissipation parameters, that is, the heat dissipation of the multiple predicted battery temperature distributions is simulated respectively according to the minimum heat dissipation parameters, and the temperature distribution is compensated by simulating the diffusion effect to obtain multiple single-compensated battery temperature distributions.

[0057] Screening the plurality of primary compensation battery temperature distributions according to the expected temperature difference index and the expected threshold temperature, and if the screening result is 0, adjusting the minimum heat dissipation parameter according to a predetermined adjustment step to obtain a primary compensation heat dissipation parameter;

[0058] Furthermore, the present invention further comprises the following steps:

[0059] Based on the expected temperature difference index and the expected threshold temperature, the deviations of the multiple predicted battery temperature distributions are calculated respectively to obtain multiple temperature difference deviation values ​​and multiple threshold temperature deviations, and the minimum temperature difference deviation and the minimum threshold temperature deviation are selected; a step adjustment coefficient is calculated according to the minimum temperature difference deviation and the minimum threshold temperature deviation, and the initial adjustment step is updated to obtain an updated adjustment step, wherein the step adjustment coefficient is positively correlated with the temperature deviation and the threshold temperature deviation; the updated adjustment step is set to the predetermined adjustment step, wherein, during each adjustment process, the minimum temperature difference deviation and the minimum threshold temperature deviation after the adjacent last adjustment are calculated in real time, and the real-time step adjustment coefficient is calculated to iteratively update the initial adjustment step.

[0060] Specifically, the multiple primary compensation battery temperature distributions are screened according to the expected temperature difference index and the expected threshold temperature. If the screening result is 0, it indicates that the heat dissipation performance after the primary compensation still cannot meet the expected demand; at this time, the minimum heat dissipation parameter is incrementally adjusted according to the predetermined adjustment step, that is, the heat dissipation parameter is gradually increased according to the set adjustment step. For example, if the initial flow velocity is 10m / s and the predetermined adjustment step is 1m / s, the flow velocity is adjusted to 11m / s after one increase; and the primary compensation heat dissipation parameter is obtained.

[0061] Among them, the method for constructing a predetermined adjustment step size is as follows: first, taking the expected temperature difference index and the expected threshold temperature as a benchmark, respectively, the multiple temperature difference data and the multiple maximum temperatures in the multiple predicted battery temperature distributions are calculated for deviation, and multiple temperature difference deviation values ​​and multiple threshold temperature deviations are obtained, wherein the temperature difference deviation value is the temperature difference value obtained by subtracting the expected temperature difference index from the temperature difference data, and the threshold temperature deviation is the temperature difference obtained by subtracting the expected threshold temperature from the maximum temperature; and the minimum temperature difference deviation and the minimum threshold temperature deviation are respectively selected from the multiple temperature difference deviation values ​​and the multiple threshold temperature deviations, that is, the deviation data closest to the optimal scheduling scheme is selected.

[0062] Next, the step adjustment coefficient is calculated based on the minimum temperature difference deviation and the minimum threshold temperature deviation, wherein the step adjustment coefficient represents the amplitude of each adjustment and is positively correlated with the temperature deviation and the threshold temperature deviation, that is, the smaller the temperature deviation, the smaller the threshold temperature deviation, and the smaller the amplitude of the daily adjustment; then the initial adjustment step (such as the initial step can be set to 1) is updated according to the step adjustment coefficient to obtain an updated adjustment step. The updated adjustment step is further set to the predetermined adjustment step, wherein, during each adjustment process, the minimum temperature difference deviation and the minimum threshold temperature deviation after the adjacent last adjustment are calculated in real time, and the real-time step adjustment coefficient is calculated to iteratively update the initial adjustment step. The initial adjustment step is updated by calculating the step adjustment coefficient. That is, the larger the temperature difference deviation and the threshold temperature deviation, the more it means that the system's heat dissipation or temperature control has not met expectations, and the adjustment speed needs to be accelerated. On the contrary, a smaller deviation means that the temperature control is close to the ideal state, and the adjustment accuracy can be improved and the adjustment rate can be slowed down. By continuously calculating and updating the step adjustment coefficient, the parameters of the battery pack heat dissipation system or charge and discharge scheduling are dynamically adjusted to ensure that the predetermined temperature difference and threshold temperature requirements are met quickly and accurately in different operating stages.

[0063] Based on the once compensated heat dissipation parameters, continue to iteratively compensate the multiple predicted battery temperature distributions until the screening result is not 0, output the current heat dissipation parameters, and obtain multiple second battery temperature distributions and multiple second battery scheduling schemes; based on the heat dissipation evaluation function, perform heat dissipation fitness evaluation on the multiple second battery temperature distributions to obtain multiple second heat dissipation fitnesses; set the second battery scheduling scheme corresponding to the second battery temperature distribution with the largest heat dissipation fitness among the multiple second heat dissipation fitnesses as the optimal second scheduling scheme, and generate the optimal scheduling scheme in combination with the current heat dissipation parameters.

[0064] Specifically, the multiple predicted battery temperature distributions are secondarily compensated based on the primary compensation heat dissipation parameters. If the screening result after the secondary compensation is still 0, the iterative compensation of the multiple predicted battery temperature distributions is continued according to the predetermined adjustment step until the screening result is not 0, and the current heat dissipation parameters are output, as well as multiple second battery temperature distributions and multiple second battery scheduling schemes that meet the expected temperature difference index and the expected threshold temperature are obtained.

[0065] Then, the multiple second high temperature area distribution discreteness and multiple second temperature consistency coefficients of the multiple second battery scheduling schemes are calculated; based on the heat dissipation evaluation function, multiple second heat dissipation fitnesses are calculated according to the multiple second high temperature area distribution discreteness and multiple second temperature consistency coefficients. Finally, the second battery scheduling scheme corresponding to the second battery temperature distribution with the largest heat dissipation fitness among the multiple second heat dissipation fitnesses is set as the optimal second scheduling scheme; and the optimal second scheduling scheme and the current heat dissipation parameters are combined to generate the optimal scheduling scheme (i.e., the optimal scheduling scheme with the participation of the heat dissipation system), and the operation scheduling of the energy storage battery group is performed according to the optimal scheduling scheme.

[0066] A modular energy storage battery charging and discharging scheduling management method provided by an embodiment of the present invention has at least the following technical effects:

[0067] By obtaining the expected operating power of the energy storage battery group, and taking the expected operating power as a constraint, the scheduling schemes are enumerated based on a number of battery cells to obtain multiple initial battery scheduling schemes; then, through the energy storage battery simulation model, the simulation operation of the multiple initial battery scheduling schemes is respectively performed to obtain multiple simulated working battery temperature sets at the end of the operation, and multiple simulated working battery temperature distributions are constructed; then, the temperature diffusion superposition prediction is performed on the multiple simulated working battery temperature distributions respectively to generate multiple predicted battery temperature distributions; further, the multiple predicted battery temperature distributions are screened with the preset rigid temperature index as a constraint, and if the screening result is not 0, the result is obtained. Take multiple first battery temperature distributions and multiple first battery scheduling plans; finally, based on the heat dissipation evaluation function, optimize the multiple first battery temperature distributions, set the first battery scheduling plan corresponding to the first battery temperature distribution with the largest heat dissipation adaptability as the optimal scheduling plan, and perform operation scheduling of the energy storage battery group according to the optimal scheduling plan; through the above method, on the premise of meeting the scheduling requirements, the scientificity and accuracy of the setting of the charging and discharging scheduling strategy can be improved, the heat dissipation problems generated during the battery charging and discharging process can be effectively controlled, the battery overheating can be avoided, and the stability and reliability of the battery group operation can be ensured; at the same time, the consumption of heat dissipation resources can be saved and the overall energy efficiency can be improved.

[0068] For example 2, please refer to Figure 2 , Figure 2 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: obtaining the expected operating power of the energy storage battery group, enumerating the scheduling schemes based on a number of battery cells to satisfy the expected operating power as a constraint, and obtaining multiple initial battery scheduling schemes; performing simulation operations of the multiple initial battery scheduling schemes respectively through the energy storage battery simulation model, obtaining multiple simulated working battery temperature sets at the end of the operation, and constructing multiple simulated working battery temperature distributions; performing temperature diffusion superposition prediction on the multiple simulated working battery temperature distributions respectively, and generating multiple predicted battery temperature distributions; screening the multiple predicted battery temperature distributions to satisfy the preset rigid temperature index as a constraint, and if the screening result is not 0, obtaining multiple first battery temperature distributions and multiple first battery scheduling schemes; optimizing the multiple first battery temperature distributions based on the heat dissipation evaluation function, setting the first battery scheduling scheme corresponding to the first battery temperature distribution with the largest heat dissipation adaptability as the optimal scheduling scheme, and performing operation scheduling of the energy storage battery group according to the optimal scheduling scheme.

[0069] For example 3, please refer to Figure 3 , Figure 3 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 3 As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by a processor, the following steps are implemented: obtaining the expected operating power of the energy storage battery group, enumerating the scheduling schemes based on a number of battery cells to meet the expected operating power as a constraint, and obtaining multiple initial battery scheduling schemes; through the energy storage battery simulation model, respectively executing the simulation operation of the multiple initial battery scheduling schemes, obtaining multiple simulated working battery temperature sets at the end of the operation, and constructing multiple simulated working battery temperature distributions; respectively performing temperature diffusion superposition prediction on the multiple simulated working battery temperature distributions to generate multiple predicted battery temperature distributions; subjecting the preset rigid temperature index to the constraint, screening the multiple predicted battery temperature distributions, if the screening result is not 0, obtaining multiple first battery temperature distributions, and multiple first battery scheduling schemes; based on the heat dissipation evaluation function, optimizing the multiple first battery temperature distributions, setting the first battery scheduling scheme corresponding to the first battery temperature distribution with the largest heat dissipation adaptability as the optimal scheduling scheme, and performing operation scheduling of the energy storage battery group according to the optimal scheduling scheme.

[0070] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0071] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0076] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A modular energy storage battery charging and discharging scheduling management method, characterized in that: The method is applied to an energy storage battery pack, wherein the energy storage battery pack includes a plurality of battery cells, including: Obtaining the expected operating power of the energy storage battery group, taking the expected operating power as a constraint, enumerating scheduling schemes based on a number of battery units, and obtaining multiple initial battery scheduling schemes; Through the energy storage battery simulation model, respectively execute the simulation operation of the multiple initial battery scheduling schemes, obtain multiple simulated working battery temperature sets at the end of the operation, and construct multiple simulated working battery temperature distributions; Performing temperature diffusion superposition prediction on the multiple simulated working battery temperature distributions respectively to generate multiple predicted battery temperature distributions; The plurality of predicted battery temperature distributions are screened based on the constraint of satisfying a preset rigid temperature index, and if the screening result is not 0, a plurality of first battery temperature distributions and a plurality of first battery scheduling schemes are obtained; Based on the heat dissipation evaluation function, the multiple first battery temperature distributions are optimized, the first battery scheduling scheme corresponding to the first battery temperature distribution with the largest heat dissipation adaptability is set as the optimal scheduling scheme, and the operation scheduling of the energy storage battery group is performed according to the optimal scheduling scheme.

2. A modular energy storage battery charging and discharging scheduling management method according to claim 1, characterized in that: Obtain the expected operating power of the energy storage battery group, and use the expected operating power as a constraint to enumerate scheduling plans based on a number of battery units to obtain multiple initial battery scheduling plans, including: Obtaining an expected operating power of an energy storage battery pack, wherein the expected operating power is an expected charging power or an expected discharging power, and the energy storage battery pack includes a plurality of battery cells, each of which is marked with a unique position coordinate; Taking the expected operating power as a constraint, the battery scheduling scheme is enumerated using the plurality of battery units to obtain a plurality of initial battery scheduling schemes, wherein the number of working batteries and the battery position coordinates in each initial battery scheduling scheme are not exactly the same.

3. A modular energy storage battery charging and discharging scheduling management method according to claim 2, characterized in that: Through the energy storage battery simulation model, the simulation operation of the multiple initial battery scheduling schemes is respectively performed, multiple simulated working battery temperature sets at the end of the operation are obtained, and multiple simulated working battery temperature distributions are constructed, including: Obtaining an expected operation target, and calculating the operation end time according to the expected operation target and the expected operation power; Perform simulation modeling on the energy storage battery group, construct an energy storage battery simulation model, and collect a sample battery scheduling plan set, a sample ambient temperature set, multiple sample initial battery temperature sets, and multiple sample working battery temperature sets at the end of historical operation as training data to train the energy storage battery simulation model until the expected convergence accuracy is met; Monitor and obtain the real-time ambient temperature and several initial battery temperatures, and use the number of working batteries and battery position coordinates in the multiple initial battery scheduling schemes to filter the several initial battery temperatures respectively to obtain multiple initial working battery temperature sets; Integrate the multiple initial battery scheduling schemes, the real-time ambient temperature and the multiple initial working battery temperature sets to obtain multiple input data, and input the multiple input data into the energy storage battery simulation model for simulation operation, and output multiple simulated working battery temperature sets at the end of the operation; The plurality of simulated working battery temperature distributions are constructed based on the working battery position coordinates and the plurality of simulated working battery temperature sets.

4. A modular energy storage battery charging and discharging scheduling management method according to claim 3, characterized in that: Performing temperature diffusion superposition prediction on the multiple simulated working battery temperature distributions respectively to generate multiple predicted battery temperature distributions, including: Query the working operation log of the energy storage battery pack, collect the sample working battery temperature distribution set, and the sample all battery temperature distribution set at the end time of historical operation; Taking the sample working battery temperature distribution as input and the sample all battery temperature distribution as supervision, the sample working battery temperature distribution set and the sample all battery temperature distribution set are used to supervise the BP neural network training until convergence, and a temperature diffusion superposition predictor is obtained; The temperature diffusion superposition predictor is used to perform temperature diffusion superposition prediction on the multiple simulated working battery temperature distributions respectively, and the multiple predicted battery temperature distributions are output.

5. A modular energy storage battery charging and discharging scheduling management method according to claim 4, characterized in that: The plurality of predicted battery temperature distributions are screened based on the constraint of satisfying a preset rigid temperature index, and if the screening result is not 0, a plurality of first battery temperature distributions and a plurality of first battery scheduling schemes are obtained, including: Acquire a preset rigid temperature index, wherein the preset rigid temperature index includes an expected temperature difference index of the energy storage battery pack and an expected threshold temperature of the battery cell; Based on the expected temperature difference index and the expected threshold temperature, the multiple predicted battery temperature distributions are screened, and a predicted battery temperature distribution that meets the expected temperature difference index and the expected threshold temperature is set as a first battery temperature distribution, and if the first battery temperature distribution is not 0, a plurality of first battery temperature distributions are obtained; The initial battery scheduling scheme corresponding to the first battery temperature distribution is set as a first battery scheduling scheme to obtain a plurality of first battery scheduling schemes.

6. A modular energy storage battery charging and discharging scheduling management method according to claim 5, characterized in that: Based on the heat dissipation evaluation function, the plurality of first battery temperature distributions are optimized, and the first battery scheduling scheme corresponding to the first battery temperature distribution with the greatest heat dissipation adaptability is set as the optimal scheduling scheme, including: Dividing the plurality of first battery temperature distributions into regions according to a predetermined high temperature threshold to obtain a plurality of first high temperature region distributions, and performing distribution discreteness evaluation on the plurality of first high temperature region distributions to obtain a plurality of high temperature region distribution discretenesses; Performing temperature variance calculation on the plurality of first battery temperature distributions respectively, setting the inverse of the variance calculation result as the temperature consistency coefficient, and obtaining a plurality of temperature consistency coefficients; Based on the heat dissipation evaluation function, a plurality of first heat dissipation adaptability is calculated according to the plurality of high temperature area distribution discreteness and the plurality of temperature consistency coefficients; Setting the first battery scheduling scheme corresponding to the first battery temperature distribution having the largest heat dissipation fitness among the multiple first heat dissipation fitnesses as the optimal scheduling scheme; Wherein, the expression of the heat dissipation evaluation function is: P = v1·Y + v2·S; Among them, P is the heat dissipation fitness, v1 is the temperature consistency weight, v2 is the local high temperature weight, Y is the temperature consistency coefficient, and S is the dispersion of the high temperature area distribution.

7. A modular energy storage battery charging and discharging scheduling management method according to claim 6, characterized in that: The method also includes: If the screening result is 0, obtain the heat dissipation system and heat dissipation operation parameters of the energy storage battery pack, and render the heat dissipation system and heat dissipation operation parameters to the energy storage battery simulation model to generate a battery heat dissipation simulation model; Determining a minimum heat dissipation parameter corresponding to a minimum heat dissipation performance according to the heat dissipation operation parameter, and based on the battery heat dissipation simulation model, performing a primary compensation on the multiple predicted battery temperature distributions according to the minimum heat dissipation parameter to obtain multiple primary compensated battery temperature distributions; Screening the plurality of primary compensation battery temperature distributions according to the expected temperature difference index and the expected threshold temperature, and if the screening result is 0, adjusting the minimum heat dissipation parameter according to a predetermined adjustment step to obtain a primary compensation heat dissipation parameter; Based on the first compensated heat dissipation parameter, continue to iterate and compensate the multiple predicted battery temperature distributions until the screening result is not 0, output the current heat dissipation parameter, and obtain multiple second battery temperature distributions and multiple second battery scheduling schemes; Based on the heat dissipation evaluation function, performing heat dissipation fitness evaluation on the plurality of second battery temperature distributions to obtain a plurality of second heat dissipation fitnesses; The second battery scheduling scheme corresponding to the second battery temperature distribution with the largest heat dissipation fitness among the multiple second heat dissipation fitnesses is set as the optimal second scheduling scheme, and the optimal scheduling scheme is generated in combination with the current heat dissipation parameters.

8. A modular energy storage battery charging and discharging scheduling management method according to claim 7, characterized in that: Construct a predetermined adjustment step size, including: Based on the expected temperature difference index and the expected threshold temperature, respectively performing deviation calculations on the multiple predicted battery temperature distributions to obtain multiple temperature difference deviation values ​​and multiple threshold temperature deviations, and selecting a minimum temperature difference deviation and a minimum threshold temperature deviation; Calculating a step length adjustment coefficient according to the minimum temperature difference deviation and the minimum threshold temperature deviation, updating the initial adjustment step length to obtain an updated adjustment step length, wherein the step length adjustment coefficient is positively correlated with the temperature deviation and the threshold temperature deviation; The updated adjustment step is set to the predetermined adjustment step, wherein during each adjustment process, the minimum temperature difference deviation and the minimum threshold temperature deviation after the last adjustment are calculated in real time, and the real-time step adjustment coefficient is calculated to iteratively update the initial adjustment step.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the steps of a modular energy storage battery charging and discharging scheduling management method as described in any one of claims 1 to 8.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements the steps of a modular energy storage battery charging and discharging scheduling management method as described in any one of claims 1 to 8.

Images