A multi-objective collaborative optimization control method for photovoltaic inverters

Abstract

The present invention provides a multi-objective collaborative optimization control method for a photovoltaic inverter, which relates to the field of collaborative control technology, and includes: obtaining the optimization type that a photovoltaic inverter needs to be collaboratively controlled to obtain a first optimization target set; establishing an initial target optimization model based on the first optimization target set, and optimizing the initial target optimization model based on the historical performance of the photovoltaic inverter to obtain a first target optimization model; obtaining a historical operating condition set of the photovoltaic inverter, thereby extracting a key historical operating condition set, and inputting each key historical operating condition into the first target optimization model one by one for simulation; optimizing the first target optimization model based on the simulation result to obtain a second target optimization model, thereby realizing multi-objective collaborative control of the photovoltaic inverter based on the second target optimization model. By performing multi-objective collaborative control on the target photovoltaic inverter, the operating efficiency and power output quality of the photovoltaic inverter can be maximized.

Description

Technical Field

[0001] The present invention relates to the field of collaborative control technology, and in particular to a multi-objective collaborative optimization control method for a photovoltaic inverter. Background Art

[0002] At present, photovoltaic power generation, as a form of clean energy, is of great significance for improving the energy structure and solving the energy needs of remote areas.

[0003] However, as a key device in the photovoltaic power generation system, the performance of the photovoltaic inverter directly affects the power generation efficiency and power quality of the entire system. Traditional photovoltaic inverter control methods often focus on the optimization of a single goal, such as only focusing on efficiency improvement or power output stability, while ignoring other important indicators, making it difficult to achieve the overall optimal effect in practical applications.

[0004] Therefore, the present invention provides a multi-objective collaborative optimization control method for a photovoltaic inverter. Summary of the invention

[0005] The present invention provides a photovoltaic inverter multi-objective collaborative optimization control method, which is used to solve the problems of poor efficiency and weak coordination of photovoltaic inverter multi-objective control in the prior art.

[0006] The present invention provides a multi-objective collaborative optimization control method for a photovoltaic inverter, comprising:

[0007] Step 1: Obtain the optimization type of the target photovoltaic inverter that needs to be coordinated and controlled, and obtain the first optimization target set;

[0008] Step 2: Establishing a corresponding initial target optimization model based on the first optimization target set, and optimizing the initial target optimization model based on the historical performance of the target photovoltaic inverter to obtain a first target optimization model;

[0009] Step 3: Obtain a historical operating condition set of the target photovoltaic inverter, thereby extracting a key historical operating condition set, and input each key historical operating condition in the key historical operating condition set into the first target optimization model one by one for simulation;

[0010] Step 4: Optimize the first objective optimization model based on the simulation results to obtain the second objective optimization model, thereby realizing multi-objective coordinated control of the photovoltaic inverter based on the second objective optimization model.

[0011] The target photovoltaic inverter provided according to the present invention needs to be optimized for coordinated control, including: efficiency, power density, special cost and predicted life of the switch tube.

[0012] According to the present invention, a corresponding initial target optimization model is established based on the first optimization target set, and the initial target optimization model is optimized based on the historical performance of the target photovoltaic inverter to obtain a first target optimization model, including:

[0013] Step 21: establishing a corresponding objective function based on each first optimization objective in the first optimization objective set, thereby obtaining a first objective function set;

[0014] Step 22: constructing an initial target optimization model of the target photovoltaic inverter based on the first objective function set;

[0015] Step 23: Obtain historical performance parameters of each first optimization target in the first optimization target set and historical operating parameters of the target photovoltaic inverter;

[0016] Step 24: Input the historical performance parameters and historical working parameters into the initial target optimization model for model optimization to obtain the first target optimization model.

[0017] According to the present invention, historical performance parameters and historical working parameters are input into the initial target optimization model for model optimization to obtain a first target optimization model, including:

[0018] Step 241: Match the historical performance parameters and the historical working parameters according to the corresponding historical moments to obtain a first historical performance set;

[0019] Step 242: input each first historical working parameter in the first historical performance set into the initial target optimization model to obtain a first historical performance parameter;

[0020] Step 243: adjusting the initial target optimization model based on the parameter difference between each first historical performance parameter and the corresponding historical performance parameter, thereby obtaining a first target optimization model of the target photovoltaic inverter.

[0021] According to the present invention, a historical operating condition set of a target photovoltaic inverter is obtained, thereby extracting a key historical operating condition set, and each key historical operating condition in the key historical operating condition set is input into a first target optimization model one by one for simulation, including:

[0022] Step 31: Obtain the historical operating conditions of the target photovoltaic inverter during its historical working process to obtain a historical operating condition set;

[0023] Step 32: Compare the operating condition similarity of each historical operating condition in the historical operating condition set with the remaining historical operating conditions in the historical operating condition set to obtain a historical operating condition similarity matrix;

[0024] ;in, is the similarity between the i-th historical operating condition and the remaining historical operating conditions in the historical operating condition set, is the parameter value of the jth historical parameter of the i-th historical condition, is the parameter value of the jth historical parameter of the kth historical condition, is the parameter conversion coefficient of the jth historical parameter of the i-th historical condition, is the weight factor of the influence of the parameter type corresponding to the jth historical parameter on the historical working condition, The parameter acquisition error of the jth historical parameter of the i-th historical condition, is the error compensation index, ni is the number of parameters of the historical parameters of the ith historical operating condition, m is the number of historical operating conditions, and exp is the base of the natural logarithm;

[0025] Among them, each row of the historical operating condition similarity matrix corresponds to the same historical operating condition;

[0026] Step 33: based on the historical operating condition similarity requirement, the invalid operating condition similarities in the historical operating condition similarity matrix are eliminated to obtain a second historical operating condition similarity matrix;

[0027] Step 34: comparing the historical operating condition similarities of each row in the second historical operating condition similarity matrix, thereby eliminating the historical operating condition similarities with operating condition similarities higher than a preset similarity value, thereby eliminating the historical operating conditions corresponding to the eliminated historical similarities, and obtaining a key historical operating condition set;

[0028] Step 35: Input each key historical operating condition in the key historical operating condition set into the first target optimization model for simulation, and obtain a first simulation control result corresponding to the current historical operating condition.

[0029] According to the present invention, the historical performance corresponding to each key historical working condition is input into the first target optimization model for simulation to obtain the first simulation control result, including:

[0030] Step 351: input each key historical operating condition into the first target optimization model to obtain a first simulation control sub-result;

[0031] Step 352: classify the key historical operating conditions in the key historical operating condition set according to the comprehensive operating conditions to obtain a first classified operating condition set;

[0032] Step 353: obtaining a first simulation control subset based on the first simulation control sub-result corresponding to each first classification operating condition subset in the first classification operating condition set;

[0033] Step 354: synthesizing the simulation results of the target photovoltaic inverter in the first simulation control subset to obtain a comprehensive simulation control sub-result of the corresponding subset;

[0034] Step 355: synthesize the integrated simulation control sub-results of each simulation control sub-set to obtain a first simulation control result of the target photovoltaic inverter.

[0035] According to the present invention, the first objective optimization model is optimized based on the simulation result to obtain the second objective optimization model, so as to realize multi-objective coordinated control of the photovoltaic inverter based on the second objective optimization model, including:

[0036] Step 41: obtaining the real-time working condition of the target photovoltaic inverter, and comparing the real-time working condition with the historical working condition one by one to obtain a first working condition similarity set between the real-time working condition and each historical working condition;

[0037] Step 42: extracting the first operating condition similarity with the highest first operating condition similarity in the first operating condition similarity set, and inputting the corresponding historical operating condition into the first target optimization model to obtain a first historical simulation result;

[0038] Step 43: obtaining a historical control result of the photovoltaic inverter corresponding to the historical working condition, and comparing the historical control result with the first historical simulation result, so as to adjust a first parameter of the first objective optimization model;

[0039] Step 44: initially optimizing the first target optimization model based on the first parameter to obtain a first optimization simulation model under the corresponding working condition;

[0040] Step 45: performing simulation based on the first optimized simulation model to obtain a second simulation control result;

[0041] Step 46: Compare the second simulation control result with the standard control result to obtain a first difference value;

[0042] Step 47: Compare the first difference value with the difference value in the difference-strategy database, thereby determining a first optimization strategy corresponding to the first difference value;

[0043] Step 48: Optimizing the first optimization simulation model based on the first optimization strategy to obtain a second target optimization model;

[0044] Step 49: Perform multi-objective coordinated control of the photovoltaic inverter based on the second objective optimization model.

[0045] After the multi-objective coordinated control of the photovoltaic inverter provided by the present invention, the method includes: real-time monitoring of the coordinated control result, specifically including:

[0046] Step 51: obtaining real-time operating parameters and real-time performance parameters of the target photovoltaic inverter after multi-objective coordinated control;

[0047] Step 52: Obtain standard operating parameters and standard performance parameters of the target photovoltaic inverter under real-time working conditions;

[0048] Step 53: performing a first comparison between the standard working parameters and the real-time working parameters, and performing a second comparison between the standard performance parameters and the real-time performance parameters;

[0049] Step 54: The first comparison result and the second comparison result are combined to determine the real-time performance of the multi-objective coordinated control of the target photovoltaic inverter, thereby optimizing and adjusting the second objective optimization model based on the real-time performance.

[0050] Compared with the prior art, the beneficial effects of the present invention are as follows: a multi-objective collaborative optimization control method for a photovoltaic inverter provided by the present invention can maximize the operating efficiency and power output quality of the photovoltaic inverter by performing multi-objective collaborative control on the target photovoltaic inverter, and can also greatly extend the life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] 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.

[0052] Figure 1 It is a flow chart of a multi-objective collaborative optimization control method for a photovoltaic inverter provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] 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.

[0054] Embodiment 1:

[0055] The embodiment of the present invention provides a multi-objective collaborative optimization control method for a photovoltaic inverter, such as Figure 1 As shown, including:

[0056] Step 1: Obtain the optimization type of the target photovoltaic inverter that needs to be coordinated and controlled, and obtain the first optimization target set;

[0057] Step 2: Establishing a corresponding initial target optimization model based on the first optimization target set, and optimizing the initial target optimization model based on the historical performance of the target photovoltaic inverter to obtain a first target optimization model;

[0058] Step 3: Obtain a historical operating condition set of the target photovoltaic inverter, thereby extracting a key historical operating condition set, and input each key historical operating condition in the key historical operating condition set into the first target optimization model one by one for simulation;

[0059] Step 4: Optimize the first objective optimization model based on the simulation results to obtain the second objective optimization model, thereby realizing multi-objective coordinated control of the photovoltaic inverter based on the second objective optimization model.

[0060] In this embodiment, the optimization types include efficiency, power density, specific cost and predicted life of the switch tube.

[0061] In this embodiment, the first optimization target set refers to an optimization target set obtained by integrating the optimization types that the target photovoltaic inverter needs to be collaboratively controlled.

[0062] In this embodiment, the initial target optimization model is a corresponding target optimization model constructed by obtaining a standard optimization function based on the optimization target of each optimization type in the first optimization target set.

[0063] In this embodiment, the historical performance refers to the performance of parameters such as the working state and working performance of the target photovoltaic inverter during the historical working process.

[0064] In this embodiment, the first target optimization model refers to a target optimization model obtained by optimizing the initial target optimization model based on the historical performance of the target photovoltaic inverter.

[0065] In this embodiment, the historical operating condition set refers to the external operating conditions of the target photovoltaic inverter during the historical working process. For example, the historical operating conditions include: external temperature, humidity, pressure, wind force, height from the ground and other operating condition types.

[0066] In this embodiment, the key historical operating condition set refers to a set of historical operating conditions remaining after removing historical operating conditions with high operating condition similarity in the historical operating condition set. Constructing the historical operating condition set for simulation can reduce data redundancy and improve simulation efficiency.

[0067] In this embodiment, the second objective optimization model refers to a model obtained by comparing the simulation results with standard performance parameters and standard operating parameters under corresponding working conditions, thereby optimizing the first objective optimization model based on the comparison differences.

[0068] The beneficial effect of the above technical solution is: by constructing a target optimization model of the target photovoltaic inverter, model optimization and simulation are carried out, so that the target optimization model can better meet the actual working conditions, thereby performing multi-objective collaborative control, which can maximize the operating efficiency and power output quality of the photovoltaic inverter, and at the same time can greatly extend the life of the equipment.

[0069] Embodiment 2:

[0070] Based on Example 1, the target photovoltaic inverter needs to perform coordinated control optimization types including: efficiency, power density, special cost and predicted life of the switch tube.

[0071] The beneficial effect of the above technical solution is: by constructing a target optimization model of the corresponding optimization type based on the optimization type of collaborative control of the target photovoltaic inverter, and then performing model optimization and simulation, the target optimization model can better meet the actual working conditions, thereby performing multi-objective collaborative control.

[0072] Embodiment 3:

[0073] Based on Example 1, a corresponding initial target optimization model is established based on the first optimization target set, and the initial target optimization model is optimized based on the historical performance of the target photovoltaic inverter to obtain a first target optimization model, including:

[0074] Step 21: establishing a corresponding objective function based on each first optimization objective in the first optimization objective set, thereby obtaining a first objective function set;

[0075] Step 22: constructing an initial target optimization model of the target photovoltaic inverter based on the first objective function set;

[0076] Step 23: Obtain historical performance parameters of each first optimization target in the first optimization target set and historical operating parameters of the target photovoltaic inverter;

[0077] Step 24: Input the historical performance parameters and historical working parameters into the initial target optimization model for model optimization to obtain the first target optimization model.

[0078] In this embodiment, the first optimization target set refers to an optimization target set obtained by integrating the optimization types that the target photovoltaic inverter needs to be collaboratively controlled.

[0079] In this embodiment, the first optimization target includes an efficiency target, a power density target, a special cost target, and a switch tube life target, which are equal to optimization targets related to the working performance of the photovoltaic inverter.

[0080] In this embodiment, the first objective function set is based on each first optimization objective to establish a corresponding objective function, thereby obtaining a set of objective functions.

[0081] In this embodiment, the initial target optimization model is a corresponding target optimization model constructed by obtaining a standard optimization function based on the optimization target of each optimization type in the first optimization target set.

[0082] In this embodiment, the historical performance parameters refer to the historical performance parameters of the parameters of the optimization type corresponding to each first optimization target of the photovoltaic inverter. For example, the historical performance parameters corresponding to the switch tube life target of the photovoltaic inverter include: switch tube life parameter, effective working time parameter, and working stability parameter for each effective working time.

[0083] In this embodiment, the historical operating parameters refer to the operating parameters of the photovoltaic inverter during the historical working process, wherein the historical operating parameters include output power, output voltage, overall efficiency, frequency, waveform distortion, load power factor and other parameters.

[0084] In this embodiment, the first target optimization model refers to a target optimization model obtained by optimizing the initial target optimization model based on the historical performance of the target photovoltaic inverter.

[0085] The beneficial effect of the above technical solution is: by inputting the historical performance of the photovoltaic inverter into the initial target optimization model, the initial target optimization model is optimized, so that the optimized first target optimization model can better meet the actual working conditions, thereby performing multi-target collaborative control.

[0086] Embodiment 4:

[0087] Based on Example 3, historical performance parameters and historical working parameters are input into the initial target optimization model for model optimization to obtain a first target optimization model, including:

[0088] Step 241: Match the historical performance parameters and the historical working parameters according to the corresponding historical moments to obtain a first historical performance set;

[0089] Step 242: input each first historical working parameter in the first historical performance set into the initial target optimization model to obtain a first historical performance parameter;

[0090] Step 243: adjusting the initial target optimization model based on the parameter difference between each first historical performance parameter and the corresponding historical performance parameter, thereby obtaining a first target optimization model of the target photovoltaic inverter.

[0091] In this embodiment, matching the historical performance parameters and the historical operating parameters according to the corresponding historical moments refers to matching the historical performance parameters and the historical operating parameters of the target photovoltaic inverter at the same historical moment, wherein the historical performance parameters and the historical operating parameters at the same historical moment are matched to obtain the first historical performance.

[0092] In this embodiment, the first historical performance set refers to a historical performance set obtained by integrating the first historical performance at each historical moment.

[0093] In this embodiment, the first historical performance parameter refers to the output parameter obtained after each first historical working parameter in the first historical performance set is input into the initial target optimization model. The first historical performance is compared with the historical performance parameters at the corresponding historical moment, so that the initial target optimization model can be optimized and adjusted.

[0094] In this embodiment, the first target optimization model refers to a target optimization model obtained by optimizing the initial target optimization model based on the historical performance of the target photovoltaic inverter.

[0095] The beneficial effect of the above technical solution is: by inputting the historical performance of the photovoltaic inverter into the initial target optimization model, the initial target optimization model is optimized, so that the optimized first target optimization model can better meet the actual working conditions, thereby performing multi-target collaborative control.

[0096] Embodiment 5:

[0097] Based on Example 3, a historical operating condition set of the target photovoltaic inverter is obtained, thereby extracting a key historical operating condition set, and each key historical operating condition in the key historical operating condition set is input into the first target optimization model one by one for simulation, including:

[0098] Step 31: Obtain the historical operating conditions of the target photovoltaic inverter during its historical working process to obtain a historical operating condition set;

[0099] Step 32: Compare the operating condition similarity of each historical operating condition in the historical operating condition set with the remaining historical operating conditions in the historical operating condition set to obtain a historical operating condition similarity matrix;

[0100] ;in, is the similarity between the i-th historical operating condition and the remaining historical operating conditions in the historical operating condition set, is the parameter value of the jth historical parameter of the i-th historical condition, is the parameter value of the jth historical parameter of the kth historical condition, is the parameter conversion coefficient of the jth historical parameter of the i-th historical condition, is the weight factor of the influence of the parameter type corresponding to the jth historical parameter on the historical working condition, The parameter acquisition error of the jth historical parameter of the i-th historical condition, is the error compensation index, ni is the number of parameters of the historical parameters of the ith historical operating condition, m is the number of historical operating conditions, and exp is the base of the natural logarithm;

[0101] Among them, each row of the historical operating condition similarity matrix corresponds to the same historical operating condition;

[0102] Step 33: based on the historical operating condition similarity requirement, the invalid operating condition similarities in the historical operating condition similarity matrix are eliminated to obtain a second historical operating condition similarity matrix;

[0103] Step 34: comparing the historical operating condition similarities of each row in the second historical operating condition similarity matrix, thereby eliminating the historical operating condition similarities with operating condition similarities higher than a preset similarity value, thereby eliminating the historical operating conditions corresponding to the eliminated historical similarities, and obtaining a key historical operating condition set;

[0104] Step 35: Input each key historical operating condition in the key historical operating condition set into the first target optimization model for simulation, and obtain a first simulation control result corresponding to the current historical operating condition.

[0105] In this embodiment, the historical operating condition set refers to the external operating conditions of the target photovoltaic inverter during the historical working process. For example, the historical operating conditions include: external temperature, humidity, pressure, wind force, height from the ground and other operating condition types.

[0106] In this embodiment, the historical operating condition similarity refers to the similarity between each historical operating condition in the historical operating condition set, wherein the historical operating condition similarity is comprehensively determined based on the similarities of different historical parameters of each historical operating condition.

[0107] In this embodiment, the historical operating condition similarity matrix is ​​a matrix containing the operating condition similarities between each historical operating condition in the historical operating condition set, wherein each row of the historical operating condition similarity represents the operating condition similarity between the same historical operating condition and each remaining historical operating condition in the historical operating condition set, and each column of the historical operating condition similarity represents the operating condition similarity between the same historical operating condition and each remaining historical operating condition in the historical operating condition set.

[0108] In this embodiment, the second historical operating condition similarity matrix refers to the operating condition similarity matrix obtained after eliminating invalid operating condition similarities in the historical operating condition similarity matrix. For example, the similarity of the same historical operating condition in the historical operating condition similarity matrix is ​​1, that is, the historical operating condition similarity on the diagonal of the historical similarity matrix is ​​1, and it belongs to invalid operating condition similarity. Based on the fact that the historical operating condition similarities corresponding to the diagonal of the historical operating condition similarity matrix are the same, the historical operating condition similarities below the diagonal of the historical similarity matrix can be eliminated. Therefore, the historical operating condition similarities below the diagonal of the historical similarity matrix also belong to invalid operating condition similarity.

[0109] In this embodiment, the key historical operating condition set refers to a set of historical operating conditions remaining after removing historical operating conditions with high operating condition similarity in the historical operating condition set. Constructing the historical operating condition set for simulation can reduce data redundancy and improve simulation efficiency.

[0110] In this embodiment, the first simulation control result is obtained by inputting each key historical operating condition in the key historical operating condition set into the first target optimization model for simulation, and obtaining the first simulation control result corresponding to each historical operating condition.

[0111] The beneficial effect of the above technical solution is: by simulating the working conditions of the photovoltaic inverter under different historical working conditions and comparing them with the performance parameters under the corresponding historical working conditions, the first target optimization model can be optimized more accurately, so that the optimized model can better meet the needs of different working conditions and improve the working efficiency of the target photovoltaic inverter.

[0112] Embodiment 6:

[0113] Based on Example 5, a first simulation control result is obtained, including:

[0114] Step 351: input each key historical operating condition into the first target optimization model to obtain a first simulation control sub-result;

[0115] Step 352: classify the key historical operating conditions in the key historical operating condition set according to the comprehensive operating conditions to obtain a first classified operating condition set;

[0116] Step 353: obtaining a first simulation control subset based on the first simulation control sub-result corresponding to each first classification operating condition subset in the first classification operating condition set;

[0117] Step 354: synthesizing the simulation results of the target photovoltaic inverter in the first simulation control subset to obtain a comprehensive simulation control sub-result of the corresponding subset;

[0118] Step 355: synthesize the integrated simulation control sub-results of each simulation control sub-set to obtain a first simulation control result of the target photovoltaic inverter.

[0119] In this embodiment, the first simulation control sub-result is a simulation control result obtained by inputting each key historical operating condition into the first target optimization model.

[0120] In this embodiment, the first classified operating condition set is classified according to the differences in the key historical operating conditions corresponding to the comprehensive operating conditions in the key historical operating condition set to obtain a first classified operating condition subset set, and then each first classified operating condition subset is combined to obtain a first classified operating condition set, wherein each first classified operating condition subset is classified based on the similarity of corresponding historical parameters.

[0121] In this embodiment, the first simulation control subset is a combination of simulation control results obtained after simulation of each first classification operating condition in the first classification operating condition set.

[0122] The beneficial effect of the above technical solution is: by simulating the working conditions of the photovoltaic inverter under different historical working conditions and comparing them with the performance parameters under the corresponding historical working conditions, the first target optimization model can be optimized more accurately, so that the optimized model can better meet the needs of different working conditions and improve the working efficiency of the target photovoltaic inverter.

[0123] Embodiment 7:

[0124] Based on Example 5, the first objective optimization model is optimized based on the simulation results to obtain a second objective optimization model, thereby realizing multi-objective coordinated control of the photovoltaic inverter based on the second objective optimization model, including:

[0125] Step 41: obtaining the real-time working condition of the target photovoltaic inverter, and comparing the real-time working condition with the historical working condition one by one to obtain a first working condition similarity set between the real-time working condition and each historical working condition;

[0126] Step 42: extracting the first operating condition similarity with the highest first operating condition similarity in the first operating condition similarity set, and inputting the corresponding historical operating condition into the first target optimization model to obtain a first historical simulation result;

[0127] Step 43: obtaining a historical control result of the photovoltaic inverter corresponding to the historical working condition, and comparing the historical control result with the first historical simulation result, so as to adjust a first parameter of the first objective optimization model;

[0128] Step 44: initially optimizing the first target optimization model based on the first parameter to obtain a first optimization simulation model under the corresponding working condition;

[0129] Step 45: performing simulation based on the first optimized simulation model to obtain a second simulation control result;

[0130] Step 46: Compare the second simulation control result with the standard control result to obtain a first difference value;

[0131] Step 47: Compare the first difference value with the difference value in the difference-strategy database, thereby determining a first optimization strategy corresponding to the first difference value;

[0132] Step 48: Optimizing the first optimization simulation model based on the first optimization strategy to obtain a second target optimization model;

[0133] Step 49: Perform multi-objective coordinated control of the photovoltaic inverter based on the second objective optimization model.

[0134] In this embodiment, the real-time operating conditions include real-time performance parameters and real-time working parameters.

[0135] In this embodiment, the first operating condition similarity set is a set formed by comparing the similarity between the real-time operating condition and each historical operating condition in the historical operating condition set, thereby determining the similarity between the real-time operating condition and each historical operating condition. For example, the first operating condition similarity set is {0.61, 0.58, 0.30, 0.23}.

[0136] In this embodiment, the first historical simulation result is a simulation result obtained by extracting the first operating condition similarity with the highest first operating condition similarity in the first operating condition similarity set, and inputting the corresponding historical operating condition into the first target optimization model.

[0137] In this embodiment, the historical control results and the corresponding control results of the target photovoltaic inverter when operating under the current historical working conditions.

[0138] In this embodiment, the first parameter refers to comparing the historical control result with the first historical simulation result one by one, extracting the sub-results with differences in the comparison results, and obtaining the model parameters related to the sub-results to obtain the first parameter.

[0139] In this embodiment, the first optimization simulation model is a target optimization model obtained by replacing parameters of corresponding parameter types in the first target optimization model based on the first parameter.

[0140] In this embodiment, the first difference value refers to the difference value between the second simulation control result and each sub-result in the standard control result.

[0141] In this embodiment, the first optimization strategy refers to selecting an optimization strategy corresponding to the difference value from a difference-strategy database based on the first difference value, thereby obtaining an optimization strategy for the first optimization simulation model of the target photovoltaic inverter.

[0142] In this embodiment, the second objective optimization model refers to a model obtained by comparing the simulation results with standard performance parameters and standard operating parameters under corresponding working conditions, thereby optimizing the first objective optimization model based on the comparison differences.

[0143] The beneficial effect of the above technical solution is: by comparing the performance parameters under the simulation corresponding to the historical working conditions, the model optimization strategy is determined, and the first target optimization model is optimized more accurately, which can improve the working efficiency of the target photovoltaic inverter.

[0144] Embodiment 8:

[0145] Based on Example 7, after the multi-objective coordinated control of the photovoltaic inverter, the method includes: real-time monitoring of the coordinated control result, specifically including:

[0146] Step 51: obtaining real-time operating parameters and real-time performance parameters of the target photovoltaic inverter after multi-objective coordinated control;

[0147] Step 52: Obtain standard operating parameters and standard performance parameters of the target photovoltaic inverter under real-time working conditions;

[0148] Step 53: performing a first comparison between the standard working parameters and the real-time working parameters, and performing a second comparison between the standard performance parameters and the real-time performance parameters;

[0149] Step 54: The first comparison result and the second comparison result are combined to determine the real-time performance of the multi-objective coordinated control of the target photovoltaic inverter, thereby optimizing and adjusting the second objective optimization model based on the real-time performance.

[0150] In this embodiment, the real-time operating parameters refer to parameters such as the operating speed, power, efficiency, and consumption of the target photovoltaic inverter when it is working.

[0151] In this embodiment, the real-time performance parameters refer to the state parameters of the target photovoltaic inverter when it is working. For example, the real-time performance parameters include: temperature, wear degree, stability, accuracy and other performance parameters.

[0152] In this embodiment, the first comparison refers to a corresponding comparison between the real-time working parameters and the standard working parameters, and the second comparison refers to a corresponding comparison between the real-time performance parameters and the standard performance parameters.

[0153] The beneficial effect of the above technical solution is: by monitoring the real-time status of the photovoltaic inverter after multi-objective collaborative control, the second objective optimization model can be optimized and adjusted, so that the target optimization model can better meet the working requirements of the target photovoltaic inverter, improve the working efficiency and working accuracy of the photovoltaic inverter, and also extend the life of the equipment.

[0154] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. 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 multi-objective collaborative optimization control method for a photovoltaic inverter, characterized in that: include: Step 1: Obtain the optimization type of the target photovoltaic inverter that needs to be coordinated and controlled, and obtain the first optimization target set; Step 2: Establishing a corresponding initial target optimization model based on the first optimization target set, and optimizing the initial target optimization model based on the historical performance of the target photovoltaic inverter to obtain a first target optimization model; Step 3: Obtain a historical operating condition set of the target photovoltaic inverter, thereby extracting a key historical operating condition set, and input each key historical operating condition in the key historical operating condition set into the first target optimization model one by one for simulation; Step 4: Optimize the first objective optimization model based on the simulation results to obtain a second objective optimization model, thereby realizing multi-objective coordinated control of the photovoltaic inverter based on the second objective optimization model; The process of obtaining a historical operating condition set of the target photovoltaic inverter, thereby extracting a key historical operating condition set, and inputting each key historical operating condition in the key historical operating condition set into the first target optimization model for simulation, including: Step 31: Obtain the historical operating conditions of the target photovoltaic inverter during its historical working process to obtain a historical operating condition set; Step 32: Compare the operating condition similarity of each historical operating condition in the historical operating condition set with the remaining historical operating conditions in the historical operating condition set to obtain a historical operating condition similarity matrix; ;in, is the similarity between the i-th historical operating condition and the remaining historical operating conditions in the historical operating condition set, is the parameter value of the jth historical parameter of the i-th historical condition, is the parameter value of the jth historical parameter of the kth historical condition, is the parameter conversion coefficient of the jth historical parameter of the i-th historical condition, is the weight factor of the influence of the parameter type corresponding to the jth historical parameter on the historical working condition, The parameter acquisition error of the jth historical parameter of the i-th historical condition, is the error compensation index, is the number of parameters of the historical parameters of the i-th historical operating condition, m is the number of historical operating conditions, and exp is the base of the natural logarithm; Among them, each row of the historical operating condition similarity matrix corresponds to the same historical operating condition; Step 33: based on the historical operating condition similarity requirement, the invalid operating condition similarities in the historical operating condition similarity matrix are eliminated to obtain a second historical operating condition similarity matrix; Step 34: comparing the historical operating condition similarities of each row in the second historical operating condition similarity matrix, thereby eliminating the historical operating condition similarities with operating condition similarities higher than a preset similarity value, thereby eliminating the historical operating conditions corresponding to the eliminated historical similarities, and obtaining a key historical operating condition set; Step 35: input each key historical operating condition in the key historical operating condition set into the first target optimization model for simulation, and obtain a first simulation control result corresponding to the current historical operating condition; The first objective optimization model is optimized based on the simulation results to obtain the second objective optimization model, thereby realizing multi-objective coordinated control of the photovoltaic inverter based on the second objective optimization model, including: Step 41: obtaining the real-time working condition of the target photovoltaic inverter, and comparing the real-time working condition with the historical working condition one by one to obtain a first working condition similarity set between the real-time working condition and each historical working condition; Step 42: extracting the first operating condition similarity with the highest first operating condition similarity in the first operating condition similarity set, and inputting the corresponding historical operating condition into the first target optimization model to obtain a first historical simulation result; Step 43: obtaining a historical control result of the photovoltaic inverter corresponding to the historical operating condition, and comparing the historical control result with the first historical simulation result, so as to adjust a first parameter of the first objective optimization model; Step 44: initially optimizing the first target optimization model based on the first parameter to obtain a first optimization simulation model under the corresponding working condition; Step 45: performing simulation based on the first optimized simulation model to obtain a second simulation control result; Step 46: Compare the second simulation control result with the standard control result to obtain a first difference value; Step 47: Compare the first difference value with the difference value in the difference-strategy database, thereby determining a first optimization strategy corresponding to the first difference value; Step 48: Optimizing the first optimization simulation model based on the first optimization strategy to obtain a second target optimization model; Step 49: Perform multi-objective coordinated control of the photovoltaic inverter based on the second objective optimization model.

2. A photovoltaic inverter multi-objective collaborative optimization control method according to claim 1, characterized in that: The target photovoltaic inverter needs to be optimized for coordinated control types, including efficiency, power density, special cost and predicted life of the switch tube.

3. A photovoltaic inverter multi-objective collaborative optimization control method according to claim 1, characterized in that: A corresponding initial target optimization model is established based on the first optimization target set, and the initial target optimization model is optimized based on the historical performance of the target photovoltaic inverter to obtain a first target optimization model, including: Step 21: establishing a corresponding objective function based on each first optimization objective in the first optimization objective set, thereby obtaining a first objective function set; Step 22: constructing an initial target optimization model of the target photovoltaic inverter based on the first objective function set; Step 23: Obtain historical performance parameters of each first optimization target in the first optimization target set and historical operating parameters of the target photovoltaic inverter; Step 24: Input the historical performance parameters and historical working parameters into the initial target optimization model for model optimization to obtain the first target optimization model.

4. A photovoltaic inverter multi-objective collaborative optimization control method according to claim 3, characterized in that: The historical performance parameters and historical working parameters are input into the initial target optimization model for model optimization to obtain the first target optimization model, including: Step 241: Match the historical performance parameters and the historical working parameters according to the corresponding historical moments to obtain a first historical performance set; Step 242: input each first historical working parameter in the first historical performance set into the initial target optimization model to obtain a first historical performance parameter; Step 243: adjusting the initial target optimization model based on the parameter difference between each first historical performance parameter and the corresponding historical performance parameter, thereby obtaining a first target optimization model of the target photovoltaic inverter.

5. A photovoltaic inverter multi-objective collaborative optimization control method according to claim 1, characterized in that: Each key historical operating condition in the key historical operating condition set is input into the first target optimization model for simulation, and a first simulation control result corresponding to the current historical operating condition is obtained, including: Step 351: input each key historical operating condition into the first target optimization model to obtain a first simulation control sub-result; Step 352: classify the key historical operating conditions in the key historical operating condition set according to the comprehensive operating conditions to obtain a first classified operating condition set; Step 353: obtaining a first simulation control subset based on the first simulation control sub-result corresponding to each first classification operating condition subset in the first classification operating condition set; Step 354: synthesizing the simulation results of the target photovoltaic inverter in the first simulation control subset to obtain a comprehensive simulation control sub-result of the corresponding subset; Step 355: synthesize the integrated simulation control sub-results of each simulation control sub-set to obtain a first simulation control result of the target photovoltaic inverter.

6. A photovoltaic inverter multi-objective collaborative optimization control method according to claim 1, characterized in that: After the multi-objective coordinated control of the photovoltaic inverter, the coordinated control results are monitored in real time, including: Step 51: obtaining real-time operating parameters and real-time performance parameters of the target photovoltaic inverter after multi-objective coordinated control; Step 52: Obtain standard operating parameters and standard performance parameters of the target photovoltaic inverter under real-time working conditions; Step 53: performing a first comparison between the standard working parameters and the real-time working parameters, and performing a second comparison between the standard performance parameters and the real-time performance parameters; Step 54: The first comparison result and the second comparison result are combined to determine the real-time performance of the multi-objective coordinated control of the target photovoltaic inverter, thereby optimizing and adjusting the second objective optimization model based on the real-time performance.

Images