An intelligent operation monitoring method for a photovoltaic power station

Abstract

The present application relates to the field of photovoltaic power station operation monitoring, and particularly relates to a kind of photovoltaic power station intelligent operation monitoring method.First, the multi-dimensional parameter data of the component collected is normalized, the normalized multi-dimensional parameter data of the component is obtained, and the power response ratio, historical operation stability index and external environmental disturbance factor of the component are calculated, a comprehensive health state evaluation formula is constructed, and the state index of the component is obtained.Then, based on the state index of the component, the scheduling adaptation coefficient of the component and the proportion of abnormal components of the subarray to which the component belongs are calculated.Based on the scheduling adaptation coefficient of the component, the normalized scheduling weight of the subarray is calculated.Finally, based on the proportion of abnormal components of the subarray and the normalized scheduling weight, the final output adjustment factor of the subarray is calculated, and the adjusted guide power of the subarray is obtained.The technical problems of power output fluctuation judgment distortion, component abnormality cannot be isolated in time and subarray operation strategy lag are solved.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power plant operation monitoring, and in particular to an intelligent operation monitoring method for photovoltaic power plants. Background Technology

[0002] With the rapid development of renewable energy, photovoltaic (PV) power generation systems, as an important form of green energy, have been widely used, especially in large-scale ground-mounted PV power plants. These plants have large installed capacity, long operating cycles, and strong environmental adaptability, placing higher demands on operational stability and power generation efficiency. Currently, PV power plants generally adopt a distributed array layout, with each subarray consisting of several PV modules connected to the grid through a combiner and inverter system. In actual operation, PV modules are affected by factors such as manufacturing differences, aging degradation, partial shading, dust pollution, and climate change, resulting in significant differences in output performance and consequently fluctuations in the operating efficiency of the entire array and even the entire power plant. Furthermore, since most existing PV power plant operation monitoring systems are still based on traditional centralized management architectures, they can only collect electrical parameters at the combiner box or inverter level, failing to achieve real-time monitoring and refined management of the status of each PV module. This severely limits the granularity of fault identification and response speed in power plants with a large number of modules. Therefore, there is an urgent need to propose an intelligent operation monitoring method for PV power plants to solve the above problems. Summary of the Invention

[0003] This invention provides a method for intelligent operation monitoring of photovoltaic power plants to solve the problems of existing methods lacking refined identification and dynamic perception of the operating status of photovoltaic modules, resulting in inaccurate assessment of module-level health status, leading to distorted judgment of power output fluctuations, failure to isolate module anomalies in a timely manner, and lagging subarray operation strategies.

[0004] The present invention provides a method for intelligent operation monitoring of a photovoltaic power plant, comprising the following steps:

[0005] S1. Normalize the collected multidimensional parameter data of the components to obtain normalized multidimensional parameter data of the components; based on the normalized multidimensional parameter data of the components, obtain the power response ratio, historical operating stability index and external environmental disturbance factor of the components; based on the power response ratio, historical operating stability index and external environmental disturbance factor of the components, construct a comprehensive health status assessment formula to obtain the status index of the components.

[0006] S2. Based on the component's status indicators, obtain the component's scheduling adaptation coefficient; based on the component's scheduling adaptation coefficient, calculate the normalized scheduling weight of the subarray to which the component belongs; based on the component's status indicators, calculate the proportion of abnormal components in the subarray; based on the proportion of abnormal components in the subarray and the normalized scheduling weight, obtain the subarray's final output adjustment factor; based on the subarray's final output adjustment factor, obtain the subarray's adjusted guidance power.

[0007] Preferably, S1 specifically includes:

[0008] The power response ratio of the component is calculated based on the normalized component output voltage, normalized component output current, and normalized external environmental irradiance from the normalized multidimensional parameter data of the component.

[0009] Preferably, S1 specifically includes:

[0010] The rate of change of the power response ratio is calculated based on the component's power response ratio; the health enhancement term is calculated based on the component's power response ratio, historical operating stability indicators, and external environmental disturbance factors.

[0011] Preferably, S1 specifically includes:

[0012] The component's state indicators are calculated based on the rate of change of health enhancement terms and power response ratio.

[0013] Preferably, S2 specifically includes:

[0014] Based on the normalized multidimensional parameter data of the component, the output power of the component is calculated; based on the component's state indicators and output power, the scheduling adaptation coefficient of the component is calculated.

[0015] Preferably, S2 specifically includes:

[0016] Within the subarray to which a component belongs, the proportion of abnormal components whose status indicators are below a preset threshold is calculated based on the component's status indicators.

[0017] Preferably, S2 specifically includes:

[0018] Based on the component's status indicators, calculate the health homogeneity compensation factor; based on the health homogeneity compensation factor, combined with the subarray's normalized scheduling weight and the proportion of abnormal components, calculate the subarray's final output adjustment factor.

[0019] Preferably, S2 specifically includes:

[0020] Based on the maximum power of the acquired components, calculate the sum of the maximum power of all components in the subarray; based on the final output adjustment factor of the subarray, and combined with the sum of the maximum power of all components in the subarray, calculate the adjusted guidance power of the subarray.

[0021] The beneficial effects of the technical solution of the present invention are:

[0022] 1. By introducing a comprehensive health status assessment formula that incorporates power response ratio, rate of change of power response ratio, historical operational stability indicators, and external environmental disturbance factors, it effectively breaks away from the traditional crude method of judging component status solely based on thresholds. This enables early identification of minor degradation and potential hazards, and provides excellent pre-diagnosis and anti-misjudgment capabilities.

[0023] 2. A comprehensive health status assessment formula based on nonlinear enhancement is introduced to improve the discriminative power of component status scores. After weighting response capability and stability, an exponential amplification process is applied, significantly widening the score gap between healthy and abnormal components, avoiding the problems of score clustering and poor discrimination in traditional linear scoring models. The health score has a continuous value range and is designed with an adjustable structure. Parameter values ​​are determined through Bayesian optimization, exhibiting strong adaptability and high adjustable accuracy, effectively supporting the dynamic weighting logic in subsequent scheduling strategies.

[0024] 3. After scheduling and adapting the status indicators of all components, a normalized scheduling weight for the subarray is constructed. Through the normalization of the entire power plant, the operation priority ranking among multiple subarrays is realized, thereby providing clear operational boundary guidance in terms of power output, grid connection, and MPPT algorithm strategy execution. The proportion of abnormal components in the subarray is introduced to realize the final output adjustment factor of the subarray, which is further used to calculate the adjusted guidance power of the subarray and update the setpoint of the MPPT algorithm. This constitutes a complete closed-loop link of data acquisition → status identification → scheduling generation → control issuance, truly realizing intelligent monitoring of the real-time and accurate control capability of the underlying power control system and eliminating the inefficient structure of traditional "manual intervention + timed setting". Attached Figure Description

[0025] Figure 1 This is a flowchart of a method for intelligent operation monitoring of a photovoltaic power station according to the present invention. Detailed Implementation

[0026] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0028] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent operation monitoring method for photovoltaic power plants provided by this invention.

[0029] See attached document Figure 1 The diagram illustrates a flowchart of an intelligent operation monitoring method for a photovoltaic power plant according to an embodiment of the present invention. The method includes the following steps:

[0030] S1. Normalize the collected multidimensional parameter data of the components to obtain normalized multidimensional parameter data of the components; based on the normalized multidimensional parameter data of the components, obtain the power response ratio, historical operating stability index and external environmental disturbance factor of the components; based on the power response ratio, historical operating stability index and external environmental disturbance factor of the components, construct a comprehensive health status assessment formula to obtain the status index of the components.

[0031] By deploying multi-dimensional parameter acquisition devices such as voltage sensors, current sensors, temperature sensors, and weather sensors, multi-dimensional parameter data representing the operating status of each photovoltaic module in the photovoltaic power station are collected, capturing the current moment's data. The system collects multidimensional parameter data of the components, including component output voltage, component output current, component surface temperature, external environmental irradiance, wind speed, etc. The collected multidimensional parameter data is normalized using existing Z-score standardization to obtain normalized multidimensional parameter data, which is then expressed as the normalized component output voltage. Normalized component output current Normalized component surface temperature Normalized external environmental radiation intensity Normalized wind speed The normalized multidimensional parameter data is then stored in a normalized multidimensional parameter database for subsequent calculations.

[0032] Normalized multidimensional parameter data is used to calculate time. The power response ratio of the component is calculated using the following formula:

[0033] ,

[0034] in, It is the current moment. The power response ratio of a photovoltaic module, i.e., the power output of a photovoltaic module at the current moment. The output power capability under irradiation intensity is a normalized energy response value used to measure the ratio between the current power generation capacity of the module and the incident energy. It is the normalized output voltage of the module, that is, the terminal voltage of the photovoltaic module at the current moment, which is used to characterize its potential output capability under load connection; It is the normalized output current of the module, that is, the current in the output circuit of the photovoltaic module at the current moment, which is used to reflect the current output capability; It is the normalized external environmental irradiance, that is, the solar radiation power density that is vertically incident on the surface of the component under the current environment. To eliminate the possibility of division by zero for decimals, let's call them... ; Indicates power generation capacity; This represents the incident energy. The power response ratio (PSR) calculation formula aims to evaluate the efficiency of a photovoltaic module in responding to sunlight. The higher the PSR value, the stronger the module's energy conversion capability under the current environment.

[0035] To reflect the time-varying trend of the power response ratio, the power response ratio at time t is calculated using the existing first-order finite difference method. rate of change This refers to the degree of change in power response ratio.

[0036] At the same time, extract at time The historical operational stability index of a component is calculated using the following formula:

[0037] ,

[0038] in, Indicates the current time Historical operational stability metrics of the components; Indicates the past The power output sequence of a time window of a certain length is obtained by multiplying the historical normalized component output voltage and normalized component output current obtained from the normalized multidimensional parameter database. The time window length is specified by technical staff and can be selected. Var and Mean represent variance and mean operations, respectively. To eliminate the possibility of division by zero for decimals, let's call them... Historical operational stability metrics are used to evaluate the degree of power output fluctuation of a module within a certain time window, reflecting the stability of the module's operating state. The worse the stability, the lower the historical operational stability index. The larger.

[0039] Calculate at time The external environmental disturbance factor is calculated using the following formula:

[0040] ,

[0041] in, Indicates the current time External environmental disturbance factors; , , These represent the normalized external environmental irradiance, the normalized component surface temperature, and the normalized wind speed, respectively, and are calculated using the first-order difference method. , , They are the past The normalized external environmental irradiance, normalized component surface temperature, and normalized wind speed standard deviation for a time window of a certain length. , , These represent the weights of the normalized external environmental irradiance, normalized module surface temperature, and normalized wind speed on module performance, respectively, determined using existing attention mechanisms, with reference value ranges of [missing values]. , , The external environmental disturbance factor is used to assess the impact of rapid environmental changes on the stability of component output. The more severe the disturbance, the stronger the interference of the environment on the component output. The larger.

[0042] Furthermore, the operational health score is calculated using a comprehensive health status assessment formula, which is as follows:

[0043] ,

[0044] in, The component at the current moment The operational health score, i.e., the status indicator of the component; This is a stability index weighting coefficient used to adjust the influence of fluctuation stability. It is determined using Bayesian optimization, and the reference value range is [range to be specified]. ; It is a nonlinear gain factor used for nonlinear enhancement, amplifying the difference in health responses. It is determined using Bayesian optimization, with a reference value range of [value missing]. ; This is the response rate penalty factor, used to control the suppression of abnormal changes in the operational health score. A larger response rate penalty factor indicates greater sensitivity to fluctuations. It is determined using Bayesian optimization, and the reference value range is [insert range here]. ; Indicates power response ratio At any moment The rate of change of power response ratio; To eliminate the possibility of division by zero for decimals, let's call them... ; It is the response capability, used to represent the normalized response of the component's output power under different irradiation intensities; Indicates stability; This is a power fluctuation penalty term, used to indicate the penalty for larger fluctuations ( The higher the elevation, the smaller the environmental disturbance. The lower the score, the greater the negative impact on the operational health rating. It is a health enhancement item, which is used to comprehensively weight response capability and stability, and then apply nonlinear enhancement to amplify the difference in the distribution of operational health scores, so that healthy components score higher and abnormal components score lower. It is an overall item for abnormal suppression. As a penalty factor, it is used to effectively suppress the operational health score of high-frequency fluctuating components without affecting normal components, which facilitates anomaly investigation and scheduling control.

[0045] S2. Based on the component's status indicators, obtain the component's scheduling adaptation coefficient; based on the component's scheduling adaptation coefficient, calculate the normalized scheduling weight of the subarray to which the component belongs; based on the component's status indicators, calculate the proportion of abnormal components in the subarray; based on the proportion of abnormal components in the subarray and the normalized scheduling weight, obtain the subarray's final output adjustment factor; based on the subarray's final output adjustment factor, obtain the subarray's adjusted guidance power.

[0046] After completing the status indicators for each component After real-time evaluation, based on the subarray to which the component belongs in the photovoltaic power plant, the status indicators of all components in the subarray are summarized to construct the scheduling adaptation coefficient. A subarray is a basic operation control unit in a photovoltaic array, further subdivided according to electrical connection and arrangement. It is typically the smallest boundary controlled by existing Maximum Power Point Tracking (MPPT) algorithms or the direct unit connected to the inverter, and is predetermined by the electrical system designers. Let the first... The subarray contains The components, of which the first The status indicators of each component, namely the operational health score, are: , No. The current output power of each component is For each component, first calculate the scheduling adaptation coefficient, using the following formula:

[0047] ,

[0048] in, Indicates the first The first subarray The scheduling adaptation coefficient of each component; This is the health enhancement index weight, used to amplify the output priority of health components. It is determined through the existing scheduling control mechanism based on the exponentially weighted moving average model, with a reference value range of [value missing]. ; Indicates the first The first subarray Status indicators of each component; Indicates the first The first subarray The current output power of each component, through the current moment The normalized component output voltage and the normalized component output current are multiplied together to obtain the result. For the current moment, the first The average component output power of each subarray is used to quantify the degree of output power deviation. ; To eliminate the possibility of division by zero for decimals, let's call them... ; This indicates the degree of output power deviation. The formula for calculating the scheduling adaptation coefficient reflects the shared scheduling orientation between the operational health score and output power consistency: both high operational health and stable output are desirable.

[0049] Furthermore, calculate the first... The normalized scheduling weight of each subarray is calculated using the following formula:

[0050] ,

[0051] in, Indicates the first Normalized scheduling weights for each subarray; It is the first Number of components in each subarray: It is the number of subarrays; It is the index of the subarray; This is the sum of all scheduling adaptation coefficients for the entire photovoltaic power plant, ensuring that the scheduling weights of all subarrays are normalized; Indicates the first The first subarray The scheduling adaptation coefficient of each component.

[0052] Furthermore, according to the first The proportion of abnormal components in each subarray is adjusted. Abnormal components are those whose status indicators are below a preset threshold, which is determined in advance by the electrical system designer, such as 0.3. The formula for calculating the proportion of abnormal components is:

[0053] ,

[0054] in, Indicates the first The percentage of abnormal components in each subarray; Indicates that the statistics satisfy The number of components.

[0055] Finally, in summary The normalized scheduling weights of each subarray and the proportion of abnormal components form the first... The final output adjustment factor of each subarray is calculated using the following formula:

[0056] ,

[0057] in, Indicates the first The final output adjustment factor of each subarray; The anomaly suppression factor represents the linear penalty scheduling weight based on the anomaly ratio. It is used to adjust the degree to which the proportion of anomaly components weakens the normalized scheduling weight. It is determined using Bayesian optimization and its value ranges from [value missing]. ; Indicates the first The variance of the state indicators of each subarray; It is a health homogeneity compensation factor, representing the reciprocal of the dispersion of the operational health score. If the proportion of abnormal components in the subarray is high, the final output adjustment factor will be significantly reduced. Even if there are many originally healthy components, they will not receive excessively high output priority, thus preventing the spread of the impact of operating with defects.

[0058] Based on the output adjustment factor, the adjusted guidance power is calculated using the following formula:

[0059] ,

[0060] in, Indicates the first Adjusted guiding power for each subarray; This represents the theoretical maximum power under the current irradiance and temperature conditions, i.e., the [number]th [unit]. The sum of the maximum power of all components in the subarray, where the maximum power of each component is obtained by referring to the component's datasheet. The adjusted guide power is used to update the setpoint of the MPPT algorithm, or to set upper and lower limits for the inverter output. The final output adjustment factor... If the value falls below the preset start / stop threshold, the subarray will be considered severely faulty, and a disconnect command will be issued directly, or it will be disconnected from the inverter input. The start / stop threshold is predetermined by the electrical system designer, such as 0.15.

[0061] In summary, a method for intelligent operation monitoring of photovoltaic power plants has been developed.

[0062] The order of the embodiments is for illustrative purposes only and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0063] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0064] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for intelligent operation monitoring of a photovoltaic power station, characterized in that, Includes the following steps: S1. The collected multidimensional parameter data of the components, including component output voltage, component output current, component surface temperature, external environmental irradiance, and wind speed, are normalized to obtain the normalized multidimensional parameter data of the components. Based on the normalized component output voltage, normalized component output current, and normalized external irradiance, the power response ratio of the component is calculated to evaluate the photovoltaic module's response efficiency to light. Based on the historical normalized component output voltage and normalized component output current obtained from the normalized multidimensional parameter database, the historical operating stability index is calculated to reflect the stability of the component's operating status. Based on the normalized external environmental irradiance, normalized component surface temperature, normalized wind speed change rate and standard deviation, the external environmental disturbance factor is calculated to assess the impact of environmental changes on component output stability. Based on the component's power response ratio, historical operating stability index and external environmental disturbance factor, a comprehensive health status assessment formula is constructed, and the component's status index is calculated through health enhancement terms and penalty factors. S2. Calculate the scheduling adaptation coefficient of the component based on the component's status indicators and output power; calculate the normalized scheduling weight of the subarray to which the component belongs based on the component's scheduling adaptation coefficient. Based on the component status indicators, calculate the proportion of abnormal components in the subarray; Based on the component status indicators, the proportion of abnormal components in the subarray, and the normalized scheduling weight, the final output adjustment factor of the subarray is obtained. Based on the final output adjustment factor of the subarray, the adjusted guiding power of the subarray is obtained.

2. The intelligent operation monitoring method for a photovoltaic power station according to claim 1, characterized in that, S1 specifically includes: The rate of change of the power response ratio is calculated based on the component's power response ratio; the health enhancement term is calculated based on the component's power response ratio, historical operating stability indicators, and external environmental disturbance factors.

3. The intelligent operation monitoring method for a photovoltaic power station according to claim 2, characterized in that, S1 specifically includes: Based on the normalized rate of change of component surface temperature and power response ratio, a penalty factor is generated for anomaly detection and scheduling control; based on health enhancement terms and the penalty factor, the component's state indicators are calculated.

4. The intelligent operation monitoring method for a photovoltaic power station according to claim 1, characterized in that, S2 specifically includes: The output power of the component is calculated based on the normalized multidimensional parameter data of the component.

5. The intelligent operation monitoring method for a photovoltaic power station according to claim 1, characterized in that, S2 specifically includes: Within the subarray to which a component belongs, the proportion of abnormal components whose status indicators are below a preset threshold is calculated based on the component's status indicators.

6. The intelligent operation monitoring method for a photovoltaic power station according to claim 5, characterized in that, S2 specifically includes: Based on the variance of the component's state indicators, calculate the health homogeneity compensation factor; based on the health homogeneity compensation factor, combined with the normalized scheduling weight of the subarray and the proportion of abnormal components, calculate the final output adjustment factor of the subarray.

7. The intelligent operation monitoring method for a photovoltaic power station according to claim 6, characterized in that, S2 specifically includes: Based on the maximum power of the acquired components, calculate the sum of the maximum power of all components in the subarray; based on the final output adjustment factor of the subarray, and combined with the sum of the maximum power of all components in the subarray, calculate the adjusted guidance power of the subarray.

Images