Intelligent photovoltaic energy storage real-time monitoring and scheduling system

Abstract

The invention relates to the technical field of electric power, in particular to an intelligent photovoltaic energy storage real-time monitoring and dispatching system. Comprising a data acquisition unit, a data analysis unit and a scheduling control unit, according to the method, the aerosol optical thickness, the dust coverage rate, the meteorological parameters and the like are fused, the predicted power of the basic photovoltaic power generation is obtained, the predicted power of the predicted photovoltaic power generation is corrected by using the environmental attenuation factor and the environmental loss coefficient, the accuracy of the predicted power of the basic photovoltaic power generation can be effectively improved, and meanwhile, the method has good application prospects. The corrected prediction error is reduced, the subsequent energy storage charge and discharge decision accuracy is improved, the energy storage state of the battery is dynamically evaluated, the dynamic energy storage state of the battery is obtained, the charge and discharge power sequence and the purchase and sale power sequence are obtained by establishing an objective function and constraint conditions, and then the real-time charge and discharge power adjustment amount is calculated, so that the real-time charge and discharge power adjustment amount is calculated. And a charging and discharging power instruction is formulated and issued, so that an intelligent dynamic scheduling effect is realized.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to an intelligent photovoltaic energy storage real-time monitoring and dispatching system. Background Art

[0002] With the global emphasis on environmental protection and sustainable development, the energy mix is gradually shifting from traditional fossil fuels to clean energy. Solar energy, as a clean, renewable energy source, holds enormous development potential. Continuous advances in photovoltaic technology have led to a gradual reduction in the cost of photovoltaic power generation and increased efficiency, leading to a rapid growth in distributed photovoltaic power generation projects worldwide. However, photovoltaic power generation is intermittent and fluctuating, with its output power significantly affected by factors such as sunlight intensity and weather conditions. This poses challenges to the stable operation of the power grid. To better utilize solar resources and enhance the reliability and flexibility of photovoltaic power generation, energy storage technology has emerged.

[0003] Existing technologies mainly rely on light intensity and temperature parameters and use traditional machine learning models for power generation prediction. They do not consider the impact of atmospheric transparency and component contamination, which affects power generation predictions. In addition, energy storage management is extensive, affecting the economic efficiency of photovoltaic energy storage.

[0004] Based on this, the present invention provides an intelligent photovoltaic energy storage real-time monitoring and scheduling system to solve the above-mentioned technical problems. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent photovoltaic energy storage real-time monitoring and scheduling system. First, the predicted power of the basic photovoltaic power generation is obtained, and the environmental attenuation factor and the environmental loss coefficient are used to correct the predicted power of the predicted photovoltaic power generation, which can effectively improve the accuracy of the predicted power of the basic photovoltaic power generation. In addition, the energy storage state of the battery is dynamically evaluated to obtain the dynamic energy storage state of the battery, and then the charging and discharging power timing and the purchasing and selling power timing are obtained, and then the real-time charging and discharging power adjustment amount is calculated, and the charging and discharging power instructions are formulated and issued, thereby achieving an intelligent dynamic scheduling effect.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The present invention provides an intelligent photovoltaic energy storage real-time monitoring and dispatching system, including a data acquisition unit, a data analysis unit and a dispatching control unit, wherein:

[0008] The data acquisition unit is used to obtain information about photovoltaic components, energy storage batteries and the environment;

[0009] The data analysis unit is used to obtain the predicted power of the basic photovoltaic power generation, and obtain the predicted power of the revised photovoltaic power generation based on the predicted power of the basic photovoltaic power generation, and dynamically evaluate the energy storage status of the battery. The predicted power of the revised photovoltaic power generation and the dynamically evaluated energy storage status of the battery are used to formulate a coordinated scheduling plan for photovoltaic power generation and energy storage. The data analysis unit is connected to the data acquisition unit;

[0010] The scheduling control unit is used to display the received information and control the response device to perform energy storage scheduling according to the received instructions and the timing of purchasing and selling electricity power. The scheduling control unit is connected to the data analysis unit.

[0011] The present invention is further configured as follows: the data acquisition unit includes an environment acquisition module, a photovoltaic acquisition module, an energy storage acquisition module and a first communication module, wherein:

[0012] The environment acquisition module is used to collect temperature information, weather information, light intensity information, aerosol optical thickness information and dust coverage information of the photovoltaic module's environment;

[0013] The photovoltaic collection module is used to obtain the historical power generation information of the photovoltaic module and the temperature of the surface of the photovoltaic module;

[0014] The energy storage acquisition module is used to collect terminal voltage information, charge and discharge current information, battery temperature information, battery internal resistance information, historical cycle number information and calendar aging days information of the energy storage battery;

[0015] The first communication module is used to realize information interaction between the data acquisition unit and the data analysis unit. The first communication module is connected to the environment acquisition module, the photovoltaic acquisition module and the energy storage acquisition module.

[0016] The present invention is further configured as follows: the data analysis unit includes a second communication module, a data preprocessing module and a power prediction module, wherein:

[0017] The second communication module is used to realize information interaction between the data analysis unit, the data acquisition unit and the scheduling control unit;

[0018] The data preprocessing module is used to preprocess the received data information, and the data preprocessing module is connected to the second communication module;

[0019] The power prediction module is used to predict the photovoltaic power generation amount, and the power prediction module is connected to the data preprocessing module.

[0020] The present invention is further configured such that: the preprocessing of the received data information includes the following contents:

[0021] If the photovoltaic output is detected to be greater than 0 at night, it is marked as abnormal data and replaced with the average value of the adjacent time period;

[0022] The weather information is feature-encoded, with sunny days coded as 1, cloudy days coded as 2, and rainy and snowy days coded as 3, to obtain the weather time series feature coding.

[0023] The present invention is further configured as follows: the process of predicting the photovoltaic power generation is as follows:

[0024] Using the trained LSTM prediction model, input the light intensity G(t), ambient temperature T amb (t), PV panel surface temperature T cell (t), aerosol optical depth AOD(t), dust coverage D(t) and historical photovoltaic power generation series P PV (t-1~tn), output the predicted power P of basic photovoltaic power generation PV (t);

[0025] Calculate the environmental attenuation factor γ(t) and the environmental loss coefficient σ(t):

[0026] γ(t)=0.05+0.1·D(t);

[0027] Where I(W(t)) is the indicator function, which takes the value 1 when the weather is rainy or snowy, and takes the value 0 otherwise;

[0028] Correction of the predicted power of photovoltaic power generation

[0029] The present invention is further configured as follows: the data analysis unit further includes a database module, an energy storage evaluation module and a collaborative scheduling module, wherein:

[0030] The database module is used to store the received data, and the database module is connected to both the second communication module and the power prediction module;

[0031] The energy storage evaluation module is used to dynamically evaluate the energy storage state of the battery, and the energy storage evaluation module is connected to both the second communication module and the database module;

[0032] The collaborative scheduling module is used to achieve collaborative scheduling of photovoltaic power generation and energy storage, and the collaborative scheduling module is connected to the second communication module, the power prediction module, the database module and the energy storage evaluation module.

[0033] The present invention is further configured as follows: the process of dynamically evaluating the energy storage state of the battery is as follows:

[0034] Calculate the actual available capacity of the battery Where C(t) is the actual available capacity of the battery at time t, C rated (t) is the rated capacity of the battery, k cycle is the cyclic attenuation coefficient, N cycle is the number of cycles of the battery, k calendar is the calendar attenuation coefficient, t age The calendar aging days of the battery;

[0035] Preliminary estimate of the battery's SOC, Where, SOC raw (t) is the battery state of charge initially estimated at time t, SOC(t0) is the battery state of charge at the initial time t0, κ is the discharge efficiency, and I(τ) is the battery charge and discharge current at time τ;

[0036] Dynamically correct the battery SOC Where, SOC corr (t) is the corrected battery state of charge at time t, R1(t) is the internal resistance of the battery at time t, R2(t) is the standard internal resistance of a new battery, β R is the internal resistance correction coefficient;

[0037] Dynamically evaluate the battery's energy storage status

[0038] The present invention is further configured as follows: the process of coordinated scheduling of photovoltaic power generation and energy storage is as follows:

[0039] Establish the objective function of day-ahead scheduling Where c grid (t) is the electricity price of the power grid at time t, P grid (t) The interaction power between the grid and the system at time t, S(t) is the energy storage state of the energy storage battery at time t, and α is the penalty coefficient;

[0040] Establishing target constraints Where, P bat (t) is the charge and discharge power of the energy storage battery at time t, is the power load at time t;

[0041] The mixed integer programming solver Gurobi is used to solve the problem and the output is the 24-hour charge and discharge power sequence. and the timing of electricity purchase and sales

[0042] Calculate the real-time charge and discharge power adjustment ΔP bat (t) = K p ·(SOC real (t)-SOC day (t)), where Kp is the proportional adjustment coefficient, SOC real (t) is the state of charge measured by the battery, SOC day (t) is the SOC value of the target battery;

[0043] Formulate and issue charging and discharging power instructions

[0044] The present invention is further configured as follows: the scheduling control unit includes a third communication module and an information display module, wherein:

[0045] The third communication module is used to realize information interaction between the scheduling control unit and the data analysis unit;

[0046] The information display module is used to display the received information, and the information display module is connected to the third communication module.

[0047] The present invention is further configured as follows: the scheduling control unit also includes a control response module, which controls the response device to perform energy storage scheduling according to the received instructions and the timing of purchasing and selling electricity power, and the scheduling control unit is connected to both the third communication module and the information display module.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The present invention integrates aerosol optical thickness, dust coverage and meteorological parameters to obtain the predicted power of basic photovoltaic power generation, and uses the environmental attenuation factor and environmental loss coefficient to correct the predicted power of predicted photovoltaic power generation, which can effectively improve the accuracy of the predicted power of basic photovoltaic power generation. At the same time, the corrected prediction error is reduced, so that the accuracy of subsequent energy storage charging and discharging decisions is improved. In addition, the energy storage state of the battery is dynamically evaluated to obtain the dynamic energy storage state of the battery. By establishing the objective function and constraint conditions, the charging and discharging power sequence and the purchasing and selling power sequence are obtained, and then the real-time charging and discharging power adjustment amount is calculated, and the charging and discharging power instructions are formulated and issued, thereby realizing the intelligent dynamic scheduling effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a system diagram of the intelligent photovoltaic energy storage real-time monitoring and scheduling system of the present invention.

[0051] Figure 2 This is a system diagram of the data acquisition unit in the intelligent photovoltaic energy storage real-time monitoring and dispatching system of the present invention.

[0052] Figure 3 This is a system diagram of the data analysis unit in the intelligent photovoltaic energy storage real-time monitoring and scheduling system of the present invention.

[0053] Figure 4This is a system diagram of the dispatching control unit in the intelligent photovoltaic energy storage real-time monitoring and dispatching system of the present invention.

[0054] Description of Figure Numbers:

[0055] 100, data acquisition unit; 110, environmental acquisition module; 120, photovoltaic acquisition module; 130, energy storage acquisition module; 140, first communication module; 200, data analysis unit; 210, second communication module; 220, data preprocessing module; 230, power prediction module; 240, database module; 250, energy storage evaluation module; 260, collaborative scheduling module; 300, scheduling control unit; 310, third communication module; 320, information display module; 330, control response module. DETAILED DESCRIPTION

[0056] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described 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 ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0057] Example:

[0058] like Figure 1-Figure 4 As shown, this embodiment provides an intelligent photovoltaic energy storage real-time monitoring and scheduling system, including a data acquisition unit 100, a data analysis unit 200 and a scheduling control unit 300, wherein: the data acquisition unit 100 is used to obtain information about photovoltaic components, energy storage batteries and the environment; the data analysis unit 200 is used to obtain the predicted power of the basic photovoltaic power generation, and obtain the predicted power of the corrected photovoltaic power generation based on the predicted power of the basic photovoltaic power generation, and dynamically evaluate the energy storage status of the battery, and use the predicted power of the corrected photovoltaic power generation and the dynamic evaluation of the energy storage status of the battery to formulate a coordinated scheduling plan for photovoltaic power generation and energy storage. The data analysis unit 200 is connected to the data acquisition unit 100; the scheduling control unit 300 is used to display the received information, and control the response device to perform energy storage scheduling according to the received instructions and the timing of purchasing and selling electricity power. The scheduling control unit 300 is connected to the data analysis unit 200.

[0059] In this embodiment, it should be noted that the data acquisition unit 100 collects and obtains information about the photovoltaic components, the energy storage battery, and the environment, and feeds it back to the data analysis unit 200. The data analysis unit 200 uses the trained LSTM prediction model to obtain the predicted power of the basic photovoltaic power generation, and uses the calculated environmental attenuation factor and the environmental loss coefficient to correct the predicted power of the predicted photovoltaic power generation. On the one hand, using the aerosol optical thickness, dust coverage, weather type, etc. as inputs to the LSTM prediction model can effectively improve the accuracy of the predicted power of the basic photovoltaic power generation. On the other hand, combining the environmental loss coefficient with the attenuation factor to correct the predicted power of the photovoltaic power generation. The prediction error can be reduced, and the corrected prediction error is reduced, so that the accuracy of subsequent energy storage charging and discharging decisions is improved. At the same time, the data analysis unit 200 will also dynamically evaluate the energy storage status of the battery to obtain the dynamic energy storage status of the battery. By establishing the objective function and constraints, the charging and discharging power sequence, as well as the power purchase and sales sequence, are obtained, and then the real-time charging and discharging power adjustment amount is calculated, and the charging and discharging power instructions are formulated and issued, which are fed back to the scheduling control unit 300 for scheduling. The provided system combines cycle and calendar aging, breaking through the traditional capacity evaluation method that only considers the number of cycles. At the same time, the internal resistance compensation mechanism is introduced to reduce the SOC estimation error and enable intelligent scheduling.

[0060] In the present invention, the data acquisition unit 100 includes an environment acquisition module 110, a photovoltaic acquisition module 120, an energy storage acquisition module 130 and a first communication module 140, wherein: the environment acquisition module 110 is used to collect temperature information, weather information, light intensity information, aerosol optical depth information and dust coverage information on the surface of the photovoltaic module in the environment in which the photovoltaic module is located; the photovoltaic acquisition module 120 is used to obtain the historical power generation information of the photovoltaic module and the temperature of the surface of the photovoltaic module; the energy storage acquisition module 130 is used to collect the terminal voltage information, charge and discharge current information, battery temperature information, battery internal resistance information, historical cycle number information and calendar aging day information of the energy storage battery; the first communication module 140 is used to realize information interaction between the data acquisition unit 100 and the data analysis unit 200, and the first communication module 140 is connected to the environment acquisition module 110, the photovoltaic acquisition module 120 and the energy storage acquisition module 130.

[0061] In this embodiment, it should be noted that the temperature information, weather information, light intensity information, aerosol optical depth information and dust coverage information on the surface of the photovoltaic module collected by the environment acquisition module 110 are transmitted to the data analysis unit 200 through the first communication module 140. At the same time, the historical power generation information of the photovoltaic module and the temperature of the surface of the photovoltaic module obtained by the photovoltaic acquisition module 120 are also transmitted to the data analysis unit 200 through the first communication module 140. In addition, the information collected by the energy storage acquisition module 130 can also be transmitted to the data analysis unit 200 through the first communication module 140.

[0062] In addition, it should be noted that the aerosol optical depth can be measured by using methods including but not limited to a sun photometer. The aerosol optical depth reflects the attenuation effect of aerosols in the atmosphere on light. Aerosols will scatter and absorb solar radiation. The higher the aerosol optical depth value, the more aerosol content in the atmosphere, the stronger the weakening effect on sunlight, and the lower the light intensity reaching the ground. Light intensity is one of the key factors affecting photovoltaic power generation. Accurately obtaining aerosol optical depth information helps to more accurately evaluate the actual amount of light reaching the photovoltaic module, thereby providing a more accurate basis for photovoltaic power generation power prediction; dust covering the surface of the photovoltaic module will block part of the light from reaching the photovoltaic cell, reducing the absorption and utilization of light, thereby reducing the power generation efficiency of the photovoltaic module. This embodiment can be obtained by using methods including but not limited to infrared cameras.

[0063] In the present invention, the data analysis unit 200 includes a second communication module 210, a data preprocessing module 220 and a power prediction module 230, wherein: the second communication module 210 is used to realize information interaction between the data analysis unit 200 and the data acquisition unit 100 and the scheduling control unit 300; the data preprocessing module 220 is used to preprocess the received data information, and the data preprocessing module 220 is connected to the second communication module 210; the power prediction module 230 is used to predict the photovoltaic power generation, and the power prediction module 230 is connected to the data preprocessing module 220.

[0064] The preprocessing of the received data information includes the following: if the photovoltaic output is detected to be greater than 0 at night, it is marked as abnormal data, and the abnormal data is replaced with the average value of the adjacent time period; the weather information is feature-encoded, with sunny days coded as 1, cloudy days coded as 2, and rain and snow coded as 3, to obtain the weather time series feature code.

[0065] In addition, the process of photovoltaic power generation prediction is as follows: using the trained LSTM prediction model, inputting the light intensity G(t), ambient temperature T amb (t), PV panel surface temperature T cell(t), aerosol optical depth AOD(t), dust coverage D(t) and historical photovoltaic power generation series P PV (t-1~tn), output the predicted power P of basic photovoltaic power generation PV (t); calculate the environmental attenuation factor γ(t) and the environmental loss coefficient σ(t): γ(t) = 0.05 + 0.1·D(t); Where I(W(t)) is the indicator function, which takes 1 when the weather is rainy or snowy, and takes 0 otherwise; the predicted power of the corrected photovoltaic power generation is

[0066] In this embodiment, it should be noted that the second communication module 210 receives the information of the data acquisition unit 100 and uploads it to the data preprocessing module 220. The data preprocessing module 220 preprocesses the received data information and then uploads it to the power prediction module 230. The power prediction module 230 predicts the photovoltaic power generation.

[0067] Table 1 shows a method for encoding gas information characteristics in this embodiment.

[0068] Table 1: Gas information feature coding table

[0069] Weather type coding Judgment conditions sunny 1 Cloud cover <20%, no precipitation partly cloudy 2 20%≤Cloud cover<80% Rain and snow 3 Precipitation or cloud cover ≥ 80%

[0070] The LSTM prediction model is a widely used long short-term memory network model, which will not be described in detail here. In this embodiment, time series data such as historical light intensity, ambient temperature, photovoltaic module surface temperature, aerosol optical depth, dust coverage, and historical photovoltaic power generation related to photovoltaic power generation can be collected, and then the data can be preprocessed. The preprocessed data is divided into a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to adjust the model's hyperparameters, and the test set is used to evaluate the model's final performance. After training, the LSTM prediction model is obtained.

[0071] In the present invention, the data analysis unit 200 also includes a database module 240, an energy storage evaluation module 250 and a collaborative scheduling module 260, wherein: the database module 240 is used to store the received data, and the database module 240 is connected to the second communication module 210 and the power prediction module 230; the energy storage evaluation module 250 is used to dynamically evaluate the energy storage status of the battery, and the energy storage evaluation module 250 is connected to the second communication module 210 and the database module 240; the collaborative scheduling module 260 is used to realize the collaborative scheduling of photovoltaic power generation and energy storage, and the collaborative scheduling module 260 is connected to the second communication module 210, the power prediction module 230, the database module 240 and the energy storage evaluation module 250.

[0072] The process of dynamic evaluation of the battery's energy storage status is as follows: Calculate the actual available capacity of the battery Where C(t) is the actual available capacity of the battery at time t, C rated (t) is the rated capacity of the battery, k cycle is the cyclic attenuation coefficient, N cycle is the number of cycles of the battery, k calendar is the calendar attenuation coefficient, t age is the calendar aging days of the battery; preliminary estimate of the battery SOC, Where, SOC raw (t) is the battery state of charge estimated at time t, SOC(t0) is the battery state of charge at the initial time t0, κ is the discharge efficiency, and I(τ) is the battery charge and discharge current at time τ; the battery SOC is dynamically corrected Where, SOC corr (t) is the corrected battery state of charge at time t, R1(t) is the internal resistance of the battery at time t, R2(t) is the standard internal resistance of a new battery, β R Internal resistance correction coefficient; Dynamically evaluate the battery's energy storage status

[0073] In addition, the process of coordinated scheduling of photovoltaic power generation and energy storage is as follows: Establish the objective function of day-ahead scheduling Where c grid (t) is the electricity price of the power grid at time t, P grid (t) is the interaction power between the grid and the system at time t, S(t) is the energy storage state of the energy storage battery at time t, and α is the penalty coefficient; establish the target constraint condition Where, P bat (t) is the charge and discharge power of the energy storage battery at time t, is the power load at time t; the mixed integer programming solver Gurobi is used to solve it, and the output is the 24-hour charging and discharging power sequence and the timing of electricity purchase and sales Calculate the real-time charge and discharge power adjustment ΔP bat (t) = K p ·(SOC real (t)-SOC day (t)), where K p is the proportional adjustment coefficient, SOC real (t) is the state of charge measured by the battery, SOC day (t) is the SOC value of the target battery; formulate and issue charging and discharging power instructions

[0074] In this embodiment, it should be noted that the energy storage assessment module 250 obtains the information uploaded by the second communication module 210, dynamically assesses the energy storage status of the battery, and uploads the dynamically assessed energy storage status information to the coordinated scheduling module 260. The coordinated scheduling module 260 implements the coordinated scheduling of photovoltaic power generation and energy storage, that is, by establishing an objective function and constraints, obtaining the charging and discharging power sequence, as well as the purchasing and selling power sequence, and then calculating the real-time charging and discharging power adjustment amount. The provided system combines cycle and calendar aging, breaking through the traditional capacity assessment method that only considers the number of cycles. At the same time, an internal resistance compensation mechanism is introduced to reduce the SOC estimation error.

[0075] In the present invention, the scheduling control unit 300 includes a third communication module 310 and an information display module 320, wherein: the third communication module 310 is used to realize information interaction between the scheduling control unit 300 and the data analysis unit 200; the information display module 320 is used to display the received information, and the information display module 320 is connected to the third communication module 310.

[0076] In addition, the scheduling control unit 300 also includes a control response module 330, which controls the response device to perform energy storage scheduling according to the received instructions and the timing of purchasing and selling electricity power. The scheduling control unit 300 is connected to both the third communication module 310 and the information display module 320.

[0077] In this embodiment, it should be noted that the information of the data analysis unit 200 is received by the third communication module 310, uploaded to the information display module 320, and displayed by the information display module 320 for management personnel to view. At the same time, the control response module 330 will receive instructions and timing information of power purchase and sale, and perform scheduling by controlling the corresponding response equipment.

[0078] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0079] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Intelligent photovoltaic energy storage real-time monitoring and dispatching system, characterized by: The system comprises a data collection unit (100), a data analysis unit (200) and a scheduling control unit (300), wherein: The data acquisition unit (100) is used to obtain information about photovoltaic components, information about energy storage batteries, and information about the environment; The data analysis unit (200) is used to obtain the predicted power of the basic photovoltaic power generation, and obtain the predicted power of the corrected photovoltaic power generation based on the predicted power of the basic photovoltaic power generation, and dynamically evaluate the energy storage state of the battery. The predicted power of the corrected photovoltaic power generation and the dynamically evaluated energy storage state of the battery are used to formulate a coordinated scheduling plan for photovoltaic power generation and energy storage. The data analysis unit (200) is connected to the data acquisition unit (100); The scheduling control unit (300) is used to display the received information and control the response equipment to perform energy storage scheduling according to the received instructions and the timing of purchasing and selling electricity power. The scheduling control unit (300) is connected to the data analysis unit (200).

2. The intelligent photovoltaic energy storage real-time monitoring and dispatching system according to claim 1 is characterized in that: The data acquisition unit (100) comprises an environment acquisition module (110), a photovoltaic acquisition module (120), an energy storage acquisition module (130) and a first communication module (140), wherein: The environment collection module (110) is used to collect temperature information, weather information, light intensity information, aerosol optical thickness information, and dust coverage information on the surface of the photovoltaic module in the environment in which the photovoltaic module is located; The photovoltaic collection module (120) is used to obtain historical power generation information of the photovoltaic module and the temperature of the surface of the photovoltaic module; The energy storage acquisition module (130) is used to collect terminal voltage information, charge and discharge current information, battery temperature information, battery internal resistance information, historical cycle number information, and calendar aging day information of the energy storage battery; The first communication module (140) is used to realize information interaction between the data acquisition unit (100) and the data analysis unit (200), and the first communication module (140) is connected to the environment acquisition module (110), the photovoltaic acquisition module (120) and the energy storage acquisition module (130).

3. The intelligent photovoltaic energy storage real-time monitoring and dispatching system according to claim 1 is characterized in that: The data analysis unit (200) comprises a second communication module (210), a data pre-processing module (220) and an electric quantity prediction module (230), wherein: The second communication module (210) is used to realize information interaction between the data analysis unit (200), the data acquisition unit (100) and the scheduling control unit (300); The data preprocessing module (220) is used to preprocess the received data information, and the data preprocessing module (220) is connected to the second communication module (210); The power prediction module (230) is used to predict photovoltaic power generation, and the power prediction module (230) is connected to the data preprocessing module (220).

4. The intelligent photovoltaic energy storage real-time monitoring and dispatching system according to claim 3 is characterized in that: The pre-processing of the received data information includes the following: If the photovoltaic output is detected to be greater than 0 at night, it is marked as abnormal data and replaced with the average value of the adjacent time period; The weather information is feature-encoded, with sunny days coded as 1, cloudy days coded as 2, and rainy and snowy days coded as 3, to obtain the weather time series feature coding.

5. The intelligent photovoltaic energy storage real-time monitoring and dispatching system according to claim 3 is characterized in that: The process of predicting photovoltaic power generation is as follows: Using the trained LSTM prediction model, input the light intensity G(t), ambient temperature T amb (t), PV panel surface temperature T cell (t), aerosol optical depth AOD(t), dust coverage D(t) and historical photovoltaic power generation series P PV (t-1~tn), output the predicted power P of basic photovoltaic power generation PV (t); Calculate the environmental attenuation factor γ(t) and the environmental loss coefficient σ(t): γ(t)=0.05+0.1·D(t); Where I(W(t)) is the indicator function, which takes the value 1 when the weather is rainy or snowy, and takes the value 0 otherwise; Correction of the predicted power of photovoltaic power generation 6. The intelligent photovoltaic energy storage real-time monitoring and dispatching system according to claim 3 is characterized in that: The data analysis unit (200) further includes a database module (240), an energy storage evaluation module (250) and a coordinated scheduling module (260), wherein: The database module (240) is used to store the received data, and the database module (240) is connected to both the second communication module (210) and the power prediction module (230); The energy storage evaluation module (250) is used to dynamically evaluate the energy storage state of the battery, and the energy storage evaluation module (250) is connected to both the second communication module (210) and the database module (240); The coordinated scheduling module (260) is used to realize the coordinated scheduling of photovoltaic power generation and energy storage, and the coordinated scheduling module (260) is connected to the second communication module (210), the power prediction module (230), the database module (240) and the energy storage evaluation module (250).

7. The intelligent photovoltaic energy storage real-time monitoring and dispatching system according to claim 6 is characterized in that: The process of dynamically evaluating the energy storage state of the battery is as follows: Calculate the actual available capacity of the battery Where C(t) is the actual available capacity of the battery at time t, C rated (t) is the rated capacity of the battery, k cycle is the cyclic attenuation coefficient, N cycle is the number of cycles of the battery, k calendar is the calendar attenuation coefficient, t age The calendar aging days of the battery; Preliminary estimate of the battery's SOC, Where, SOC raw (t) is the battery state of charge initially estimated at time t, SOC(t0) is the battery state of charge at the initial time t0, κ is the discharge efficiency, and I(τ) is the battery charge and discharge current at time τ; Dynamically correct the battery SOC Where, SOC corr (t) is the corrected battery state of charge at time t, R1(t) is the internal resistance of the battery at time t, R2(t) is the standard internal resistance of a new battery, β R is the internal resistance correction coefficient; Dynamically evaluate the battery's energy storage status 8. The intelligent photovoltaic energy storage real-time monitoring and dispatching system according to claim 6 is characterized in that: The process of coordinated scheduling of photovoltaic power generation and energy storage is as follows: Establish the objective function of day-ahead scheduling Where c grid (t) is the electricity price of the power grid at time t, P grid (t) The interaction power between the grid and the system at time t, S(t) is the energy storage state of the energy storage battery at time t, and α is the penalty coefficient; Establishing target constraints Where, P bat (t) is the charge and discharge power of the energy storage battery at time t, is the power load at time t; The mixed integer programming solver Gurobi is used to solve the problem and the output is the 24-hour charge and discharge power sequence. and the timing of electricity purchase and sales Calculate the real-time charge and discharge power adjustment ΔP bat (t) = K p ·(SOC real (t)-SOC day (t)), where K p is the proportional adjustment coefficient, SOC real (t) is the state of charge measured by the battery, SOC day (t) is the SOC value of the target battery; Formulate and issue charging and discharging power instructions 9. The intelligent photovoltaic energy storage real-time monitoring and dispatching system according to claim 1 is characterized in that: The dispatch control unit (300) includes a third communication module (310) and an information display module (320), wherein: The third communication module (310) is used to realize information interaction between the scheduling control unit (300) and the data analysis unit (200); The information display module (320) is used to display the received information, and the information display module (320) is connected to the third communication module (310).

10. The intelligent photovoltaic energy storage real-time monitoring and dispatching system according to claim 9, characterized in that: The dispatch control unit (300) further comprises a control response module (330), wherein the control response module (330) controls the response device to perform energy storage dispatch according to the received instructions and the power purchase and sale timing. The dispatch control unit (300) is connected to both the third communication module (310) and the information display module (320).

Images