A new energy light storage and charging integrated management system and method

Abstract

The application relates to the technical field of new energy, and particularly discloses a management system and method for new energy photovoltaic storage and charging integration, which comprises a photovoltaic power generation amount prediction module, a charging demand amount prediction module, a feature inflection point identification module, a feature inflection point drawing module, a charging and discharging rate control adjustment module and a control strategy execution feedback module; the application identifies the feature inflection point in a photovoltaic predicted power generation amount curve, avoids the calculation complexity of full-amount data analysis, collects a charging demand feature sequence to predict the charging demand, dynamically adjusts the charging and discharging rate based on the difference between the photovoltaic power generation amount and the charging demand amount, in combination with the temperature and efficiency state of the energy storage equipment, and feeds back the real-time monitoring control strategy execution result; the application solves the problems of response lag, inaccurate demand prediction and inadaptation of charging and discharging control of the photovoltaic storage and charging system in a high-altitude environment, and improves the system reliability and the service life of the energy storage equipment.

Description

Technical Field

[0001] This invention relates to the field of new energy technology, and in particular to a management system and method for integrating photovoltaic, energy storage and charging in new energy. Background Technology

[0002] Ecological monitoring networks in high-altitude areas serve as critical scientific research infrastructure, typically deployed in remote regions with poor transportation, requiring long-term unattended operation. These monitoring stations generally employ integrated photovoltaic-storage-charging systems, but lack dedicated management systems adapted to high-altitude environments. The unique environmental conditions of high-altitude regions make traditional integrated photovoltaic-storage-charging management systems unsuitable, frequently leading to unstable power supply and affecting the acquisition and transmission of critical monitoring data.

[0003] Traditional integrated photovoltaic-storage-charging management systems for new energy sources have several shortcomings. First, traditional systems perform full data analysis of photovoltaic power generation curves, failing to identify key inflection points and exhibiting high computational complexity and slow response, making it impossible to capture sudden changes in predicted photovoltaic power generation at high altitudes. Second, charging demand forecasting ignores unique high-altitude factors such as equipment power consumption change rates, snow cover rates, and data transmission deviation rates, leading to significant discrepancies between predicted results and actual demand. Furthermore, charge / discharge rate control lacks a dynamic adjustment mechanism, failing to consider temperature and efficiency changes in energy storage devices and thus unable to adaptively adjust control strategies based on real-time operating conditions. This results in shortened equipment lifespan and compromised power supply reliability in extreme environments. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a management system and method for integrated photovoltaic, energy storage and charging of new energy, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a management system for integrated photovoltaic, energy storage, and charging of new energy sources, comprising: Photovoltaic power generation prediction module: used to predict photovoltaic power generation in future time periods through a neural network model, and to draw a photovoltaic power generation prediction curve within a preset time period based on the photovoltaic power generation. Charging demand prediction module: used to acquire charging demand feature sequence, build charging demand prediction model, obtain charging demand prediction, and draw charging demand prediction curve within a preset time period. Feature inflection point identification module: used to identify all feature inflection points appearing in the photovoltaic power generation prediction curve, and to mark the feature inflection points as the 1st to the nth feature inflection points in chronological order; Feature Inflection Point Plotting Module: Used to extract the photovoltaic predicted power generation values ​​and time coordinates corresponding to the 1st to nth feature inflection points, locate and match the time coordinates in the charging predicted demand curve, extract the charging predicted demand values, and plot the feature inflection point time curve. Charge and discharge rate control adjustment module: Based on the characteristic inflection point time curve, calculate the difference between the photovoltaic predicted power generation value and the charging predicted demand value corresponding to the time coordinate, perform charge and discharge rate control based on the difference, generate a first charge and discharge rate control strategy, and adjust it to generate an adjusted second charge and discharge rate control strategy. Control strategy execution feedback module: used to execute the second charge and discharge rate control strategy, monitor the execution result of the control strategy, and transmit the monitoring result to the display screen of the monitoring management platform in real time.

[0006] Preferably, the charging demand prediction module performs the following operations: Real-time monitoring and analysis are performed on monitoring equipment in high-altitude areas to obtain a charging demand characteristic sequence of the monitoring equipment. The charging demand characteristic sequence includes the power consumption change rate, snow coverage rate, and data transmission deviation rate of the monitoring equipment. The obtained charging demand characteristic sequence is normalized, and a charging demand prediction model is constructed based on the charging demand characteristic sequence to calculate the charging demand prediction index. The first charging predicted demand is obtained based on the charging demand prediction index, and the charging predicted demand is corrected by environmental impact factors to obtain the second charging predicted demand. A charging predicted demand curve is plotted for a preset time period based on the second charging predicted demand. The method for obtaining the power consumption change rate is as follows: obtain the actual power consumption of the monitoring device within a preset period, extract the reference power consumption corresponding to the monitoring device within the preset period, calculate the difference between the actual power consumption of the monitoring device and the reference power consumption within the preset period, calculate the ratio of the difference to the reference power consumption, and analyze to obtain the power consumption change rate of the monitoring device. ; The data transmission deviation rate is obtained by: obtaining the actual data transmission volume within a preset period. And extract the corresponding baseline transmission volume within the preset period. The data transmission deviation rate was calculated. .

[0007] Preferably, the first predicted charging demand is obtained based on the charging demand forecast index, and the predicted charging demand is corrected by an environmental impact factor to obtain the second predicted charging demand, which is as follows: Read the power consumption change rate, snow coverage rate and data transmission deviation rate of the monitoring equipment, construct a charging demand prediction model, and calculate the charging demand prediction index. Read the charging demand forecast index and obtain the baseline load value of the monitoring equipment. The predicted charging demand is calculated using the formula for converting predicted charging demand, and this is marked as the first predicted charging demand. ; Environmental data from monitoring equipment in high-altitude areas is acquired, environmental impact factors are calculated, and the demand for the first charging phase is predicted based on these environmental impact factors. Make corrections to the calculated environmental impact factors. Multiplying the first predicted charging demand by the second predicted charging demand yields the corrected predicted charging demand, which is then designated as the second predicted charging demand. Furthermore, by acquiring the actual charging demand of the monitoring equipment in real time, analyzing the deviation of the predicted charging demand, and adjusting the charging demand prediction model based on the deviation analysis results; The environmental impact factors are obtained as follows: environmental data from monitoring equipment in high-altitude areas is acquired; temperature correction factors and air pressure correction factors are obtained based on the environmental data analysis; and the temperature correction factors and air pressure correction factors are weighted and calculated to obtain the environmental impact factors. .

[0008] Preferably, the analysis of the charging demand prediction deviation includes: real-time acquisition of the second charging prediction demand and the actual charging demand of the monitoring equipment; calculation of the charging prediction deviation coefficient by constructing a charging prediction deviation coefficient model; and determination of whether charging demand prediction adjustment is needed based on the charging prediction deviation coefficient. Specifically, the charging prediction deviation coefficient is read and compared with a preset charging prediction deviation coefficient threshold. If the charging prediction deviation coefficient is less than the preset charging prediction deviation coefficient threshold, it is determined that the charging demand prediction of the monitoring equipment has no deviation and no adjustment is needed; otherwise, it is determined that the charging demand prediction of the monitoring equipment has an abnormal deviation and adjustment is needed, and the parameters of the charging demand prediction model are adjusted.

[0009] Preferably, the execution content of the feature inflection point recognition module is as follows: A photovoltaic power generation forecast curve within a preset time period is obtained. All characteristic inflection points appearing sequentially in the photovoltaic power generation forecast curve are identified. The identification method of the characteristic inflection points is as follows: adjacent time points and their corresponding photovoltaic power generation values ​​are obtained from the photovoltaic power generation forecast curve. The slope values ​​of adjacent time points are calculated, and the absolute difference between adjacent slope values ​​is calculated. Based on the absolute difference, it is determined whether it is a characteristic inflection point of the photovoltaic power generation forecast curve. The determination method of the characteristic inflection point is as follows: the absolute difference is compared with a preset threshold, and the time points corresponding to the absolute difference being greater than the preset threshold are selected and marked as characteristic inflection points of the photovoltaic power generation forecast curve. They are then numbered sequentially from the 1st to the nth characteristic inflection point according to the time sequence.

[0010] Preferably, the execution content of the feature inflection point map drawing module is as follows: Read all the feature inflection points that appear in the photovoltaic power generation prediction curve. For the first to nth feature inflection points, extract the photovoltaic power generation value corresponding to each feature inflection point in turn. At the same time, obtain the time coordinate value corresponding to each feature inflection point in the photovoltaic power generation prediction curve. Record the time coordinate values ​​in the form of timestamps and mark them as the first to nth time nodes respectively. Based on the timestamps of the first to nth time nodes, in the charging forecast demand curve within the same preset time period, the time coordinates that match each timestamp are located sequentially, and the charging forecast demand value corresponding to each matching time coordinate is extracted. Based on the photovoltaic power generation forecast value corresponding to each feature inflection point and the charging demand forecast value corresponding to each matching time coordinate, a feature inflection point time curve is plotted.

[0011] Preferably, the charge / discharge rate control and adjustment module performs the following operations: Read the feature inflection point time curve, filter the photovoltaic predicted power generation value corresponding to the time coordinate in the feature inflection point time curve to be greater than or less than the charging predicted demand value, calculate the difference between the photovoltaic predicted power generation value and the charging predicted demand value for all time coordinates in the feature inflection point time curve, control the charging and discharging state based on the difference, and generate the corresponding first charging and discharging rate control strategy based on the control result. The content of controlling the charging and discharging state based on the difference is as follows: read the difference between the photovoltaic predicted power generation value and the charging predicted demand value corresponding to the time coordinate; when the difference is positive, store the remaining power at the corresponding time coordinate into the energy storage device according to the preset first charging rate; when the difference is negative, control the energy storage device to supply power to the charging device according to the preset first discharging rate; and mark the preset first charging rate and the preset first discharging rate as the first charging and discharging rate control strategy. The first charge / discharge rate control strategy is implemented, and the operating status of the energy storage device and the actual demand of the charging device are monitored in real time. The current actual temperature and standard operating temperature of the energy storage device are obtained, and the temperature deviation value is calculated. Td ; Calculate the efficiency deviation ratio between the current charge / discharge efficiency of the energy storage device and the reference charge / discharge efficiency. Dr The control strategy adjustment coefficient is calculated based on the temperature deviation value and the efficiency deviation ratio. The first charge and discharge rate control strategy is adjusted based on the control strategy adjustment coefficient to generate the adjusted second charge and discharge rate control strategy.

[0012] To achieve the above objectives, the present invention provides the following technical solution: a management method for integrated photovoltaic, energy storage, and charging systems for new energy sources. Implementing the aforementioned management system for integrated photovoltaic, energy storage, and charging systems for new energy sources includes the following steps: S1: Predict photovoltaic power generation: Predict photovoltaic power generation for future time periods using a neural network model, and plot the photovoltaic power generation prediction curve for the preset time period based on the photovoltaic power generation. S2: Predict charging demand: Obtain the charging demand feature sequence, construct a charging demand prediction model, obtain the predicted charging demand, and draw a curve of the predicted charging demand within a preset time period. S3: Identify feature inflection points: Identify all feature inflection points appearing in the photovoltaic power generation prediction curve, and mark the feature inflection points as the 1st to the nth feature inflection points in chronological order; S4: Draw a feature inflection point graph: Extract the photovoltaic predicted power generation values ​​and time coordinates corresponding to the 1st to nth feature inflection points, locate and match the time coordinates in the charging predicted demand curve graph, extract the charging predicted demand values, and draw the feature inflection point time curve graph. S5: Control and adjust the charging and discharging rate: Based on the characteristic inflection point time curve, calculate the difference between the photovoltaic predicted power generation value and the charging predicted demand value corresponding to the time coordinate, control the charging and discharging rate based on the difference, generate a first charging and discharging rate control strategy, and adjust it to generate an adjusted second charging and discharging rate control strategy. S6: Execute feedback control strategy: Execute the second charge / discharge rate control strategy, monitor the execution result of the control strategy, and transmit the monitoring result to the display screen of the monitoring management platform in real time.

[0013] As described above, the management system and method for integrated photovoltaic, energy storage, and charging of new energy sources provided by the present invention have at least the following beneficial effects: This invention provides a management system and method for integrated photovoltaic, energy storage, and charging systems in the new energy sector. It predicts photovoltaic power generation using a neural network model and plots a photovoltaic power generation curve over a preset time period. Simultaneously, it acquires a charging demand feature sequence and plots a charging demand curve. By identifying characteristic inflection points in the photovoltaic power generation curve and plotting a time curve for each inflection point, it calculates the difference between the photovoltaic power generation value and the charging demand value corresponding to the time coordinate. Based on this difference, it performs charge / discharge rate control, generating a first charge / discharge rate control strategy. This strategy is then adjusted to generate a second charge / discharge rate control strategy, which is executed, and the execution results are monitored and fed back in real time. This invention solves the problems of delayed response, inaccurate demand forecasting, and unsuitable charge / discharge control in high-altitude environments, improving operational reliability and extending the lifespan of energy storage equipment.

[0014] This invention significantly reduces computational complexity and improves response speed through feature inflection point identification; the prediction model based on high-altitude-specific parameters significantly improves the accuracy of charging demand prediction; dynamically adjusted charge and discharge rate control effectively extends the service life of energy storage equipment; and the real-time monitoring and feedback mechanism ensures reliable operation under extreme conditions, greatly enhancing the continuity and integrity of data collection in the high-altitude ecological monitoring network. Attached Figure Description

[0015] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the structure of a management system for integrated photovoltaic, energy storage and charging of new energy sources according to the present invention.

[0017] Figure 2 This is a flowchart illustrating a management method for integrated photovoltaic, energy storage, and charging systems in the field of new energy, according to the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1 Please see Figure 1As shown, the present invention provides a management system for integrated photovoltaic, energy storage and charging of new energy sources, including a photovoltaic power generation prediction module, a charging demand prediction module, a feature inflection point identification module, a feature inflection point graph drawing module, a charging and discharging rate control and adjustment module, and a control strategy execution feedback module.

[0020] Photovoltaic power generation prediction module: used to predict photovoltaic power generation in future time periods through a neural network model, and to draw a photovoltaic power generation prediction curve within a preset time period based on the photovoltaic power generation. In this embodiment, it should be specifically explained that the execution content of the photovoltaic power generation prediction module is as follows: Historical power generation data and meteorological monitoring data of photovoltaic equipment in high-altitude areas are acquired. The meteorological monitoring data includes solar radiation intensity, ambient temperature, cloud coverage, and atmospheric transparency. The acquired historical power generation data and meteorological monitoring data are standardized to construct an input feature vector. A neural network model is constructed based on the input feature vector. The neural network model includes an input layer, a hidden layer, and an output layer, wherein the hidden layer adopts a long short-term memory network structure. Historical data is used to train and validate the neural network model. The neural network model parameters are optimized by minimizing the mean square error between the predicted and actual values. Real-time meteorological monitoring data is input into the trained neural network model to predict the photovoltaic power generation within a preset time period. Based on the predicted photovoltaic power generation, a photovoltaic power generation curve is plotted within the preset time period. The deviation between the actual photovoltaic power generation and the photovoltaic power generation prediction is monitored in real time. When the deviation exceeds a preset threshold, the adaptive adjustment mechanism of the neural network model is triggered to update the model parameters.

[0021] Charging demand prediction module: used to acquire charging demand feature sequence, build charging demand prediction model, obtain charging demand prediction, and draw charging demand prediction curve within a preset time period. In this embodiment, it should be specifically explained that the execution content of the charging demand prediction module is as follows: Real-time monitoring and analysis are performed on monitoring equipment in high-altitude areas to obtain a charging demand characteristic sequence of the monitoring equipment. The charging demand characteristic sequence includes the power consumption change rate, snow coverage rate, and data transmission deviation rate of the monitoring equipment. The obtained charging demand characteristic sequence is normalized to eliminate the influence of dimensions. A charging demand prediction model is constructed based on the charging demand characteristic sequence to calculate the charging demand prediction index. The first charging predicted demand is obtained based on the charging demand prediction index. The charging predicted demand is then corrected by environmental impact factors to obtain the second charging predicted demand. A charging predicted demand curve is plotted for a preset time period based on the second charging predicted demand. The method for obtaining the power consumption change rate is as follows: obtain the actual power consumption of the monitoring device within a preset period, extract the reference power consumption corresponding to the monitoring device within the preset period, calculate the difference between the actual power consumption of the monitoring device and the reference power consumption within the preset period, calculate the ratio of the difference to the reference power consumption, and analyze to obtain the power consumption change rate of the monitoring device. ; It should be noted that the preset period refers to a preset time period. In this embodiment, one week is used as the preset period.

[0022] It should be noted that when the power consumption change rate of the monitoring device is positive, it means that the actual power consumption of the monitoring device is greater than the reference power consumption, indicating that the charging demand of the monitoring device has increased.

[0023] When the power consumption change rate of the monitoring device is negative, it means that the actual power consumption of the monitoring device is less than the reference power consumption, indicating that the charging demand of the monitoring device has decreased.

[0024] The snow coverage rate is obtained as follows: A surface image of the monitoring equipment is acquired using an industrial camera; image processing technology is used to identify the area of ​​the monitoring equipment covered by snow; simultaneously, the total area corresponding to the monitoring equipment is obtained from the management database; the ratio of the snow-covered area to the total area is calculated; and the snow coverage rate of the monitoring equipment is then obtained through analysis. ; The greater the snow coverage of the monitoring equipment, the greater its charging needs.

[0025] The data transmission deviation rate is obtained by: obtaining the actual data transmission volume within a preset period. And extract the corresponding baseline transmission volume within the preset period. The data transmission deviation rate was calculated. The calculation formula is: ; It should be noted that the reference transmission volume refers to the transmission volume at the regular monitoring frequency (such as transmitting 10MB of meteorological data per hour).

[0026] In this embodiment, it should be specifically noted that the first predicted charging demand is obtained based on the charging demand forecast index, and the second predicted charging demand is obtained by correcting the predicted charging demand using environmental impact factors, as follows: Read the power consumption change rate of the monitoring device Snow cover rate and data transmission deviation rate A charging demand forecasting model was constructed, and the charging demand forecasting index was calculated. The calculation formula for the charging demand prediction model is as follows: ,in, This represents the charging demand forecast index. These represent the weighting coefficients for the rate of change in power consumption, snow cover rate, and data transmission deviation rate, respectively. ; Read the charging demand forecast index and obtain the baseline load value of the monitoring equipment. The predicted charging demand is calculated using the formula for converting predicted charging demand, and this is marked as the first predicted charging demand. The formula for calculating the first predicted charging demand is: , where k represents the conversion coefficient; Environmental data from monitoring equipment in high-altitude areas is acquired, environmental impact factors are calculated, and the demand for the first charging phase is predicted based on these environmental impact factors. Make corrections to the calculated environmental impact factors. Multiplying the first predicted charging demand by the second predicted charging demand yields the corrected predicted charging demand, which is then designated as the second predicted charging demand. Furthermore, by acquiring the actual charging demand of the monitoring equipment in real time, analyzing the deviation of the predicted charging demand, and adjusting the charging demand prediction model based on the deviation analysis results; The environmental impact factors are obtained as follows: environmental data from monitoring equipment in high-altitude areas is acquired, including ambient temperature and air pressure values. Temperature correction factors and air pressure correction factors are obtained based on the environmental data analysis. These factors are then weighted and calculated to obtain the environmental impact factors. ; The temperature correction factor is obtained as follows: When the current ambient temperature in the high-altitude area is lower than the optimal operating temperature of the monitoring equipment, the temperature correction factor... TCF The calculation formula is: ,in, T Indicates the current ambient temperature. This indicates the optimal operating temperature of the monitoring equipment. T 0 Indicates the reference ambient temperature. This represents the temperature sensitivity coefficient; for example, α = 0.01 means that the correction factor increases by 1% for every degree Celsius temperature difference. It should be noted that when the current ambient temperature in the high-altitude area is higher than the optimal operating temperature of the monitoring equipment, the temperature correction factor is set to 1.

[0027] In one specific embodiment, for situations where the current ambient temperature in a high-altitude area is lower than the optimal operating temperature of the monitoring equipment, if the optimal operating temperature of the monitoring equipment is 25 degrees Celsius and the current ambient temperature is -20 degrees Celsius, and the reference ambient temperature is taken as 20 degrees Celsius, the calculation formula is used. The calculated environmental correction factor is 1.0225.

[0028] The pressure correction factor BCF The calculation formula is: ,in, P Indicates the current air pressure. Indicates standard atmospheric pressure. P 0 Indicates reference air pressure. This represents the pressure sensitivity coefficient; for example, β=0.005 means that the correction factor increases by 0.5% for every kPa pressure difference. Environmental impact factors The calculation formula is: ,in, These represent the weighting coefficients of the temperature correction factor and the air pressure correction factor, respectively.

[0029] It should be specifically explained that the analysis of the charging demand prediction deviation involves: acquiring the second charging prediction demand and the actual charging demand from the monitoring equipment in real time; calculating the charging prediction deviation coefficient by constructing a charging prediction deviation coefficient model; and determining whether charging demand prediction adjustment is needed based on the charging prediction deviation coefficient. Specifically, the charging prediction deviation coefficient is read and compared with a preset charging prediction deviation coefficient threshold. If the charging prediction deviation coefficient is less than the preset threshold, it is determined that the charging demand prediction of the monitoring equipment has no deviation and no adjustment is needed; otherwise, it is determined that the charging demand prediction of the monitoring equipment has an abnormal deviation and adjustment is needed. The parameters of the charging demand prediction model are adjusted to correct the charging demand prediction deviation.

[0030] Charging prediction deviation coefficient PBC The calculation formula is: ,in, This indicates the actual charging demand of the monitoring equipment.

[0031] Feature inflection point identification module: used to identify all feature inflection points appearing in the photovoltaic power generation prediction curve, and to mark the feature inflection points as the 1st to the nth feature inflection points in chronological order; In this embodiment, it should be specifically explained that the execution content of the feature inflection point recognition module is as follows: A photovoltaic power generation forecast curve within a preset time period is obtained. All characteristic inflection points appearing sequentially in the photovoltaic power generation forecast curve are identified. The identification method of the characteristic inflection points is as follows: adjacent time points and their corresponding photovoltaic power generation values ​​are obtained from the photovoltaic power generation forecast curve. The slope values ​​of adjacent time points are calculated, and the absolute difference between adjacent slope values ​​is calculated. Based on the absolute difference, it is determined whether it is a characteristic inflection point of the photovoltaic power generation forecast curve. The determination method of the characteristic inflection point is as follows: the absolute difference is compared with a preset threshold, and the time points corresponding to the absolute difference being greater than the preset threshold are selected and marked as characteristic inflection points of the photovoltaic power generation forecast curve. They are then numbered sequentially from the 1st to the nth characteristic inflection point according to the time sequence.

[0032] Feature Inflection Point Plotting Module: Used to extract the photovoltaic predicted power generation values ​​and time coordinates corresponding to the 1st to nth feature inflection points, locate and match the time coordinates in the charging predicted demand curve, extract the charging predicted demand values, and plot the feature inflection point time curve. In this embodiment, it should be specifically explained that the execution content of the feature inflection point map drawing module is as follows: Read all the feature inflection points that appear in the photovoltaic power generation prediction curve. For the first to nth feature inflection points, extract the photovoltaic power generation value corresponding to each feature inflection point in turn. At the same time, obtain the time coordinate value corresponding to each feature inflection point in the photovoltaic power generation prediction curve. Record the time coordinate values ​​in the form of timestamps and mark them as the first to nth time nodes respectively. Based on the timestamps of the first to nth time nodes, in the charging forecast demand curve within the same preset time period, the time coordinates that match each timestamp are located sequentially, and the charging forecast demand value corresponding to each matching time coordinate is extracted. Based on the photovoltaic power generation forecast value corresponding to each feature inflection point and the charging demand forecast value corresponding to each matching time coordinate, a feature inflection point time curve is plotted.

[0033] It should be specifically noted that the horizontal axis of the feature inflection point time curve represents the timestamp, and the vertical axis represents the photovoltaic power generation and charging demand values ​​corresponding to the feature inflection point. By drawing the feature inflection point time curve, the value comparison between the photovoltaic power generation and the charging demand at each inflection point can be intuitively displayed, providing a visual reference for subsequent difference calculation.

[0034] Charge and discharge rate control adjustment module: Based on the characteristic inflection point time curve, calculate the difference between the photovoltaic predicted power generation value and the charging predicted demand value corresponding to the time coordinate, perform charge and discharge rate control based on the difference, generate a first charge and discharge rate control strategy, and adjust it to generate an adjusted second charge and discharge rate control strategy. In this embodiment, it should be specifically explained that the execution content of the charge / discharge rate control and adjustment module is as follows: Read the feature inflection point time curve, filter the photovoltaic predicted power generation value corresponding to the time coordinate in the feature inflection point time curve to be greater than or less than the charging predicted demand value, calculate the difference between the photovoltaic predicted power generation value and the charging predicted demand value for all time coordinates in the feature inflection point time curve, control the charging and discharging state based on the difference, and generate the corresponding first charging and discharging rate control strategy based on the control result. The content of controlling the charging and discharging state based on the difference is as follows: read the difference between the photovoltaic predicted power generation value and the charging predicted demand value corresponding to the time coordinate; when the difference is positive, store the remaining power at the corresponding time coordinate into the energy storage device according to the preset first charging rate; when the difference is negative, control the energy storage device to supply power to the charging device according to the preset first discharging rate; and mark the preset first charging rate and the preset first discharging rate as the first charging and discharging rate control strategy. The first charge / discharge rate control strategy is implemented, and the operating status of the energy storage device and the actual demand of the charging device are monitored in real time. The current actual temperature and standard operating temperature of the energy storage device are obtained, and the temperature deviation value is calculated. Td ; Calculate the efficiency deviation ratio between the current charge / discharge efficiency of the energy storage device and the reference charge / discharge efficiency. Dr The control strategy adjustment coefficient is calculated based on the temperature deviation value and the efficiency deviation ratio. The first charge and discharge rate control strategy is adjusted based on the control strategy adjustment coefficient to generate the adjusted second charge and discharge rate control strategy. The second charge and discharge rate control strategy includes a second charging rate and a second discharging rate.

[0035] Control strategy adjustment coefficient The calculation formula is: ,in, This indicates the preset standard temperature deviation value. This indicates the lower limit of the control strategy adjustment coefficient (e.g., 0.5). This represents the coefficient for the temperature deviation term (e.g., 0.1). This represents the efficiency deviation coefficient (e.g., 0.2).

[0036] The second charging rate is calculated by multiplying the preset first charging rate by the control strategy adjustment coefficient to obtain the second charging rate. The second discharge rate is calculated by multiplying the preset first discharge rate by the control strategy adjustment coefficient.

[0037] The preset first charging rate is a charging power value dynamically calculated based on the current state of charge of the energy storage device. The calculation method is as follows: when the state of charge of the energy storage device is below 30%, the first charging rate is set to 80%–95% of the rated charging power of the energy storage device; when the state of charge of the energy storage device is between 30% and 80%, the first charging rate is set to 50%–80% of the rated charging power of the energy storage device; when the state of charge of the energy storage device is above 80%, the first charging rate is set to 20%–50% of the rated charging power of the energy storage device. Within the aforementioned range, the system further determines the specific charging rate based on the magnitude of the difference and the health status of the energy storage device.

[0038] The preset first discharge rate is a discharge power value calculated based on the urgency of the charging device's needs and the current state of charge of the energy storage device. The calculation method is as follows: when the energy storage device's state of charge is higher than 70%, the first discharge rate is set to 70%–100% of the energy storage device's rated discharge power; when the energy storage device's state of charge is between 40% and 70%, the first discharge rate is set to 40%–70% of the energy storage device's rated discharge power; when the energy storage device's state of charge is lower than 40%, the first discharge rate is set to 20%–40% of the energy storage device's rated discharge power. The system determines the specific discharge rate within the corresponding range based on the urgency of the charging demand and the magnitude of the difference.

[0039] Control strategy execution feedback module: used to execute the second charge and discharge rate control strategy, monitor the execution result of the control strategy, and transmit the monitoring result to the display screen of the monitoring management platform in real time.

[0040] In this embodiment, it should be specifically noted that the above formulas are all dimensionless calculations. The formulas are derived from software simulations using a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0041] Example 2 Please see Figure 2 As shown, this invention provides a management method for integrated photovoltaic, energy storage, and charging systems in the new energy sector, comprising the following steps: S1: Predict photovoltaic power generation: Predict photovoltaic power generation for future time periods using a neural network model, and plot the photovoltaic power generation prediction curve for the preset time period based on the photovoltaic power generation. S2: Predict charging demand: Obtain the charging demand feature sequence, construct a charging demand prediction model, obtain the predicted charging demand, and draw a curve of the predicted charging demand within a preset time period. S3: Identify feature inflection points: Identify all feature inflection points appearing in the photovoltaic power generation prediction curve, and mark the feature inflection points as the 1st to the nth feature inflection points in chronological order; S4: Draw a feature inflection point graph: Extract the photovoltaic predicted power generation values ​​and time coordinates corresponding to the 1st to nth feature inflection points, locate and match the time coordinates in the charging predicted demand curve graph, extract the charging predicted demand values, and draw the feature inflection point time curve graph. S5: Control and adjust the charging and discharging rate: Based on the characteristic inflection point time curve, calculate the difference between the photovoltaic predicted power generation value and the charging predicted demand value corresponding to the time coordinate, control the charging and discharging rate based on the difference, generate a first charging and discharging rate control strategy, and adjust it to generate an adjusted second charging and discharging rate control strategy. S6: Execute feedback control strategy: Execute the second charge / discharge rate control strategy, monitor the execution result of the control strategy, and transmit the monitoring result to the display screen of the monitoring management platform in real time.

[0042] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0043] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A management system for integrated photovoltaic, energy storage, and charging systems in the new energy sector, characterized in that: include: Photovoltaic power generation prediction module: used to predict photovoltaic power generation in future time periods through a neural network model, and to draw a photovoltaic power generation prediction curve within a preset time period based on the photovoltaic power generation. Charging demand prediction module: used to acquire charging demand feature sequence, build charging demand prediction model, obtain charging demand prediction, and draw charging demand prediction curve within a preset time period. Feature inflection point identification module: used to identify all feature inflection points appearing in the photovoltaic power generation prediction curve, and to mark the feature inflection points as the 1st to the nth feature inflection points in chronological order; Feature Inflection Point Plotting Module: Used to extract the photovoltaic predicted power generation values ​​and time coordinates corresponding to the 1st to nth feature inflection points, locate and match the time coordinates in the charging predicted demand curve, extract the charging predicted demand values, and plot the feature inflection point time curve. Charge and discharge rate control adjustment module: Based on the characteristic inflection point time curve, calculate the difference between the photovoltaic predicted power generation value and the charging predicted demand value corresponding to the time coordinate, perform charge and discharge rate control based on the difference, generate a first charge and discharge rate control strategy, and adjust it to generate an adjusted second charge and discharge rate control strategy. Control strategy execution feedback module: used to execute the second charge and discharge rate control strategy, monitor the execution result of the control strategy, and transmit the monitoring result to the display screen of the monitoring management platform in real time.

2. The management system for integrated photovoltaic, energy storage, and charging of new energy sources according to claim 1, characterized in that: The charging demand prediction module performs the following operations: Real-time monitoring and analysis are performed on monitoring equipment in high-altitude areas to obtain a charging demand characteristic sequence of the monitoring equipment. The charging demand characteristic sequence includes the power consumption change rate, snow coverage rate, and data transmission deviation rate of the monitoring equipment. The obtained charging demand characteristic sequence is normalized, and a charging demand prediction model is constructed based on the charging demand characteristic sequence to calculate the charging demand prediction index. The first charging predicted demand is obtained based on the charging demand prediction index, and the charging predicted demand is corrected by environmental impact factors to obtain the second charging predicted demand. A charging predicted demand curve is plotted for a preset time period based on the second charging predicted demand. The method for obtaining the power consumption change rate is as follows: obtain the actual power consumption of the monitoring device within a preset period, extract the reference power consumption corresponding to the monitoring device within the preset period, calculate the difference between the actual power consumption of the monitoring device and the reference power consumption within the preset period, calculate the ratio of the difference to the reference power consumption, and analyze to obtain the power consumption change rate of the monitoring device. ; The data transmission deviation rate is obtained by: obtaining the actual data transmission volume within a preset period. And extract the corresponding baseline transmission volume within the preset period. The data transmission deviation rate was calculated. .

3. A management system for integrated photovoltaic, energy storage, and charging of new energy sources according to claim 2, characterized in that: The first predicted charging demand is obtained based on the charging demand forecast index, and then the predicted charging demand is corrected by environmental impact factors to obtain the second predicted charging demand, which is as follows: Read the power consumption change rate, snow coverage rate and data transmission deviation rate of the monitoring equipment, construct a charging demand prediction model, and calculate the charging demand prediction index. Read the charging demand forecast index and obtain the baseline load value of the monitoring equipment. The predicted charging demand is calculated using the formula for converting predicted charging demand, and this is marked as the first predicted charging demand. ; Environmental data from monitoring equipment in high-altitude areas is acquired, environmental impact factors are calculated, and the demand for the first charging phase is predicted based on these environmental impact factors. Make corrections to the calculated environmental impact factors. Multiplying the first predicted charging demand by the second predicted charging demand yields the corrected predicted charging demand, which is then designated as the second predicted charging demand. Furthermore, by acquiring the actual charging demand of the monitoring equipment in real time, analyzing the deviation of the predicted charging demand, and adjusting the charging demand prediction model based on the deviation analysis results; The environmental impact factors are obtained as follows: environmental data from monitoring equipment in high-altitude areas is acquired; temperature correction factors and air pressure correction factors are obtained based on the environmental data analysis; and the temperature correction factors and air pressure correction factors are weighted and calculated to obtain the environmental impact factors. .

4. A management system for integrated photovoltaic, energy storage, and charging of new energy sources according to claim 3, characterized in that: The analysis of charging demand prediction deviation includes: real-time acquisition of the second charging prediction demand and actual charging demand from the monitoring equipment; calculation of the charging prediction deviation coefficient by constructing a charging prediction deviation coefficient model; and determination of whether charging demand prediction adjustment is needed based on the charging prediction deviation coefficient. Specifically, the charging prediction deviation coefficient is read and compared with a preset charging prediction deviation coefficient threshold. If the charging prediction deviation coefficient is less than the preset threshold, it is determined that the charging demand prediction of the monitoring equipment has no deviation and no adjustment is needed; otherwise, it is determined that the charging demand prediction of the monitoring equipment has an abnormal deviation and adjustment is needed, and the parameters of the charging demand prediction model are adjusted.

5. A management system for integrated photovoltaic, energy storage, and charging of new energy sources according to claim 1, characterized in that: The execution content of the feature inflection point recognition module is as follows: A photovoltaic power generation forecast curve within a preset time period is obtained. All characteristic inflection points appearing sequentially in the photovoltaic power generation forecast curve are identified. The identification method of the characteristic inflection points is as follows: adjacent time points and their corresponding photovoltaic power generation values ​​are obtained from the photovoltaic power generation forecast curve. The slope values ​​of adjacent time points are calculated, and the absolute difference between adjacent slope values ​​is calculated. Based on the absolute difference, it is determined whether it is a characteristic inflection point of the photovoltaic power generation forecast curve. The determination method of the characteristic inflection point is as follows: the absolute difference is compared with a preset threshold, and the time points corresponding to the absolute difference being greater than the preset threshold are selected and marked as characteristic inflection points of the photovoltaic power generation forecast curve. They are then numbered sequentially from the 1st to the nth characteristic inflection point according to the time sequence.

6. A management system for integrated photovoltaic, energy storage, and charging of new energy sources according to claim 1, characterized in that: The execution content of the feature inflection point map drawing module is as follows: Read all the feature inflection points that appear in the photovoltaic power generation prediction curve. For the first to nth feature inflection points, extract the photovoltaic power generation value corresponding to each feature inflection point in turn. At the same time, obtain the time coordinate value corresponding to each feature inflection point in the photovoltaic power generation prediction curve. Record the time coordinate values ​​in the form of timestamps and mark them as the first to nth time nodes respectively. Based on the timestamps of the first to nth time nodes, in the charging forecast demand curve within the same preset time period, the time coordinates that match each timestamp are located sequentially, and the charging forecast demand value corresponding to each matching time coordinate is extracted. Based on the photovoltaic power generation forecast value corresponding to each feature inflection point and the charging demand forecast value corresponding to each matching time coordinate, a feature inflection point time curve is plotted.

7. A management system for integrated photovoltaic, energy storage, and charging of new energy sources according to claim 1, characterized in that: The charge / discharge rate control and adjustment module performs the following operations: Read the feature inflection point time curve, filter the photovoltaic predicted power generation value corresponding to the time coordinate in the feature inflection point time curve to be greater than or less than the charging predicted demand value, calculate the difference between the photovoltaic predicted power generation value and the charging predicted demand value for all time coordinates in the feature inflection point time curve, control the charging and discharging state based on the difference, and generate the corresponding first charging and discharging rate control strategy based on the control result. The content of controlling the charging and discharging state based on the difference is as follows: read the difference between the photovoltaic predicted power generation value and the charging predicted demand value corresponding to the time coordinate; when the difference is positive, store the remaining power at the corresponding time coordinate into the energy storage device according to the preset first charging rate; when the difference is negative, control the energy storage device to supply power to the charging device according to the preset first discharging rate; and mark the preset first charging rate and the preset first discharging rate as the first charging and discharging rate control strategy. The first charge / discharge rate control strategy is implemented, and the operating status of the energy storage device and the actual demand of the charging device are monitored in real time. The current actual temperature and standard operating temperature of the energy storage device are obtained, and the temperature deviation value is calculated. Td ; Calculate the efficiency deviation ratio between the current charge / discharge efficiency of the energy storage device and the reference charge / discharge efficiency. Dr The control strategy adjustment coefficient is calculated based on the temperature deviation value and the efficiency deviation ratio. The first charge and discharge rate control strategy is adjusted based on the control strategy adjustment coefficient to generate the adjusted second charge and discharge rate control strategy.

8. A management method for integrated photovoltaic, energy storage, and charging systems for new energy sources, comprising using the management system for integrated photovoltaic, energy storage, and charging systems for new energy sources as described in any one of claims 1-7, characterized in that, Includes the following steps: S1: Predict photovoltaic power generation: Predict photovoltaic power generation for future time periods using a neural network model, and plot the photovoltaic power generation prediction curve for the preset time period based on the photovoltaic power generation. S2: Predict charging demand: Obtain the charging demand feature sequence, construct a charging demand prediction model, obtain the predicted charging demand, and draw a curve of the predicted charging demand within a preset time period. S3: Identify feature inflection points: Identify all feature inflection points appearing in the photovoltaic power generation prediction curve, and mark the feature inflection points as the 1st to the nth feature inflection points in chronological order; S4: Draw a feature inflection point graph: Extract the photovoltaic predicted power generation values ​​and time coordinates corresponding to the 1st to nth feature inflection points, locate and match the time coordinates in the charging predicted demand curve graph, extract the charging predicted demand values, and draw the feature inflection point time curve graph. S5: Control and adjust the charging and discharging rate: Based on the characteristic inflection point time curve, calculate the difference between the photovoltaic predicted power generation value and the charging predicted demand value corresponding to the time coordinate, control the charging and discharging rate based on the difference, generate a first charging and discharging rate control strategy, and adjust it to generate an adjusted second charging and discharging rate control strategy. S6: Execute feedback control strategy: Execute the second charge / discharge rate control strategy, monitor the execution result of the control strategy, and transmit the monitoring result to the display screen of the monitoring management platform in real time.

Images