Photovoltaic-based load regulation method, device and equipment and storage medium

Abstract

The invention provides a photovoltaic-based load regulation method, device and equipment and a storage medium, and the method comprises the steps: generating a current node dependency graph according to the collected real-time data of each node in a photovoltaic system; running dynamic simulation based on the current node dependency graph to obtain simulation data, and adjusting the output of the inverter in real time according to the simulation data to obtain a matching optimization result; performing genetic algorithm optimization on the basis of a matching optimization result to obtain optimized power regulator parameter configuration, and performing system load balance test on the basis of the optimized power regulator parameter configuration to obtain a system load balance result; and performing real-time feedback adjustment on the photovoltaic system based on a system load balancing result to obtain optimized output configuration of the photovoltaic system. According to the scheme provided by the invention, the future energy demand can be accurately predicted and the resource configuration can be optimized according to the real-time data of each node, and the accuracy and reliability of load regulation are improved.

Description

Technical Field

[0001] The present invention relates to the field of digital control technology, and in particular to a photovoltaic-based load regulation method, device, equipment and storage medium. Background Art

[0002] Digital control is a technology field that covers a wide range of applications. It relies on digital signal processors (DSPs), microcontrollers or computers to execute control algorithms to manage and optimize the performance of various systems and equipment. This technology is not limited to simple switch control, but also includes more complex feedback and feedforward control strategies, which can achieve precise process regulation, dynamic optimization and fault diagnosis. In power systems, digital control is used to optimize power generation, transmission and distribution processes, improve energy efficiency and system responsiveness, and reduce operating costs. In addition, it also supports advanced data analysis and real-time monitoring, making energy management more intelligent and automated.

[0003] Among them, the photovoltaic-based load regulation method refers to the use of electricity generated by photovoltaic systems to adjust and optimize energy demand related to changes in the external environment (for example, seasonal changes). This method pays special attention to how to meet changing load demands in different external environments by adjusting the output of photovoltaic systems or by working in coordination with other energy systems. This usually includes the use of intelligent algorithms and control systems to predict energy demand, manage battery storage, and optimize photovoltaic output. Its main purpose is to improve the efficiency of energy use, reduce dependence on traditional energy, while reducing energy costs and improving the overall performance and reliability of renewable energy systems.

[0004] Existing technologies are not good at dealing with complex environmental changes and seasonal demand fluctuations, especially in predicting future energy demand and optimizing resource allocation. This limitation leads to inefficient matching of energy supply and demand, and it is difficult to adjust output to meet demand changes during peak or trough periods of energy demand, often resulting in energy waste or insufficient supply. In addition, traditional technologies are also limited in their ability to process real-time data and perform long-term performance optimization. These deficiencies affect the economic benefits and operational reliability of the system. Summary of the invention

[0005] The present invention provides a photovoltaic-based load regulation method, device, equipment and storage medium to address the shortcomings of the prior art in coping with complex environmental changes and seasonal demand fluctuations, especially the limited ability to predict future energy demand and optimize resource allocation, thereby achieving accurate prediction of future energy demand and optimizing resource allocation, and improving the accuracy and reliability of photovoltaic system power supply control.

[0006] The present invention provides a photovoltaic-based load regulation method, which is applied to a photovoltaic system, wherein the photovoltaic system includes a plurality of nodes, an inverter, and a power regulator; the method includes: Generate a current node dependency graph based on the collected real-time data of each node in the photovoltaic system; wherein the real-time data includes the output power of the photovoltaic panels and environmental parameters; Based on the current node dependency graph, a dynamic simulation is run to obtain simulation data, and according to the simulation data, the inverter output is adjusted in real time to obtain a matching optimization result; Based on the matching optimization result, a genetic algorithm optimization is performed to obtain an optimized power regulator parameter configuration, and based on the optimized power regulator parameter configuration, a system load balancing test is performed to obtain a system load balancing result; Based on the system load balancing result, real-time feedback adjustment is performed on the photovoltaic system to obtain an optimized output configuration of the photovoltaic system.

[0007] According to a photovoltaic-based load regulation method provided by the present invention, the current node dependency graph is generated according to the collected real-time data of each node in the photovoltaic system, including: According to the collected real-time data of each node in the photovoltaic system, the correlation between the nodes in the photovoltaic system is calculated, and an initial node dependency graph is generated according to the correlation between the nodes in the photovoltaic system; Based on the initial node dependency graph and according to current environment parameters, a current weight matrix between nodes is calculated; A current node dependency graph is generated according to the current weight matrix between the nodes.

[0008] According to a photovoltaic-based load regulation method provided by the present invention, the simulation data includes: estimated output power and power difference data at each time point in a preset future period; based on the current node dependency graph, running dynamic simulation to obtain simulation data includes: Based on the current node dependency graph, a dynamic simulation is run to obtain an estimated output power corresponding to each time point in a preset future period; For each time point in a preset future time period, the power difference data at the time point is calculated based on the estimated output power and the real-time required power at the time point.

[0009] According to a photovoltaic-based load regulation method provided by the present invention, the inverter output is adjusted in real time according to the simulation data to obtain a matching optimization result, including: According to the difference data corresponding to each time point in the preset future period, the average power difference in the preset future period is calculated; generating an adjustment instruction according to the average power difference; The adjustment instruction is applied to the inverter, the inverter output is adjusted in real time, the adjusted inverter output power is obtained, and the matching optimization result is generated.

[0010] According to a photovoltaic-based load regulation method provided by the present invention, the genetic algorithm optimization is performed based on the matching optimization result to obtain the optimized power regulator parameter configuration, including: Initializing a genetic algorithm population based on the matching optimization result; Define a fitness function and calculate the fitness score of each power conditioner parameter configuration; The power conditioner parameter configuration is optimized by applying crossover and mutation operations, and the optimized power conditioner parameter configuration is selected according to the fitness score of each power conditioner parameter configuration.

[0011] According to a photovoltaic-based load regulation method provided by the present invention, based on the system load balancing result, real-time feedback adjustment is performed on the photovoltaic system to obtain an optimized output configuration of the photovoltaic system, including: Based on the system load balancing result, real-time feedback adjustment is performed on the photovoltaic system, and a deviation value between an actual output of the photovoltaic system and a predicted output of the photovoltaic system is monitored; Based on the deviation value, adjusting the selection, crossover and mutation steps in the genetic algorithm to generate adjusted genetic algorithm parameters; According to the adjusted genetic algorithm parameters, the parameter optimization of the photovoltaic system is re-executed to generate an optimized output configuration of the photovoltaic system.

[0012] According to a photovoltaic-based load regulation method provided by the present invention, before generating a current node dependency graph based on the collected real-time data of each node in the photovoltaic system, the method further includes: The real-time data of each node in the photovoltaic system is normalized.

[0013] The present invention also provides a photovoltaic-based load regulation device, which is applied to a photovoltaic system. The photovoltaic system includes a plurality of nodes, an inverter, and a power regulator. The device includes the following modules: A data association module is used to generate a current node dependency graph based on the collected real-time data of each node in the photovoltaic system; wherein the real-time data includes the output power of the photovoltaic panels and environmental parameters; A dynamic simulation module, used to run dynamic simulation based on the current node dependency graph to obtain simulation data; An output adjustment module, used to adjust the inverter output in real time according to the simulation data to obtain a matching optimization result; An algorithm optimization module, used for performing genetic algorithm optimization based on the matching optimization result to obtain an optimized power regulator parameter configuration; A load balancing test module, used to perform a system load balancing test based on the optimized power regulator parameter configuration to obtain a system load balancing result; The feedback adjustment module is used to perform real-time feedback adjustment on the photovoltaic system based on the system load balancing result to obtain an optimized output configuration of the photovoltaic system.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the photovoltaic-based load regulation method described above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the photovoltaic-based load regulation method described in any one of the above is implemented.

[0016] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the photovoltaic-based load regulation method described above is implemented.

[0017] The photovoltaic-based load regulation method, device, equipment and storage medium provided by the present invention generate a current node dependency graph based on the real-time data of each node in the photovoltaic system collected; wherein the real-time data includes the output power and environmental parameters of the photovoltaic panels; based on the current node dependency graph, a dynamic simulation is run to obtain simulation data, and according to the simulation data, the inverter output is adjusted in real time to obtain a matching optimization result; based on the matching optimization result, a genetic algorithm optimization is performed to obtain an optimized power regulator parameter configuration, and based on the optimized power regulator parameter configuration, a system load balancing test is performed to obtain a system load balancing result; based on the system load balancing result, a real-time feedback adjustment is performed on the photovoltaic system to obtain an optimized output configuration of the photovoltaic system. The solution of the present invention realizes accurate adjustment of power output by deeply analyzing the relationship between the output power of photovoltaic panels and environmental parameters; dynamically simulates the future scenarios of photovoltaic output and power demand, adjusts the inverter output in advance, and ensures the matching between supply and demand; optimizes the power regulator parameters by genetic algorithm, improves the system adaptive adjustment ability and energy utilization efficiency; further, based on the optimized power regulator parameter configuration, performs system load balancing test to obtain the system load balancing result; based on the system load balancing result, performs real-time feedback adjustment on the photovoltaic system to obtain the optimized output configuration of the photovoltaic system, realizes real-time monitoring and parameter adjustment of output deviation, not only enhances the reliability of the system, but also promotes the reduction of energy cost and the overall optimization of system performance. Therefore, the solution of the present invention can accurately predict future energy demand and optimize resource allocation according to the real-time data of each node, and improves the accuracy and reliability of load regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is one of the flow charts of the photovoltaic-based load regulation method provided by the present invention.

[0020] Figure 2 This is the second flow chart of the photovoltaic-based load regulation method provided by the present invention.

[0021] Figure 3 It is a schematic structural diagram of a photovoltaic-based load regulation device provided by the present invention.

[0022] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The technical solution of the present invention is used to solve the above technical problems. The technical solution of the present application and how the technical solution of the present application solves the above technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. Figure 1-Figure 2 The photovoltaic-based load regulation method of the present invention is described.

[0025] In practical applications, the executor of the photovoltaic-based load regulation method can be a photovoltaic-based load regulation device, which can be implemented in a variety of ways, such as through a computer program, such as application software, etc.; or, for example, a chip, etc. It can also be implemented as a medium storing relevant computer programs, such as a USB flash drive, a cloud disk, etc.; or, it can also be implemented through a physical device integrated or installed with relevant computer programs, such as a server, etc.

[0026] Figure 1 is one of the flow charts of the photovoltaic-based load regulation method provided by the present invention, such as Figure 1 As shown, the method includes steps 101 to 106.

[0027] Step 101: Generate a current node dependency graph based on the collected real-time data of each node in the photovoltaic system.

[0028] The method provided in this embodiment is applied to a photovoltaic system, which is composed of multiple photovoltaic panels (modules) and also includes other auxiliary equipment and control systems, such as brackets, cables, junction boxes, inverters, monitoring systems, etc. The purpose of the photovoltaic system is to collect the electricity generated by each panel, convert it into a format suitable for use by the power grid or load, and manage and monitor it. In this implementation, the photovoltaic system includes multiple nodes, inverters, and power conditioners.

[0029] Each node represents a single photovoltaic panel or a group of photovoltaic panels. Photovoltaic panels are the basic energy conversion units in photovoltaic systems, responsible for converting sunlight directly into direct current (DC). They are usually composed of multiple photovoltaic cells (photovoltaic cells), which are connected in series or in parallel to provide the required voltage and current.

[0030] Among them, the inverter is a key component in the photovoltaic system, which converts the direct current (DC) generated by the photovoltaic panel into alternating current (AC) to supply the load or connect to the grid. Optionally, the inverter is also responsible for isolating the DC side and the AC side, protecting the system safety, and providing some monitoring and protection functions, such as overload protection, short circuit protection, and island effect protection.

[0031] Specifically, in a photovoltaic system, a power conditioner refers to a management device or system used to control the output of an inverter, the charging and discharging of a battery energy storage system, and the interaction with a power grid. The power conditioner can ensure that the power generated by the photovoltaic system can be safely and efficiently supplied to the load or incorporated into the power grid. Therefore, a power conditioner can be a hardware device, a software system, or a combination of the two. For example, as hardware, a power conditioner generally refers to a physical device that can directly control and adjust the flow, voltage, and current of power. For example, these devices may include transformers, circuit breakers, frequency converters, power factor correction devices, etc., which are used in power systems to maintain the stability and effective distribution of power. For another example, as software, a power conditioner generally refers to a software program or algorithm used to monitor and control a power system. These software can run on a computer or embedded system to optimize the operation of the power system through data analysis and control logic. For another example, in many modern power systems, power conditioners are often the product of a combination of hardware and software. The hardware device is responsible for performing the actual power regulation tasks, while the software system provides intelligent control and decision support, and the two work together to achieve more efficient and reliable power regulation.

[0032] Among them, real-time data includes photovoltaic panel output power and environmental parameters. Environmental parameters refer to external conditions and variables that affect the output of photovoltaic systems. These parameters have a direct or indirect impact on the performance and power generation of photovoltaic panels. For example, environmental parameters can be light intensity, temperature, solar radiation angle, atmospheric transparency, humidity, air pressure, rainfall, etc.

[0033] In practical applications, real-time data is collected from each node in the photovoltaic system. For example, a sensor is set at each node, and the sensor collects the real-time data of the corresponding node in real time. The real-time data of each node in the photovoltaic system is collected from the sensor corresponding to each node, including the output power, temperature and light intensity of the photovoltaic panel, to generate a real-time data set. The real-time data set D is expressed by the following formula: in, is the temperature collected at node j, is the light intensity collected at node j, is the output power collected at node j, Represents the total number of data points.

[0034] Furthermore, the linear regression model is used to deeply analyze the correlation between the output power of photovoltaic panels and environmental parameters in real-time data, and the current node dependency graph is generated according to the node connection status.

[0035] In practical applications, in order to improve the accuracy and reliability of load regulation, the current node dependency graph is updated in real time according to the real-time data of each node in the photovoltaic system collected in real time, and the following steps are performed according to the updated node dependency graph.

[0036] As an example, in some embodiments, in combination with Figure 2 , the above step 101 includes: step 1011 to step 1013.

[0037] Step 1011: Calculate the correlation between nodes in the photovoltaic system based on the collected real-time data of each node in the photovoltaic system, and generate an initial node dependency graph based on the correlation between nodes in the photovoltaic system.

[0038] Specifically, for the real-time data in the real-time data set, a correlation analysis is performed, and the correlation coefficient formula is used to calculate the correlation between nodes to obtain a correlation matrix.

[0039] For example, the association between node j and node k , the calculation formula is as follows: in, is the average temperature, is the average value of power, is the coefficient that adjusts the association calculation.

[0040] Furthermore, based on the correlation matrix, an initial node dependency graph is constructed, and a graph algorithm is used to represent the dependency between nodes. Each node represents a data point, and the connection strength between nodes is determined by the correlation degree. Determine and generate the initial node dependency graph G.

[0041] Step 1012: Based on the initial node dependency graph and according to the current environment parameters, calculate and obtain the current weight matrix between nodes.

[0042] Step 1013: Generate a current node dependency graph based on the current weight matrix between nodes.

[0043] In practical applications, based on the initial node dependency graph and referring to the changes in environmental parameters, the current weight matrix between nodes is calculated. For example, the current weight matrix between node j and node k is , can be obtained by using the following formula: in, are the temperatures collected at node j and node k, respectively. To collect the light intensity at node j and node k respectively, is the weight adjustment factor.

[0044] Furthermore, the current weight matrix between nodes is applied to calculate the dependency strength of each node and generate a dependency list of each node. For example, the dependency strength of node j is calculated using the following formula: : Where n is the total number of nodes in the photovoltaic system, is the current weight matrix between node j and node k.

[0045] Furthermore, based on the dependency list of each node, the node dependency graph is rebuilt to obtain the current node dependency graph . The current node dependency graph It can be expressed as: in, For a node set, in the current node dependency graph In each node, The size or color of shows the strength of the dependency, and the weight of the edge is determined by the current weight.

[0046] Step 102: Based on the current node dependency graph, run dynamic simulation to obtain simulation data.

[0047] Dynamic simulation refers to a process that simulates the performance and behavior of a photovoltaic system over a specific period of time in the future. This simulation takes into account the response of the photovoltaic system under different environmental parameters and operating conditions, and how these factors affect the system's power output and load demand. The purpose of dynamic simulation is to predict and optimize the performance of the photovoltaic system, ensure the match between power supply and demand, and improve the overall efficiency and reliability of the system.

[0048] As an example, in some embodiments, the simulation data includes: estimated output power and power difference data at each time point in a preset future period. Figure 2 , the above step 102 includes: step 1021 and step 1022.

[0049] Step 1021: Based on the current node dependency graph, run a dynamic simulation to obtain the estimated output power corresponding to each time point in a preset future period.

[0050] Step 1022: For each time point in the preset future period, the power difference data at the time point is calculated based on the estimated output power and the real-time required power at the time point.

[0051] In practical applications, based on the current node dependency graph , set the starting parameters of the dynamic simulation, generate the initialization simulation time point t, the initialization simulation time point t can be expressed as: in, is the start time, It's the end time. is a random number in the interval [0,1].

[0052] Furthermore, the estimated output power of node j at the initial simulation time point t is calculated and generated by combining external environmental factors and the node connection strength of the dependency graph. For example, the estimated output power of node j at the initial simulation time point t is The calculation formula is: in, is the number of nodes in the PV system, , Parameters for adjusting the output reaction rate and time offset.

[0053] Furthermore, the estimated output power at the initial simulation time point t is With real-time power demand Compare and calculate the power difference data at the initial simulation time point t For example, initialize the power difference data at the simulation time point t It can be expressed as the following formula: Among them, ρ is a parameter that adjusts the influence of the difference.

[0054] For example, the real-time power demand It can be predicted and analyzed through historical data analysis, weather forecasts and environmental parameter predictions, user behavior patterns and electricity usage habits analysis, etc.

[0055] Furthermore, the estimated output power and power difference data at each time point in a preset future period are integrated to obtain simulation data.

[0056] Step 103: According to the simulation data, the inverter output is adjusted in real time to obtain a matching optimization result.

[0057] In one example, according to the simulation data, a linear programming algorithm is used to adjust the inverter output in real time to obtain the adjusted inverter output power. The inverter output power is adjusted to match the real-time power demand to generate a matching optimization result.

[0058] Optionally, in some embodiments, the above step 103 includes: step 1031 to step 1033.

[0059] Step 1031: Calculate the average power difference in the preset future time period according to the difference data corresponding to each time point in the preset future time period.

[0060] Step 1032: Generate an adjustment instruction according to the average power difference.

[0061] Step 1033: Apply the adjustment instruction to the inverter, adjust the inverter output in real time, obtain the adjusted inverter output power, and generate a matching optimization result.

[0062] Specifically, the difference data corresponding to each time point in the preset future period is extracted from the simulation data, and the average power difference in the preset future period is calculated. , the calculation formula is as follows: in, is the power difference data at time point t, and T is the total number of time points in the preset future period.

[0063] Furthermore, according to the average power difference in the preset future period , set the inverter adjustment range A, the calculation formula of the inverter adjustment range A is: in, is the basic adjustment factor, For smooth adjustment process, Adjust the periodicity factor.

[0064] Furthermore, the sensitivity and size of the adjustment amplitude are controlled to generate an adjustment instruction, which includes the adjustment amplitude A of the inverter. The adjustment instruction is applied to the inverter, and the inverter output is adjusted in real time to obtain the adjusted inverter output power. , the adjusted inverter output power The expression is as follows: in, is the initial output power of the inverter, is the adjusted inverter output power.

[0065] Furthermore, the inverter output power is adjusted to match the real-time power demand, and a matching optimization result is generated. As an example, the matching optimization result includes the actual output power of the photovoltaic system, the adjusted inverter output power, the matching degree, etc.

[0066] Step 104: Based on the matching optimization result, perform genetic algorithm optimization to obtain an optimized power conditioner parameter configuration.

[0067] Among them, the genetic algorithm (GA) is a heuristic search algorithm that simulates the biological evolution process. The genetic algorithm solves the optimization problem by simulating biological evolution mechanisms such as natural selection, inheritance, crossover (hybridization) and mutation. In this embodiment, the power regulator parameters are optimized by the genetic algorithm to improve the system performance and energy efficiency.

[0068] Specifically, the optimized power regulator parameter configuration includes algorithm parameters, regulator settings, response strategies, etc.

[0069] As an example, in some embodiments, the above step 104 includes: step 1041 to step 1044.

[0070] Step 1041: Initialize the genetic algorithm population based on the matching optimization result.

[0071] Step 1042: Define a fitness function and calculate the fitness score of each power conditioner parameter configuration.

[0072] Step 1043: Apply crossover and mutation operations to optimize the power conditioner parameter configuration, and select the optimized power conditioner parameter configuration according to the fitness score of each power conditioner parameter configuration.

[0073] Specifically, the adjusted inverter output power is extracted from the matching optimization result, and the genetic algorithm population is initialized. Further, a fitness function is defined to calculate the fitness score of each power conditioner parameter configuration. For example, the fitness score of the power conditioner parameter configuration The expression is: in, For multi-parameter performance improvement, is the weight of multiple performance indicators.

[0074] Furthermore, the population is screened according to the fitness score of each power conditioner parameter configuration. For example, the fitness score of each power conditioner parameter configuration is sorted, and the power conditioner parameter configuration with a higher fitness score is selected to screen the population to guide the algorithm to evolve toward the optimal solution.

[0075] Specifically, crossover and mutation operations are applied to optimize the power conditioner parameter configuration, and the optimal power conditioner parameter configuration is selected according to the fitness score of each power conditioner parameter configuration.

[0076] Further, based on the optimal power conditioner parameter configuration, the parameters are adjusted to enhance system performance, and an optimized power conditioner parameter configuration is generated. . For example, the optimized power conditioner parameter configuration The calculation formula is as follows: in, is the original parameter configuration of the power conditioner, To control the genetic mixing ratio, , is a parameter for adjusting the degree of variation.

[0077] Step 105: Based on the optimized power conditioner parameter configuration, a system load balancing test is performed to obtain a system load balancing result.

[0078] Specifically, the optimized power conditioner parameter configuration is applied to perform a system load balancing test and calculate the system load balancing degree. For example, the system load balance The calculation formula is as follows: in, is the system load balance, , is the node power demand and supply, For total power supply.

[0079] Furthermore, a system load balancing result is generated, and the system load balancing result includes a balance test value, a stability evaluation, and an allocation efficiency.

[0080] Step 106: Based on the system load balancing result, perform real-time feedback adjustment on the photovoltaic system to obtain an optimized output configuration of the photovoltaic system.

[0081] Specifically, the optimized output configuration of the photovoltaic system includes optimization results, adjustment strategies, and feedback responsiveness.

[0082] As an example, in some embodiments, the above step 106 includes: step 1061 to step 1063.

[0083] Step 1061: Based on the system load balancing result, real-time feedback adjustment is performed on the photovoltaic system, and the deviation value between the actual output of the photovoltaic system and the predicted output of the photovoltaic system is monitored.

[0084] Step 1062: Based on the deviation value, the selection, crossover and mutation steps in the genetic algorithm are adjusted to generate adjusted genetic algorithm parameters.

[0085] Step 1063: re-execute the parameter optimization of the photovoltaic system according to the adjusted genetic algorithm parameters to generate an optimized output configuration of the photovoltaic system.

[0086] Specifically, real-time feedback adjustment is performed based on the system load balancing result, and the deviation value between the actual output of the photovoltaic system and the predicted output of the photovoltaic system is monitored. For example, the deviation value may be the root mean square error between the actual output of the photovoltaic system and the predicted output of the photovoltaic system, and the root mean square error between the actual output of the photovoltaic system and the predicted output of the photovoltaic system is calculated. , using the following formula: in, is the root mean square error, and Respectively Actual and predicted output at each measurement point.

[0087] Furthermore, based on the root mean square error between the actual output of the photovoltaic system and the predicted output of the photovoltaic system , adjust the selection, crossover and mutation steps in the genetic algorithm to generate adjusted genetic algorithm parameters , the adjusted genetic algorithm parameters The expression is as follows: in, are the adjusted genetic algorithm parameters, Control the maximum adjustment range. Control response slope, is the target deviation, is the root mean square error.

[0088] Furthermore, according to the adjusted genetic algorithm parameters, the parameter optimization of the photovoltaic system is re-executed to generate the optimal output configuration of the photovoltaic system , optimized output configuration of photovoltaic system The expression is: in, For the optimal output configuration of the photovoltaic system, The weight of each parameter is used to adjust the contribution of multiple parameters.

[0089] The scheme of this embodiment realizes accurate adjustment of power output by deeply analyzing the relationship between the output power of photovoltaic panels and environmental parameters; dynamically simulates the future scenarios of photovoltaic output and power demand, and adjusts the inverter output in advance to ensure the matching between supply and demand; optimizes the power regulator parameters by genetic algorithm to improve the system's adaptive adjustment ability and energy utilization efficiency; further, based on the optimized power regulator parameter configuration, the system load balancing test is performed to obtain the system load balancing result; based on the system load balancing result, the photovoltaic system is subjected to real-time feedback adjustment to obtain the optimized output configuration of the photovoltaic system, and the real-time monitoring and parameter adjustment of the output deviation are realized, which not only enhances the reliability of the system, but also promotes the reduction of energy costs and the overall optimization of system performance. Therefore, the scheme of this embodiment can accurately predict future energy demand and optimize resource allocation according to the real-time data of each node, thereby improving the accuracy and reliability of load regulation.

[0090] In addition, in some embodiments, before the above step 101, the above method further includes: normalizing the real-time data of each node in the photovoltaic system.

[0091] In practical applications, normalizing the real-time data of each node in the photovoltaic system helps to eliminate the differences between data of different dimensions and magnitudes, so that the data are on the same scale, thereby improving the accuracy and reliability of load regulation.

[0092] It should be noted that the above embodiments can be implemented separately or in combination. Figure 2 This is the second flow chart of the photovoltaic-based load regulation method provided by the present invention, such as Figure 2 As shown, the photovoltaic-based load regulation method includes the following steps.

[0093] Step 1011: Calculate the correlation between nodes in the photovoltaic system based on the collected real-time data of each node in the photovoltaic system, and generate an initial node dependency graph based on the correlation between nodes in the photovoltaic system.

[0094] Step 1012: Based on the initial node dependency graph and according to the current environment parameters, calculate and obtain the current weight matrix between nodes.

[0095] Step 1013: Generate a current node dependency graph based on the current weight matrix between nodes.

[0096] Step 1021: Based on the current node dependency graph, run a dynamic simulation to obtain the estimated output power corresponding to each time point in a preset future period.

[0097] Step 1022: For each time point in the preset future period, the power difference data at the time point is calculated based on the estimated output power and the real-time required power at the time point.

[0098] Step 1031: Calculate the average power difference in the preset future time period according to the difference data corresponding to each time point in the preset future time period.

[0099] Step 1032: Generate an adjustment instruction according to the average power difference.

[0100] Step 1033: Apply the adjustment instruction to the inverter, adjust the inverter output in real time, obtain the adjusted inverter output power, and generate a matching optimization result.

[0101] Step 1041: Initialize the genetic algorithm population based on the matching optimization result.

[0102] Step 1042: Define a fitness function and calculate the fitness score of each power conditioner parameter configuration.

[0103] Step 1043: Apply crossover and mutation operations to optimize the power conditioner parameter configuration, and select the optimized power conditioner parameter configuration according to the fitness score of each power conditioner parameter configuration.

[0104] Step 105: Based on the optimized power conditioner parameter configuration, a system load balancing test is performed to obtain a system load balancing result.

[0105] Step 1061 : Perform real-time feedback adjustment based on the system load balancing result, and monitor the deviation value between the actual output of the photovoltaic system and the predicted output of the photovoltaic system.

[0106] Step 1062: Based on the deviation value, the selection, crossover and mutation steps in the genetic algorithm are adjusted to generate adjusted genetic algorithm parameters.

[0107] Step 1063: re-execute the parameter optimization of the photovoltaic system according to the adjusted genetic algorithm parameters to generate an optimized output configuration of the photovoltaic system.

[0108] The photovoltaic-based load regulation method provided in this embodiment generates a current node dependency graph based on the real-time data of each node in the photovoltaic system collected; wherein the real-time data includes the output power of the photovoltaic panels and environmental parameters; based on the current node dependency graph, a dynamic simulation is run to obtain simulation data, and according to the simulation data, the inverter output is adjusted in real time to obtain a matching optimization result; based on the matching optimization result, a genetic algorithm optimization is performed to obtain an optimized power conditioner parameter configuration, and based on the optimized power conditioner parameter configuration, a system load balancing test is performed to obtain a system load balancing result; based on the system load balancing result, a real-time feedback adjustment is performed on the photovoltaic system to obtain an optimized output configuration of the photovoltaic system. The scheme of this embodiment realizes accurate adjustment of power output by deeply analyzing the relationship between the output power of photovoltaic panels and environmental parameters; dynamically simulates the future scenarios of photovoltaic output and power demand, and adjusts the inverter output in advance to ensure the matching between supply and demand; optimizes the power regulator parameters by genetic algorithm to improve the system's adaptive adjustment ability and energy utilization efficiency; further, based on the optimized power regulator parameter configuration, the system load balancing test is performed to obtain the system load balancing result; based on the system load balancing result, the photovoltaic system is subjected to real-time feedback adjustment to obtain the optimized output configuration of the photovoltaic system, and the real-time monitoring and parameter adjustment of the output deviation are realized, which not only enhances the reliability of the system, but also promotes the reduction of energy costs and the overall optimization of system performance. Therefore, the scheme of this embodiment can accurately predict future energy demand and optimize resource allocation according to the real-time data of each node, thereby improving the accuracy and reliability of load regulation.

[0109] The photovoltaic-based load regulation device provided by the present invention is described below. The photovoltaic-based load regulation device described below and the photovoltaic-based load regulation method described above can be referred to each other.

[0110] The device provided in this embodiment is applied to a photovoltaic system, which includes a plurality of nodes, an inverter, and a power conditioner.

[0111] Figure 3 is a schematic diagram of the structure of the photovoltaic-based load regulation device provided by the present invention, such as Figure 3 As shown, the photovoltaic-based load regulation device includes: a data association module 31 , a dynamic simulation module 32 , an output adjustment module 33 , an algorithm optimization module 34 , a load balancing test module 35 and a feedback adjustment module 36 .

[0112] The data association module 31 is used to generate a current node dependency graph based on the collected real-time data of each node in the photovoltaic system; wherein the real-time data includes the output power of the photovoltaic panels and environmental parameters.

[0113] The dynamic simulation module 32 is used to run dynamic simulation based on the current node dependency graph to obtain simulation data.

[0114] The output adjustment module 33 is used to adjust the inverter output in real time according to the simulation data to obtain a matching optimization result.

[0115] The algorithm optimization module 34 is used to perform genetic algorithm optimization based on the matching optimization result to obtain the optimized power conditioner parameter configuration.

[0116] The load balancing test module 35 is used to perform a system load balancing test based on the optimized power conditioner parameter configuration to obtain a system load balancing result.

[0117] The feedback adjustment module 36 is used to perform real-time feedback adjustment on the photovoltaic system based on the system load balancing result to obtain an optimized output configuration of the photovoltaic system.

[0118] Optionally, in some embodiments, the data association module 31 is specifically used to: According to the collected real-time data of each node in the photovoltaic system, the correlation between the nodes in the photovoltaic system is calculated, and an initial node dependency graph is generated according to the correlation between the nodes in the photovoltaic system; Based on the initial node dependency graph and the current environment parameters, the current weight matrix between nodes is calculated; Generate the current node dependency graph based on the current weight matrix between nodes.

[0119] Optionally, in some embodiments, the dynamic simulation module 32 is specifically used to: Based on the current node dependency graph, a dynamic simulation is run to obtain the estimated output power corresponding to each time point in the preset future period.

[0120] For each time point in the preset future period, the power difference data at that time point is calculated based on the estimated output power and the real-time required power at that time point.

[0121] Optionally, in some embodiments, the output adjustment module 33 is specifically used to: According to the difference data corresponding to each time point in the preset future period, the average power difference in the preset future period is calculated; Generate an adjustment instruction according to the average power difference; The adjustment instruction is applied to the inverter, the inverter output is adjusted in real time, the adjusted inverter output power is obtained, and a matching optimization result is generated.

[0122] Optionally, in some embodiments, the algorithm optimization module 34 is specifically used to: Initialize the genetic algorithm population based on the matching optimization results; Define a fitness function and calculate the fitness score of each power conditioner parameter configuration; The crossover and mutation operations are applied to optimize the power conditioner parameter configuration, and the optimized power conditioner parameter configuration is selected according to the fitness score of each power conditioner parameter configuration.

[0123] Optionally, in some embodiments, the feedback adjustment module 36 is specifically configured to: Based on the system load balancing results, the photovoltaic system is adjusted in real time, and the deviation between the actual output of the photovoltaic system and the predicted output of the photovoltaic system is monitored; Based on the deviation value, adjusting the selection, crossover and mutation steps in the genetic algorithm to generate adjusted genetic algorithm parameters; According to the adjusted genetic algorithm parameters, the parameter optimization of the photovoltaic system is re-executed to generate the optimized output configuration of the photovoltaic system.

[0124] In addition, in some embodiments, the photovoltaic-based load regulation device further includes: a preprocessing module for normalizing the real-time data of each node in the photovoltaic system.

[0125] The scheme of this embodiment realizes accurate adjustment of power output by deeply analyzing the relationship between the output power of photovoltaic panels and environmental parameters; dynamically simulates the future scenarios of photovoltaic output and power demand, and adjusts the inverter output in advance to ensure the matching between supply and demand; optimizes the power regulator parameters by genetic algorithm to improve the system's adaptive adjustment ability and energy utilization efficiency; further, based on the optimized power regulator parameter configuration, the system load balancing test is performed to obtain the system load balancing result; based on the system load balancing result, the photovoltaic system is subjected to real-time feedback adjustment to obtain the optimized output configuration of the photovoltaic system, and the real-time monitoring and parameter adjustment of the output deviation are realized, which not only enhances the reliability of the system, but also promotes the reduction of energy costs and the overall optimization of system performance. Therefore, the scheme of this embodiment can accurately predict future energy demand and optimize resource allocation according to the real-time data of each node, thereby improving the accuracy and reliability of load regulation.

[0126] Figure 4 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the photovoltaic-based load regulation method, which includes: generating a current node dependency graph based on the collected real-time data of each node in the photovoltaic system; wherein the real-time data includes the output power and environmental parameters of the photovoltaic panels; based on the current node dependency graph, running a dynamic simulation to obtain simulation data, and adjusting the inverter output in real time according to the simulation data to obtain a matching optimization result; based on the matching optimization result, performing genetic algorithm optimization to obtain an optimized power conditioner parameter configuration, and based on the optimized power conditioner parameter configuration, performing a system load balancing test to obtain a system load balancing result; based on the system load balancing result, performing real-time feedback adjustment on the photovoltaic system to obtain an optimized output configuration of the photovoltaic system.

[0127] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0128] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the photovoltaic-based load regulation method provided by the above-mentioned methods, and the method includes: generating a current node dependency graph based on the collected real-time data of each node in the photovoltaic system; wherein the real-time data includes the output power and environmental parameters of the photovoltaic panels; based on the current node dependency graph, running a dynamic simulation to obtain simulation data, and based on the simulation data, adjusting the inverter output in real time to obtain a matching optimization result; based on the matching optimization result, performing genetic algorithm optimization to obtain an optimized power conditioner parameter configuration, and based on the optimized power conditioner parameter configuration, performing a system load balancing test to obtain a system load balancing result; based on the system load balancing result, performing real-time feedback adjustment on the photovoltaic system to obtain an optimized output configuration of the photovoltaic system.

[0129] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the photovoltaic-based load regulation method provided by the above-mentioned methods, the method comprising: generating a current node dependency graph based on the collected real-time data of each node in the photovoltaic system; wherein the real-time data includes the output power and environmental parameters of the photovoltaic panels; based on the current node dependency graph, running a dynamic simulation to obtain simulation data, and based on the simulation data, making real-time adjustments to the inverter output to obtain matching optimization results; based on the matching optimization results, performing genetic algorithm optimization to obtain an optimized power conditioner parameter configuration, and based on the optimized power conditioner parameter configuration, performing a system load balancing test to obtain a system load balancing result; based on the system load balancing result, performing real-time feedback adjustment on the photovoltaic system to obtain an optimized output configuration of the photovoltaic system.

[0130] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A photovoltaic-based load regulation method, characterized in that: Applied to a photovoltaic system, the photovoltaic system includes a plurality of nodes, an inverter and a power conditioner; the method includes: Generate a current node dependency graph based on the collected real-time data of each node in the photovoltaic system; wherein the real-time data includes the output power of the photovoltaic panels and environmental parameters; Based on the current node dependency graph, a dynamic simulation is run to obtain simulation data, and according to the simulation data, the inverter output is adjusted in real time to obtain a matching optimization result; Based on the matching optimization result, a genetic algorithm optimization is performed to obtain an optimized power regulator parameter configuration, and based on the optimized power regulator parameter configuration, a system load balancing test is performed to obtain a system load balancing result; Based on the system load balancing result, real-time feedback adjustment is performed on the photovoltaic system to obtain an optimized output configuration of the photovoltaic system.

2. The photovoltaic-based load regulation method according to claim 1, characterized in that: The method generates a current node dependency graph based on the collected real-time data of each node in the photovoltaic system, including: According to the collected real-time data of each node in the photovoltaic system, the correlation between the nodes in the photovoltaic system is calculated, and an initial node dependency graph is generated according to the correlation between the nodes in the photovoltaic system; Based on the initial node dependency graph and according to current environment parameters, a current weight matrix between nodes is calculated; A current node dependency graph is generated according to the current weight matrix between the nodes.

3. The photovoltaic-based load regulation method according to claim 1, characterized in that: The simulation data includes: estimated output power and power difference data at each time point in a preset future period; the simulation data obtained by running dynamic simulation based on the current node dependency graph includes: Based on the current node dependency graph, a dynamic simulation is run to obtain an estimated output power corresponding to each time point in a preset future period; For each time point in a preset future time period, the power difference data at the time point is calculated based on the estimated output power and the real-time required power at the time point.

4. The photovoltaic-based load regulation method according to claim 3, characterized in that: The step of adjusting the inverter output in real time according to the simulation data to obtain a matching optimization result includes: According to the difference data corresponding to each time point in the preset future period, the average power difference in the preset future period is calculated; generating an adjustment instruction according to the average power difference; The adjustment instruction is applied to the inverter, the inverter output is adjusted in real time, the adjusted inverter output power is obtained, and the matching optimization result is generated.

5. The photovoltaic-based load regulation method according to claim 1, characterized in that: The genetic algorithm optimization is performed based on the matching optimization result to obtain the optimized power regulator parameter configuration, including: Initializing a genetic algorithm population based on the matching optimization result; Define a fitness function and calculate the fitness score of each power conditioner parameter configuration; The power conditioner parameter configuration is optimized by applying crossover and mutation operations, and the optimized power conditioner parameter configuration is selected according to the fitness score of each power conditioner parameter configuration.

6. The photovoltaic-based load regulation method according to claim 1, characterized in that: The method of performing real-time feedback adjustment on the photovoltaic system based on the system load balancing result to obtain an optimized output configuration of the photovoltaic system includes: Based on the system load balancing result, real-time feedback adjustment is performed on the photovoltaic system, and a deviation value between an actual output of the photovoltaic system and a predicted output of the photovoltaic system is monitored; Based on the deviation value, adjusting the selection, crossover and mutation steps in the genetic algorithm to generate adjusted genetic algorithm parameters; According to the adjusted genetic algorithm parameters, the parameter optimization of the photovoltaic system is re-executed to generate an optimized output configuration of the photovoltaic system.

7. The photovoltaic-based load regulation method according to any one of claims 1 to 6, characterized in that: Before generating the current node dependency graph based on the collected real-time data of each node in the photovoltaic system, the method further includes: The real-time data of each node in the photovoltaic system is normalized.

8. A photovoltaic-based load regulation device, characterized in that: Applied to a photovoltaic system, the photovoltaic system includes a plurality of nodes, an inverter and a power regulator; the device includes: A data association module is used to generate a current node dependency graph based on the collected real-time data of each node in the photovoltaic system; wherein the real-time data includes the output power of the photovoltaic panels and environmental parameters; A dynamic simulation module, used to run dynamic simulation based on the current node dependency graph to obtain simulation data; An output adjustment module, used to adjust the inverter output in real time according to the simulation data to obtain a matching optimization result; An algorithm optimization module, used for performing genetic algorithm optimization based on the matching optimization result to obtain an optimized power regulator parameter configuration; A load balancing test module, used to perform a system load balancing test based on the optimized power regulator parameter configuration to obtain a system load balancing result; The feedback adjustment module is used to perform real-time feedback adjustment on the photovoltaic system based on the system load balancing result to obtain an optimized output configuration of the photovoltaic system.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the photovoltaic-based load regulation method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the photovoltaic-based load regulation method according to any one of claims 1 to 7 is implemented.

Images