An intelligent LED display device for virtual power plants

Abstract

The present invention relates to an intelligent LED display device applied to a virtual power plant. The device includes a data acquisition module for collecting performance indicator data and sending it to a content management module. The content management module receives data and obtains key performance indicators of the virtual power plant and their eigenvalues ​​and eigenvectors. The weight of each key performance indicator is calculated by eigenvalue calculation, and a constraint optimization model is used to ensure that the display space of the relevant content of the key performance indicator on the LED display screen matches its weight. Finally, the content management module sends the relevant content of the key performance indicator to the LED display screen for display. The intelligent LED display device effectively displays the key performance indicators of the virtual power plant through accurate weight calculation and optimization models, provides an intuitive understanding of the operating status of the virtual power plant, and can flexibly adjust the display content to reflect the real-time performance of the virtual power plant.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent display for virtual power plant monitoring, and in particular to an intelligent LED display device and method applied to a virtual power plant. Background Art

[0002] A virtual power plant is a complex system that integrates a variety of distributed energy resources. It integrates different energy resources and achieves efficient use and stable supply of energy through optimized control and management. Effective management of a virtual power plant requires real-time monitoring and analysis of its internal performance indicators, which is crucial to the stability and efficiency of system operation.

[0003] In the prior art, the performance indicators of virtual power plants are usually displayed on different display interfaces, which may include temperature, humidity, voltage and other parameters. However, there may be complex relationships between these performance indicators, and simple parallel display may not reveal the inherent relationship between these performance indicators, nor is it conducive for operators to quickly grasp the overall operating status of the system.

[0004] In addition, since there are many performance indicators of virtual power plants, how to reasonably display these indicators in a limited display space while accurately reflecting their importance is a challenge faced by existing technologies. Some existing display methods may only mechanically list various indicators, lack of prominent display of key performance indicators, which is not conducive to operators to quickly identify and respond to possible problems.

[0005] Therefore, there is an urgent need for a new display device that can intelligently analyze and display the key performance indicators of the virtual power plant, so as to improve the management efficiency and operation safety of the virtual power plant. Summary of the invention

[0006] The present application provides an intelligent LED display device applied to a virtual power plant to improve the management efficiency and operation safety of the virtual power plant.

[0007] The present application provides an intelligent LED display device applied to a virtual power plant, comprising:

[0008] A data collection module, used for collecting performance index data of the virtual power plant; and sending the performance index data to the content management module;

[0009] The content management module is used to receive the performance indicator data sent by the data acquisition module; perform feature extraction on the performance indicator data to obtain the key performance indicators of the virtual power plant and their eigenvalues ​​and eigenvectors; calculate the weight w of each key performance indicator according to the eigenvalues ​​of the key performance indicators i , and its calculation formula is as follows:

[0010]

[0011] Among them, w i is the weight of the i-th key performance indicator, λ i is the characteristic value of the i-th key performance indicator, and n is the number of all key performance indicators; using the constraint optimization model, the relevant content of the key performance indicator that needs to be displayed on the LED display screen is calculated so that the display space of the relevant content matches the weight of the corresponding key performance indicator. The constraint optimization model can be expressed as follows:

[0012] minimize

[0013] Submit to d i ≥d mini , i=1,2,3,…,n

[0014] as well as

[0015] Among them, d i Indicates the display size of the i-th item related content, D total represents the total display space on the LED display, n represents the total number of related contents, and w i represents the weight of the key performance indicator corresponding to the i-th item, is the minimum display size of the relevant content of the i-th item; and sends the relevant content of the key performance indicator to the LED display screen;

[0016] The LED display screen is used to receive and display the relevant content of the key performance indicators sent by the content management module.

[0017] Furthermore, the content management module further includes:

[0018] A principal component analysis unit, used to perform principal component analysis on the performance indicator data of the virtual power plant, obtain principal components, and determine the principal components as key performance indicators, where the key performance indicators are linear combinations of original features in the performance indicator data;

[0019] Correlation calculation unit, used to calculate the correlation ρ between the key performance indicator and each original feature i , the calculation formula is as follows:

[0020]

[0021] Among them, x ij represents the jth observation value of the i-th original feature, y j represents the j-th observation value of the principal component, and are the means of the i-th original feature and principal component, respectively, and n is the number of observations;

[0022] The threshold comparison unit is used to compare the calculated correlation with a predetermined threshold and determine that the original features exceeding the threshold are relevant contents of the key performance indicator.

[0023] Furthermore, the content management module further includes:

[0024] A kernel principal component analysis unit, used for performing a kernel principal component analysis on the performance index data of the virtual power plant to obtain a principal component, and determining the principal component as a key performance index, where the key performance index is a linear combination of the original features in the performance index data in a higher dimensional feature space;

[0025] The first correlation calculation unit is used to calculate the correlation ρ between the key performance indicator and each original feature i , the calculation formula is as follows:

[0026]

[0027] Among them, x ij represents the jth observation value of the i-th original feature, y j represents the j-th observation value of the principal component, and are the means of the i-th original feature and principal component, respectively, and n is the number of observations;

[0028] The first threshold comparison unit is used to compare the calculated correlation with a predetermined threshold, and determine that the original features exceeding the threshold are relevant contents of the key performance indicator.

[0029] Furthermore, the content management module further includes:

[0030] The update frequency determination unit is used to determine the update frequency of the relevant content of the key performance indicators on the LED display screen, and the update frequency is determined based on the following rules:

[0031] When the operation state of the virtual power plant is in a stable state and the rate of change of the performance indicator data is lower than the threshold value A, the display update frequency is set to the first frequency;

[0032] When the operating state of the virtual power plant is in a changing state, or the performance indicator data change rate is between threshold A and threshold B, the display update frequency is set to the second frequency;

[0033] When the operating status of the virtual power plant is in a critical or emergency state, or the performance indicator data change rate is higher than threshold B, the display update frequency is set to the third frequency.

[0034] Furthermore, the content management module further includes:

[0035] The update frequency analysis unit is used to analyze the historical fluctuation characteristics of the performance indicator data of the virtual power plant, calculate the average change rate and fluctuation range of each performance indicator, and dynamically adjust the update frequency of the relevant content of the key performance indicators on the LED display screen according to the calculation results.

[0036] Furthermore, the content management module further includes:

[0037] The data processing unit is used to receive the performance index data from the data acquisition module and smooth the performance index data through a moving average algorithm to reduce the fluctuation frequency and noise interference of the data.

[0038] Furthermore, the content management module further includes:

[0039] A data receiving unit, used for receiving the performance index data of the virtual power plant sent from the data acquisition module;

[0040] A data cleaning and verification unit, used for cleaning and verifying the original data received from the data receiving unit to obtain cleaned data;

[0041] The data format conversion unit is used to convert the cleaned data into a format suitable for analysis.

[0042] Furthermore, the content management module further includes a color selection unit for selecting specific colors according to the importance and urgency of key performance indicators to highlight certain performance indicators; the color selection unit includes:

[0043] The importance analysis subunit is used to grade and evaluate the importance of the key performance indicators and set the corresponding relationship between colors and importance levels;

[0044] The urgency analysis subunit is used to analyze the urgency of the key performance indicators and use brighter or darker colors to indicate more urgent indicators.

[0045] Furthermore, the performance indicator data of the virtual power plant collected by the data collection module includes power generation, load, temperature, proportion of distributed energy and carbon emissions.

[0046] Furthermore, the data acquisition module includes:

[0047] Current and voltage sensors;

[0048] Temperature sensor;

[0049] Load sensor;

[0050] fuel and emissions sensors;

[0051] Distributed energy monitoring equipment.

[0052] The intelligent LED display device provided by the present application considers the influence of each key performance indicator on the overall performance of the virtual power plant by calculating the weight of each key performance indicator. The device uses a unique constraint optimization model, the purpose of which is to ensure that the display space of the key performance indicator-related content on the LED display screen matches its corresponding weight.

[0053] The technical solution provided by this application has the following beneficial effects:

[0054] (1) Efficient identification: Through dynamic weighting and optimization models, operators can identify and respond to key performance changes of virtual power plants more accurately and quickly.

[0055] (2) Flexibility: Due to the use of dynamic weight calculation based on eigenvalues, this method can adapt to different operating environments and requirements and provide tailor-made solutions for different power plants.

[0056] (3) Resource optimization: The constrained optimization model ensures the best utilization of display resources, emphasizing the most important indicators while retaining enough space to display other important information.

[0057] (4) Ease of use: By integrating all functions into a unified content management module, the device is easy to implement and maintain. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a schematic diagram of an intelligent LED display device applied to a virtual power plant provided in the first embodiment of the present application. DETAILED DESCRIPTION

[0059] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0060] The first embodiment of the present application provides an intelligent LED display device for use in a virtual power plant. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 The first embodiment of the present application provides a detailed description of an intelligent LED display device applied to a virtual power plant.

[0061] The intelligent LED display device includes a data collection module 101 , a content management module 102 , and an LED display screen 103 .

[0062] The data collection module 101 is used to collect performance indicator data of the virtual power plant; and send the performance indicator data to the content management module.

[0063] The data acquisition module 101 is a key part of the intelligent LED display device of the virtual power plant, and is specifically responsible for collecting the performance index data of the virtual power plant. The following is a detailed description of the data acquisition module.

[0064] The data acquisition module 101 includes a series of sensors, interfaces and processing units, which are connected to various devices and systems of the virtual power plant to collect real-time data about the performance of the virtual power plant.

[0065] The data acquisition module 101 may include the following types of sensors and interfaces:

[0066] Current and voltage sensors: used to monitor current and voltage conditions within the power plant.

[0067] Temperature sensor: monitors the temperature of equipment and environment inside the power plant.

[0068] Load sensor: monitors the load condition of the virtual power plant.

[0069] Fuel and emissions sensors: Monitor fuel consumption and carbon emissions.

[0070] Distributed energy monitoring equipment: collects information related to the proportion of distributed energy (such as solar energy, wind energy, etc.).

[0071] There are many performance indicators of virtual power plants. The following is a small part of them, which can be collected by the data acquisition module 101:

[0072] Power generation (MW): reflects the total power generation capacity of the virtual power plant.

[0073] Load (MW): represents the amount of demand that the virtual power plant is serving.

[0074] Temperature (℃): can include the temperature of various equipment and environment, reflecting the operating efficiency and health status.

[0075] Proportion of distributed energy (%): reflects the share of renewable and distributed energy in the total energy mix.

[0076] Carbon emissions (kg): monitor carbon emissions related to environmental impact.

[0077] Equipment operating status: such as equipment operating frequency, load factor, life span, etc.

[0078] The data collection module 101 also includes necessary data transmission and processing capabilities to ensure that the collected data can be sent to the content management module in real time and accurately. This may involve steps such as data cleaning, conversion, encryption and transmission.

[0079] The data acquisition module plays a key role in the intelligent LED display device of the virtual power plant. Through comprehensive and accurate data acquisition, it provides a basis for further analysis, optimization and display.

[0080] The content management module 102 is used to receive the performance indicator data sent by the data acquisition module 101, perform feature extraction on the performance indicator data, and obtain the feature vector of the key performance indicator of the virtual power plant; according to the feature vector, calculate the weight w of the key performance indicator by using the calculation method of variance explanation ratio i , and its calculation formula is as follows:

[0081]

[0082] Among them, λ i is the eigenvalue of the eigenvector of the i-th key performance indicator, and n is the number of eigenvectors of the key performance indicators; using the constraint optimization model, the relevant content of the key performance indicators that need to be displayed on the LED display screen is calculated so that the display space of the relevant content matches the weight of the corresponding key performance indicator. The constraint optimization model can be expressed as follows:

[0083]

[0084]

[0085]

[0086] Among them, d i Indicates the display size of the i-th item related content, D total represents the total display space on the LED display, n represents the total number of related contents, and w i represents the weight of the key performance indicator corresponding to the i-th item, It is the minimum display size of the relevant content of the i-th item; and sends the relevant content of the key performance indicator to the LED display screen.

[0087] The content management module 102 is the core part of the intelligent LED display device of the virtual power plant. It is mainly responsible for receiving the performance index data sent by the data acquisition module, extracting features, obtaining key performance indicators, and processing them using the constraint optimization model. The following are the components and detailed steps of this module:

[0088] (1) Receiving and preliminary processing of data

[0089] Data receiving unit: This module receives the performance indicator data of the virtual power plant sent from the data acquisition module 101, such as power generation, load, temperature, etc.

[0090] Data cleaning and verification unit: Clean and verify the collected raw data to remove duplicate, abnormal or incomplete data.

[0091] Data format conversion unit: Converts data into a format suitable for analysis, which may involve steps such as normalization or standardization to obtain a data set.

[0092] The content management module further includes: a data processing unit, which is used to receive the performance indicator data from the data acquisition module and smooth the performance indicator data through a moving average algorithm to reduce the fluctuation frequency and noise interference of the data.

[0093] (2) Feature extraction

[0094] This embodiment provides two feature extraction embodiments, including principal component analysis and kernel principal component analysis.

[0095] Principal Component Analysis (PCA):

[0096] Principal component analysis is a statistical analysis method used to transform multiple feature variables that may be correlated into a smaller number of uncorrelated principal components. Principal component analysis reduces dimensions by finding the main variance directions of the data, thereby capturing the main patterns and structures in the data while removing noise and unimportant details. PCA is a linear transformation method.

[0097] In this embodiment, the use of PCA helps to analyze the performance indicator data of the virtual power plant, extract key performance indicators, and determine them as operational key performance indicators. By reducing the dimension of the data, it is easier to identify and analyze the core operating characteristics of the virtual power plant, thereby achieving more accurate and efficient monitoring and management.

[0098] Kernel Principal Component Analysis (KPCA):

[0099] Kernel principal component analysis is an extension of PCA, which uses kernel techniques to achieve nonlinear mapping. Unlike PCA, which can only capture the linear structure of data, KPCA can capture more complex nonlinear relationships. KPCA captures richer data patterns by mapping the original data to a higher-dimensional feature space and then performing PCA in the new space.

[0100] In this embodiment, if the data has a complex nonlinear structure, it may be more appropriate to use KPCA instead of PCA. The performance indicators of the virtual power plant may include multiple interrelated nonlinear factors that may be difficult to capture through linear analysis. By using KPCA, these hidden nonlinear relationships can be revealed, thereby achieving more accurate performance monitoring and more flexible display content management.

[0101] Principal component analysis is mainly used for data analysis of linear relationships, while kernel principal component analysis is used for analysis of nonlinear relationships. In this embodiment, the choice of which method to use depends on the specific structure and requirements of the virtual power plant performance indicator data, and needs to be flexibly selected according to the specific application scenario and data characteristics.

[0102] Since the steps of kernel principal component analysis are basically similar to those of principal component analysis, the following description only describes the relevant parts of principal component analysis, and those skilled in the art may implement kernel principal component analysis with reference to the parts of principal component analysis.

[0103] The content management module further includes:

[0104] The principal component analysis unit is used to perform principal component analysis on the performance index data of the virtual power plant, obtain principal components, and determine the principal components as key performance indicators, which are linear combinations of original features in the performance index data.

[0105] The principal component analysis unit needs to perform principal component analysis through the following steps. Since principal component analysis is a common method, only a brief example is given here:

[0106] Calculate the covariance matrix: Calculate the covariance between each performance indicator in the data set to reveal the relationship between them. For example, the data set may include five original features such as power generation, load, temperature, distributed energy ratio, and carbon emissions.

[0107] Solving eigenvalues ​​and eigenvectors: Calculate eigenvalues ​​and eigenvectors from the covariance matrix. These eigenvalues ​​and eigenvectors represent the main direction of change of the data.

[0108] For example, the following eigenvalues ​​and eigenvectors may be obtained:

[0109] Eigenvalues: λ1=1.2, λ2=0.9, λ3=0.4, λ4=0.3, λ5=0.2

[0110] Eigenvector: The direction vector corresponding to each eigenvalue.

[0111] Select principal components: Based on the size of the eigenvalues, select the first n eigenvectors as principal components. For example, you can select the principal components that explain the first 90% of the total variance. In this example, you can select the first three principal components because λ1+λ2+λ3 account for the vast majority of the total eigenvalues. In this embodiment, the selected principal components are used as the key performance indicators of the virtual power plant.

[0112] Calculate weights: Use the following formula to calculate the weights of the key performance indicators:

[0113]

[0114] For example:

[0115]

[0116]

[0117]

[0118] (3) Constrained Optimization Model

[0119] The model is a mathematical model for finding the optimal solution under a set of constraints. In this embodiment, the model is used to calculate the relevant content of the key performance indicators of the virtual power plant that needs to be displayed on the LED display screen, so that the display space of these contents matches the weight of the corresponding key performance indicators.

[0120] The objective function of this model is to minimize

[0121] The constraints of the model are:

[0122] as well as

[0123] This problem can be solved using various optimization algorithms such as linear programming, quadratic programming, etc. This involves the use of specialized mathematical optimization libraries and tools. The resulting optimization solution will determine the optimal display size for each key performance indicator related content on the LED display.

[0124] The following describes a correlation calculation unit and a threshold comparison unit for generating relevant contents of a key performance indicator.

[0125] Correlation calculation unit, used to calculate the correlation ρ between the key performance indicator and each original feature i , the calculation formula is as follows:

[0126]

[0127] Among them, x ijrepresents the jth observation value of the i-th original feature, y j represents the j-th observation value of the principal component, and are the means of the i-th original feature and principal component, respectively, and n is the number of observations;

[0128] The main function of the correlation calculation unit is to calculate the correlation between the key performance indicator and each original feature, also known as the Pearson correlation coefficient. Correlation is a measure of the strength and direction of the linear relationship between two variables, and its value ranges from -1 to 1.

[0129] The calculation formula is divided into three parts:

[0130] a) Molecular part,

[0131] This part calculates the sum of the deviation products between the original features and the principal component observations. ij is the jth observation value of the ith original feature, y j is the jth observation of the principal component. By calculating the difference between each observation and its corresponding mean, we can measure how the data varies around its mean.

[0132] b) The denominator,

[0133] This part calculates the product of the standard deviation of the original features and the principal component observations. It plays a normalization role so that the correlation value is between -1 and 1.

[0134] The threshold comparison unit is used to compare the calculated correlation with a predetermined threshold and determine that the original features exceeding the threshold are relevant contents of the key performance indicator.

[0135] The purpose of this unit is to compare the calculated correlation with a predetermined threshold.

[0136] a) Comparison process:

[0137] If the correlation between a certain original feature and the principal component exceeds a predetermined threshold, the feature is determined as relevant to the key performance indicator. The threshold can be set based on actual needs and experience, usually to ensure that there is a sufficiently strong linear relationship between the selected original feature and the principal component.

[0138] b) Determination of key performance indicators:

[0139] Through this comparison process, the system can identify original features that have significant linear relationships with the principal components, which are considered as key performance indicators of the virtual power plant.

[0140] The content management module further includes:

[0141] A kernel principal component analysis unit, used for performing a kernel principal component analysis on the performance index data of the virtual power plant to obtain a principal component, and determining the principal component as a key performance index, where the key performance index is a linear combination of the original features in the performance index data in a higher dimensional feature space;

[0142] The first correlation calculation unit is used to calculate the correlation ρ between the key performance indicator and each original feature i , the calculation formula is as follows:

[0143]

[0144] Among them, x ij represents the jth observation value of the i-th original feature, y j represents the j-th observation value of the principal component, and are the means of the i-th original feature and principal component, respectively, and n is the number of observations;

[0145] The first threshold comparison unit is used to compare the calculated correlation with a predetermined threshold, and determine that the original features exceeding the threshold are relevant contents of the key performance indicator.

[0146] As the kernel principal component analysis unit, the first correlation calculation unit and the first threshold comparison unit are similar to the principal component analysis unit, the correlation calculation unit and the threshold comparison unit mentioned above, they will not be described in detail here.

[0147] The content management module further includes:

[0148] The update frequency determination unit is used to determine the update frequency of the relevant content of the key performance indicators on the LED display screen, and the update frequency is determined based on the following rules:

[0149] When the operation state of the virtual power plant is in a stable state and the rate of change of the performance indicator data is lower than the threshold value A, the display update frequency is set to the first frequency;

[0150] When the operating state of the virtual power plant is in a changing state, or the performance indicator data change rate is between threshold A and threshold B, the display update frequency is set to the second frequency;

[0151] When the operating status of the virtual power plant is in a critical or emergency state, or the performance indicator data change rate is higher than threshold B, the display update frequency is set to the third frequency.

[0152] The update frequency determination unit is a key component that ensures that the update frequency of the key performance indicator related content on the LED display is synchronized with the actual operating status of the virtual power plant. According to the different operating conditions of the virtual power plant, this unit can dynamically adjust the update frequency of the display. The following explains this process in detail:

[0153] (a) The first frequency in steady state and slow rate of change

[0154] Condition: The operating status of the virtual power plant is stable and the change rate of the performance indicator data is lower than threshold A.

[0155] Action: Set the display update frequency to the first frequency.

[0156] Example: Assume that threshold A is 5%. If the power plant runs smoothly and the performance indicator data changes less than 5% per minute, the LED display will be updated at a slower frequency (such as once every 10 seconds) because the data is relatively stable and does not need to be updated frequently.

[0157] Purpose: Reduce unnecessary updates, save resources, and keep the interface clean and tidy.

[0158] (b) Second frequency at a changing state or moderate rate of change

[0159] Condition: The operating state of the virtual power plant is in a changing state, or the performance indicator data change rate is between threshold A and threshold B.

[0160] Action: Set the display update frequency to the second frequency.

[0161] Example: Assume threshold A is 5% and threshold B is 15%. If the virtual power plant is performing some non-routine operations, resulting in a performance indicator change rate of 5% to 15% per minute, then the LED display will be updated at a moderate frequency (such as once every 5 seconds).

[0162] Purpose: To keep in sync with the actual operating status and ensure that relevant personnel are aware of moderate changes in key performance indicators in a timely manner.

[0163] (c) Third frequency in critical or emergency situations

[0164] Condition: The operating status of the virtual power plant is in a critical or emergency state, or the performance indicator data change rate is higher than threshold B.

[0165] Action: Set the display update frequency to the third frequency.

[0166] Example: Assume that threshold B is 15%. If the virtual power plant encounters a certain fault or emergency, causing the performance indicator to change by more than 15% per minute, the LED display will be updated at a faster frequency (such as once per second).

[0167] Purpose: To provide timely information at critical moments so that necessary measures can be taken to ensure the safety and efficiency of the power plant.

[0168] The update frequency determination unit ensures flexibility and timeliness by accurately matching the operating status of the virtual power plant with the display update frequency, while also reducing unnecessary interference and resource consumption. The three different frequency settings reflect the various operating conditions that the virtual power plant may encounter, allowing operators and managers to respond promptly based on actual conditions. This dynamically adaptive approach makes the monitoring and management of virtual power plants more intelligent and efficient.

[0169] The content management module further includes:

[0170] The update frequency analysis unit is used to analyze the historical fluctuation characteristics of the performance indicator data of the virtual power plant, calculate the average change rate and fluctuation range of each performance indicator, and dynamically adjust the update frequency of the relevant content of the key performance indicators on the LED display screen according to the calculation results.

[0171] The update frequency analysis unit is an advanced algorithm component, which is used to dynamically adjust the update frequency of the relevant content of the key performance indicators on the LED display screen according to the historical fluctuation characteristics of the virtual power plant performance indicator data.

[0172] (a) Analyzing historical volatility characteristics

[0173] Purpose: To understand the historical change patterns of various performance indicators of the virtual power plant in order to more accurately adjust the display update frequency.

[0174] Action: Collect past performance indicator data and analyze its time series to identify any periodicity, trends, or unusual fluctuations.

[0175] Example: For example, if a particular performance metric always changes significantly during a certain time period each day, this pattern can be identified and used to make future update frequency decisions.

[0176] (b) Calculate the average rate of change and fluctuation range

[0177] Average rate of change: measures the average rate of change of performance indicators over time.

[0178] Example: If a metric increased from 10 to 20 over the past 10 minutes, the average rate of change is 1 per minute.

[0179] Volatility: Measures the difference between the highest and lowest values ​​of a performance indicator over a period of time.

[0180] For example: In the same time period, if the maximum value of the indicator is 25 and the minimum value is 5, the fluctuation range is 20.

[0181] (c) Dynamically adjust update frequency

[0182] Action: Determine the appropriate display update frequency based on the calculation results of the average change rate and fluctuation amplitude.

[0183] Strategy:

[0184] High volatility and high rate of change: Higher update frequency to capture rapid changes in a timely manner.

[0185] Low volatility and low rate of change: Lower update frequency because the data is relatively stable.

[0186] Example: If a key indicator of a power plant fluctuates rapidly during an emergency, the update frequency analysis unit may increase the refresh rate of the LED screen to once per second to ensure that the situation is reflected in real time.

[0187] The update frequency analysis unit realizes the dynamic update of key performance indicators on the LED display screen by deeply analyzing the historical fluctuation characteristics of the performance indicator data of the virtual power plant and calculating its average change rate and fluctuation amplitude. This advanced method improves the responsiveness and flexibility of the system, allowing operators to monitor and manage the status of the virtual power plant more accurately. By adapting to historical data and current conditions, the unit ensures intelligent operation and effective monitoring of the virtual power plant.

[0188] The content management module further includes a color selection unit for selecting specific colors according to the importance and urgency of key performance indicators to highlight certain performance indicators; the color selection unit includes:

[0189] The importance analysis subunit is used to grade and evaluate the importance of the key performance indicators and set the corresponding relationship between colors and importance levels;

[0190] The urgency analysis subunit is used to analyze the urgency of the key performance indicators and use brighter or darker colors to indicate more urgent indicators.

[0191] Assume that the virtual power plant has four key performance indicators: power generation efficiency (KPI1), machine temperature (KPI2), load rate (KPI3), and system stability (KPI4). We will select colors for these performance indicators based on importance and urgency.

[0192] (a) Importance Analysis Subunit

[0193] The importance analysis subunit grades and evaluates the impact of each key performance indicator on the operation of the virtual power plant by considering it and assigns a color to each grade.

[0194] KPI 1: Power generation efficiency. This indicator is very important as it directly affects the energy output of the power plant. It is classified as "most important" and assigned the color blue.

[0195] KPI 2: Machine temperature. This indicator is of medium importance, as a slight increase in machine temperature may not immediately affect performance. It is classified as "important" and assigned the color green.

[0196] KPI 3: Load Factor. This indicator is critical as it affects the output of the power plant. It is classified as "very important" and assigned the color yellow.

[0197] KPI 4: System stability. This indicator is crucial to the stable operation of the entire system and is classified as "most important" and assigned the color red.

[0198] (b) Urgency Analysis Subunit

[0199] The urgency analysis sub-units use brighter or darker colors depending on the urgency of the indicator.

[0200] KPI1: Power generation efficiency. If the power generation efficiency drops sharply, immediate action may be required. Therefore, dark blue is used in emergency situations.

[0201] KPI 2: Machine temperature. Machine overheating may need to be addressed quickly, so dark green is used in emergency situations.

[0202] KPI 3: Load rate. A sharp change in load may indicate a problem, so dark yellow is used in emergency situations.

[0203] KPI 4: System stability. System stability issues may need to be addressed immediately, so dark red is used in emergency situations.

[0204] This design solution ensures that the performance indicators on the LED display can be displayed in an intuitive way according to their importance and urgency. Through carefully selected colors, operators can quickly identify the status of the power plant and make corresponding decisions. For example, if the power generation efficiency on the display turns dark blue, the operator can immediately know that there is a sharp drop in power generation efficiency and can quickly take measures to solve the problem.

[0205] (4) Data transmission

[0206] Format content: Format the relevant content of the calculated key performance indicators into a format suitable for the LED display screen.

[0207] Send to LED display: Send the formatted content to the LED display for display.

[0208] The LED display screen 103 is used to receive and display the key performance indicator related content sent by the content management module.

[0209] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. An intelligent LED display device applied to a virtual power plant, characterized in that: include: Data acquisition module, used to collect performance indicator data of virtual power plants; Sending the performance indicator data to a content management module; The content management module is used to receive the performance indicator data sent by the data acquisition module; perform feature extraction on the performance indicator data to obtain the key performance indicators of the virtual power plant and their eigenvalues ​​and eigenvectors; calculate the weight w of each key performance indicator according to the eigenvalues ​​of the key performance indicators i , and its calculation formula is as follows: Among them, w i is the weight of the i-th key performance indicator, λ i is the characteristic value of the i-th key performance indicator, and n is the number of all key performance indicators; the constraint optimization model is used to calculate the relevant content of the key performance indicator that needs to be displayed on the LED display screen, so that the display space of the relevant content matches the weight of the corresponding key performance indicator. The constraint optimization model is expressed as follows: Minimize Submission as well as Among them, d i Indicates the display size of the i-th item related content, D total represents the total display space on the LED display, n represents the total number of related contents, and w i represents the weight of the key performance indicator corresponding to the i-th item, is the minimum display size of the relevant content of the i-th item; and sends the relevant content of the key performance indicator to the LED display screen; The LED display screen is used to receive and display the relevant content of the key performance indicators sent by the content management module.

2. The intelligent LED display device according to claim 1, characterized in that: The content management module further includes: A principal component analysis unit, used to perform principal component analysis on the performance indicator data of the virtual power plant, obtain principal components, and determine the principal components as key performance indicators, where the key performance indicators are linear combinations of original features in the performance indicator data; Correlation calculation unit, used to calculate the correlation ρ between the key performance indicator and each original feature i , the calculation formula is as follows: Among them, x ij represents the jth observation value of the i-th original feature, y j represents the j-th observation value of the principal component, and are the means of the i-th original feature and principal component, respectively, and n is the number of observations; The threshold comparison unit is used to compare the calculated correlation with a predetermined threshold and determine that the original features exceeding the threshold are relevant contents of the key performance indicator.

3. The intelligent LED display device according to claim 1, characterized in that: The content management module further includes: A kernel principal component analysis unit, used for performing a kernel principal component analysis on the performance index data of the virtual power plant to obtain a principal component, and determining the principal component as a key performance index, where the key performance index is a linear combination of the original features in the performance index data in a higher dimensional feature space; The first correlation calculation unit is used to calculate the correlation ρ between the key performance indicator and each original feature i , the calculation formula is as follows: Among them, x ij represents the jth observation value of the i-th original feature, y j represents the j-th observation value of the principal component, and are the means of the i-th original feature and principal component, respectively, and n is the number of observations; The first threshold comparison unit is used to compare the calculated correlation with a predetermined threshold, and determine that the original features exceeding the threshold are relevant contents of the key performance indicator.

4. The intelligent LED display device according to claim 1, characterized in that: The content management module further includes: The update frequency determination unit is used to determine the update frequency of the relevant content of the key performance indicators on the LED display screen, and the update frequency is determined based on the following rules: When the operation state of the virtual power plant is in a stable state and the rate of change of the performance indicator data is lower than the threshold value A, the display update frequency is set to the first frequency; When the operating state of the virtual power plant is in a changing state, or the performance indicator data change rate is between threshold A and threshold B, the display update frequency is set to the second frequency; When the operating status of the virtual power plant is in a critical or emergency state, or the performance indicator data change rate is higher than threshold B, the display update frequency is set to the third frequency.

5. The intelligent LED display device according to claim 1, characterized in that: The content management module further includes: The update frequency analysis unit is used to analyze the historical fluctuation characteristics of the performance indicator data of the virtual power plant, calculate the average change rate and fluctuation range of each performance indicator, and dynamically adjust the update frequency of the relevant content of the key performance indicators on the LED display screen according to the calculation results.

6. The intelligent LED display device according to claim 1, characterized in that: The content management module further includes: The data processing unit is used to receive the performance index data from the data acquisition module and smooth the performance index data through a moving average algorithm to reduce the fluctuation frequency and noise interference of the data.

7. The intelligent LED display device according to claim 1, characterized in that: The content management module further includes: A data receiving unit, used for receiving the performance index data of the virtual power plant sent from the data acquisition module; A data cleaning and verification unit, used for cleaning and verifying the original data received from the data receiving unit to obtain cleaned data; The data format conversion unit is used to convert the cleaned data into a format suitable for analysis.

8. The intelligent LED display device according to claim 1, characterized in that: The content management module further includes a color selection unit for selecting specific colors according to the importance and urgency of key performance indicators to highlight certain performance indicators; the color selection unit includes: The importance analysis subunit is used to grade and evaluate the importance of the key performance indicators and set the corresponding relationship between colors and importance levels; The urgency analysis subunit is used to analyze the urgency of the key performance indicators and use brighter or darker colors to indicate more urgent indicators.

9. The intelligent LED display device according to claim 1, characterized in that: The performance indicator data of the virtual power plant collected by the data collection module include power generation, load, temperature, proportion of distributed energy and carbon emissions.

10. The intelligent LED display device according to claim 1, characterized in that: The data acquisition module comprises: Current and voltage sensors; Temperature sensor; Load sensor; fuel and emissions sensors; Distributed energy monitoring equipment.

Images