New energy system operation state monitoring analysis method and device based on multi-level structure and storage medium

Abstract

The invention provides a new energy system operation state monitoring analysis method and device based on a multi-level structure and a storage medium, and relates to the technical field of data monitoring analysis. The method comprises the following steps: dividing acquired data of a new energy monitoring system according to a preset hierarchical structure to obtain hierarchical structure data; constructing the hierarchical structure into a hierarchical data model through a dynamic time sequence modeling algorithm; constructing a cross-regional panoramic monitoring graph, and performing optimization scheduling of regional hierarchical data in combination with a dynamic network optimization algorithm; and collecting real-time data of the new energy access point through an incremental data synchronization algorithm, performing data analysis on the new energy access point, and generating an analysis result. By introducing hierarchical data modeling, dynamic data synchronization, incremental data processing and panoramic modeling, the data management flexibility, the real-time monitoring precision, the cross-regional data synchronization and scheduling efficiency and the risk assessment and abnormal response capability of the new energy monitoring system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring and analysis, and in particular to a method, device and storage medium for monitoring and analyzing the operating status of a new energy system based on a multi-level structure. Background Art

[0002] As the global demand for new energy continues to increase, the large-scale development of new energy (such as wind power and solar energy) has become an important direction for the global power industry. However, since the power generation of new energy depends on natural conditions, its data presents complex time series characteristics. How to efficiently monitor, model and manage the operating status of new energy systems has become a major technical challenge in the current development of new energy systems.

[0003] Existing technologies usually collect and analyze the operating status of new energy equipment through traditional monitoring methods and simple data models, but there are significant deficiencies in the following aspects:

[0004] Complexity and limitations of modeling: The data of the new energy monitoring system has complex spatiotemporal characteristics. Traditional modeling methods usually use static or single-level models to represent the status of equipment or systems, which is difficult to accurately reflect the real-time changes of new energy equipment in a dynamic environment. At the same time, existing modeling methods often lack comprehensive consideration of the regional, station and equipment levels, resulting in the data model being unable to flexibly cope with the complexity of the system structure when dealing with cross-regional, multi-station systems. For example, it is difficult for traditional models to take into account data synchronization and collaborative monitoring between different regions, and it is impossible to achieve panoramic monitoring across regions.

[0005] Low efficiency of dynamic data synchronization and incremental data processing: New energy equipment is widely distributed, and existing systems usually adopt a periodic full data collection method. This method will lead to a significant decrease in transmission and processing efficiency when the data update frequency is high. Especially when the equipment status changes frequently, the traditional full data synchronization method cannot effectively distinguish important incremental data, which not only wastes data transmission and computing resources, but also affects the real-time and accuracy of monitoring. At the same time, the existing technology fails to introduce incremental modeling and dynamic data update mechanisms, resulting in the inability to quickly adjust the model according to real-time data, making it difficult to cope with the rapid changes in the operating status of new energy equipment.

[0006] Lack of data priority and risk assessment models: Traditional data modeling and analysis methods fail to prioritize data of different importance when processing large-scale new energy data, resulting in insufficient response to abnormal situations during monitoring. In addition, existing technologies lack effective risk assessment models and cannot accurately assess the potential risks of new energy access points, which in turn affects the reliability and security of the system. Summary of the invention

[0007] Purpose of the invention: The present invention proposes a new energy system operating status monitoring and analysis method, device and storage medium based on a multi-level structure, aiming to effectively solve the above-mentioned problems existing in the prior art.

[0008] In a first aspect of the present invention, a method for monitoring and analyzing the operating status of a new energy system based on a multi-level structure is proposed, and the steps are as follows:

[0009] Access to the existing new energy monitoring system to collect operating status data of new energy equipment;

[0010] Dividing the operating status data according to a preset hierarchical structure to obtain hierarchical structure data; the preset hierarchical structure includes a regional level, a station level, and an equipment level;

[0011] constructing the hierarchical structure into a hierarchical data model through a dynamic time series modeling algorithm;

[0012] Construct a cross-regional panoramic monitoring map, and connect the hierarchical data model to the panoramic monitoring map; optimize and schedule the data flow in the panoramic monitoring map through a dynamic network optimization algorithm;

[0013] Through the incremental data synchronization algorithm, real-time data of new energy access points is collected, data analysis is performed on the new energy access points, and the analysis results are displayed in the panoramic monitoring map.

[0014] The present invention is further configured such that the regional level is responsible for cross-regional data collection and management, the station level is used to process equipment and power grid data within the station, the device level is used to monitor the operating status of a single device, and the regional level, the station level and the device level perform real-time data collection and upload by setting sensors and communication modules.

[0015] In a further embodiment of the first aspect, the process of constructing the hierarchical structure into a hierarchical data model by a dynamic time series modeling algorithm specifically includes:

[0016] Extracting time series features from the hierarchical data using a dynamic time series modeling algorithm;

[0017] According to the extracted time series features, dynamic data models are constructed for the three levels of region, station, and equipment;

[0018] After the multi-level dynamic data model is built, real-time data is continuously collected and the dynamic data model is updated online through a dynamic time series modeling algorithm.

[0019] In a further embodiment of the first aspect, the process of extracting time series features from the hierarchical data using a dynamic time series modeling algorithm is specifically as follows:

[0020] At the regional level, a cluster analysis algorithm is used to process regional time series data, calculate the similarity of regional time series data, and extract time series features; at the station level, a convolutional neural network is used to analyze the dependencies and time series characteristics between stations; at the equipment level, a support vector machine is used to classify the operating status and time series characteristics of the equipment.

[0021] In a further embodiment of the first aspect, a cross-regional panoramic monitoring map is constructed, and the hierarchical data model is connected to the panoramic monitoring map; and the data flow in the panoramic monitoring map is optimized and scheduled by a dynamic network optimization algorithm, and the specific process includes:

[0022] Set the stations as nodes of the graph, set the connection between nodes as edges, set regional attributes for the nodes, that is, set the region to which the nodes belong, and build a cross-regional panoramic monitoring map;

[0023] According to the cross-regional panoramic monitoring map, the data flow in the panoramic monitoring map is optimized and scheduled by using a dynamic network optimization algorithm in graph theory. The dynamic network optimization algorithm includes a shortest path algorithm and / or a maximum flow algorithm.

[0024] In a further embodiment of the first aspect, real-time data of the new energy access point is collected through an incremental data synchronization algorithm, and data analysis is performed on the new energy access point. The specific process includes:

[0025] Acquire real-time data based on the collection frequency of the new energy access point, compare the data at the current time point with the data at the previous time point, extract the data points where the status or value has changed, and transmit the incremental data to the data processing center;

[0026] In the data processing center, after receiving the incremental data, all the incremental data with value changes in the incremental data are obtained and set as the incremental data set;

[0027] Calculate the priority of corresponding data according to the incremental change value in the incremental data set, and perform data prediction on the corresponding data according to the priority of the corresponding data;

[0028] According to the predicted value predicted by the data, the risk probability of the new energy access point is calculated by a preset risk assessment formula, and the predicted value and the risk probability are set as the analysis result.

[0029] In a further embodiment of the first aspect, the calculation logic of the priority of the corresponding data is: ,in, For the Incremental data The priority of For the Incremental data At the point in time The value of For the Incremental data At the point in time The value of .

[0030] The calculation logic of the risk probability of new energy access points is: ,in, is the risk probability of the new energy access point, is the number of incremental data of new energy access points, For the Incremental data At the point in time The predicted value of With Incremental data Preset status thresholds The distance between.

[0031] According to a second aspect of the present invention, an electronic device is proposed, which includes a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the new energy system operation status monitoring and analysis method based on a multi-level structure as disclosed in the first aspect and its further embodiments.

[0032] According to the third aspect of the present invention, a computer-readable storage medium is provided, which stores at least one executable instruction. When the executable instruction is executed on an electronic device, the electronic device executes the new energy system operation status monitoring and analysis method based on a multi-level structure as disclosed in the first aspect and its further embodiments.

[0033] Compared with the prior art, the present invention has at least the following beneficial effects:

[0034] 1. Flexibility and intuitiveness of hierarchical data management: By building a multi-level data model at the regional level, station level and equipment level, it is possible to effectively distinguish data content at different levels, solving the problem that the single-layer structure in the existing technology cannot adapt to complex scenarios. The division of labor between each level is clear, which not only facilitates efficient data management, but also improves the scalability and flexibility of the system, and is suitable for the monitoring and management of large-scale new energy systems.

[0035] 2. Greatly improved real-time performance and accuracy: The present invention uses a dynamic time series modeling algorithm to collect and update data models in real time according to changes in the operating status of new energy equipment. Compared with traditional static models, dynamic models can more accurately reflect the timing characteristics of new energy equipment, achieve accurate prediction and real-time monitoring of equipment status, and effectively avoid data lag and error.

[0036] 3. Cross-regional data synchronization and panoramic monitoring: The panoramic modeling technology based on graph theory can build a cross-regional monitoring system to achieve global monitoring of new energy equipment in each region. At the same time, combined with dynamic network optimization algorithms, data flows in different regions are intelligently scheduled and optimized to ensure efficient operation of the system in a complex network environment and to ensure data integrity and consistency;

[0037] 4. Improved incremental data processing efficiency: Through the incremental data synchronization algorithm, the present invention can automatically extract the change points of the device status and transmit incremental data according to the change situation, thereby reducing the transmission burden of redundant data and significantly improving the efficiency of data transmission and processing. The introduction of incremental data ensures that the monitoring system can still operate efficiently and accurately in an environment with high-frequency data updates, solving the resource waste and delay problems caused by traditional full data transmission;

[0038] 5. Data priority management and risk assessment: This invention introduces data priority calculation and risk assessment models. By analyzing incremental data, the risk probability of new energy access points can be dynamically assessed. The setting of priorities enables the system to process key data more intelligently, improves the response speed of abnormal situations and the ability to predict risks, and effectively improves the safety and stability of the new energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Flow chart of a method for monitoring and analyzing the operating status of a new energy system based on a multi-level structure in an embodiment.

[0040] Figure 2 Schematic diagram of the structure of the new energy system operation status monitoring and analysis system in the embodiment. DETAILED DESCRIPTION

[0041] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features known in the art are not described.

[0042] like Figure 1 As shown, the present invention provides a new energy system operating status monitoring and analysis method based on a multi-level structure, the steps are as follows:

[0043] Dividing the acquired data of the new energy monitoring system according to a preset hierarchical structure to obtain hierarchical structure data, wherein the preset hierarchical structure includes a regional level, a station level and a device level;

[0044] Construct hierarchical data models based on hierarchical data through dynamic time series modeling algorithms;

[0045] Based on the panoramic modeling technology of graph theory algorithm, a cross-regional panoramic monitoring map is constructed, and the regional hierarchical data is optimized and scheduled in combination with the dynamic network optimization algorithm;

[0046] Through the incremental data synchronization algorithm, real-time data of new energy access points is collected, data analysis is performed on the new energy access points, and analysis results are generated.

[0047] Specifically, the regional level is responsible for cross-regional data collection and management, the station level is used to process the equipment and power grid data inside the station, and the equipment level is used to monitor the operating status of a single device. The regional level, station level and equipment level collect and upload data in real time by setting sensors and communication modules. According to the preset hierarchical structure, the data obtained from the new energy monitoring system is divided. The hierarchical structure includes three levels: regional level: responsible for cross-regional data collection and monitoring, processing comprehensive data of new energy equipment in large-scale areas, such as the operating status of multiple stations, energy flow in the region, etc.; station level: the station is the basic unit of the new energy system, managing and monitoring the operating data and power transmission data of the internal equipment of a single or multiple power stations; equipment level: responsible for the monitoring and data recording of the detailed operating conditions of a single device (such as wind turbines, photovoltaic panels), including the health status of the equipment, power output, etc.; through this hierarchical division, large-scale and complex new energy monitoring systems can be effectively managed to ensure that the data at each level can be analyzed and optimized in a targeted manner.

[0048] After the hierarchical data is divided, the data at each level is modeled using a dynamic time series modeling algorithm. Dynamic time series modeling is used to process the trend of data changes over time, and can effectively identify the operation mode and anomalies of the equipment. The present invention is further configured to construct a hierarchical data model based on the hierarchical data using a dynamic time series modeling algorithm, including:

[0049] The hierarchical data is extracted using a dynamic time series modeling algorithm; the present invention is further configured to extract time series features from the hierarchical data using a dynamic time series modeling algorithm, including: using a clustering analysis algorithm at the regional level to process regional time series data, calculating the similarity of regional time series data, and extracting time series features; using a convolutional neural network at the station level to analyze the dependencies and time series characteristics between stations; using a support vector machine at the equipment level to classify the operating status and time series characteristics of the equipment; specifically, according to the requirements of the new energy monitoring system, the data is divided into three levels: the regional level, the station level, and the equipment level. The data at each level has different granularity and characteristics, so different algorithms need to be used to extract time series features. Through the dynamic time series modeling algorithm, the time series features are extracted and analyzed at different levels in order to build an accurate prediction model; the data at the regional level usually represents a wide range of energy flows and equipment operating conditions. Since there are many devices and stations in the region and the amount of data is huge, a clustering analysis algorithm is used to process the regional level data. Specifically, the clustering algorithm can divide different data sources in a region into several groups based on the similarity of the time series data in the region, so that data with high similarity can be classified into the same cluster; the data structure at the station level is complex, reflecting the collaborative relationship and operating characteristics of different equipment within the station. Therefore, a convolutional neural network (CNN) is used to extract time series features. Convolutional neural networks are good at processing multidimensional data with local correlations. At the station level, the time series dependency between devices can be regarded as a kind of "local correlation", and these relationships are extracted through convolution kernels; the data at the equipment level reflects the operating status of a single device. For this level, support vector machines (SVMs) are used for classification to identify the operating status (such as normal, abnormal, faulty, etc.) and operating characteristics of equipment. Support vector machines classify the operating status of equipment into different categories by finding classification boundaries in high-dimensional space;

[0050] According to the extracted time series features, dynamic data models are constructed for the three levels of region, station, and equipment; specifically, after extracting the time series features of each level, dynamic data models are constructed for the three levels of region, station, and equipment according to these features. The basis for the use of dynamic data models is the characteristics of time series. These models can be continuously updated and self-corrected over time. The dynamic data models at each level use real-time data as input for prediction and analysis;

[0051] After the multi-level dynamic data model is built, real-time data is continuously collected and the dynamic data model is updated online through the dynamic time series modeling algorithm. Specifically, by extracting features from the dynamic time series data at the three levels of region, station, and equipment, the unique information at each level can be accurately captured. Cluster analysis at the regional level provides a large-scale data overview, convolutional neural networks at the station level can provide an in-depth understanding of the collaborative relationship between devices, and support vector machine classification at the device level ensures a detailed analysis of the device status.

[0052] The present invention is further configured to construct a cross-regional panoramic monitoring map based on a panoramic modeling technology based on a graph theory algorithm, and optimize and schedule regional hierarchical data in combination with a dynamic network optimization algorithm, including:

[0053] The stations are set as nodes in the graph, the interconnection relationship between the nodes is set as edges, and the regional attributes are set for the nodes, that is, the regions to which the nodes belong are set, so as to construct a cross-regional panoramic monitoring map; specifically, a cross-regional panoramic monitoring map is constructed. In this graph, the stations are regarded as nodes in the graph, and the interconnection relationship between the stations is regarded as edges in the graph. The nodes not only represent the physical location of the stations, but also carry the regional attributes of the stations to distinguish different regions. The steps to construct a panoramic monitoring map are as follows: Node setting: Each station is set as a node in the graph. The node not only represents the station itself, but also contains the operating data of the station, such as power generation, equipment health status, etc.; Edge setting: In the graph, every two adjacent stations are connected by edges, and the edges represent the interconnection relationship between the stations, such as power transmission paths, data transmission channels, etc. Each edge has a weight, which can represent the bandwidth, distance or cost of the transmission; Regional attribute setting: Each node is attached with a regional attribute according to the region to which it belongs. Through the regional attributes of the nodes, the cross-regional data flow can be intuitively represented on the panoramic monitoring map.

[0054] According to the cross-regional panoramic monitoring map, the data flow in the panoramic monitoring map is optimized and scheduled by the dynamic network optimization algorithm in graph theory, and the dynamic network optimization algorithm includes the shortest path algorithm and / or the maximum flow algorithm; specifically, after the complete panoramic monitoring map is constructed, the dynamic network optimization algorithm in graph theory is used to optimize and schedule the data flow in the panoramic monitoring map. The goal of dynamic network optimization is to optimize the path and transmission efficiency of the data flow, so that cross-regional energy data and power scheduling are more efficient. Dynamic network optimization includes the following two main algorithms: Shortest path algorithm: used to find the optimal path for data or power transmission between stations. The algorithm calculates the shortest path between any two nodes in the graph, so as to ensure that the data can be transmitted to the target station through the least transit nodes, reducing transmission delay; Maximum flow algorithm: When processing cross-regional data and power flow, the maximum flow algorithm is used to find the maximum transmission capacity between stations. Through this algorithm, the data transmission rate on each edge in the network can be dynamically adjusted to ensure that high-priority data or power can be transmitted first and avoid transmission bottlenecks; through the shortest path algorithm and the maximum flow algorithm, the system can dynamically optimize and schedule the data flow in the panoramic monitoring map during operation. Dynamic network optimization can not only ensure data transmission efficiency under normal circumstances, but also respond to emergencies. For example, when certain nodes or paths fail, the system can quickly adjust by recalculating the shortest path or maximum flow to ensure that the transmission of data and energy will not be significantly affected.

[0055] The present invention is further configured to collect real-time data of new energy access points through an incremental data synchronization algorithm, perform data analysis on the new energy access points, and generate analysis results, including:

[0056] According to the acquisition frequency of the new energy access point, real-time data is obtained, the data at the current time point is compared with the data at the previous time point, the data points with changed status or value are extracted, and the incremental data is transmitted to the data processing center; specifically, according to the acquisition frequency of the new energy access point, the system will periodically obtain the real-time data of the access point. The real-time data of each access point is composed of operating parameters of multiple dimensions, including power generation, equipment status, load conditions of the connected power grid, etc. The above parameters are updated at fixed intervals, and the corresponding values ​​are collected by sensors; in order to reduce the burden of redundant data transmission, the system will not transmit all the data collected each time, but will extract the changed data points by comparing the data at the current time point with the data at the previous time point.

[0057] In the data processing center, after receiving the incremental data, all the incremental data with value changes in the incremental data are obtained and set as the incremental data set;

[0058] The priority of the corresponding data is calculated according to the incremental change value in the incremental data set, and data prediction is performed on the corresponding data according to the priority of the corresponding data; the present invention is further configured that the calculation logic of the priority of the corresponding data is: ,in, For the Incremental data The priority of For the Incremental data At the point in time The value of For the Incremental data At the point in time value; specifically, the above calculation logic measures the magnitude of data change by calculating the relative change rate of incremental data at adjacent time points (i.e., the ratio change of the current data value to the previous data value); by calculating the relative change rate of incremental data, the system can accurately assign data priority. This ensures that the data with significant changes can be processed first, so as to detect equipment anomalies or system failures in a timely manner; in the monitoring system of new energy access points, the amount of real-time data is usually huge, but not all data will change significantly. Through priority calculation, only data with significant changes are processed and transmitted first, reducing unnecessary data transmission burden and improving system efficiency;

[0059] According to the predicted value predicted by the data, the risk probability of the new energy access point is calculated by a preset risk assessment formula, and the predicted value and the risk probability are set as the analysis result; the present invention is further configured that the calculation logic of the risk probability of the new energy access point is: ,in, is the risk probability of the new energy access point, is the number of incremental data of new energy access points, For the Incremental data At the point in time The predicted value of With Incremental data Preset status thresholds Specifically, first, the system predicts the incremental data of the new energy access point and generates the future time The predicted value of The prediction model uses historical data and current data to infer the equipment status or power generation at future times. This is an existing technology and will not be described in detail here. and preset thresholds , calculate the distance between the current predicted value and the threshold. This distance is used to measure whether the predicted value is close to or exceeds the safety threshold, so as to determine whether the operating status of the new energy access point is at the risk edge. Represents the distance function between the predicted value and the threshold. Generally, the larger the distance, the closer the system state is to danger. The distance function can be defined as the Euclidean distance or other measurement methods. There is no restriction here. For each incremental data point, its risk assessment value is calculated, and the risks of all incremental data points are superimposed. By predicting the data at future moments and calculating the risk probability in combination with the state threshold, the system can perceive the potential risks of new energy access points in advance. This early warning mechanism can effectively avoid sudden equipment failures, thereby ensuring the safe and stable operation of the system; the cumulative value of the risk is limited by the exponential decay model, so that the risk probability varies within a reasonable range. This model avoids the unlimited growth of the risk value, and at the same time can reflect the overall risk situation of the current system by accumulating the risk of incremental data.

[0060] In addition, if Figure 2 As shown, this embodiment also discloses a new energy system operation status monitoring and analysis system 500. The new energy system operation status monitoring and analysis system 500 includes a collection module 501, a structure division module 502, a data model construction module 503, a panoramic view construction module 504, a data flow optimization module 505, and an analysis result display module 506.

[0061] The acquisition module 501 is connected to the existing new energy monitoring system to collect the operating status data of the new energy equipment. The structure division module 502 divides the operating status data according to the preset hierarchical structure to obtain hierarchical structure data; the preset hierarchical structure includes regional level, station level, and equipment level. The data model construction module 503 constructs the hierarchical structure into a hierarchical data model through a dynamic time series modeling algorithm. The panoramic map construction module 504 is used to construct a cross-regional panoramic monitoring map and connect the hierarchical data model to the panoramic monitoring map. The data flow optimization module 505 optimizes and schedules the data flow in the panoramic monitoring map through a dynamic network optimization algorithm. The analysis result display module 506 collects real-time data of new energy access points through an incremental data synchronization algorithm, performs data analysis on the new energy access points, and displays the analysis results in the panoramic monitoring map.

[0062] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0063] It should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0064] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0065] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0066] It should be noted that the method for monitoring and analyzing the operation status of a new energy system based on a multi-level structure disclosed in the above embodiment can be implemented in whole or in part by software, hardware, firmware or any other combination in the actual application process. When implemented using software, the above embodiment can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0067] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0068] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0069] As described above, although the present invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the present invention itself. Various changes may be made to it in form and detail without departing from the spirit and scope of the present invention as defined in the appended claims.

Claims

1. A new energy system operation status monitoring and analysis method based on a multi-level structure, characterized in that: The steps include: Access to the existing new energy monitoring system to collect operating status data of new energy equipment; Dividing the operating status data according to a preset hierarchical structure to obtain hierarchical structure data; the preset hierarchical structure includes a regional level, a station level, and an equipment level; constructing the hierarchical structure into a hierarchical data model through a dynamic time series modeling algorithm; Construct a cross-regional panoramic monitoring map, and connect the hierarchical data model to the panoramic monitoring map; optimize and schedule the data flow in the panoramic monitoring map through a dynamic network optimization algorithm; Through the incremental data synchronization algorithm, real-time data of new energy access points is collected, data analysis is performed on the new energy access points, and the analysis results are displayed in the panoramic monitoring map.

2. The method for monitoring and analyzing the operation status of a new energy system based on a multi-level structure according to claim 1 is characterized in that: The regional level is responsible for cross-regional data collection and management; the station level is used to process equipment and power grid data within the station; the equipment level is used to monitor the operating status of a single device; The regional level, station level and equipment level collect and upload data in real time by setting sensors and communication modules.

3. The method for monitoring and analyzing the operation status of a new energy system based on a multi-level structure according to claim 1 is characterized in that: The hierarchical structure is constructed into a hierarchical data model through a dynamic time series modeling algorithm, specifically including: Extracting time series features from the hierarchical data using a dynamic time series modeling algorithm; According to the extracted time series features, dynamic data models are constructed for the three levels of region, station, and equipment; After the multi-level dynamic data model is built, real-time data is continuously collected and the dynamic data model is updated online through a dynamic time series modeling algorithm.

4. The method for monitoring and analyzing the operation status of a new energy system based on a multi-level structure according to claim 3 is characterized in that: The hierarchical data is subjected to time series feature extraction using a dynamic time series modeling algorithm, specifically including: At the regional level, cluster analysis algorithm is used to process regional time series data, calculate the similarity of regional time series data, and extract time series features; The station level uses convolutional neural networks to analyze the dependencies and timing characteristics between stations; The device level uses support vector machines to classify the operating status and timing characteristics of devices.

5. The method for monitoring and analyzing the operation status of a new energy system based on a multi-level structure according to claim 1 is characterized in that: Construct a cross-regional panoramic monitoring map, including: Set the stations as nodes of the graph, set the connection relationships between nodes as edges, set regional attributes for the nodes, that is, set the regions to which the nodes belong, and build a cross-regional panoramic monitoring map.

6. The method for monitoring and analyzing the operation status of a new energy system based on a multi-level structure according to claim 1 is characterized in that: The dynamic network optimization algorithm includes a shortest path algorithm and / or a maximum flow algorithm.

7. The method for monitoring and analyzing the operation status of a new energy system based on a multi-level structure according to claim 1 is characterized in that: Through the incremental data synchronization algorithm, real-time data of new energy access points are collected and data analysis is performed on the new energy access points, including: Acquire real-time data based on the collection frequency of the new energy access point, compare the data at the current time point with the data at the previous time point, extract the data points where the state or value has changed, and transmit the incremental data to the data processing center; In the data processing center, after receiving the incremental data, all the incremental data with value changes in the incremental data are obtained and set as the incremental data set; Calculate the priority of corresponding data according to the incremental change value in the incremental data set, and perform data prediction on the corresponding data according to the priority of the corresponding data; According to the predicted value predicted by the data, the risk probability of the new energy access point is calculated by a preset risk assessment formula, and the predicted value and the risk probability are set as the analysis result.

8. The method for monitoring and analyzing the operation status of a new energy system based on a multi-level structure according to claim 7 is characterized in that: The priority of the corresponding data is calculated according to the incremental change value in the incremental data set. The calculation formula is as follows: ； In the formula, For the Incremental data The priority of For the Incremental data At the point in time The value of For the Incremental data At the point in time The value of The risk probability of the new energy access point is calculated by a preset risk assessment formula, and the risk assessment formula is as follows: ； In the formula, is the risk probability of the new energy access point, is the number of incremental data of new energy access points, For the Incremental data At the point in time The predicted value of With Incremental data Preset status thresholds The distance between.

9. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for monitoring and analyzing the operating status of a new energy system based on a multi-level structure as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one executable instruction. When the executable instruction is executed on the electronic device, the electronic device executes the multi-level structure-based new energy system operation status monitoring and analysis method as described in any one of claims 1 to 8.

Images