Optical storage cooperative control optimization method, electronic equipment and medium

Abstract

The invention relates to an optical storage cooperative control optimization method, electronic equipment and a medium. The method comprises the steps of collecting historical energy consumption and photovoltaic data of a park, constructing a photovoltaic electronic model based on the data, performing day-ahead prediction by adopting CNN-BiGRU, and generating a load power and photovoltaic generation power sequence; calculating the electricity consumption and the photovoltaic generating capacity of each time period; setting the capacity of an energy storage module, and calculating the energy storage charging and discharging capacity based on an SOC formula; according to the electricity consumption, the generating capacity and the energy storage capacity, determining a peak section discharge demand; photovoltaic fluctuation constraint is combined, and energy storage charging and discharging power is adjusted to stabilize fluctuation; optimizing load power utilization, photovoltaic power generation and energy storage power scheduling based on the power balance relation; and constructing a revenue maximization objective function, establishing a light storage collaborative optimization model in combination with constraints, and solving an optimal operation scheme of a prediction day. According to the method, photovoltaic power generation errors are reduced, power output is balanced, power grid requirements are met, the photovoltaic consumption rate is improved, healthy operation of the system is guaranteed, and operation benefits are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a photovoltaic-storage collaborative control optimization method, electronic equipment and medium. Background Art

[0002] With the continuous growth of global energy demand and the gradual advancement of carbon emission reduction targets, the large-scale application of renewable energy, especially photovoltaic power generation, has developed rapidly around the world. However, photovoltaic power generation is intermittent and volatile due to the influence of natural conditions such as weather and light intensity, and it is difficult to achieve stable output, which poses a great challenge to the operation of the power grid. At the same time, there is often a mismatch between the load demand of traditional power systems and the time characteristics of photovoltaic power generation, which further limits the utilization efficiency of photovoltaic energy.

[0003] To solve the above problems, the coordinated optimization technology of photovoltaic power generation and energy storage system came into being. The energy storage system can not only smooth out the fluctuation of photovoltaic power generation, but also effectively improve the stability and reliability of the power grid by storing energy when photovoltaic power generation is in excess and releasing energy during peak demand periods. In addition, the rapid response capability of the energy storage system enables it to participate in auxiliary services, peak-valley price arbitrage, etc. in the power market to maximize economic benefits. Summary of the invention

[0004] The present invention provides a photovoltaic-storage coordinated control optimization method, electronic equipment and medium, the purpose of which is to solve the problems of low energy utilization efficiency and insufficient economy of energy storage system caused by large volatility of photovoltaic power generation and mismatch between load demand and power generation time.

[0005] To achieve the above object, the first aspect of the present invention provides a photovoltaic energy storage coordinated control optimization method, comprising the following steps:

[0006] Collect historical data of the park, including energy consumption data on the energy output and demand sides and data related to photovoltaic power generation;

[0007] Based on the historical data, a photovoltaic power generation model is constructed, and a CNN-BiGRU model is used for day-ahead prediction, generating a predicted daily load power data sequence and a photovoltaic power generation power data sequence respectively;

[0008] According to the forecasted daily load power data sequence and photovoltaic power generation data sequence, the power consumption and photovoltaic power generation in each period of the forecasted day are calculated, and the time period is divided into the valley period, the first peak period, the first flat period, the second peak period and the second flat period;

[0009] Set the rated capacity and current remaining power of the energy storage module, and calculate the charging and discharging capacity of the energy storage module at each time period of the forecast day based on the energy storage state of charge SOC calculation formula;

[0010] Determine the discharge power requirements of the energy storage module in the first peak section and the second peak section based on the power consumption, photovoltaic power generation and charging and discharging capacity of the energy storage module in each period of the forecast day;

[0011] Set the photovoltaic fluctuation smoothing constraint conditions, adjust the charging and discharging power of the energy storage module according to the photovoltaic power prediction value and the fluctuation allowable deviation, and calculate the energy storage power signal to smooth the photovoltaic fluctuation;

[0012] Based on the power balance relationship of the park, determine the scheduling relationship between load power consumption, photovoltaic power generation power and energy storage module charging and discharging power;

[0013] An optimization objective function with the goal of maximizing the comprehensive benefits of the park is constructed, and a park-level photovoltaic-storage collaborative optimization model is established by combining photovoltaic utilization constraints, energy storage SOC constraints, and power balance constraints.

[0014] The optimization algorithm is used to solve the park-level photovoltaic energy storage collaborative optimization model to obtain the optimal operation plan for photovoltaic power generation, energy storage modules and loads in each period of the forecast day.

[0015] Furthermore, the method of constructing a photovoltaic electronic model includes:

[0016] Preprocess the historical data, remove outliers and interpolate missing values, and form a complete data set after normalization;

[0017] According to the input and output characteristics of photovoltaic power generation, irradiance, ambient temperature and wind speed are used as input variables, and photovoltaic power generation power is used as output variable;

[0018] A photovoltaic power generation model is constructed using a regression algorithm, and the photovoltaic power generation model parameters are trained through historical data, so that the photovoltaic power generation model can predict photovoltaic power generation power based on input variables;

[0019] Verify the constructed photovoltaic power generation sub-model and use the test data set in the historical data set to evaluate the model accuracy so that the photovoltaic power generation sub-model can accurately characterize the relationship between photovoltaic power generation power and environmental variables.

[0020] Furthermore, according to the load power data sequence and photovoltaic power generation data sequence of the forecast day, the method for calculating the power consumption and photovoltaic power generation in each period of the forecast day includes:

[0021] The load power data series and photovoltaic power generation data series of the forecast day are divided into five time periods in chronological order, namely the valley period, the first peak period, the first flat period, the second peak period and the second flat period;

[0022] According to the load power data sequence, the power consumption of each period of the forecast day is calculated, which are the valley power consumption, the first peak power consumption, the first flat power consumption, the second peak power consumption and the second flat power consumption;

[0023] According to the photovoltaic power generation data sequence, the photovoltaic power generation in each period of the forecast day is calculated, namely the photovoltaic power generation in the valley section, the photovoltaic power generation in the first peak section, the photovoltaic power generation in the first flat section, the photovoltaic power generation in the second peak section and the photovoltaic power generation in the second flat section.

[0024] Furthermore, the state of charge SOC calculation formula of the energy storage module is:

[0025] SOC(t+1)=(1-γ)SOC(t)-E b (t) / E b，max

[0026] Among them, SOC(t+1) represents the state of charge of the energy storage module at time t+1, SOC(t) represents the state of charge of the energy storage module at time t, γ is the energy storage self-discharge rate, E b is the change in stored energy, E b (t) is the energy change at time t. A negative value indicates charging, and a positive value indicates discharging. E b,max The maximum storable power value of the energy storage.

[0027] Furthermore, the constraints for PV fluctuation suppression are:

[0028] PV b (t)+PV pre (t)-PV(t)≤αPV(t)

[0029] Among them, PV b (t) is the power signal of the energy storage system used to smooth out the photovoltaic fluctuations, PV pre (t) represents the dynamic correction value of the photovoltaic predicted power, PV(t) represents the actual photovoltaic power at time t, and α is the allowable deviation rate of photovoltaic power.

[0030] Furthermore, the comprehensive income of the park includes load electricity income, energy storage module discharge income and charging expenses, specifically:

[0031] W1(t)=C1(t)·P1(t)+C2(t)·P bd (t)-C3(t)·P bc (t)

[0032] Among them, C1(t), C2(t), and C3(t) are the user electricity price, energy storage discharge price, and energy storage charging price, respectively. bd (t), P bc(t) are load power, energy storage discharge power and energy storage charging power respectively.

[0033] Furthermore, the steps of constructing an optimization objective function with the goal of maximizing the comprehensive benefits of the park include:

[0034] The comprehensive income of the park is determined to be composed of load electricity income, energy storage discharge income and energy storage charging expenditure. The expression of the optimization objective function is:

[0035] W total =∑ t [C1(t)·P1(t)+C2(t)·P bd (t)-C3(t)·P bc (t)]

[0036] Among them, W total is the comprehensive income of the park, C1(t), C2(t), and C3(t) are the user electricity price, energy storage discharge price, and energy storage charging price respectively; P1(t), P bd (t), P bc (t) are load power, energy storage discharge power and energy storage charging power respectively;

[0037] Considering the economic life loss of the energy storage module, the economic loss formula of the energy storage module is supplemented by correcting the loss of charging and discharging:

[0038] W b (t) = αC b ·|P bat (t)|·Δt+βC b ·|P bat (t)|·Δt

[0039] Among them, W b (t) is the economic loss of the energy storage module, α and β are the energy storage charge and discharge loss coefficients, C b is the unit price of energy storage life loss, P bad (t) is the energy storage operating power, Δt is the time interval;

[0040] The energy storage economic loss W b (t) Introducing the objective function, the optimization objective function is finally expressed as:

[0041] maxW total =Σ t [C1(t)·P1(t)+C2(t)·P bd (t)-C3(t)·P bc (t)-W b (t)].

[0042] Furthermore, the step of establishing a park-level photovoltaic-storage collaborative optimization model includes:

[0043] Set the photovoltaic utilization rate constraint to ensure that the utilization rate of photovoltaic power generation reaches the minimum requirement. The constraint conditions are:

[0044]

[0045] Among them, ρ is the photovoltaic utilization rate, PV(t) represents the actual photovoltaic power at time t, and PV pre (t) is the predicted photovoltaic power, ρ0 is the set minimum photovoltaic utilization rate;

[0046] Set the energy storage SOC constraint to ensure that the charge state of the energy storage module operates within a safe range. The constraint conditions are:

[0047] SOC min ≤SOC(t)≤SOC max

[0048] Among them, SOC(t) is the state of charge of the energy storage module at time t; SOC min and SOC max They are the lower and upper limits of the state of charge of the energy storage module respectively;

[0049] Set the park power balance constraint to ensure that the load demand in the park is balanced with the photovoltaic power generation power and energy storage power. The constraint conditions are:

[0050] P1(t)+P ad (t) = P pv (t)+P bd (t)-P bc (t)

[0051] Among them, P1(t), P bd (t), P bc (t) are load power, energy storage discharge power and energy storage charging power respectively, P ad (t) represents the additional load power demand in the park; P pv (t) represents the power output of the photovoltaic power generation system at time t;

[0052] The optimization objective function is combined with the above constraints to construct a park-level photovoltaic-storage collaborative optimization model, and finally a photovoltaic-storage collaborative optimization model is formed with the goal of maximizing the comprehensive benefits of the park.

[0053] To achieve the above-mentioned purpose, the second aspect of the present invention provides an electronic device, including a memory and a processor, wherein the memory is used to store a program that supports the processor to execute the photovoltaic-storage collaborative control optimization method, and the processor is configured to execute the program stored in the memory.

[0054] To achieve the above-mentioned purpose, the third aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the photovoltaic-storage collaborative control optimization method are executed.

[0055] Beneficial effects of the present invention:

[0056] Compared with the prior art, the present invention provides a photovoltaic storage coordinated control optimization method, electronic device and medium. By introducing the CNN-BiGRU model, the load power and photovoltaic power generation power of the park are predicted with high precision. Combined with the refined division of power consumption time periods, the difference between power consumption and photovoltaic power generation in each time period is clarified. At the same time, based on the state of charge (SOC) and charging and discharging capacity of the energy storage module, a dynamic charging and discharging strategy is formulated to effectively make up for the time difference between photovoltaic power generation and load demand. In addition, by setting photovoltaic fluctuation smoothing constraints and power balance constraints, the rapid response capability of energy storage is used to smooth photovoltaic fluctuations, achieve stable output of photovoltaic power generation, and improve the operational reliability of the system. On this basis, an optimization model with the goal of maximizing the comprehensive benefits of the park is constructed, and an intelligent optimization algorithm is used to solve it, and the optimal operation plan of photovoltaic, energy storage and load is obtained, which not only improves the utilization rate of photovoltaic power generation, but also significantly reduces the loss cost of the energy storage system, thereby solving the problems of low energy utilization efficiency and insufficient economy of the energy storage system caused by large fluctuations in photovoltaic power generation and mismatch between load and power generation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments.

[0058] Figure 1 It is a flow chart of a photovoltaic-storage collaborative control optimization method disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] like Figure 1 As shown, the present invention provides a photovoltaic energy storage coordinated control optimization method, comprising the following steps:

[0060] Step S100, collecting historical data of the park, including energy consumption data of the energy output end and the demand end and photovoltaic power generation related data;

[0061] Through the park's energy management system, historical operating data on energy output and demand are obtained, including but not limited to:

[0062] Energy consumption data: load power requirements of different equipment and time periods in the park;

[0063] Photovoltaic power generation related data: historical power generation, irradiance, temperature and other environmental parameters of photovoltaic modules.

[0064] The time range for data collection should cover representative typical seasons and operating conditions to ensure the comprehensiveness and representativeness of the data.

[0065] Step S200: Based on the historical data, a photovoltaic power generation model is constructed, and a CNN-BiGRU model is used to perform day-ahead prediction, thereby generating a predicted day load power data sequence and a photovoltaic power generation power data sequence respectively;

[0066] Using historical photovoltaic power generation data and environmental data, combined with physical models and data-driven models, a photovoltaic power generation model is constructed to reflect the dynamic characteristics of photovoltaic power generation with environmental changes; the prediction model uses a CNN-BiGRU combination model, in which CNN (convolutional neural network) extracts spatiotemporal features and BiGRU (bidirectional gated recurrent unit) captures the long-term and short-term dependencies of time series, and predicts load power and photovoltaic power generation power respectively. Generate the predicted daily load power data sequence {P pre,1 ,P pre,2 ,P pre,3 ,…,P pre,N} and photovoltaic power generation data series {PV pre,1 ,PV pre,2 ,PV pre,3 ,…,PV pre,N}, where N is the total number of time frequency points on the forecast day.

[0067] Step S300, according to the load power data sequence and photovoltaic power generation data sequence of the forecast day, calculate the power consumption and photovoltaic power generation of each time period of the forecast day, and divide the time period into a valley section, a first peak section, a first flat section, a second peak section and a second flat section;

[0068] According to the power price policy of the power grid and the characteristics of power consumption in the park, the forecast day is divided into five periods: Valley 1 (low electricity price period), the first peak period Peak 1 (peak power consumption period), the first flat period Flat 1 (between peak and valley), the second peak period Peak 2 (another peak power consumption period), and the second flat period Flat 2 (similar to the first flat period).

[0069] Calculate the total electricity consumption and photovoltaic power generation in each period of the forecast day:

[0070] Electricity consumption includes: The first peak electricity consumption The first level section power consumption The second peak electricity consumption The second stage power consumption

[0071] Photovoltaic power generation includes: photovoltaic power generation in valley section Photovoltaic power generation in the first peak period Photovoltaic power generation in the first stage Photovoltaic power generation in the second peak period Photovoltaic power generation in the second stage

[0072] Step S400, setting the rated capacity and current remaining power of the energy storage module, and calculating the charge and discharge capacity of the energy storage module in each period of the forecast day based on the state of charge SOC calculation formula of the energy storage;

[0073] Set the rated capacity of the energy storage module to ESS DC , calculate the current remaining power of the energy storage module to be ESS R , the energy storage module can be charged to ESS RC , the self-discharge rate is γ; the energy storage SOC in each period is calculated based on the following formula:

[0074] SOC(t+1)=(1-γ)SOC(t)-E b (t) / E b，max

[0075] Among them, SOC(t+1) represents the state of charge of the energy storage module at time t+1, SOC(t) represents the state of charge of the energy storage module at time t, γ is the energy storage self-discharge rate, E b is the change in energy storage, E b (t) is the energy change at time t. A negative value indicates charging, and a positive value indicates discharging. E b,max is the maximum storable power value of the energy storage; and then determines the charging capacity of the energy storage module in each period (ESS RC ) and discharge capacity.

[0076] Step S500, determining the discharge power requirements of the energy storage module in the first peak section and the second peak section according to the power consumption, photovoltaic power generation and charging and discharging capacity of the energy storage module in each period of the forecast day;

[0077] Taking into account the difference between comprehensive load demand and photovoltaic power generation, the power gap of the energy storage module in each time period is analyzed, especially in the first peak period and the second peak period, to determine the specific discharge power requirement of the energy storage module to meet the load demand of the park and optimize economic benefits.

[0078] Step S600: setting photovoltaic fluctuation smoothing constraint conditions, adjusting the charging and discharging power of the energy storage module according to the photovoltaic power prediction value and the fluctuation allowable deviation, and calculating the energy storage power signal for smoothing photovoltaic fluctuations;

[0079] Step S700: Determine the scheduling relationship between load power consumption, photovoltaic power generation, and energy storage module charging and discharging power based on the power balance relationship of the park;

[0080] Step S800: construct an optimization objective function with the goal of maximizing the comprehensive benefits of the park, and establish a park-level photovoltaic storage collaborative optimization model by combining photovoltaic utilization constraints, energy storage SOC constraints, and power balance constraints;

[0081] Step S900: using an optimization algorithm to solve the park-level photovoltaic energy storage collaborative optimization model to obtain the optimal operation plan for photovoltaic power generation, energy storage modules and loads in each period of the forecast day.

[0082] Adopt intelligent optimization algorithm (such as genetic algorithm or particle swarm optimization algorithm), solve based on objective function and constraint conditions, and output the optimal operation plan for each time period of the forecast day, including the specific scheduling plan of photovoltaic power generation, energy storage charging and discharging power and load power consumption.

[0083] It is understandable that the core of the coordinated optimization of photovoltaic and energy storage is to achieve intelligent and efficient system operation through advanced prediction and control technologies. By collecting historical data on photovoltaic power generation and load demand in real time and establishing an accurate prediction model, photovoltaic power generation and power load demand can be predicted more accurately. Combining the operating characteristics of the energy storage system and the demand characteristics of the power grid, building a comprehensive optimization model and optimizing the charging and discharging behavior of the system can effectively improve the utilization rate of photovoltaic power generation and maximize the economic benefits of the park.

[0084] In addition, the photovoltaic-storage collaborative optimization technology needs to fully consider a variety of operating constraints, including the state of charge (SOC) limit of energy storage, power balance constraints, photovoltaic utilization constraints, etc., to ensure the safe and stable operation of the system. At the same time, it is also necessary to comprehensively consider the economic life loss of energy storage, and use scientific optimization strategies to extend the service life of the energy storage system and reduce operating costs.

[0085] In this embodiment, the method for constructing a photovoltaic power generation electronic model includes: preprocessing the historical data, eliminating outliers and interpolating missing values, and forming a complete data set after normalization; according to the input and output characteristics of photovoltaic power generation, using irradiance, ambient temperature and wind speed as input variables, and photovoltaic power generation power as output variables; using a regression algorithm to construct a photovoltaic power generation electronic model, training photovoltaic power generation electronic model parameters through historical data, so that the photovoltaic power generation electronic model can predict photovoltaic power generation power based on input variables; verifying the constructed photovoltaic power generation electronic model, using a test data set in the historical data set to evaluate the model accuracy, so that the photovoltaic power generation electronic model can accurately characterize the relationship between photovoltaic power generation power and environmental variables.

[0086] In this embodiment, the photovoltaic fluctuation allowable deviation α is defined, and a fluctuation smoothing model (i.e., the constraint condition for photovoltaic fluctuation smoothing) is constructed:

[0087] PV b (t)+PV pre(t)-PV(t)≤αPV(t)

[0088] Among them, PV b (t) is the power signal of the energy storage system used to smooth out the photovoltaic fluctuations, PV pre (t) represents the dynamic correction value of the photovoltaic predicted power, PV(t) represents the actual photovoltaic power at time t, and α is the allowable deviation rate of photovoltaic power. Adjust the power output of the energy storage module to ensure that the fluctuation of photovoltaic power generation remains within the allowable range.

[0089] It should be noted that PV pre (t) is not a direct representation of the PV predicted power, but rather a PV predicted power under a special condition or an intermediate quantity between the PV power and the predicted value. pre (t) is used to compare with the actual power PV(t) and smooth the signal PV b (t) participates in the calculation together, which indicates that it is an adjustment value of the predicted power in the process of fluctuation smoothing, specifically a dynamic correction value of the photovoltaic predicted power (for example, a corrected predicted value after combining the energy storage response).

[0090] In this embodiment, the comprehensive income of the park includes the income from load electricity consumption, the income from energy storage module discharge and the charging expenditure, which is specifically:

[0091] W1(t)=C1(t)·P1(t)+C2(t)·P bd (t)-C3(t)·P bc (t)

[0092] Among them, C1(t), C2(t), and C3(t) are the user electricity price, energy storage discharge price, and energy storage charging price, respectively. bd (t), P bc (t) are load power, energy storage discharge power and energy storage charging power respectively.

[0093] In this embodiment, the steps of constructing an optimization objective function with the goal of maximizing the comprehensive benefits of the park include:

[0094] The comprehensive income of the park is determined to be composed of load electricity income, energy storage discharge income and energy storage charging expenditure. The expression of the optimization objective function is:

[0095] W total =Σ t [C1(t)·P1(t)+C2(t)·P bd (t)-C3(t)·P bc (t)]

[0096] Among them, W totalis the comprehensive income of the park, C1(t), C2(t), and C3(t) are the user electricity price, energy storage discharge price, and energy storage charging price respectively; P1(t), P bd (t), P bc (t) are load power, energy storage discharge power and energy storage charging power respectively;

[0097] Considering the economic life loss of the energy storage module, the economic loss formula of the energy storage module is supplemented by correcting the loss of charging and discharging:

[0098] W b (t) = αC b ·|P bat (t)|·Δt+βC b ·|P bat (t)·Δt

[0099] Among them, W b (t) is the economic loss of the energy storage module, α and β are the energy storage charge and discharge loss coefficients, C b is the unit price of energy storage life loss, P bad (t) is the energy storage operating power, Δt is the time interval;

[0100] The energy storage economic loss W b (t) Introducing the objective function, the optimization objective function is finally expressed as:

[0101] maxW total =Σ t [C1(t)·P1(t)+C2(t)·P bd (t)-C3(t)·P bc (t)-W b (t)].

[0102] The steps to construct an optimization objective function with the goal of maximizing the comprehensive benefits of the park are mainly to maximize the economic benefits of the energy system in the park. First, it is necessary to clarify the composition of the comprehensive benefits of the park, including load electricity benefits, energy storage discharge benefits, and energy storage charging expenses, and quantify them through mathematical expressions in order to establish the objective function. Secondly, it is also necessary to consider the economic life loss of the energy storage module during the charging and discharging process, and correct it through the mathematical formulas of charging loss and discharge loss, and incorporate the energy storage loss into the objective function to reflect the true cost of the operation of the energy storage system. Finally, after comprehensively considering the benefits and losses, the objective function expression is defined as the mathematical form of maximizing the comprehensive benefits of the park, specifically the cumulative sum of benefits and losses in each time period.

[0103] In this embodiment, the steps of establishing a park-level photovoltaic-storage collaborative optimization model include:

[0104] Set the photovoltaic utilization rate constraint to ensure that the utilization rate of photovoltaic power generation reaches the minimum requirement. The constraint conditions are:

[0105]

[0106] Among them, ρ is the photovoltaic utilization rate, PV(t) represents the actual photovoltaic power at time t, and PV pre (t) is the predicted photovoltaic power, ρ0 is the set minimum photovoltaic utilization rate;

[0107] Set the energy storage SOC constraint to ensure that the charge state of the energy storage module operates within a safe range. The constraint conditions are:

[0108] SOC min ≤SOC(t)≤SOC max

[0109] Among them, SOC(t) is the state of charge of the energy storage module at time t; SOC min and SOC max They are the lower and upper limits of the state of charge of the energy storage module respectively;

[0110] Set the park power balance constraint to ensure that the load demand in the park is balanced with the photovoltaic power generation power and energy storage power. The constraint conditions are:

[0111] P1(t)+P ad (t) = P pv (t)+P bd (t)-P bc (t)

[0112] Among them, P1(t), P bd (t), P bc (t) are load power, energy storage discharge power and energy storage charging power respectively, P ad (t) represents the additional load power demand in the park; P pv (t) represents the power output of the photovoltaic power generation system at time t;

[0113] The optimization objective function is combined with the above constraints to construct a park-level photovoltaic-storage collaborative optimization model, and finally a photovoltaic-storage collaborative optimization model is formed with the goal of maximizing the comprehensive benefits of the park.

[0114] It is understandable that the steps of establishing a park-level photovoltaic-storage collaborative optimization model are to comprehensively optimize the coordinated dispatch of photovoltaic power generation and energy storage systems while meeting the safety and stability of park operation. First, it is necessary to set constraints on photovoltaic utilization to ensure that photovoltaic power generation can be utilized as much as possible, and quantify the utilization rate by the ratio of actual photovoltaic power generation to predicted power to ensure that it is not lower than the minimum requirement. Secondly, it is necessary to constrain the state of charge (SOC) of the energy storage module to ensure that the energy storage system operates within a safe range and avoid damage to the equipment due to overcharging or over-discharging. Thirdly, power balance constraints are set to ensure the dynamic balance of energy supply and demand in the park through the balance relationship between load power, photovoltaic power generation power and energy storage charging and discharging power. Finally, the above constraints are combined with the objective function, and the maximum benefit and system safety are comprehensively considered. Through mathematical modeling and optimization algorithms, a complete park-level photovoltaic-storage collaborative optimization model is constructed to provide a decision-making basis for the efficient operation of the energy system in the park.

[0115] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in the present application, or a combination thereof.

[0116] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The electronic device includes a memory and a processor; wherein the memory is used to store a readable program, and the readable program is loaded and executed by the processor to implement the method as described above.

[0117] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0118] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0119] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0120] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0121] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk. It should be noted that, in this article, the term "includes", "includes" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "includes one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0122] One or more embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A photovoltaic-storage coordinated control optimization method, characterized in that: The steps include: Collect historical data of the park, including energy consumption data on the energy output and demand sides and data related to photovoltaic power generation; Based on the historical data, a photovoltaic power generation model is constructed, and a CNN-BiGRU model is used for day-ahead prediction, generating a predicted daily load power data sequence and a photovoltaic power generation power data sequence respectively; According to the forecasted daily load power data sequence and photovoltaic power generation data sequence, the power consumption and photovoltaic power generation in each period of the forecasted day are calculated, and the time period is divided into the valley period, the first peak period, the first flat period, the second peak period and the second flat period; Set the rated capacity and current remaining power of the energy storage module, and calculate the charging and discharging capacity of the energy storage module at each time period of the forecast day based on the energy storage state of charge SOC calculation formula; Determine the discharge power requirements of the energy storage module in the first peak section and the second peak section based on the power consumption, photovoltaic power generation and charging and discharging capacity of the energy storage module in each period of the forecast day; Set the photovoltaic fluctuation smoothing constraint conditions, adjust the charging and discharging power of the energy storage module according to the photovoltaic power prediction value and the fluctuation allowable deviation, and calculate the energy storage power signal to smooth the photovoltaic fluctuation; Based on the power balance relationship of the park, determine the scheduling relationship between load power consumption, photovoltaic power generation power and energy storage module charging and discharging power; An optimization objective function with the goal of maximizing the comprehensive benefits of the park is constructed, and a park-level photovoltaic-storage collaborative optimization model is established by combining photovoltaic utilization constraints, energy storage SOC constraints, and power balance constraints. The optimization algorithm is used to solve the park-level photovoltaic energy storage collaborative optimization model to obtain the optimal operation plan for photovoltaic power generation, energy storage modules and loads in each period of the forecast day.

2. The photovoltaic-storage coordinated control optimization method according to claim 1, characterized in that: Methods for constructing photovoltaic electronic models include: Preprocess the historical data, remove outliers and interpolate missing values, and form a complete data set after normalization; According to the input and output characteristics of photovoltaic power generation, irradiance, ambient temperature and wind speed are used as input variables, and photovoltaic power generation power is used as output variable; A photovoltaic power generation model is constructed using a regression algorithm, and the photovoltaic power generation model parameters are trained through historical data, so that the photovoltaic power generation model can predict photovoltaic power generation power based on input variables; Verify the constructed photovoltaic power generation sub-model and use the test data set in the historical data set to evaluate the model accuracy so that the photovoltaic power generation sub-model can accurately characterize the relationship between photovoltaic power generation power and environmental variables.

3. The photovoltaic-storage coordinated control optimization method according to claim 1, characterized in that: According to the load power data sequence and photovoltaic power generation data sequence of the forecast day, the method for calculating the power consumption and photovoltaic power generation in each period of the forecast day includes: The load power data series and photovoltaic power generation data series of the forecast day are divided into five time periods in chronological order, namely the valley period, the first peak period, the first flat period, the second peak period and the second flat period; According to the load power data sequence, the power consumption of each period of the forecast day is calculated, which are the valley power consumption, the first peak power consumption, the first flat power consumption, the second peak power consumption and the second flat power consumption; According to the photovoltaic power generation data sequence, the photovoltaic power generation in each period of the forecast day is calculated, namely the photovoltaic power generation in the valley section, the photovoltaic power generation in the first peak section, the photovoltaic power generation in the first flat section, the photovoltaic power generation in the second peak section and the photovoltaic power generation in the second flat section.

4. The photovoltaic-storage coordinated control optimization method according to claim 1, characterized in that: The calculation formula of the state of charge SOC of the energy storage module is: SOC(t+1)=(1-γ)SOC(t)-E b (tea b，max Among them, SOC(t+1) represents the state of charge of the energy storage module at time t+1, SOC(t) represents the state of charge of the energy storage module at time t, γ is the energy storage self-discharge rate, E b is the change in energy storage, E b (t) is the energy change at time t. A negative value indicates charging, and a positive value indicates discharging. E b,max The maximum storable amount of energy.

5. The photovoltaic-storage coordinated control optimization method according to claim 1, characterized in that: The constraints for PV fluctuation smoothing are: PV b (t)+PV pre (t)-PV(t)≤αPV(t) Among them, PV b (t) is the power signal of the energy storage system used to smooth out the photovoltaic fluctuations, PV pre (t) represents the dynamic correction value of the photovoltaic predicted power, PV(t) represents the actual photovoltaic power at time t, and α is the allowable deviation rate of photovoltaic power.

6. The photovoltaic-storage coordinated control optimization method according to claim 1, characterized in that: The comprehensive income of the park includes load electricity income, energy storage module discharge income and charging expenses, specifically: W1(t)=C1(t)·P1(t)+C2(t)·P bd (t)-C3(t)·P bc (t) Among them, C1(t), C2(t), and C3(t) are the user electricity price, energy storage discharge price, and energy storage charging price, respectively. bd (t), P bc (t) are load power, energy storage discharge power and energy storage charging power respectively.

7. The photovoltaic-storage coordinated control optimization method according to claim 1, characterized in that: The steps to construct an optimization objective function with the goal of maximizing the comprehensive benefits of the park include: The comprehensive income of the park is determined to be composed of load electricity income, energy storage discharge income and energy storage charging expenditure. The expression of the optimization objective function is: W total =∑ t [C1(t)·P1(t)+C2(t)·P bd (t)-C3(t)·P bc (t)] Among them, W total is the comprehensive income of the park, C1(t), C2(t), and C3(t) are the user electricity price, energy storage discharge price, and energy storage charging price respectively; P1(t), P bd (t), P bc (t) are load power, energy storage discharge power and energy storage charging power respectively; Considering the economic life loss of the energy storage module, the economic loss formula of the energy storage module is supplemented by correcting the loss of charging and discharging: W b (t)=αC b ·|P bat (t)|·Δt+βC b ·|P bat (t)|·Δt Among them, W b (t) is the economic loss of the energy storage module, α and β are the energy storage charge and discharge loss coefficients, C b is the unit price of energy storage life loss, P bad (t) is the energy storage operating power, Δt is the time interval; The energy storage economic loss W b (t) Introducing the objective function, the optimization objective function is finally expressed as: maxW total =∑ t [C1(t)·P1(t)+C2(t)·P bd (t)-C3(t)·P bc (t)-W b (t)]。 8. The photovoltaic-storage coordinated control optimization method according to claim 7, characterized in that: The steps of establishing a park-level photovoltaic-storage collaborative optimization model include: Set the photovoltaic utilization rate constraint to ensure that the utilization rate of photovoltaic power generation reaches the minimum requirement. The constraint conditions are: Among them, ρ is the photovoltaic utilization rate, PV(t) represents the actual photovoltaic power at time t, and PV pre (t) is the predicted photovoltaic power, ρ0 is the set minimum photovoltaic utilization rate; Set the energy storage SOC constraint to ensure that the charge state of the energy storage module operates within a safe range. The constraint conditions are: SOC min ≤SOC(t)≤SOC max Among them, SOC(t) is the state of charge of the energy storage module at time t; SOC min and SOC max They are the lower and upper limits of the state of charge of the energy storage module respectively; Set the park power balance constraint to ensure that the load demand in the park is balanced with the photovoltaic power generation power and energy storage power. The constraint conditions are: P1(t)+P ad (t)=P pv (t)+P bd (t)-P bc (t) Among them, P1(t), P bd (t), P bc (t) are load power, energy storage discharge power and energy storage charging power respectively, P ad (t) represents the additional load power demand in the park; P pv (t) represents the power output of the photovoltaic power generation system at time t; The optimization objective function is combined with the above constraints to construct a park-level photovoltaic-storage collaborative optimization model, and ultimately a photovoltaic-storage collaborative optimization model is formed with the goal of maximizing the comprehensive benefits of the park.

9. An electronic device, comprising a memory and a processor, characterized in that: The memory is used to store a program that supports the processor to execute any of the photovoltaic-storage collaborative control optimization methods described in claims 1-8, and the processor is configured to execute the program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of any one of the photovoltaic energy storage coordinated control optimization methods described in claims 1-8 are executed.

Images