Photovoltaic power station inverter capacity ratio optimization method and system based on multivariable cooperation

Abstract

The invention discloses a photovoltaic power station inverter capacity ratio optimization method and system based on multivariable coordination, and relates to the technical field of inverter capacity ratio optimization, and the method comprises the steps: determining a key variable influencing the capacity ratio of an inverter in a photovoltaic power station; constructing a multivariable collaborative optimization model by taking the full-life-cycle net income maximization of the photovoltaic power station as an objective function; solving the multivariable collaborative optimization model, and outputting an optimal capacity ratio; and the optimal capacity ratio is applied to a simulation model of a photovoltaic power station or an actual pilot power station, and reconstruction optimization processing is executed through comparative analysis verification. According to the method and the device, the technical problems of unreasonable capacity ratio, low inverter operation efficiency and poor scheme adaptability caused by the fact that the influence of multiple key variables is not fully considered when the capacity ratio of the inverter is determined in the prior art are solved, and the technical effects of determining the optimal capacity ratio of the inverter and improving the inverter operation efficiency and the capacity ratio scheme adaptability are achieved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of inverter capacity ratio optimization, and in particular to a photovoltaic power station inverter capacity ratio optimization method and system based on multivariable coordination. BACKGROUND

[0002] In a photovoltaic power station operation system, the inverter capacity ratio is a core parameter determining the power station power generation efficiency, investment cost and operation stability. A reasonable capacity ratio can maximize the use of photovoltaic resources under the premise of ensuring equipment safety, otherwise it may cause problems such as photovoltaic resource waste, inverter overload damage or low power generation efficiency. In the current prior art, the determination of the inverter capacity ratio depends on experience or single variable analysis, and the capacity ratio is set only according to the illumination conditions of the region where the power station is located, ignoring the influence of environmental temperature on the power generation efficiency of the component, the output power decline caused by the long-term decay of the photovoltaic component, the efficiency difference of the inverter under different load rates and the restriction of the investment cost on the overall income, and it is difficult to adapt to complex and variable actual operation scenarios.

[0003] In the prior art, the influence of multiple key variables is not fully considered when determining the inverter capacity ratio, resulting in the technical problems of unreasonable capacity ratio, low inverter operation efficiency and poor scheme adaptability. SUMMARY

[0004] The application provides a photovoltaic power station inverter capacity ratio optimization method and system based on multivariable coordination, which is used to solve the technical problems that the influence of multiple key variables is not fully considered when determining the inverter capacity ratio in the prior art, resulting in unreasonable capacity ratio, low inverter operation efficiency and poor scheme adaptability.

[0005] In view of the above problems, the application provides a photovoltaic power station inverter capacity ratio optimization method and system based on multivariable coordination.

[0006] In a first aspect, the application provides a photovoltaic power station inverter capacity ratio optimization method based on multivariable coordination, which comprises: determining key variables affecting the inverter capacity ratio in the photovoltaic power station, the key variables including illumination intensity, environmental temperature, photovoltaic component decay rate, inverter efficiency curve and investment cost parameter; constructing a multivariable coordinated optimization model with the maximum net income of the photovoltaic power station in the whole life cycle as the objective function and the inverter not being overloaded, the inverter load rate being in the preset efficiency working interval and the capacity ratio being in the preset range as the constraint conditions; solving the multivariable coordinated optimization model by using a particle swarm optimization algorithm, outputting the optimal capacity ratio through particle initialization, fitness calculation, speed and position updating and iteration termination judgment; and applying the optimal capacity ratio to a simulation model or an actual pilot power station of the photovoltaic power station and verifying the execution of the reconstruction optimization process through comparative analysis.

[0007] A second aspect of this application provides a photovoltaic power plant inverter capacity ratio optimization system based on multivariate collaboration, the system comprising: The system comprises the following modules: a key variable determination module, used to identify key variables affecting the inverter capacity ratio in a photovoltaic power plant; a optimization model construction module, used to construct a multi-variable collaborative optimization model with the objective function of maximizing the net revenue of the photovoltaic power plant throughout its entire life cycle, and with constraints including inverter overload, inverter load rate within a preset efficiency operating range, and capacity ratio within a preset range; an optimal capacity ratio output module, used to solve the multi-variable collaborative optimization model using a particle swarm optimization algorithm, and outputting the optimal capacity ratio through particle initialization, fitness calculation, velocity and position updates, and iteration termination judgment; and a reconstruction optimization processing module, used to apply the optimal capacity ratio to a simulation model of the photovoltaic power plant or an actual pilot power plant, and verify the execution of reconstruction optimization processing through comparative analysis.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: Key variables affecting the inverter capacity ratio in photovoltaic (PV) power plants were identified. A multi-variable collaborative optimization model was constructed, with the objective function of maximizing the net revenue of the PV power plant throughout its lifecycle, and constraints including inverter overload, inverter load rate within a preset efficiency operating range, and capacity ratio within a preset range. The multi-variable collaborative optimization model was solved using a particle swarm optimization algorithm. The optimal capacity ratio was output through particle initialization, fitness calculation, velocity and position updates, and iteration termination judgment. This optimal capacity ratio was applied to a simulation model of a PV power plant or an actual pilot power plant, and the reconfiguration optimization process was verified through comparative analysis. This method achieved the technical effect of determining the optimal inverter capacity ratio, improving inverter operating efficiency, and enhancing the adaptability of the capacity ratio scheme. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A schematic diagram of the process for optimizing the capacity ratio of photovoltaic power plant inverters based on multivariate collaboration, provided in an embodiment of this application; Figure 2 This is a schematic diagram of the photovoltaic power plant inverter capacity ratio optimization system structure provided in the embodiments of this application.

[0011] Figure labeling: Key variable determination module 10, optimization model construction module 20, optimal capacity ratio output module 30, reconstruction optimization processing module 40. Detailed Implementation

[0012] This application provides a method and system for optimizing the capacity ratio of photovoltaic power plant inverters based on multivariate collaboration. This method addresses the technical problem in existing technologies where the determination of inverter capacity ratio does not fully consider the influence of multiple key variables, resulting in unreasonable capacity ratios, low inverter operating efficiency, and poor adaptability of the solution.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] Example 1, as Figure 1 As shown, this application provides a method for optimizing the inverter capacity ratio of a photovoltaic power plant based on multivariate synergy, the method comprising: Step S100: Determine the key variables affecting the inverter capacity ratio in the photovoltaic power plant. The key variables include irradiance, ambient temperature, photovoltaic module degradation rate, inverter efficiency curve, and investment cost parameters.

[0015] Specifically, by combining the operating patterns and equipment characteristics of photovoltaic power plants, key variables affecting the capacity ratio are accurately identified, providing comprehensive and realistic input for subsequent model construction. The identified key variables cover five dimensions, and each variable must be supported by actual data: Irradiance requires the selection of average irradiance data for different times of the year in the area where the photovoltaic power plant is located, such as obtaining data from the local meteorological station over the past five years, distinguishing between high, medium, and low irradiance periods. This directly determines the actual output power of the photovoltaic array, thus affecting the matching relationship between the capacity ratio and power generation efficiency; Ambient temperature requires the collection of annual temperature variation data for the area where the power plant is located, including extreme high and low temperature periods, as temperature fluctuations will change the power generation efficiency of photovoltaic modules, indirectly affecting the stability of the inverter's input power; Photovoltaic module degradation rate requires obtaining power degradation data of modules at different service years, such as a 2.5% degradation rate for monocrystalline silicon modules in the first year, and a degradation rate of 0.5% annually thereafter. A 0.7% degradation rate indicates that long-term component degradation will lead to a decrease in output power, necessitating the provision of adaptation margin in the capacity ratio. The inverter efficiency curve should utilize measured efficiency data from the selected inverter to clearly define its efficiency variation under different load rates. For example, the efficiency should be ≥96% at load rates of 40%~80%, with significant efficiency drops below or above this range, providing a basis for matching the capacity ratio to the inverter's high-efficiency operating range. Investment cost parameters require calculation of inverter purchase cost, installation cost, and photovoltaic module cost. For instance, if the module unit price is 1.2 yuan / W, the inverter unit price is 0.3 yuan / W, and the installation cost is 10% of the total equipment investment, the cost parameters are needed to balance revenue and investment, as the capacity ratio is directly related to the number of equipment purchased and the total investment scale.

[0016] Step S200: With the goal of maximizing the net income of the photovoltaic power plant throughout its entire life cycle, and with the constraints of inverter not being overloaded, inverter load rate being within the preset efficiency operating range, and capacity ratio being within the preset range, a multi-variable collaborative optimization model is constructed.

[0017] Specifically, the objective function is set as the net revenue of the photovoltaic power plant throughout its entire life cycle, calculated as total power generation revenue minus total investment cost minus operation and maintenance cost. Total power generation revenue needs to be calculated based on actual power generation under key variables such as irradiance, ambient temperature, and photovoltaic module degradation rate, along with the feed-in tariff. Total investment cost is determined based on parameters such as capacity ratio, inverter purchase cost, photovoltaic module cost, and installation cost (e.g., installation cost is 10% of the total equipment investment). Operation and maintenance cost is set with reference to power plant operation and maintenance experience data and the impact of capacity ratio on operation and maintenance difficulty. Simultaneously, three constraints are clearly defined. To ensure the feasibility of the solution: Inverter overload constraint requires that the actual output power of the photovoltaic array be ≤ the rated input power of the inverter × (1 + 0.1), with an overload factor set to 0.1 to avoid equipment damage; Inverter load rate constraint limits the load rate to a preset efficiency operating range of [40%, 80%] to ensure the inverter operates in a high-efficiency range of ≥96% for extended periods; Capacity ratio constraint, based on industry standards and actual application scenarios, presets the capacity ratio value range to [1.0, 1.8]. Ultimately, this constructs a multi-variable collaborative optimization model that balances objectives and constraints.

[0018] Step S300: Solve the multivariate collaborative optimization model using the particle swarm optimization algorithm, and output the optimal capacity ratio through particle initialization, fitness calculation, velocity and position update, and iteration termination judgment.

[0019] Specifically, the process begins with particle initialization. Each particle's position is defined as a set of key variables, such as combinations of light intensity and ambient temperature, along with their corresponding capacity ratios. Referring to the constraints of the key variable value range and the capacity ratio [1.0, 1.8], the particle swarm's position and velocity are randomly initialized. The number of particles is set to 50-100 to balance optimization efficiency and accuracy. Next, the fitness value is calculated. The key variable value combination for each particle is substituted into the objective function that maximizes the net benefit over the entire lifecycle. The result of the objective function calculation is used as the particle fitness value; a higher value indicates a better capacity ratio scheme for that particle. Then, velocity and position are updated. Based on the individual optimal fitness value (i.e., the historical best solution for a single particle) and the swarm optimal fitness value (i.e., the current best solution for all particles), the particle velocity and position are adjusted according to the particle swarm algorithm update formula. During the update process, it is crucial to ensure that the particle position, i.e., the capacity ratio, variable values, and velocity, remain within a reasonable range to avoid exceeding the constraint boundaries. Finally, an iteration termination judgment is performed, setting the maximum number of iterations to 80-120 and the accuracy threshold to 1×10⁻⁶. -4 ~1×10 -3 When the number of iterations reaches the maximum value or the difference between the optimal fitness values ​​of two adjacent iterations is less than the accuracy threshold, the iteration stops. At this time, the capacity ratio corresponding to the optimal particle in the population is the optimal capacity ratio that satisfies the objective function and the constraints.

[0020] Step S400: Apply the optimal capacity ratio to the simulation model of the photovoltaic power station or the actual pilot power station, and verify the execution of the reconstruction optimization process through comparative analysis.

[0021] Specifically, through simulation and actual testing, the rationality of the optimization results is verified, and refactoring and optimization are performed as needed to ensure that the capacity ratio matches the actual operating requirements of the photovoltaic power station. First, the optimal capacity ratio obtained by the solution is applied to the photovoltaic power station simulation model. The actual environmental data such as sunlight and temperature in the area where the power station is located, as well as equipment parameters such as component power and inverter rated power, are input. The power generation and inverter load rate at different times of the year are simulated to verify whether it is stable in the high-efficiency range of [40%, 80%] and the net income throughout the entire life cycle. The performance difference is compared with the traditional experience capacity ratio, such as K=1.2, such as the increase in power generation and the growth of income. At the same time, some areas of the power station, such as a 10MW pilot area, can be selected as actual test scenarios. Inverters and photovoltaic modules are configured according to the optimal capacity ratio, and actual operation tests are carried out for several months to half a year to collect and analyze data such as actual power generation, equipment failure rate, and operation and maintenance costs. If the simulation or actual test results deviate significantly from the optimal effect calculated by the model, such as the actual power generation increase not meeting expectations or the inverter load rate frequently exceeding the high-efficiency range, then trace the cause of the deviation. For example, if the data accuracy of key variables is insufficient or the model constraint conditions are set unreasonably, adjust the selection range of key variables, model parameters, or particle swarm optimization algorithm iteration parameters, and then re-execute the multivariate collaborative optimization model construction and solution process until the optimal capacity ratio that highly matches the actual operation and has both economic efficiency and stability is obtained, providing a reliable basis for the configuration of equipment throughout the power plant.

[0022] In one possible implementation, step S100 further includes: The light intensity refers to the average light intensity data of the area where the photovoltaic power station is located at different times of the year. The ambient temperature refers to the annual temperature variation data of the area where the photovoltaic power station is located. The photovoltaic module degradation rate refers to the power degradation data of the module at different service years. The inverter efficiency curve refers to the efficiency data of the corresponding inverter at different load rates. The investment cost parameters include the inverter purchase cost, installation cost, and photovoltaic module cost.

[0023] Specifically, the solar irradiance needs to be based on the area where the photovoltaic power station is located, obtaining historical data for the past 5 years or more through local meteorological stations, photovoltaic monitoring platforms, etc., and statistically analyzing it to obtain the average solar irradiance data for different periods of the year, such as monthly data for January-February, March-May, etc., or seasonal data. Similarly, the ambient temperature needs to collect annual temperature variation data for the area where the power station is located, covering extreme high and low temperatures as well as temperature values ​​during periods of normal fluctuation. Temperature affects the power temperature coefficient of photovoltaic modules, thus altering the module's power generation efficiency and indirectly affecting the stability of the inverter's input power; therefore, it needs to be accurately incorporated into the variable system. The photovoltaic module degradation rate needs to be determined by combining the module type and the manufacturer's technical data, obtaining power degradation data for different service years throughout its entire life cycle, such as the first-year degradation of monocrystalline silicon modules. The initial capacity is approximately 2.5%, with an annual degradation of 0.7%. This data reflects the long-term changes in the component's output capacity, preventing insufficient adaptability of the capacity ratio in the later stages due to neglecting degradation. The inverter efficiency curve needs to be plotted based on the measured data of the selected inverter, clearly defining its efficiency value at different load rates. For example, centralized inverters can achieve an efficiency of over 96% in the load rate range of 40% to 80%, with a significant decrease in efficiency below 40% or above 80%. This curve is a key reference to ensure that the capacity ratio allows the inverter to operate in the high-efficiency range for a long time. Investment cost parameters need to be comprehensively considered in terms of equipment procurement and construction, covering inverter purchase costs, photovoltaic module costs, and installation costs. These parameters are directly related to the impact of capacity ratio adjustments on the total investment of the power plant and are important variables for balancing power generation revenue and cost input.

[0024] In one possible implementation, step S200 further includes: The objective function F(K) = total power generation revenue - total investment cost - operation and maintenance cost, where the total power generation revenue is calculated based on the power generation and grid connection price under different key variables, the total investment cost is determined based on the capacity ratio and cost parameters of related equipment, and the operation and maintenance cost is determined based on the operation and maintenance experience data of photovoltaic power plants and the impact of the capacity ratio.

[0025] Specifically, in the multivariate collaborative optimization model, the objective function F(K) is guided by maximizing the net income of the photovoltaic power plant throughout its entire life cycle. Through the calculation logic of total power generation revenue - total investment cost - operation and maintenance cost, the comprehensive impact of the capacity ratio K on the economic benefits of the power plant is quantified. The calculation of each component is closely related to key variables and actual scenarios. The total power generation revenue needs to be dynamically calculated by considering key variables such as irradiance, ambient temperature, and photovoltaic module degradation rate. First, the actual power generation during each period of the entire life cycle is calculated based on the average irradiance at different times, the module power factor at the corresponding temperature, and the module degradation rate at different service years. Then, the total power generation revenue is obtained by multiplying the power plant's grid-connected electricity price. The total investment cost is directly determined by the capacity ratio K and equipment cost parameters. If the total rated power of the photovoltaic array is fixed and the total rated power of the inverter is 100 / K (MW), the total investment cost corresponding to different K values ​​can be calculated by combining the unit price of photovoltaic modules, the unit price of inverters, and installation costs. The operation and maintenance cost needs to be adjusted by referring to industry operation and maintenance experience data and considering the impact of the capacity ratio. For example, an excessively high capacity ratio may increase the frequency of inverter operation and maintenance, while an excessively low capacity ratio may lead to increased maintenance costs due to idle modules. It is usually calculated by multiplying the total investment cost by the entire life cycle, and finally, the objective function value is obtained by the difference between the three factors, so as to accurately measure the economic benefits of different capacity ratio schemes.

[0026] In one possible implementation, step S300 further includes: Step S310: Initialize the particle swarm, representing the position of each particle as a combination of values ​​of a set of key variables and the corresponding capacity ratio. Based on the value range of the key variables and the constraint range of the capacity ratio, randomly initialize the position and velocity of the particle swarm.

[0027] Step S320: Substitute the combination of key variable values ​​corresponding to the particles into the objective function to calculate the fitness value of each particle.

[0028] Step S330: Update the particle's velocity and position based on the individual optimal fitness value and the population optimal fitness value.

[0029] Step S340: Output the optimal capacity ratio based on the iterative update results.

[0030] Specifically, the first step is to define the position rules of the particles, mapping the position of each particle to a complete set of capacity ratio optimization parameters. This includes the specific values ​​of five key variables: light intensity, ambient temperature, photovoltaic module degradation rate, inverter efficiency curve, and investment cost parameters, as well as the inverter capacity ratio K corresponding to this variable combination. Then, random initialization is performed based on the actual constraints of each parameter: the values ​​of key variables must conform to the environmental characteristics of the power plant's location, such as the light and temperature range in the northwest region and the equipment technical parameters, such as the inverter efficiency curve and module degradation standards. The capacity ratio K must be limited to a preset reasonable range of [1.0, 1.8]. Simultaneously, considering the optimization accuracy and efficiency requirements, the particle swarm size is set to 50-100 particles, and an initial velocity is randomly assigned to each particle. The velocity value must be controlled within a reasonable range to prevent the particle position from exceeding the constraint boundary during subsequent searches. Finally, a particle swarm initialization that combines randomness and constraint is completed, ensuring that subsequent iterative searches can proceed within an effective range.

[0031] The key variable combinations for each particle are extracted, encompassing the average solar irradiance of the photovoltaic power plant area during a specific time period, the ambient temperature during that time period, the degradation rate of photovoltaic modules over a specific service life, the inverter efficiency at the corresponding load rate, and investment cost parameters such as inverter purchase cost, photovoltaic module cost, and installation cost. The capacity ratio K corresponding to this variable combination is also defined. These key variable values ​​are then substituted into a function F(K) with the objective of maximizing the net revenue throughout the photovoltaic power plant's lifecycle. The total power generation revenue is calculated sequentially. Combining the total lifecycle power generation with the grid-connected electricity price, total investment cost, and operation and maintenance cost, the objective function value for the particle is obtained by subtracting the total investment cost from the operation and maintenance cost. This value is the particle's fitness value; a higher fitness value indicates that the key variable combination and capacity ratio scheme corresponding to that particle are more economically efficient.

[0032] In each iteration, the individual optimal fitness value obtained by each particle during its historical search process is recorded, which is the maximum fitness value among all previous positions of the particle, along with the corresponding key variable values ​​and tolerance ratios. Simultaneously, the swarm optimal fitness value among all current particle fitness values ​​is calculated, representing the fitness value and parameter combination corresponding to the current optimal solution globally. Then, based on the classic update formula of the particle swarm optimization algorithm, and combining the guiding weights of individual and swarm optimality, the ability of particles to explore autonomously and the swarm to search collaboratively is balanced. A new velocity for each particle is calculated, which integrates the particle's current velocity, the difference between its individual optimal position and its current position, and the difference between its swarm optimal position and its current position, ensuring that particles can both move closer to their historical optimal solutions and adjust towards the global optimum. After obtaining the new velocity, the particle position is further updated. That is, the combination of key variable values ​​and the capacity ratio K corresponding to the particle are adjusted according to the new velocity. At the same time, the updated position is constrained and verified to ensure that key variables, such as light intensity and temperature, are still within the reasonable range and the capacity ratio is still within the preset range of [1.0, 1.8]. This prevents the particle from deviating from the effective search range due to excessive velocity. Finally, an iterative update of particle velocity and position is completed, which drives the entire particle swarm to gradually approach the optimal capacity ratio of multi-variable collaboration.

[0033] Considering the accuracy requirements and optimization efficiency of photovoltaic power plant capacity ratio optimization, two iteration termination conditions are preset: first, a maximum number of iterations is set, typically 80-120, to ensure the algorithm has sufficient search space; second, an accuracy threshold is set, which is 1×10⁻⁶. -4 ~1×10 -3 To avoid excessive iteration, after each iteration updates the particle velocity and position, the change in the population's optimal fitness value is continuously monitored. If the number of iterations reaches a preset maximum value or the difference between the population's optimal fitness values ​​obtained from two adjacent iterations is less than a precision threshold, the algorithm is considered to have converged, and the iteration is stopped. Subsequently, the particle position corresponding to the population's optimal fitness value at convergence is extracted. The combination of key variable values ​​contained in this position and the capacity ratio K constitute the optimal capacity ratio that satisfies constraints such as inverter overload, load rate within the high-efficiency range of 40% to 80%, and capacity ratio within the range of 1.0 to 1.8, while maximizing the net income of the photovoltaic power plant throughout its entire life cycle. Finally, this optimal capacity ratio is output as the solution result, providing a basis for subsequent simulation verification or practical applications.

[0034] In one possible implementation, step S340 further includes: Step S341: Set the maximum number of iterations and the precision threshold; Step S342: When the number of iterations meets the maximum number of iterations or the difference between the optimal fitness values ​​of the population obtained from two adjacent iterations meets the accuracy threshold, the iteration is stopped and the optimal capacity ratio is output.

[0035] Specifically, the parameters are determined by combining the actual needs and algorithm characteristics of photovoltaic power plant inverter capacity ratio optimization: On the one hand, a maximum number of iterations is set, typically between 80 and 120, referencing industry practices and optimization accuracy requirements. This provides sufficient search space for the particle swarm optimization to traverse key variable combinations and capacity ratio ranges while avoiding inefficiency due to excessive iterations. On the other hand, an accuracy threshold is set, considering the precision requirements for calculating net income over the entire lifecycle, and is set to 1×10⁻⁶. -4 ~1×10 -3 This ensures that the final output capacity ratio scheme is stable in terms of economic benefits.

[0036] Convergence judgment and result output are performed based on preset conditions: After each update of particle velocity and position, two indicators are monitored simultaneously: first, whether the current iteration count has reached the set maximum iteration count; and second, whether the difference between the net profit values ​​corresponding to the global optimal solution in each iteration and the population optimal fitness value obtained from two adjacent iterations is less than the accuracy threshold. If either condition is met, the algorithm is considered to have converged, and the iteration process is stopped. Subsequently, the particle position corresponding to the population optimal fitness value at convergence is extracted. The capacity ratio contained in this position is the optimal capacity ratio that satisfies constraints such as inverter overload, load rate within the high-efficiency range of 40% to 80%, and capacity ratio within the range of 1.0 to 1.8, and maximizes the net profit of the photovoltaic power plant throughout its entire life cycle. This is output as the final result, providing accurate basis for subsequent simulation verification or actual power plant application.

[0037] In one possible implementation, step S431 further includes: The particle swarm has 50-100 particles, the maximum number of iterations is set to 80-120, and the precision threshold is 10. -4 ~1×10 -3 .

[0038] Specifically, when using the particle swarm optimization algorithm to solve the multivariate collaborative optimization model of photovoltaic power plant inverters, it is necessary to reasonably set the core parameters of the algorithm based on the requirements of optimization accuracy and efficiency. This ensures that the model solution fully traverses the effective solution space while avoiding excessive iteration and resource consumption. Specifically, the number of particles in the particle swarm is set to 50-100: this range balances search breadth and computational efficiency. Too few particles can limit the search range, making it difficult to find the global optimum; too many particles will increase the computational load and reduce the iteration speed. 50-100 particles can cover key variable combinations such as light intensity and ambient temperature while ensuring the algorithm's operating efficiency. The maximum number of iterations is set to 80-120: referring to the actual scenario of photovoltaic power plant capacity ratio optimization, 80 iterations can meet the basic optimization requirements, and 120 iterations can further improve the accuracy of the solution. This range avoids the solution not converging due to insufficient iterations or wasting resources due to excessive iterations, ensuring that the algorithm approaches the optimal capacity ratio within a reasonable time. The accuracy threshold is set to 1×10⁻⁶. -4 ~1×10 -3 This threshold corresponds to the slight difference in net income over the entire life cycle. It can ensure the stability of the economic benefits corresponding to the optimal capacity ratio, and will not prolong the iteration cycle due to an overly strict threshold. This makes the capacity ratio output by the algorithm at the time of convergence both accurate and in line with the actual application requirements.

[0039] In one possible implementation, step S200 further includes: The preset efficiency operating range is [40%, 80%], the preset capacity ratio range is [1.0, 1.8], and the constraint condition for the inverter not to be overloaded is that the actual output power of the photovoltaic array is ≤ the rated input power of the inverter × (1 + overload coefficient), and the overload coefficient is 0.1.

[0040] Specifically, in setting the constraints of the multivariate collaborative optimization model, all parameters are determined around the safe and efficient operation of photovoltaic power plants and the actual application scenarios in the industry, ensuring that the capacity ratio optimization is both feasible and practical. The inverter's preset efficiency operating range is set to [40%, 80%], which is based on the characteristics of the inverter efficiency curve. Most photovoltaic inverters can stably maintain an efficiency above 96% within this load rate range. Efficiency drops significantly below 40% or above 80%. This range ensures that the inverter is in a long-term high-efficiency power generation state, avoiding energy waste. The preset range of the capacity ratio is set to [1.0, 1.8], which references both industry standards and the characteristics of photovoltaic resources in different regions. For example, in high-irradiance areas, a range closer to 1.8 can be used to fully utilize sunlight, while in low-irradiance areas, a range closer to 1.0 can be used to avoid... This approach avoids equipment idleness, balances equipment investment with power generation revenue, prevents excessively low capacity from wasting photovoltaic resources, and avoids excessively high capacity from increasing operation and maintenance risks. The inverter overload constraint is clearly defined as the actual output power of the photovoltaic array ≤ the rated input power of the inverter × (1 + 0.1). The overload factor of 0.1 takes into account the short-term power fluctuations that may occur in the photovoltaic array under extreme light and temperature conditions. The 10% overload margin can prevent the inverter from being damaged due to instantaneous power exceeding the limit, while also preventing excessive overload margin from increasing equipment costs. Ultimately, this forms a constraint system that takes into account efficiency, revenue, and safety.

[0041] Example 2, based on the same inventive concept as the photovoltaic power plant inverter capacity ratio optimization method based on multivariate collaboration in the previous examples, such as... Figure 2 As shown, this application provides a photovoltaic power plant inverter capacity ratio optimization system based on multivariate collaboration. The system and method embodiments in this application are based on the same inventive concept. The system includes: The key variable determination module 10 is used to determine the key variables that affect the inverter capacity ratio in a photovoltaic power plant. The key variables include irradiance, ambient temperature, photovoltaic module degradation rate, inverter efficiency curve, and investment cost parameters.

[0042] The optimization model construction module 20 is used to construct a multi-variable collaborative optimization model with the objective function of maximizing the net income of the photovoltaic power plant throughout its entire life cycle, and with the constraints of inverter not being overloaded, inverter load rate being within a preset efficiency operating range, and capacity ratio being within a preset range.

[0043] The optimal capacity ratio output module 30 is used to solve the multivariate collaborative optimization model using the particle swarm optimization algorithm, and outputs the optimal capacity ratio through particle initialization, fitness calculation, velocity and position update, and iteration termination judgment.

[0044] The reconstruction optimization processing module 40 is used to apply the optimal capacity ratio to the simulation model of the photovoltaic power station or the actual pilot power station, and to verify the execution of the reconstruction optimization processing through comparative analysis.

[0045] Furthermore, the system is also used to implement the following functions: The light intensity refers to the average light intensity data of the area where the photovoltaic power station is located at different times of the year. The ambient temperature refers to the annual temperature variation data of the area where the photovoltaic power station is located. The photovoltaic module degradation rate refers to the power degradation data of the module at different service years. The inverter efficiency curve refers to the efficiency data of the corresponding inverter at different load rates. The investment cost parameters include the inverter purchase cost, installation cost, and photovoltaic module cost.

[0046] Furthermore, the system is also used to implement the following functions: The objective function F(K) = total power generation revenue - total investment cost - operation and maintenance cost, where the total power generation revenue is calculated based on the power generation and grid connection price under different key variables, the total investment cost is determined based on the capacity ratio and cost parameters of related equipment, and the operation and maintenance cost is determined based on the operation and maintenance experience data of photovoltaic power plants and the impact of the capacity ratio.

[0047] Furthermore, the system is also used to implement the following functions: Initialize the particle swarm, representing the position of each particle as a combination of key variable values ​​and a corresponding capacity ratio. Based on the value range of the key variables and the constraint range of the capacity ratio, randomly initialize the position and velocity of the particle swarm. Substitute the key variable value combination corresponding to the particle into the objective function to calculate the fitness value of each particle. Update the velocity and position of the particles based on the individual optimal fitness value and the swarm's optimal fitness value. Output the optimal capacity ratio based on the iterative update results.

[0048] Furthermore, the system is also used to implement the following functions: Set a maximum number of iterations and a precision threshold; when the number of iterations meets the maximum number of iterations or the difference between the optimal fitness values ​​of the population obtained from two adjacent iterations meets the precision threshold, stop the iteration and output the optimal capacity ratio.

[0049] Furthermore, the system is also used to implement the following functions: The number of particles in the particle swarm is The maximum number of iterations is set to The accuracy threshold is .

[0050] Furthermore, the system is also used to implement the following functions: The preset efficiency operating range is [40%, 80%], the preset capacity ratio range is [1.0, 1.8], and the constraint condition for the inverter not to be overloaded is that the actual output power of the photovoltaic array is ≤ the rated input power of the inverter × (1 + overload coefficient), and the overload coefficient is 0.1.

[0051] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0052] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0053] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A photovoltaic power station inverter capacity ratio optimization method based on multivariate coordination, characterized in that, The method comprises: determining key variables affecting the capacity ratio of inverters in a photovoltaic power station, the key variables including irradiance, ambient temperature, photovoltaic component attenuation rate, inverter efficiency curve and investment cost parameters; constructing a multivariate collaborative optimization model with the maximum net income of the whole life cycle of the photovoltaic power station as an objective function, and with the inverter not being overloaded, the inverter load rate being in a preset efficiency working interval and the capacity ratio being in a preset range as constraint conditions; solving the multivariate collaborative optimization model by using a particle swarm optimization algorithm, and outputting an optimal capacity ratio through particle initialization, fitness calculation, speed and position updating, and iteration termination judgment; applying the optimal capacity ratio to a simulation model or an actual pilot photovoltaic power station, and verifying the execution of the reconstruction optimization process through comparative analysis. 2.The photovoltaic power station inverter capacity ratio optimization method based on multivariate coordination of claim 1, wherein The irradiance is the average irradiance data of different time periods throughout the year in the region where the photovoltaic power station is located, the ambient temperature is the annual temperature variation data of the region where the photovoltaic power station is located, the photovoltaic component attenuation rate is the power attenuation data of the component under different service life, the inverter efficiency curve is the efficiency data of the corresponding inverter under different load rates, and the investment cost parameters include the purchase cost, installation cost and photovoltaic component cost of the inverter. 3.The photovoltaic power station inverter capacity ratio optimization method based on multivariate coordination of claim 1, wherein, The objective function F(K) = total power generation income - total investment cost - operation and maintenance cost, wherein the total power generation income is calculated according to the power generation and the on-grid electricity price under different key variables, the total investment cost is determined according to the capacity ratio and the cost parameters of related equipment, and the operation and maintenance cost is determined according to the operation and maintenance experience data of the photovoltaic power station and the influence of the capacity ratio. 4.The photovoltaic power station inverter capacity ratio optimization method based on multivariate coordination of claim 1, wherein, Solving the multivariate collaborative optimization model by using a particle swarm optimization algorithm comprises: initializing the particle swarm, taking the position of each particle as a combination of values of the key variables and the corresponding capacity ratio, and randomly initializing the position and speed of the particle swarm according to the value range of the key variables and the constraint range of the capacity ratio; substituting the combination of values of the key variables corresponding to the particle into the objective function to calculate the fitness value of each particle; updating the speed and position of the particle according to the individual optimal fitness value and the group optimal fitness value of the particle; outputting the optimal capacity ratio according to the iteration update result.

5. The photovoltaic power station inverter capacity ratio optimization method based on multivariate coordination according to claim 4, characterized in that, Outputting the optimal capacity ratio according to the iteration update result comprises: setting the maximum number of iterations and the precision threshold; stopping iteration and outputting the optimal capacity ratio when the number of iterations meets the maximum number of iterations or the difference between the group optimal fitness values obtained by adjacent two iterations meets the precision threshold. 6.The method of claim 5, wherein, The particle quantity of the particle group is , the maximum iteration number is set to , and the precision threshold is . 7.The photovoltaic power station inverter capacity ratio optimization method based on multivariate coordination of claim 1, wherein, The preset efficiency working interval is [40%, 80%], the preset range of the capacity ratio is [1.0, 1.8], and the constraint condition that the inverter is not overloaded is specifically that the actual output power of the photovoltaic array ≤ rated input power of the inverter × (1 + overload coefficient), and the overload coefficient is 0.

1.

8. A photovoltaic power station inverter capacity ratio optimization system based on multivariate coordination, characterized in that, The system is used to implement the multivariate collaborative photovoltaic power station inverter capacity ratio optimization method according to any one of claims 1-7, and the system comprises: a key variable determination module for determining key variables affecting the capacity ratio of inverters in a photovoltaic power station, the key variables including irradiance, ambient temperature, photovoltaic component attenuation rate, inverter efficiency curve and investment cost parameters; The optimization model construction module is configured to construct a multivariable collaborative optimization model with the maximum of the full life cycle net income of the photovoltaic power station as a target function, and with the inverter not being overloaded, the inverter load rate being in a preset efficiency working interval, and the capacity ratio being in a preset range as constraint conditions; The optimal capacity ratio output module is configured to solve the multivariable collaborative optimization model by using a particle swarm optimization algorithm, and output an optimal capacity ratio through particle initialization, fitness calculation, speed and position updating, and iteration termination judgment. The reconstruction optimization processing module is configured to apply the optimal capacity ratio to a simulation model or an actual pilot power station of the photovoltaic power station, and verify and execute reconstruction optimization processing through comparative analysis.

Images