Photovoltaic and energy storage combined configuration auxiliary decision method and device, equipment and medium

Abstract

The present disclosure provides a photovoltaic and energy storage combined configuration auxiliary decision method and device, equipment and medium, relating to the technical field of photovoltaic installation and maintenance. The method comprises: establishing a per-hour power generation power model of a plurality of photovoltaic support type photovoltaic power generation devices, combining a dynamic electricity price sequence generated by a long short-term memory network, and calculating a price weighted unit capacity performance function; taking the installed capacity of each photovoltaic support type photovoltaic power generation device and the energy storage capacity as the joint optimization variables, constructing a ternary coupled optimization model and solving a candidate configuration solution set; combining multi-dimensional economic indicators for weighted sorting and visual display, and outputting the configuration recommendation scheme of each photovoltaic support type photovoltaic power generation device and energy storage. The present scheme can realize efficient matching and scientific decision of photovoltaic support and energy storage configuration scheme in a dynamic market environment.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of photovoltaic installation and maintenance, in particular to a photovoltaic and energy storage combined configuration auxiliary decision method and device, equipment and medium. BACKGROUND

[0002] In a new energy power generation system, photovoltaic power generation technology is widely used due to its renewability and cleanliness. With the advancement of the power marketization process, more and more photovoltaic projects directly participate in the spot trading of the power grid, and the electricity price shows significant dynamic fluctuation characteristics. The design and configuration of traditional photovoltaic power stations are mostly based on the annual average yield of a single power generation curve as a reference, which is difficult to fully adapt to the differences in electricity prices at different times, and is prone to mismatch between power generation peaks and electricity price troughs, resulting in suboptimal power generation revenue.

[0003] In related technologies, the power generation prediction of different types of photovoltaic supports mainly relies on the annual average irradiation model, and lacks fine modeling of hourly power generation. Although some schemes attempt to combine historical irradiation and component performance parameters to form a power generation curve, there is a lack of complete calculation methods that can intuitively reflect the impact of support form on hourly power generation differences. At the same time, electrochemical energy storage has been gradually applied to photovoltaic power stations to balance the load and improve power dispatching flexibility. However, related energy storage configurations are often based on fixed capacity or empirical judgment, making it difficult to consider the timing changes in electricity prices and power generation fluctuations, resulting in low energy storage return on investment and unstable overall economic benefits of the system.

[0004] In addition, related photovoltaic project economic analysis methods are limited, mostly based on static revenue accounting or single technical parameter comparison, making it difficult to comprehensively demonstrate the differentiated performance of different support forms and energy storage capacity schemes in a dynamic market environment. Moreover, the project development and investment decision-making process often relies on manual judgment, lacking effective data support and scheme comparison, which is significantly limited in a dynamic electricity price and diversified scenario environment. SUMMARY

[0005] The purpose of the embodiments of the present disclosure is to provide a photovoltaic and energy storage combined configuration auxiliary decision method and device, equipment and medium, thereby enabling efficient matching and scientific decision-making of photovoltaic support and energy storage configuration schemes in a dynamic market environment.

[0006] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0007] According to a first aspect of the embodiments of the present disclosure, a photovoltaic and energy storage combined configuration auxiliary decision method is provided, comprising:

[0008] acquire historical meteorological data, power grid spot price data and project basic parameters of a target site, establish a unit capacity hourly power generation model of a fixed tilt support, a vertical installation support and a flat single-axis tracking support type photovoltaic power generation device respectively, and generate a corresponding annual unit capacity power generation prediction curve of each photovoltaic support type photovoltaic power generation device;

[0009] based on a pre-trained long short-term memory network prediction model, perform time series analysis on historical electricity price data, regional electricity load and meteorological factors to generate a dynamic electricity price time series of a future period;

[0010] couple the annual unit capacity power generation prediction curve and the dynamic electricity price time series hourly, and determine the electricity price weighted unit capacity performance function corresponding to each photovoltaic support type photovoltaic power generation device;

[0011] based on the electricity price weighted unit capacity performance function, taking the installed capacity of the fixed tilt support, vertical installation support and flat single-axis tracking support type photovoltaic power generation device and the capacity of the electrochemical energy storage system as joint optimization variables, and taking the maximization of the internal rate of return as the core target, a ternary coupling optimization model of photovoltaic, energy storage and electricity price is constructed, and a candidate configuration solution set is solved;

[0012] perform economic index calculation and visual display on the candidate configuration solution set, and generate a weighted score ranking result combined with user preference setting parameters;

[0013] output a recommended scheme of the joint configuration of each photovoltaic support type photovoltaic power generation device and energy storage according to the weighted score ranking result.

[0014] In some example embodiments of the present disclosure, based on the foregoing scheme, the generation of the annual unit capacity power generation prediction curve corresponding to each photovoltaic support type photovoltaic power generation device comprises:

[0015] acquire hourly incident irradiance and ambient temperature data of the target site;

[0016] based on the hourly incident irradiance and ambient temperature, calculate the component photoelectric conversion efficiency corresponding to the fixed tilt support, the vertical installation support and the flat single-axis tracking support type photovoltaic power generation device respectively;

[0017] determine the hourly power generation according to the component photoelectric conversion efficiency, temperature correction factor, dust shielding factor and inverter efficiency;

[0018] normalize the hourly power generation by unit capacity to form a unit capacity hourly power generation model of the fixed tilt support, the vertical installation support and the flat single-axis tracking support type photovoltaic power generation device;

[0019] The unit capacity hourly power generation model is expanded on the whole year time sequence to obtain a whole year unit capacity power generation prediction curve corresponding to each photovoltaic support type photovoltaic power generation device.

[0020] In some example embodiments of the present disclosure, based on the foregoing scheme, the construction of the photovoltaic, energy storage and electricity price ternary coupling optimization model comprises:

[0021] An energy storage energy dynamic equation is established, the energy storage energy dynamic equation is used to describe the charging power, discharging power and state of charge of the electrochemical energy storage system at each time period, and the charging and discharging efficiency and charging and discharging mutual exclusion constraint are introduced into the energy storage energy dynamic equation to form an energy storage submodel;

[0022] The whole year unit capacity power generation prediction curve and the electricity price weighted unit capacity efficiency function are combined with the energy storage submodel to construct a ternary coupling optimization model.

[0023] In some example embodiments of the present disclosure, based on the foregoing scheme, the solving of the candidate configuration solution set comprises:

[0024] The installed capacity of the fixed tilt support, the vertical installation support, the flat single-axis tracking support type photovoltaic power generation device and the capacity of the electrochemical energy storage system are input into the ternary coupling optimization model;

[0025] Based on the ternary coupling optimization model, a non-dominated sorting genetic algorithm is used to perform a multi-objective evolutionary search;

[0026] Internal rate of return iterative calculation is performed in the multi-objective evolutionary search process, and the internal rate of return is calculated for each set of joint optimization variables;

[0027] The internal rate of return is fed back to the evolutionary search process of the ternary coupling optimization model as a fitness value, a Pareto non-inferior solution set is generated, and the Pareto non-inferior solution set is taken as a candidate configuration solution set.

[0028] In some example embodiments of the present disclosure, based on the foregoing scheme, the generation of the weighted score ranking result in combination with the user preference setting parameters comprises:

[0029] The user set preference weight parameters are obtained, the preference weight parameters include weight coefficients for the internal rate of return, the net present value, the degree of electricity cost and the investment recovery period;

[0030] Each economic indicator of the candidate configuration solution set is weighted and calculated with the preference weight parameters to obtain a comprehensive score value of each solution scheme;

[0031] The solution schemes in the candidate configuration solution set are sorted according to the comprehensive score value to obtain a weighted score ranking result.

[0032] In some example embodiments of the present disclosure, based on the foregoing scheme, the candidate configuration solution set is subjected to economic index calculation, including:

[0033] The internal rate of return and net present value of the project life cycle are calculated based on the installed capacity and energy storage capacity in the candidate configuration solution set;

[0034] According to the internal rate of return, the net present value, the degree of electric cost, and the investment recovery period, a comprehensive economic index matrix is generated, and the comprehensive economic index matrix is taken as the economic index of the candidate configuration solution set.

[0035] In some example embodiments of the present disclosure, based on the foregoing scheme, the candidate configuration solution set is subjected to visual display, including:

[0036] An economic index radar chart, a configuration proportion chart, and an energy storage behavior trajectory chart of the candidate configuration solution set are generated;

[0037] After receiving a user adjustment operation on the installed capacity or energy storage capacity of each photovoltaic support type photovoltaic power generation device, the economic index matrix is recalculated based on the adjusted installed capacity and energy storage capacity;

[0038] The updated economic index matrix is fed back to the economic index radar chart, the configuration proportion chart, and the energy storage behavior trajectory chart in real time to realize dynamic visual updating.

[0039] According to a second aspect of the embodiments of the present disclosure, a photovoltaic and energy storage joint configuration auxiliary decision device is provided, including:

[0040] A power generation prediction curve generation module is configured to obtain historical meteorological data, grid spot price data, and project basic parameters of a target site, establish a unit capacity hourly power generation model of a fixed tilt support, a vertical installation support, and a flat single-axis tracking support type photovoltaic power generation device, respectively, and generate an annual unit capacity power generation prediction curve corresponding to each photovoltaic support type photovoltaic power generation device;

[0041] A future dynamic price generation module is configured to perform time series analysis on historical price data, regional electricity load, and meteorological factors based on a pre-trained long short-term memory network prediction model to generate a dynamic price time series of a future period;

[0042] An efficiency function construction module is configured to couple the annual unit capacity power generation prediction curve and the dynamic price time series hourly by weight to determine a price weighted unit capacity efficiency function corresponding to each photovoltaic support type photovoltaic power generation device;

[0043] The coupling optimization model solving module is configured to construct a ternary coupling optimization model of photovoltaic, energy storage and electricity price based on the electricity price weighted unit capacity performance function, taking the installed capacity of the fixed tilt support, vertical installation support and flat single-axis tracking support type photovoltaic power generation device and the capacity of the electrochemical energy storage system as joint optimization variables, and taking the maximization of the internal rate of return as a core target, and to solve a candidate configuration solution set;

[0044] The candidate configuration solution set sorting module is configured to perform economic index calculation and visual display on the candidate configuration solution set, and to generate a weighted score sorting result in combination with a user preference setting parameter;

[0045] The joint configuration auxiliary recommendation module is configured to output a recommended scheme of joint configuration of each photovoltaic support type photovoltaic power generation device and energy storage according to the weighted score sorting result.

[0046] According to a third aspect of the embodiments of the present disclosure, an electronic device is provided, which comprises a processor and a memory having computer readable instructions stored thereon, the computer readable instructions being executed by the processor to implement the photovoltaic and energy storage joint configuration auxiliary decision-making method according to any one of the above aspects.

[0047] According to a fourth aspect of the embodiments of the present disclosure, a computer readable storage medium is provided, having a computer program stored thereon, the computer program being executed by a processor to implement the photovoltaic and energy storage joint configuration auxiliary decision-making method according to any one of the above aspects.

[0048] The technical solutions provided by the embodiments of the present disclosure can have the following beneficial effects:

[0049] The photovoltaic and energy storage combined configuration auxiliary decision method in the example embodiments of the present disclosure, on one hand, realizes the organic combination of power generation time sequence characteristics and price fluctuations through the weighted coupling calculation of the unit capacity hourly power generation power model of different photovoltaic support type photovoltaic power generation devices and the dynamic electricity price time sequence, so that the power generation contribution of each photovoltaic support type photovoltaic power generation device in different electricity price intervals can be finely identified, avoiding the distortion problem of the traditional scheme that only evaluates the economy according to the annual average power generation, and the loss of income caused by the mismatch of power generation peak and low electricity price can be effectively reduced; on the other hand, by including the installed capacity of each photovoltaic support type photovoltaic power generation device and the capacity of the electrochemical energy storage system into the three-element coupling optimization model, an interactive mechanism between power generation time sequence characteristics, price fluctuations and energy storage scheduling is formed, which can make the charging and discharging strategy of energy storage and photovoltaic power generation output match each other, realize flexible response to dynamic electricity price, thereby overcoming the limitations of related technologies that energy storage capacity configuration relies on empirical values and the utilization rate is low, and improving the overall economic return rate of energy storage resources; on the other hand, through multi-dimensional economic index calculation and visual display of the candidate configuration solution set, and combined with user preference weights for comprehensive scoring and sorting, the advantages and disadvantages of different configuration schemes can be presented in an intuitive and data-based manner, breaking through the shortcomings of the traditional scheme that relies on static accounting and artificial experience judgment, and providing flexible and transparent scheme comparison and optimization basis for different investment preferences, ensuring that the decision-making process is more targeted and operable.

[0050] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0051] The drawings incorporated into the specification and constituting a part of the specification show embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure. It is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained from these drawings without creative labor for those skilled in the art.

[0052] Figure 1 The schematic diagram of the photovoltaic and energy storage combined configuration auxiliary decision method according to some embodiments of the present disclosure is schematically shown.

[0053] Figure 2 The flowchart of determining the annual unit capacity power generation prediction curve according to some embodiments of the present disclosure is schematically shown.

[0054] Figure 3 The flowchart of determining the candidate configuration solution set based on the three-element coupling optimization model according to some embodiments of the present disclosure is schematically shown.

[0055] Figure 4A structural schematic diagram of a photovoltaic and energy storage combined configuration auxiliary decision device is shown schematically.

[0056] Figure 5 A structural schematic diagram of a computer system of an electronic device is shown schematically.

[0057] Figure 6 A schematic diagram of a computer readable storage medium is shown schematically.

[0058] In the drawings, the same or similar notations used in different drawings represent the same or similar parts. DETAILED DESCRIPTION

[0059] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The description of the exemplary embodiments is not meant to limit the scope of the present disclosure. Rather, the exemplary embodiments are intended to illustrate the principles of the present disclosure. Other embodiments, which do not depart from the scope of the present disclosure, will be readily disclosed by those skilled in the art based on the description herein.

[0060] Further, the drawings are merely schematic and are not necessarily drawn to scale. The block diagrams in the drawings represent functional entities, which do not necessarily correspond to physically separate entities. That is, the functional entities can be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0061] In the present exemplary embodiment, a photovoltaic and energy storage combined configuration auxiliary decision method is first provided, which can be applied to terminal devices such as mobile phones, computers, and other electronic devices, and can also be applied to servers. The present embodiment is not limited thereto, and the method will be described hereinafter as being executed by a server. Figure 1 A flowchart of a photovoltaic and energy storage combined configuration auxiliary decision method is shown schematically. Figure 1 As shown, the photovoltaic and energy storage combined configuration auxiliary decision method can include the following steps:

[0062] In step S110, historical meteorological data, power grid spot price data, and project basic parameters of a target site are obtained, and a unit capacity hourly power generation model of a fixed tilt support, a vertical installation support, and a flat single-axis tracking support type photovoltaic power generation device is established, and a full-year unit capacity power generation prediction curve corresponding to each photovoltaic support type photovoltaic power generation device is generated.

[0063] Step S120, based on the pre-trained long short-term memory network prediction model, the historical electricity price data, regional electricity load and meteorological factors are analyzed in time sequence to generate a dynamic electricity price time sequence of a future period;

[0064] Step S130, the annual unit capacity generation prediction curve is coupled with the dynamic electricity price time sequence by time weighting to determine a price weighted unit capacity efficiency function corresponding to each photovoltaic support type photovoltaic power generation device;

[0065] Step S140, based on the price weighted unit capacity efficiency function, the installed capacity of the fixed tilt support, vertical installation support and flat single-axis tracking support type photovoltaic power generation device and the capacity of the electrochemical energy storage system are taken as joint optimization variables, a ternary coupling optimization model of photovoltaic, energy storage and electricity price is constructed with the maximization of internal rate of return as the core target, and a candidate configuration solution set is solved;

[0066] Step S150, economic index calculation and visual display are performed on the candidate configuration solution set, and a weighted score ranking result is generated in combination with user preference setting parameters;

[0067] Step S160, a recommended scheme of joint configuration of each photovoltaic support type photovoltaic power generation device and energy storage is output according to the weighted score ranking result.

[0068] According to the photovoltaic and energy storage joint configuration auxiliary decision-making method in the example embodiment, on the one hand, through the weighted coupling calculation of the unit capacity time-of-day power generation model of different photovoltaic support type photovoltaic power generation devices and the dynamic electricity price time sequence, the organic combination of power generation time sequence characteristics and electricity price fluctuation is realized, so that the power generation contribution of each support type photovoltaic power generation device in different electricity price intervals can be finely identified, avoiding the distortion problem of traditional schemes that only evaluate the economy according to the annual average power generation, and the loss of income caused by the mismatch between power generation peak and low electricity price can be effectively reduced; on the other hand, by including the installed capacity of each photovoltaic support type photovoltaic power generation device and the capacity of the electrochemical energy storage system into the ternary coupling optimization model, an interactive mechanism between power generation time sequence characteristics, electricity price fluctuation and energy storage scheduling is formed, which can match the charging and discharging strategy of energy storage with photovoltaic power generation output, realize flexible response to dynamic electricity price, and overcome the limitations of related technologies that the energy storage capacity configuration depends on empirical values and the utilization rate is low, thereby improving the overall economic return rate of energy storage resources; on the other hand, through multi-dimensional economic index calculation and visual display of the candidate configuration solution set, and comprehensive scoring and ranking in combination with user preference weights, the advantages and disadvantages of different configuration schemes can be presented in an intuitive and data-based manner, breaking through the shortcomings of traditional schemes that rely on static accounting and artificial experience judgment, and providing flexible and transparent scheme comparison and optimization basis for different investment preferences, so as to ensure that the decision-making process is more targeted and operable.

[0069] In the following, the photovoltaic and energy storage combined configuration auxiliary decision-making method in the present example embodiment will be further described.

[0070] In step S110, the historical meteorological data of the target site, the spot market electricity price data of the power grid and the project basic parameters are obtained, and the hourly power generation power model of the unit capacity of the fixed tilt support, the vertical installation support and the flat single-axis tracking support type photovoltaic power generation device is established respectively, and the annual unit capacity power generation prediction curve corresponding to each support type photovoltaic power generation device is generated.

[0071] In an example embodiment of the present disclosure, the target site refers to the specific geographical location where the photovoltaic power station is planned to be built or has been built, and the meteorological conditions of which directly determine the actual power generation capacity of the photovoltaic module.

[0072] The historical meteorological data can include but is not limited to hourly total solar radiation, direct radiation, scattered radiation, ambient temperature, sunshine duration, atmospheric quality, wind speed and humidity, etc. By collecting these data from long-term monitoring stations or authoritative meteorological databases, high-precision environmental inputs can be provided for subsequent power generation prediction models. The spot market electricity price data of the power grid refers to the hourly price curve formed in the power spot market transaction, which is usually released by the power dispatch center or the trading platform, and its time resolution can reach the hourly level. The project basic parameters can include the rated power of the photovoltaic module, the component efficiency, the number of components, the type of inverter and its efficiency curve, the installation angle and the azimuth angle, etc. Engineering information is used to accurately simulate the power generation characteristics of the photovoltaic system.

[0073] The fixed tilt support type photovoltaic power generation device refers to the photovoltaic power generation device with fixed and unchanged tilt angle of the photovoltaic module, which has the advantages of simple structure and convenient maintenance. The vertical installation support type photovoltaic power generation device refers to the photovoltaic power generation device with photovoltaic modules installed in a vertical state, which is suitable for specific geographical conditions or double-sided component gain utilization. The flat single-axis tracking support type photovoltaic power generation device refers to the photovoltaic power generation device with photovoltaic modules tracking the sun path within a certain range around a horizontal or near-horizontal axis, thereby improving the daily power generation.

[0074] Through the historical meteorological data of the target site, the spot market electricity price data of the power grid and the project basic parameters, the hourly power generation power model of the unit capacity of the three types of photovoltaic support type photovoltaic power generation device is established, that is, the power generation power in different time periods is calculated based on 1 kilowatt rated power. The modeling process can use photovoltaic array simulation software (such as PVsyst) or self-built mathematical model, and comprehensively consider the influencing factors such as the photoelectric conversion efficiency of the component, the temperature correction coefficient, the dust shielding factor, the reflection factor and the inverter conversion loss.

[0075] Generating the annual unit capacity power generation prediction curve refers to expanding the hourly power generation power model on the time sequence of 8760 hours in a year to obtain a hourly power generation capacity prediction curve covering the changes of four seasons. Alternatively, the annual unit capacity power generation prediction curve can be generated based on a solar radiation inversion method of satellite remote sensing data, a power generation power fitting method based on an artificial intelligence model, etc., which is not specially limited in the example embodiment.

[0076] In step S120, based on the pre-trained long short-term memory network prediction model, the historical electricity price data, the regional electricity load and the meteorological factors are analyzed in time sequence to generate a dynamic electricity price time sequence in a future period.

[0077] In an example embodiment of the present disclosure, the long short-term memory network (LSTM) is a special recurrent neural network structure, and its core advantage is that it can capture the long-term dependence relationship in the time sequence, and is suitable for the prediction of nonlinear fluctuation sequences such as electricity prices. The pre-trained long short-term memory network prediction model refers to using existing large-scale historical electricity price and load data to train the LSTM model offline to optimize the weights and parameters of the model, so that it can accurately capture the time sequence mode of the electricity price. In the specific offline training implementation, a sliding window input sequence of a certain length (such as 72 hours of electricity price and load data in the past) can be selected, and a 24-hour electricity price prediction sequence in the future can be output; the mean square error (MSE) is used as the loss function, and the network weight is adjusted through the back propagation algorithm. Alternatively, a gated recurrent unit (GRU), a time sequence prediction model based on an attention mechanism, or a hybrid ARIMA-LSTM model can be used to train the prediction model.

[0078] The historical electricity price data is the basis for model training, and reflects the price fluctuation trend of the electricity market in different time periods. The regional electricity load refers to the amount of electricity demand in a certain region in a specific time period, which can help to predict the change of supply and demand relationship of electricity price by combining with the historical electricity price data. Meteorological factors such as temperature, wind speed, and light intensity also affect the power supply at the generation end of the electricity market, thereby indirectly affecting the electricity price fluctuation. Generating a dynamic electricity price time sequence in a future period refers to the future hourly electricity price prediction result output by the model, which usually has an hourly minimum time resolution and can cover 24 hours, 48 hours or even longer periods in the future.

[0079] In step S130, the annual unit capacity power generation prediction curve and the dynamic electricity price time sequence are coupled in time weighting to determine the electricity price weighted unit capacity efficiency function corresponding to each type of photovoltaic support photovoltaic power generation device.

[0080] In an example embodiment of the present disclosure, the annual unit capacity power generation prediction curve reflects the power generation of each photovoltaic support type photovoltaic power generation device under the conditions of each hour of the year, and the dynamic electricity price time series reflects the price signal of the future hourly electricity market. Hourly weighted coupling means multiplying the power generation value with the corresponding electricity value at each time point, and accumulating or integrating in the range of the whole year, so as to obtain an index comprehensively reflecting the power generation benefit potential. The electricity price weighted unit capacity efficiency function is a quantitative index for characterizing the weighted benefit value that the unit installed capacity can bring under different photovoltaic support type photovoltaic power generation devices. Optionally, a price weight coefficient can be introduced to nonlinearly amplify the peak-valley electricity price, or a seasonal correction factor can be introduced for segmented weighting, which is not specially limited in the present embodiment.

[0081] In step S140, based on the electricity price weighted unit capacity efficiency function, the installed capacity of the fixed tilt support, vertical installation support, and flat single-axis tracking support type photovoltaic power generation device and the capacity of the electrochemical energy storage system are taken as joint optimization variables, the ternary coupling optimization model of photovoltaic, energy storage, and electricity price is constructed with the core target of maximizing the internal rate of return of the project, and the candidate configuration solution set is solved.

[0082] In an example embodiment of the present disclosure, the electricity price weighted unit capacity efficiency function is used as an input index for measuring the power generation configuration benefit potential, for guiding the economic evaluation of the configuration scheme of the multiple photovoltaic support type photovoltaic power generation devices. The joint optimization variables refer to taking the installed capacity of the three photovoltaic support type photovoltaic power generation devices and the capacity of the electrochemical energy storage system as optimization parameters, and there is a complementary relationship between these variables: the time sequence characteristics of photovoltaic power generation output affect the charging and discharging strategy of energy storage, and the capacity of energy storage determines the adjustment ability to electricity price fluctuation. The electrochemical energy storage system can adopt lithium ion battery, sodium-sulfur battery or flow battery, with a capacity ranging from hundreds of kilowatt-hours to hundreds of megawatt-hours.

[0083] The internal rate of return (IRR) is the core economic indicator of the optimization target, which is used to measure the return level of the project investment. When building the ternary coupling optimization model, the photovoltaic power generation curve, the electricity price time series and the energy storage dynamic equation need to be considered comprehensively, so that the power generation power, the electricity price and the energy storage scheduling form a three-dimensional constraint and interaction relationship. For example, the multi-objective optimization problem can be converted into a single-objective iteration solution with weights by using linear programming, nonlinear programming or genetic algorithm, or a multi-objective evolutionary algorithm of Pareto non-inferior solution can be used. Of course, heuristic algorithms, simulated annealing algorithms or particle swarm optimization algorithms can also be used for solving, and the specific way of solving the candidate configuration solution set is not specially limited in the embodiment. The ternary coupling optimization model established can quickly screen out the candidate scheme with the optimal balance between income and cost from a large number of combination schemes, and provide a high-quality solution set for subsequent economic ranking and decision-making.

[0084] In step S150, economic indicator calculation and visual display are performed on the candidate configuration solution set, and a weighted score ranking result is generated by combining user preference setting parameters.

[0085] In an example embodiment of the present disclosure, the candidate configuration solution set refers to a plurality of combinations of photovoltaic support type photovoltaic power generation device installed capacity and energy storage capacity filtered by an optimization algorithm, and each combination represents a feasible configuration scheme.

[0086] The economic indicators can include internal rate of return, net present value (NPV), levelized cost of electricity (LCOE) and investment recovery period, which can comprehensively evaluate the long-term profitability, cost level and fund recovery speed of the scheme. Of course, other economic indicators that can evaluate the long-term profitability, cost level and fund recovery speed of the scheme can also be used, and the example embodiment is not specially limited.

[0087] The calculation process of the economic indicators can be based on a standard cash flow discounting model, and the construction investment, operation cost and power generation income in the project life cycle are analyzed. The visual display can present the complex economic indicator information in an intuitive graph by generating an economic indicator radar chart, a configuration proportion chart and an energy storage scheduling curve, so as to facilitate comparison of the advantages and disadvantages of different schemes.

[0088] The user preference setting parameter refers to the weight that the user gives to different economic indicators according to the investment strategy of the user, such as being biased towards high return, low cost or short period recovery. By weighting and calculating these weights with the economic indicators of the candidate configuration solution set, a comprehensive score value can be generated, and the schemes can be sorted according to the score result. Alternatively, a machine learning model can also be used to automatically model the user preference or dynamically adjust the weight through an interactive interface.

[0089] In step S160, a recommended scheme of the photovoltaic power generation device combined with energy storage of each photovoltaic support type is output according to the weighted score ranking result.

[0090] In an example embodiment of the present disclosure, the recommended scheme is the preferred configuration selected based on the ranking result, which includes the installed capacity proportion of each photovoltaic support type photovoltaic power generation device, the energy storage capacity and the expected economic indicator performance. The output of the recommended scheme can be provided in the form of a text report, a visual interface or a data file, etc., for the user to directly apply to project planning and investment evaluation.

[0091] By weighting and coupling calculation of the hourly power generation power model of the unit capacity of different photovoltaic support type photovoltaic power generation devices and the dynamic electricity price time series, the organic combination of power generation timing characteristics and electricity price fluctuations is realized, so that the power generation contribution of each support form in different electricity price intervals can be finely identified, avoiding the distortion problem of traditional schemes that only evaluate the economy according to the annual average power generation, which can effectively reduce the loss of income caused by the mismatch between power generation peak and low electricity price; by including the installed capacity of each photovoltaic support type photovoltaic power generation device and the capacity of the electrochemical energy storage system into the ternary coupling optimization model, an interactive mechanism between power generation timing characteristics, electricity price fluctuations and energy storage scheduling is formed, which can make the charging and discharging strategy of the energy storage match the photovoltaic power generation output, realize flexible response to dynamic electricity price, thereby overcoming the limitations of related technologies that the energy storage capacity configuration relies on empirical values and the utilization rate is low, and improving the overall economic return rate of energy storage resources; through multi-dimensional economic indicator calculation and visual display of the candidate configuration solution set, and combined with user preference weight for comprehensive scoring and sorting, the advantages and disadvantages of different configuration schemes can be presented in an intuitive and data-based manner, breaking through the shortcomings of traditional schemes that rely on static accounting and manual experience, and providing flexible and transparent scheme comparison and optimization basis for different investment preferences, ensuring that the decision-making process is more targeted and operable.

[0092] The contents in steps S110 to S160 will be described in detail below.

[0093] In an example embodiment of the present disclosure, the generation of the annual unit capacity power generation prediction curve corresponding to each photovoltaic support type photovoltaic power generation device can be realized by the steps in Figure 2 , and as shown in Figure 2 , specifically can include:

[0094] Step S210, collecting the hourly incident irradiance and ambient temperature data of the target site; Step S220, calculating the corresponding component photoelectric conversion efficiency of the fixed tilt support, the vertical installation support and the flat single-axis tracking support type photovoltaic power generation device based on the hourly incident irradiance and ambient temperature; Step S230, determining the hourly power generation according to the component photoelectric conversion efficiency, the temperature correction factor, the dust shielding factor and the inverter efficiency; Step S240, normalizing the hourly power generation per unit capacity to form the unit capacity hourly power generation model of the fixed tilt support, the vertical installation support and the flat single-axis tracking support type photovoltaic power generation device; Step S250, expanding the unit capacity hourly power generation model in the whole year time sequence to obtain the corresponding annual unit capacity power generation prediction curve of each photovoltaic support type photovoltaic power generation device.

[0095] The hourly incident irradiance refers to the solar radiation energy perpendicular to the ground in unit time, and its unit is usually watt per square meter (W / m²). The light receiving condition of the photovoltaic component at different time points can be refined through the acquisition of hourly data. The hourly incident irradiance can be monitored in real time by a pyranometer or a photoelectric sensor installed at the target site, or can be extracted by using the historical observation data or satellite inversion data provided by the meteorological department, which is not specially limited in the embodiment.

[0096] The ambient temperature data can include the hourly change value of air temperature, which is a key parameter affecting the temperature and photoelectric conversion efficiency of the photovoltaic component. The ambient temperature data can be measured by a weather station, or the data can be remotely transmitted through an automatic weather collection system, which is not specially limited in the embodiment. In order to ensure the data accuracy, multi-point sampling, outlier rejection and data interpolation and other preprocessing methods can be used. Alternatively, the meteorological reanalysis data generated by a numerical weather prediction (NWP) model can be used as the input of the hourly incident irradiance and ambient temperature.

[0097] The component photoelectric conversion efficiency refers to the proportion of the incident solar energy converted into electric energy by the photovoltaic component under specific working conditions, which is affected by factors such as irradiance intensity, component temperature, spectral distribution and incident angle. The installation mode of different photovoltaic supports directly determines the incident angle of the photovoltaic component and sunlight, thereby affecting the effective component of the incident irradiation. The photoelectric conversion efficiency of the component of the fixed inclination support can be calculated by the irradiation component under the fixed incident angle and the correction factor of the component efficiency under the standard test conditions. The vertical installation support can consider the light loss under different solar elevation angles throughout the year, and the efficiency is generally low but can be combined with the double-sided component to improve the overall power generation. The flat single-axis tracking support can automatically adjust the component orientation through single-axis, so that it is perpendicular to the incident direction of the sunlight as much as possible, thereby improving the hourly irradiation utilization rate.

[0098] The calculation of the component photoelectric conversion efficiency can be based on the component efficiency model, such as the photovoltaic component temperature model (NOCT model) and the spectral correction factor, of course, the component photoelectric conversion efficiency can also be determined based on the three-dimensional light simulation software or by regressing and fitting the efficiency parameters using the measured power data, and the example embodiments are not limited thereto.

[0099] The temperature correction factor is used to describe the linear or nonlinear attenuation law of the component efficiency with temperature, which can be determined by the temperature coefficient provided by the component manufacturer. The dust shielding factor is used to reflect the decrease of light transmittance caused by dust accumulation or pollution, and its value can be corrected by long-term monitoring or empirical formula. The inverter efficiency refers to the energy conversion ratio when converting direct current into alternating current, which is usually between 95% and 99%, and can be calculated according to the rated parameters of the inverter corresponding to each photovoltaic support type photovoltaic power generation device.

[0100] The hourly power generation power normalization refers to dividing the actual power generation power by the rated installed capacity, so as to make a unified comparison under different capacity scales. The unit capacity hourly power generation power model takes 1 kilowatt or 1 megawatt of standard installed capacity as the benchmark, and can comprehensively reflect the power generation capacity of the unit capacity photovoltaic system in different time periods under various meteorological conditions and installation modes. In specific implementation, the calculated hourly power generation power sequence can be normalized according to each photovoltaic support type photovoltaic power generation device, thereby obtaining the hourly power curve of the photovoltaic support type photovoltaic power generation device. The establishment of the unit capacity hourly power generation power model needs to consider factors such as the photovoltaic component attenuation rate, inverter partial load effect and line loss, so as to ensure the accuracy of the results. In some optional embodiments, the unit capacity output power curve can be directly generated by the simulation software, or the model can be calibrated by the measured data.

[0101] For example, the unit capacity hourly power generation power model can be represented by the following relationship:

[0102] ; wherein, The unit capacity hourly power generation of the first The unit capacity hourly power generation of the first The unit capacity hourly power generation of the first The unit capacity hourly power generation of the first The unit capacity hourly power generation of the first The unit capacity hourly power generation of the first The reference efficiency of the PV module under standard test conditions can be represented as The temperature correction factor of the PV module can be represented as The unit capacity hourly power generation of the first The unit capacity hourly power generation of the first The dust shading factor can be represented as The comprehensive system loss factor can be represented as, which can include inverter efficiency, cable loss, etc.

[0103] The annual time sequence development refers to the accumulation and display of the unit capacity hourly power generation model on the time sequence of one year, covering the comprehensive influence of four seasons, day and night, and different weather conditions on power generation capacity. In specific implementation, based on 8760 hours (i.e. 365 days x 24 hours) of hourly meteorological data, the unit capacity power generation model can be gradually calculated and an annual unit capacity power generation prediction curve can be generated. The annual unit capacity power generation prediction curve can clearly describe the time sequence characteristics of annual power generation, including peak period, valley period and seasonal differences. In order to further improve the prediction accuracy, weather prediction data or typical meteorological year data can be introduced in the time sequence development process to reflect the trend of future operating environment. Of course, a photovoltaic power generation simulation platform (such as SAM or PVlib) can also be used to directly generate an annual hourly power generation curve.

[0104] By collecting hourly incident irradiance and ambient temperature data, and combining with component photoelectric conversion efficiency, temperature correction factor, dust shading factor and inverter efficiency, the unit capacity hourly power generation model of different photovoltaic support type photovoltaic power generation devices can be established and the annual prediction curve can be generated, which can finely model the influence of support installation mode on power generation time sequence, avoid the deviation caused by traditional annual average irradiance estimation, and thus provide reliable basic data for accurate income comparison of different support schemes.

[0105] In an example embodiment of the present disclosure, a three-element coupling optimization model of photovoltaic, energy storage and electricity price can be constructed by the following steps, which can specifically include:

[0106] A storage energy dynamic equation can be established, the storage energy dynamic equation is used for describing charging power, discharging power and state of charge of the electrochemical storage system in each period, and charging and discharging efficiency and charging and discharging mutual exclusion constraints are introduced into the storage energy dynamic equation to form a storage submodel; the annual unit capacity generation prediction curve and the electricity price weighted unit capacity efficiency function are combined with the storage submodel to construct a ternary coupling optimization model.

[0107] The storage energy dynamic equation is a mathematical model used to represent the change of the energy state of the storage system over time, and the core variables include charging power, discharging power and state of charge (SOC). The state of charge refers to the proportion of the current storage capacity of the storage system to its rated capacity, usually expressed in percentage. The charging and discharging efficiency is the loss coefficient of the energy conversion of the storage system, usually between 90% and 98%, depending on the type of storage technology. To prevent simultaneous charging and discharging of the storage, mutual exclusion constraints need to be added to the equation, i.e. when the charging power is greater than 0, the discharging power is 0, and vice versa. This mutual exclusion constraint can control the switching of charging and discharging through binary logic variables. In specific implementation, optimization methods based on linear programming or mixed integer programming can be used to solve the equation together with the photovoltaic power generation prediction results and the electricity price signal. Of course, more detailed energy dynamic equations can also be established using equivalent circuit models (ECM), or the equation parameters can be updated through data-driven charging and discharging efficiency prediction models.

[0108] The ternary coupling optimization model refers to the simultaneous integration of photovoltaic power generation time series characteristics, electricity price dynamic signals and storage energy scheduling capabilities into a unified optimization framework. The annual unit capacity generation prediction curve provides hourly power generation power input for the model, which is used to determine the distribution of power available for storage charging and direct grid connection. The electricity price weighted unit capacity efficiency function can be used as an index function to evaluate the benefits, providing an economic reference for each power generation power allocation and storage scheduling strategy. The storage submodel limits the upper and lower bounds of energy flow through state of charge, charging and discharging power constraints and efficiency parameters, so that the optimization process can consider the actual availability of storage at different time periods. For example, the non-dominated sorting genetic algorithm II (NSGA-II), particle swarm optimization algorithm or other multi-objective evolutionary algorithms can be used to iteratively solve the ternary coupling model as the objective function. Of course, linear programming (LP) or mixed integer linear programming (MILP) based mathematical modeling methods can also be used for optimization, which is not specially limited in the present embodiment.

[0109] For example, the dynamic electricity price time series for future periods can be determined using the following relationship:

[0110] ;in, It can represent the predicted dynamic electricity price time series for the next t+h hours. It can represent the input sequence, which may include characteristic quantities such as historical electricity price data, regional electricity load, and meteorological factors. It can represent the mapping function of the Long Short-Term Memory network prediction model.

[0111] The electricity price-weighted unit capacity efficiency function can be determined using the following relationship:

[0112] ;in, This can represent the price-weighted unit capacity efficiency value of a photovoltaic power generation device of the i-th type of photovoltaic support structure. It can represent the first Photovoltaic power generation devices of various types of photovoltaic brackets in the first Hourly power generation per unit capacity It can represent the first The hourly predicted electricity price is calculated from the time series of dynamic electricity prices. It can represent the total number of hours throughout the year, usually 8760.

[0113] The energy storage dynamic equation, i.e., the energy storage sub-model, can be expressed by the following relationship:

[0114] ;

[0115] in, This can represent the electrochemical energy storage system in the first... State of charge at time t, This can represent the electrochemical energy storage system in the first... State of charge at time t, It can represent the first Charging power at any time It can represent the first Discharge power at any given time This can represent charging efficiency, typically ranging from 0.9 to 0.98. This can represent discharge efficiency, typically ranging from 0.9 to 0.98. It can represent the time step. This can represent a charge-discharge mutual exclusion constraint, meaning that the energy storage system cannot charge and discharge simultaneously within the same time period.

[0116] For example, the ternary coupled optimization model can be represented by the following objective function:

[0117]

[0118] wherein, may represent the internal rate of return of the project, may represent the power generation of the photovoltaic system at the time, may represent the charging power at the time, may represent the discharging power at the time, may represent the predicted electricity price at the hour, may represent the operation and maintenance cost at the hour, may represent the additional investment cost of the energy storage configuration, may represent the initial project investment, may represent the total number of hours in a year, usually 8760, may represent the rated capacity of the electrochemical energy storage system, may represent the maximum charging power, may represent the maximum discharging power, may represent the net cash flow of the year, may represent the project life cycle, that is, the total number of years from the completion of the project to the end of operation, which can usually be taken as 20-25 years, related to the service life of photovoltaic components, the service life of energy storage systems and the economic feasibility evaluation period.

[0119] By establishing an energy dynamic equation of energy storage, introducing charging and discharging efficiency and mutual exclusion constraints, and combining them with the annual unit capacity generation prediction curve and the electricity price weighted performance function to construct a ternary coupling optimization model, the photovoltaic power generation characteristics, the dynamic change of electricity price and the energy storage scheduling ability can be considered at the same time, the dynamic matching between power generation and energy storage is realized, the energy loss caused by disordered charging and discharging of the energy storage system is avoided, and thus a reasonable scheduling model is provided for subsequent comprehensive benefit optimization.

[0120] In an example embodiment of the present disclosure, the candidate configuration solution set can be solved by the steps in Figure 3 , as shown in Figure 3 , which can specifically include:

[0121] Step S310, input the installed capacity of the fixed tilt support, the vertical installation support, the flat single-axis tracking support type photovoltaic power generation device and the capacity of the electrochemical energy storage system into the ternary coupling optimization model;

[0122] Step S320, performing multi-objective evolutionary search based on the ternary coupling optimization model using a non-dominated sorting genetic algorithm;

[0123] Step S330, performing internal rate of return iterative calculation in the multi-objective evolutionary search process, and calculating the internal rate of return for each set of joint optimization variables;

[0124] Step S340, feeding back the internal rate of return as a fitness value to the evolutionary search process of the ternary coupling optimization model, generating a Pareto non-inferior solution set, and taking the Pareto non-inferior solution set as a candidate configuration solution set.

[0125] The installed capacity refers to the total power of the photovoltaic modules configured in the project by each photovoltaic support type photovoltaic power generation device, usually in kilowatts or megawatts. Different installed capacities directly determine the peak power and the amplitude of the overall output curve, and the installation method of each support affects the power generation timing characteristics. The electrochemical energy storage system capacity refers to the rated energy storage capacity of the energy storage device, usually expressed in kilowatt-hours (kWh) or megawatt-hours (MWh), which directly affects the scheduling depth and peak clipping and valley filling capacity of the energy storage system. The process of inputting the above parameters into the ternary coupling optimization model refers to parameterizing the combination of installed capacity of each photovoltaic support type photovoltaic power generation device and energy storage capacity as a variable vector as the design space when solving the model. For example, the installed capacity and energy storage capacity can be inputted into the optimization algorithm module in matrix or vector format through data structuring, such as using Python, Matlab or C++ program interface, of course, the project parameters can also be automatically called through a database or a cloud configuration platform, and the input values can be dynamically updated, which is not specially limited in the embodiment.

[0126] The non-dominated sorting genetic algorithm NSGA-II is an improved multi-objective evolutionary optimization algorithm, which can optimize multiple conflicting objective functions simultaneously, such as considering economic benefits and resource utilization rate in the ternary coupling optimization model. The principle of the non-dominated sorting genetic algorithm is to ensure the diversity and convergence of the solution by performing fast non-dominated sorting, congestion distance calculation and elite strategy reservation on the population. For example, the initial population containing installed capacity and energy storage capacity can be encoded, each individual representing a configuration scheme; then new solutions are generated by genetic operations such as crossover and mutation, and the fitness value is evaluated according to the price weighted unit capacity efficiency function, internal rate of return and other economic indicators; finally, the Pareto frontier solution is selected by non-dominated sorting and enters the next generation iteration.

[0127] In the evolutionary search process, the photovoltaic and energy storage combination corresponding to each candidate solution needs to be calculated by the cash flow calculation method, based on the power generation, dynamic electricity price and investment cost data in the project life cycle, to iteratively solve its internal rate of return. Specific implementation can be calculated by numerical methods such as bisection method and Newton iteration method, or automatically completed with the help of financial analysis module. Alternative implementation methods include using the rate of return matrix evaluation method of net present value and internal rate of return joint calculation or risk and return analysis based on Monte Carlo simulation.

[0128] The Pareto non-inferior solution set refers to a set of solutions in which there is no solution that is superior to all other solutions in all optimization objectives. The solutions in this set represent the optimal solutions under different trade-offs between objectives. The internal rate of return is fed back to the evolutionary search process as the fitness value, guiding the selection, crossover and mutation operations of the algorithm, thus promoting the population to gradually converge to the Pareto frontier. In specific implementation, after each iteration, non-inferior solutions are selected through fitness ranking and crowding degree sorting, and the final solution set is output when the iteration termination condition is met. Alternatively, hierarchical clustering can be used to simplify the Pareto solution set, or a multi-objective optimization method based on distribution estimation can be used to improve the coverage of the solution set, without being limited to the present example embodiment.

[0129] By inputting the installed capacity of each photovoltaic support type photovoltaic power generation device and the electrochemical energy storage capacity into the three-way coupling optimization model, and performing multi-objective evolutionary search based on the non-dominated sorting genetic algorithm, multiple configuration combinations can be optimized in a larger parameter space. By combining the iterative calculation of the internal rate of return and feeding back the economic indicators as fitness, a Pareto non-inferior solution set with balanced benefits and costs can be effectively formed, providing more abundant and high-quality configuration solutions for multi-solution selection.

[0130] In an example embodiment of the present disclosure, the weighted score ranking result generated in combination with the user preference setting parameters can be achieved by the following steps, which can specifically include:

[0131] The user-set preference weight parameters can be obtained, including weight coefficients for the internal rate of return, net present value, degree of electricity cost and investment recovery period; the economic indicators of the candidate configuration solution set are weighted and calculated with the preference weight parameters to obtain the comprehensive score value of each solution; and the solution schemes in the candidate configuration solution set are sorted according to the comprehensive score value to obtain the weighted score ranking result.

[0132] The user-set preference weight parameter refers to the priority proportion assigned by the user to different economic indicators in the actual project evaluation, and is used to reflect the income target and risk preference of the investor. The internal rate of return measures the capital return rate of the project, the net present value reflects the net income in the whole life cycle of the project, the degree of electricity cost is used to evaluate the comprehensive cost of unit electricity, and the investment recovery period is used to reflect the speed of capital recovery. In specific implementation, the user can input the weight value of each indicator through the visual interface, and the system can ensure that the weight and is 1 or meets the pre-set allocation proportion through input verification. Of course, the weight distribution can also be automatically recommended according to the user's historical preference data by using a machine learning algorithm, or the weight parameter can be quickly configured for different users through a default investment strategy template, and the present embodiment does not specially limit this.

[0133] The candidate configuration solution set is a plurality of feasible configuration schemes of photovoltaic support type photovoltaic power generation devices and energy storage capacities generated by optimizing the model, and each scheme corresponds to a set of economic indicator data. The weighted calculation refers to multiplying each economic indicator standardization value by the user-set weight coefficient one by one, and then summing to obtain the comprehensive score value of the scheme. The indicators of different dimensions can be converted into dimensionless comparable values through range normalization or Z-score standardization method. Specific implementation can realize matrix operation through programming language, such as Python NumPy or Pandas library. Alternatively, a multi-criteria decision making (MCDM) method such as analytic hierarchy process (AHP) or grey relational analysis (GRA) can also be used to complete the weighted score calculation.

[0134] The sorting is the arrangement of the comprehensive score values of all candidate configuration schemes from high to low, so as to identify the optimal or top several priority schemes. In specific implementation, quicksort or mergesort algorithm can be used, and the score value and the corresponding scheme configuration parameter are retained in the sorting result for subsequent display and decision-making. The score result can also be graded, for example, the schemes are divided into different levels such as excellent, good, medium, etc. according to the score interval, so as to facilitate the user to select according to the investment strategy. The sorting process can also be combined with the user-set constraint conditions such as investment budget upper limit and maximum recovery period for secondary filtering, and the present embodiment does not specially limit this.

[0135] By setting the preference weight parameters of the user, the multi-dimensional economic indicators of the candidate configuration solution set are weighted and calculated, and the complex economic data is structured into comprehensive score values that can be directly compared. This process can realize personalized configuration recommendations for different investment preferences, avoid the one-sidedness of scheme selection caused by a single economic indicator, and thus improve the pertinence and accuracy of decision-making.

[0136] In an example embodiment of the present disclosure, the economic indicator calculation of the candidate configuration solution set can be realized by the following steps, which can specifically include:

[0137] The internal rate of return and net present value of the project life cycle can be calculated based on the installed capacity and energy storage capacity in the candidate configuration solution set; the comprehensive economic indicator matrix is generated according to the internal rate of return, the net present value, and the cost per kilowatt-hour and the investment recovery period, and the comprehensive economic indicator matrix is taken as the economic indicator of the candidate configuration solution set.

[0138] The project life cycle refers to the whole cycle from construction, operation to retirement, usually 20 to 25 years, and the internal rate of return is an indicator for measuring the profitability of the project by solving the discount rate when the net present value of the project is zero. The net present value is the total value at the current point of time based on the cash flow of each year in the whole life cycle of the project, which is converted according to the preset discount rate, and is used to evaluate the overall investment return of the project. In the calculation process, the hourly power generation of the photovoltaic support type photovoltaic power generation device, the electricity price income, the energy storage charging and discharging income, the equipment depreciation, the operation and maintenance cost and the investment cost can be considered comprehensively.

[0139] The cost per kilowatt-hour refers to the ratio of the total investment and operating cost to the total power generation of the photovoltaic power station in the whole life cycle, which is used to evaluate the balanced level of power generation cost. The investment recovery period refers to the time required for the cumulative net cash flow of the project to be zero, which is usually used to measure the speed of capital recovery. The comprehensive economic indicator matrix organizes the internal rate of return, the net present value, the cost per kilowatt-hour and the investment recovery period in the form of column vector or matrix, and corresponds the economic indicators of each candidate configuration scheme one by one, thereby forming a multi-dimensional data set. In specific implementation, the unitization and standardization of each indicator can be performed to eliminate the dimensional difference, and then the matrix operation tool (such as Pandas of Python, Excel or Matlab) is used to construct the indicator matrix. Alternatively, a weighted score matrix can be introduced, the economic indicators are weighted according to the user preference weight to directly generate a weighted matrix, or the economic indicators are hierarchically aggregated through a multi-criteria decision analysis method.

[0140] For example, the internal rate of return can be calculated by the following relationship:

[0141] ;

[0142] wherein, NPV can represent the net present value of the project, NPV can represent the net present value of the project, NPV can represent the internal rate of return of the project, NPV can represent the initial project investment.

[0143] NPV can be calculated by the following relationship:

[0144] ;

[0145] wherein, r can represent the discount rate.

[0146] LCOE can be determined by the following relationship:

[0147] ;

[0148] wherein, LCOE can represent the levelized cost of electricity, IC can represent the investment cost amortization in the nth year, OM can represent the operation and maintenance cost, G can represent the power generation in the nth year. By calculating the economic indicators such as internal rate of return, net present value, levelized cost of electricity and investment recovery period based on the installed capacity and energy storage capacity of the candidate configuration solution set, and generating a comprehensive economic indicator matrix, the long-term economic performance of the configuration scheme can be evaluated in multiple dimensions. The matrix provides a unified data platform for subsequent weighted scoring and visual display, making the economic performance comparison of the configuration scheme more comprehensive and intuitive.

[0149] In an example embodiment of the present disclosure, the candidate configuration solution set can be visualized by the following steps, which can specifically include:

[0150] The economic indicator radar chart, configuration proportion chart and energy storage behavior trajectory chart of the candidate configuration solution set can be generated; after receiving the user's adjustment operation on the installed capacity or energy storage capacity of each photovoltaic support type photovoltaic power generation device, the economic indicator matrix is recalculated based on the adjusted installed capacity and energy storage capacity; the updated economic indicator matrix is fed back to the economic indicator radar chart, configuration proportion chart and energy storage behavior trajectory chart in real time, realizing dynamic visual update.

[0151] The economic indicator radar chart, configuration proportion chart and energy storage behavior trajectory chart of the candidate configuration solution set can be generated; after receiving the user's adjustment operation on the installed capacity or energy storage capacity of each photovoltaic support type photovoltaic power generation device, the economic indicator matrix is recalculated based on the adjusted installed capacity and energy storage capacity; the updated economic indicator matrix is fed back to the economic indicator radar chart, configuration proportion chart and energy storage behavior trajectory chart in real time, realizing dynamic visual update.

[0152] ​​The economic indicator radar chart is a multi-dimensional visualization method that maps internal rate of return, net present value, cost per kilowatt-hour, and investment payback period to isometric axes, and forms a polygon by connecting the scoring points of different indicators, to intuitively show the advantages and disadvantages of each candidate scheme in multiple dimensions. The configuration proportion chart is used to reflect the installed capacity proportion of the photovoltaic power generation device of each type of photovoltaic support and the energy storage capacity allocation, and can use column chart, stacked chart or ring chart to present the structure characteristics. The energy storage behavior trajectory chart is used to show the charging and discharging power curve and state of charge (SOC) change of the energy storage system in different time periods, which can intuitively reflect the timing characteristics of energy storage scheduling. In the specific implementation process, the above-mentioned graphics can be generated by using Python's Matplotlib, Plotly or commercial visualization tools; alternative implementation methods include using a Web-based interactive graphical interface to dynamically render graphics through a front-end framework such as ECharts or D3.js.

[0153] The user's adjustment operation is usually input through a human-computer interaction interface, including dragging a slider, inputting a numerical value, or selecting a preset template, to modify the installed proportion of the photovoltaic power generation device of the candidate scheme or the energy storage capacity. The system calls the original power generation prediction model and energy storage dynamic equation according to the user input adjustment parameters, recalculates the hourly power generation and energy storage scheduling strategy, and updates the economic indicators such as internal rate of return, net present value, cost per kilowatt-hour, and investment payback period based on the adjusted results. In specific implementation, the background calculation module can quickly recalculate part of the model data related to the adjustment parameters to improve response speed. Alternative implementation methods include using a caching mechanism to store key calculation results in advance, or using a machine learning-based regression model to quickly predict the trend of economic indicators. Through this step, the data displayed in the visualization can be synchronized with the user's dynamic needs, ensuring the real-time and accuracy of the analysis results.

[0154] Real-time feedback refers to automatically triggering the refresh of the front-end visualization component when the economic indicator matrix is updated, mapping the latest economic results to the radar chart, proportion chart, and trajectory chart, to ensure that the displayed content is consistent with the background calculation results. Dynamic visualization update can be achieved through data binding and event-driven mechanisms, such as using a two-way data binding framework (such as Vue.js or React) in the Web front-end to achieve automatic linkage between data update and interface rendering. Alternative implementation methods include API interface calling based on desktop visualization applications, or establishing a real-time data channel between the front-end and back-end through WebSocket.

[0155] By generating economic indicator radar chart, configuration proportion chart and energy storage behavior trajectory chart, and dynamically updating economic indicator matrix and chart after user adjusts photovoltaic or energy storage parameters, visualization and instant feedback of economic performance of candidate scheme can be realized. This interactive dynamic display enables user to intuitively master the trend of adjusted revenue, thereby improving the efficiency of scheme evaluation and decision-making.

[0156] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired result. In addition or alternatively, some steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps, etc.

[0157] In addition, in the present example embodiment, a photovoltaic and energy storage combined configuration auxiliary decision-making device is also provided. Referring to Figure 4 As shown in the figure, the photovoltaic and energy storage combined configuration auxiliary decision-making device 400 comprises:

[0158] The power generation prediction curve generation module 410 is configured to obtain historical meteorological data of a target site, power grid spot price data and project basis parameters, respectively establish hourly power generation models of unit capacity of photovoltaic power generation devices of fixed tilt support, vertical installation support and flat single-axis tracking support types, and generate annual unit capacity power generation prediction curves corresponding to the photovoltaic power generation devices of each support type;

[0159] The future dynamic price generation module 420 is configured to perform time series analysis on historical price data, regional electricity load and meteorological factors based on a pre-trained long short-term memory network prediction model, and generate a dynamic price time series of a future period;

[0160] The performance function construction module 430 is configured to weight and couple the annual unit capacity power generation prediction curves and the dynamic price time series hourly, and determine price-weighted unit capacity performance functions corresponding to the photovoltaic power generation devices of each support type;

[0161] The coupled optimization model solving module 440 is configured to, based on the price-weighted unit capacity performance functions, take the installed capacity of the photovoltaic power generation devices of the fixed tilt support, vertical installation support and flat single-axis tracking support types and the capacity of the electrochemical energy storage system as joint optimization variables, take maximizing the internal rate of return of the project as the core target, construct a ternary coupled optimization model of photovoltaic, energy storage and price, and solve a candidate configuration solution set;

[0162] The candidate configuration solution set sorting module 450 is configured to perform economic indicator calculation and visual display on the candidate configuration solution set, and generate a weighted score sorting result in combination with user preference setting parameters.

[0163] The joint configuration auxiliary recommendation module 460 is configured to output a recommended scheme of the photovoltaic power generation device of each photovoltaic support type and energy storage joint configuration according to the weighted score ranking result.

[0164] In some example embodiments of the present disclosure, based on the foregoing scheme, the power generation prediction curve generation module 410 is configured to:

[0165] Collect hourly incident irradiance and ambient temperature data of the target site;

[0166] Based on the hourly incident irradiance and ambient temperature, the component photoelectric conversion efficiency corresponding to the fixed tilt support, the vertical installation support, and the flat single-axis tracking support type photovoltaic power generation device is calculated respectively;

[0167] According to each component photoelectric conversion efficiency, a temperature correction factor, a dust shielding factor, and an inverter efficiency, the hourly power generation power is determined;

[0168] The hourly power generation power is normalized by unit capacity to form a unit capacity hourly power generation power model of the fixed tilt support, the vertical installation support, and the flat single-axis tracking support type photovoltaic power generation device;

[0169] The unit capacity hourly power generation power model is expanded in the whole year time sequence to obtain the whole year unit capacity power generation prediction curve corresponding to each photovoltaic support type photovoltaic power generation device.

[0170] In some example embodiments of the present disclosure, based on the foregoing scheme, the coupling optimization model solving module 440 is configured to:

[0171] An energy storage energy dynamic equation is established, which is used to describe the charging power, discharging power, and state of charge of the electrochemical energy storage system at each time period, and the charging and discharging efficiency and the charging and discharging mutual exclusion constraint are introduced into the energy storage energy dynamic equation to form an energy storage sub-model;

[0172] The whole year unit capacity power generation prediction curve and the electricity price weighted unit capacity efficiency function are combined with the energy storage sub-model to construct a ternary coupling optimization model.

[0173] In some example embodiments of the present disclosure, based on the foregoing scheme, the coupling optimization model solving module 440 is configured to:

[0174] The installed capacity of the fixed tilt support, the vertical installation support, the flat single-axis tracking support type photovoltaic power generation device, and the capacity of the electrochemical energy storage system are input into the ternary coupling optimization model;

[0175] Performing multi-objective evolutionary search based on the ternary coupling optimization model by using a non-dominated sorting genetic algorithm;

[0176] Performing internal rate of return iterative calculation in the multi-objective evolutionary search process, and calculating the internal rate of return for each set of joint optimization variables;

[0177] Feeding back the internal rate of return as a fitness value to the evolutionary search process of the ternary coupling optimization model, generating a Pareto non-inferior solution set, and taking the Pareto non-inferior solution set as a candidate configuration solution set.

[0178] In some example embodiments of the present disclosure, based on the foregoing scheme, the candidate configuration solution set sorting module 450 is configured to:

[0179] Obtaining a user-set preference weight parameter, the preference weight parameter including weight coefficients for the internal rate of return, the net present value, the cost per kilowatt-hour, and the investment payback period;

[0180] Performing weighted calculation on each economic indicator of the candidate configuration solution set and the preference weight parameter, to obtain a comprehensive score value of each solution scheme;

[0181] According to the comprehensive score value, sorting the solution schemes in the candidate configuration solution set to obtain a weighted score sorting result.

[0182] In some example embodiments of the present disclosure, based on the foregoing scheme, the candidate configuration solution set sorting module 450 is configured to:

[0183] Calculating the internal rate of return and the net present value of the project life cycle based on each installed capacity and energy storage capacity in the candidate configuration solution set;

[0184] Generating a comprehensive economic indicator matrix according to the internal rate of return, the net present value, the cost per kilowatt-hour, and the investment payback period, and taking the comprehensive economic indicator matrix as the economic indicator of the candidate configuration solution set.

[0185] In some example embodiments of the present disclosure, based on the foregoing scheme, the candidate configuration solution set sorting module 450 is configured to:

[0186] Generating an economic indicator radar chart, a configuration proportion chart, and an energy storage behavior trajectory chart of the candidate configuration solution set;

[0187] After receiving a user adjustment operation on the installed capacity or the energy storage capacity of each photovoltaic support type photovoltaic power generation device, recalculating the economic indicator matrix based on the adjusted installed capacity and energy storage capacity;

[0188] The updated economic index matrix is fed back to the economic index radar chart, the configuration proportion chart and the energy storage behavior trajectory chart in real time to realize dynamic visual updating.

[0189] The specific details of the modules of the photovoltaic and energy storage joint configuration auxiliary decision device described above have been described in detail in the corresponding photovoltaic and energy storage joint configuration auxiliary decision method, and therefore will not be described here.

[0190] It should be noted that although several modules or units of the photovoltaic and energy storage joint configuration auxiliary decision device are mentioned in the foregoing detailed description, such a division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into a plurality of modules or units.

[0191] In addition, in the exemplary embodiments of the present disclosure, an electronic device capable of implementing the above-mentioned photovoltaic and energy storage joint configuration auxiliary decision method is also provided.

[0192] Those skilled in the art can understand that various aspects of the present disclosure can be implemented as a system, a method or a program product. Therefore, various aspects of the present disclosure can be embodied as a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" here.

[0193] The electronic device 500 according to such embodiments of the present disclosure will be described below with reference to Figure 5 The electronic device 500 shown is merely one example and should not be taken as limiting the functionality and use of embodiments of the present disclosure. Figure 5 The electronic device 500 shown is merely one example and should not be taken as limiting the functionality and use of embodiments of the present disclosure.

[0194] As shown in Figure 5 The components of electronic device 500 can include, but are not limited to, at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including storage unit 520 and processing unit 510), a display unit 540.

[0195] The storage unit stores program code that can be executed by the processing unit 510, so that the processing unit 510 performs the steps described in the "Exemplary Method" section of the present specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 510 can execute the steps described in the "Exemplary Method" section of the present specification according to various exemplary embodiments of the present disclosure. Figure 1At step S110 shown in the middle, the historical meteorological data, the power grid spot price data and the project basic parameters of the target site are acquired, the hourly power generation power model of the unit capacity of the fixed tilt support, the vertical installation support and the flat single-axis tracking support type photovoltaic power generation device is respectively established, and the annual unit capacity power generation prediction curve corresponding to each photovoltaic support type photovoltaic power generation device is generated; at step S120, based on the pre-trained long short-term memory network prediction model, the historical price data, the regional electricity load and the meteorological factors are analyzed in time sequence, and the dynamic price time sequence of the future period is generated; at step S130, the annual unit capacity power generation prediction curve and the dynamic price time sequence are weighted and coupled in time, and the price weighted unit capacity performance function corresponding to each photovoltaic support type photovoltaic power generation device is determined; at step S140, based on the price weighted unit capacity performance function, the installed capacity of the fixed tilt support, the vertical installation support and the flat single-axis tracking support type photovoltaic power generation device and the electrochemical energy storage system capacity are taken as joint optimization variables, and the maximization of the internal rate of return of the project is taken as the core target, a ternary coupling optimization model of photovoltaic, energy storage and price is constructed, and a candidate configuration solution set is solved; at step S150, the candidate configuration solution set is calculated and visualized in economic indicators, and a weighted score ranking result is generated in combination with user preference setting parameters; at step S160, the recommended scheme of the joint configuration of each photovoltaic support type photovoltaic power generation device and energy storage is output according to the weighted score ranking result.

[0196] The storage unit 520 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 521 and / or a cache memory unit 522, and can further include a read-only memory (ROM) 523.

[0197] The storage unit 520 can further include program / utility 524 having a set of program modules 525, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof can include implementation of a network environment.

[0198] The bus 530 can represent one or more of several types of bus structures, including a storage unit bus or storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of a variety of bus structures.

[0199] The electronic device 500 can also communicate with one or more external devices 570 such as a keyboard or pointing devices, a Bluetooth device, or a database, etc.; and / or one or more devices that enable a user to interact with the electronic device 500; and / or any devices (e.g., a router, a modem, a server, etc.) that enable the electronic device 500 to communicate with one or more other computing devices. Such communication can occur via an input / output (I / O) interface 550. Still yet, the electronic device 500 can communicate with one or more networks, such as a local area network (LAN), a general wide area network (WAN), and / or the Internet, through a network adapter 560. As depicted, the network adapter 560 communicates with the other components of the electronic device 500 via the bus 530. It should be appreciated that the electronic device 500 can be a part of another device or can be a stand-alone device. In addition, the electronic device 500 can be a personal computer, a server, a tablet computer, a laptop computer, etc. In some embodiments, the electronic device 500 can be a portable multi-media device of the like.

[0200] From the above description of the embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0201] In the example embodiments of the present disclosure, a computer-readable storage medium having a program product stored thereon capable of implementing the above-mentioned method of the present disclosure is also provided. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program codes for causing a terminal device to perform the steps according to various example embodiments of the present disclosure described in the above-mentioned "example method" section of the present specification when the program product is run on the terminal device.

[0202] Reference Figure 6 As shown, the program product 600 for implementing the above-mentioned photovoltaic and energy storage combined configuration auxiliary decision-making method according to the embodiments of the present disclosure is described, which can adopt a portable compact disc read-only memory (CD-ROM) and includes program codes, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited to this, and in the present document, the readable storage medium can be any tangible medium containing or storing a program, which can be used or combined with an instruction execution system, device or apparatus.

[0203] The program product can employ any combination of one or more computer-readable media. The computer-readable media can be a computer-readable storage medium or a computer-readable signal medium. The computer-readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0204] The computer-readable signal medium can include a computer-readable storage medium that is configured to store and deliver a computer-readable program code. The computer-readable program code can be propagated as a computer-readable signal medium.

[0205] The program code embodied on the computer-readable media can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0206] The program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, etc., and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider. The present disclosure can be implemented in a computing system that includes a back-end component, or a middleware component, or a front-end component, or any combination thereof.

[0207] In addition, the above-described flowcharts are merely illustrative of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to limit the present disclosure. It is readily understood that the processes shown in the above-described flowcharts do not indicate or limit the time sequence of the processes. In addition, it is readily understood that the processes can be executed synchronously or asynchronously, for example, in a plurality of modules.

[0208] Those skilled in the art can easily understand, through the above description of the embodiments, that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0209] Other embodiments of the present disclosure will be apparent to those skilled in the art with the accomplishment of the present disclosure as set forth in the specification and practice of the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known or customary practice in the art of the present disclosure not specifically disclosed. The specification and examples are to be regarded as illustrative only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0210] It should be understood that the present disclosure is not limited to the precise structures described above and shown in the drawings, and that various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for photovoltaic and energy storage combined configuration auxiliary decision-making, characterized in that, The method comprises the following steps: acquiring historical meteorological data, power grid spot price data and project basic parameters of a target site, establishing hourly power generation models of unit capacity of photovoltaic power generation devices of fixed tilt support, vertical installation support and flat single-axis tracking support types respectively, and generating annual unit capacity power generation prediction curves of the photovoltaic power generation devices of the three types of supports; based on a pre-trained long short-term memory network prediction model, performing time series analysis on historical electricity price data, regional electricity load and meteorological factors to generate a dynamic electricity price time series of a future period; hourly weighting and coupling the annual unit capacity power generation prediction curves and the dynamic electricity price time series to determine the electricity price weighted unit capacity performance function of the photovoltaic power generation devices of each type of support; based on the electricity price weighted unit capacity performance function, taking the installed capacity of the photovoltaic power generation devices of the fixed tilt support, vertical installation support and flat single-axis tracking support types and the capacity of the electrochemical energy storage system as joint optimization variables, and taking the maximization of internal rate of return as the core target, a ternary coupling optimization model of photovoltaic, energy storage and electricity price is constructed, and a candidate configuration solution set is solved; performing economic index calculation and visual display on the candidate configuration solution set, and generating a weighted score ranking result combined with user preference setting parameters; outputting a recommended scheme of the joint configuration of each type of photovoltaic power generation device and energy storage according to the weighted score ranking result.

2. The method of claim 1, wherein, The method for generating annual unit capacity power generation prediction curves of photovoltaic power generation devices of each type of support comprises the following steps: collecting hourly incident irradiance and ambient temperature data of the target site; based on the hourly incident irradiance and ambient temperature, calculating the component photoelectric conversion efficiency corresponding to the fixed tilt support, the vertical installation support and the flat single-axis tracking support type photovoltaic power generation device respectively; determining hourly power generation according to the component photoelectric conversion efficiency, temperature correction factor, dust shielding factor and inverter efficiency; normalizing the hourly power generation by unit capacity to form the hourly power generation model of unit capacity of the fixed tilt support, the vertical installation support and the flat single-axis tracking support type photovoltaic power generation device; expanding the hourly power generation model of unit capacity in the annual time series to obtain the annual unit capacity power generation prediction curve corresponding to the photovoltaic power generation device of each type of support.

3. The method of claim 1, wherein, The method for constructing a ternary coupling optimization model of photovoltaic, energy storage and electricity price comprises the following steps: establishing a dynamic equation of energy storage, which is used to describe the charging power, discharging power and state of charge of the electrochemical energy storage system at each period, and introducing charging and discharging efficiency and charging and discharging mutual exclusion constraints in the dynamic equation of energy storage to form an energy storage sub-model; combining the annual unit capacity power generation prediction curve, the electricity price weighted unit capacity performance function and the energy storage sub-model to construct a ternary coupling optimization model.

4. The method of claim 1, wherein, The method for solving the candidate configuration solution set comprises the following steps: inputting the installed capacity of the photovoltaic power generation devices of the fixed tilt support, the vertical installation support and the flat single-axis tracking support type and the capacity of the electrochemical energy storage system into the ternary coupling optimization model; Performing multi-objective evolutionary search based on the three-coupling optimization model by using a non-dominated sorting genetic algorithm; During the multi-objective evolutionary search, iteratively calculating the internal rate of return for each set of joint optimization variables; Feeding back the internal rate of return as a fitness value to the evolutionary search process of the three-coupling optimization model to generate a Pareto non-inferior solution set, and taking the Pareto non-inferior solution set as a candidate configuration solution set.

5. The method of claim 1, wherein, The combined user preference setting parameter generates a weighted score ranking result, including: Obtaining a user-set preference weight parameter, the preference weight parameter including weight coefficients for internal rate of return, net present value, cost per kilowatt-hour, and investment recovery period; Weighted calculation of each economic indicator of the candidate configuration solution set and the preference weight parameter to obtain a comprehensive score value of each solution scheme; According to the comprehensive score value, the solution schemes in the candidate configuration solution set are sorted to obtain a weighted score ranking result.

6. The method of claim 1, wherein, The economic indicator calculation of the candidate configuration solution set includes: Based on the installed capacity and energy storage capacity in the candidate configuration solution set, the internal rate of return and net present value of the project life cycle are calculated; According to the internal rate of return, the net present value, the cost per kilowatt-hour, and the investment recovery period, a comprehensive economic indicator matrix is generated, and the comprehensive economic indicator matrix is taken as the economic indicator of the candidate configuration solution set.

7. The method of claim 6, wherein, The visualization display of the candidate configuration solution set includes: Generating economic indicator radar charts, configuration proportion charts, and energy storage behavior trajectory charts of the candidate configuration solution set; After receiving a user adjustment operation on the installed capacity or energy storage capacity of each photovoltaic support type photovoltaic power generation device, the comprehensive economic indicator matrix is recalculated based on the adjusted installed capacity and energy storage capacity; The updated comprehensive economic indicator matrix is fed back to the economic indicator radar chart, the configuration proportion chart, and the energy storage behavior trajectory chart in real time to realize dynamic visualization update.

8. A photovoltaic and energy storage combined configuration auxiliary decision device, characterized in that, It includes: A power generation prediction curve generation module is used to obtain historical meteorological data, grid spot price data, and project base parameters of a target site, establish hourly power generation models of unit capacity for fixed tilt support, vertical installation support, and flat single-axis tracking support type photovoltaic power generation devices, and generate annual unit capacity power generation prediction curves corresponding to each photovoltaic support type photovoltaic power generation device; A future dynamic electricity price generation module is used to perform time series analysis on historical electricity price data, regional electricity load, and meteorological factors based on a pre-trained long short-term memory network prediction model to generate a dynamic electricity price time series for a future period; An efficiency function construction module is used to weight and couple the annual unit capacity power generation prediction curves and the dynamic electricity price time series hourly to determine the price-weighted unit capacity efficiency function corresponding to each photovoltaic support type photovoltaic power generation device; The coupling optimization model solving module is configured to construct a ternary coupling optimization model of photovoltaic, energy storage and electricity price based on the electricity price weighted unit capacity performance function, taking the installed capacity of the fixed tilt support, vertical installation support and flat single-axis tracking support type photovoltaic power generation device and the capacity of the electrochemical energy storage system as joint optimization variables, and maximizing the internal rate of return as the core target, and to solve a candidate configuration solution set; The candidate configuration solution set sorting module is configured to perform economic index calculation and visual display on the candidate configuration solution set, and generate a weighted score ranking result in combination with a user preference setting parameter; The joint configuration auxiliary recommendation module is configured to output a recommended scheme of joint configuration of each photovoltaic support type photovoltaic power generation device and energy storage according to the weighted score ranking result.

9. An electronic device, comprising: Comprise: a processor; and a memory having computer readable instructions stored thereon, the computer readable instructions, when executed by the processor, implement the photovoltaic and energy storage joint configuration auxiliary decision-making method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, a computer program stored thereon, the computer program, when executed by a processor, implements the photovoltaic and energy storage joint configuration auxiliary decision-making method according to any one of claims 1 to 7.

Images