New energy station operation index comparative analysis display method and system

Abstract

The invention discloses a new energy station operation index multi-dimensional comparative analysis display method and system, and belongs to the field of new energy station operation management and data analysis. The method comprises the following steps: fusing and standardizing multi-source heterogeneous data, collecting and cleaning multi-station data, and classifying and storing the multi-station data as a standardized data pool; rasterized multi-dimensional indexes are calculated, grids are divided, data are mapped, and grid-level and hierarchical multi-dimensional indexes are generated; performing dynamic weight and TOPSIS evaluation, constructing an evaluation model to calculate the score of a single station, extracting a core index intersection, and transversely comparing the ranking of the stations; the evaluation result is subjected to instantiation storage and hierarchical storage to guarantee data query and tracing; and performing multi-dimensional visual display, displaying the data by multiple terminals, and generating a decision report. The system comprises corresponding function modules. According to the method, the problems of data fragmentation, evaluation system deficiency, non-visual display and the like are solved, multi-station data integration, quantitative evaluation and visual decision making are realized, and the operation management efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of new energy power station operation management and data analysis technology, and in particular to a method and system for comparative analysis and display of new energy power station operation indicators. Background Technology

[0002] With the rapid growth of installed capacity of new energy sources such as wind power and photovoltaics, the scale of new energy power plants operated by power generation companies is becoming increasingly large. However, the types of data in new energy power plants are diverse (including real-time operation data, equipment status data, environmental monitoring data, etc.) and the amount of data is enormous. Moreover, there are differences between power plants in terms of resource conditions, equipment models, and installed capacity, resulting in low integration of operational data and making it difficult to form a unified and quantifiable evaluation system for operational capabilities.

[0003] Currently, existing technical solutions mostly focus on real-time monitoring of a single power plant (such as the PMU-based performance monitoring system disclosed in reference document CN202211392622.4), or on prediction and scheduling of a single dimension such as power generation (such as CN118367593A). These solutions have the following obvious shortcomings: First, they lack a complete operational evaluation index system that can cover multiple dimensions such as power generation capacity, equipment efficiency, operating conditions, and maintenance quality; second, the data analysis perspective is singular, mostly limited to comparison with the historical data of the power plant itself, lacking horizontal benchmarking analysis with similar power plants in the same region, and failing to help power generation companies discover their relative position and operational shortcomings in the industry; finally, the data analysis results are not presented intuitively, failing to comprehensively present complex multi-dimensional indicators through visualization, which is not conducive to managers quickly grasping the overall operational status and making accurate decisions.

[0004] Therefore, there is an urgent need for a new energy power station operation and management solution that can integrate multi-source data, construct a scientific evaluation system, realize multi-dimensional comparative analysis, and provide intuitive display. Summary of the Invention

[0005] In view of the shortcomings of the prior art, the purpose of this invention is to overcome the shortcomings of the prior art and provide a method and system for analyzing the operation indicators of new energy power stations that can realize multi-source data fusion, construct a scientific evaluation system, and support multi-dimensional comparative analysis.

[0006] A method for multi-dimensional comparative analysis and display of operational indicators of new energy power stations includes the following steps:

[0007] S100. Multi-source heterogeneous data fusion and standardization processing: Real-time operation data of multiple new energy power stations are collected through a secure interface at a preset cycle. After data quality control, the data is standardized by time, station and equipment and stored in a distributed cache to form a standardized data pool.

[0008] S200. Based on the calculation of multi-dimensional indicators of gridded spatial units, it inherits the standardized data pool of S100, divides the target analysis area into basic grids, generates grid-level benchmark values ​​through data space mapping and grid aggregation operations, calculates multi-dimensional operation indicators and summarizes them according to equipment, station and region levels to form multi-time dimension indicator results, and determines the core indicator dataset at the same time.

[0009] S300. Comprehensive evaluation of operational capabilities based on dynamic weights and TOPSIS algorithm: Based on multi-dimensional indicator results, an operational capability evaluation model is constructed to calculate the comprehensive score of a single site; the TOPSIS algorithm is used to make horizontal comparisons of sites of the same type to generate relative similarity and ranking.

[0010] S400. Evaluation results are instantiated and dynamically stored. Based on the indicator calculation results of S200 and the evaluation results of S300, data is efficiently queried and traceable in the long term through instantiated storage, hierarchical storage and lifecycle management.

[0011] S500 provides multi-dimensional visualization and decision support. Based on the indicators and evaluation results stored in S400, it builds a multi-terminal visualization system through display screens, web terminals, and mobile terminals. It presents data intuitively in the form of overview dashboards, heat maps, trend charts, radar charts, etc. It supports multi-dimensional filtering and drill-down analysis, generates customized decision reports, and completes the closed loop from technical analysis to business decision-making.

[0012] As a further solution, the real-time operational data includes millisecond-level telemetry and telecontrol data, power generation data, equipment fault logs, and environmental monitoring data, ensuring coverage of the entire operational scenario.

[0013] As a further solution, in the data quality control, the collected data is first checked for completeness. If the proportion of missing values ​​exceeds 5% for a single type of data, a linear interpolation or mean completion process is triggered to ensure data integrity. Then, outlier cleaning is performed. Based on the equipment's rated parameters and historical data distribution, outlier data is identified and removed. Finally, according to the preset data retention strategy, expired and invalid data is deleted to avoid occupying storage resources.

[0014] As a further solution, the steps of dividing the target analysis area into basic grids, generating grid-level baseline values ​​through data spatial mapping and grid aggregation operations, calculating multi-dimensional operational indicators, and then summarizing them at the equipment, site, and region levels to form multi-time-dimensional indicator results include:

[0015] S201. Grid division: Based on the target analysis area, basic grid units are divided according to standard specifications to ensure that each station and equipment can be accurately mapped to the corresponding grid through latitude and longitude, providing a spatial basis for subsequent regional indicator aggregation and avoiding data spatial misalignment;

[0016] S202. Data Spatial Mapping: Extract the latitude and longitude labels of each data point from the standardized data pool of S100, and accurately allocate the data points to the corresponding basic grids through Geographic Information System (GIS) positioning technology, so as to transform the discrete raw data into spatialized data with grid-data association, which facilitates subsequent data aggregation within the grid.

[0017] S203. Grid-level indicator calculation: Within each grid, spatial data is aggregated and calculated to generate grid-level indicator benchmark values. Multi-dimensional operational indicators are calculated based on the benchmark values ​​to form a grid-level operational indicator set.

[0018] At the same time, core indicators were identified from multi-dimensional indicators, combined with industry standards and operational priorities, and a core indicator dataset was constructed.

[0019] S204. Indicator hierarchy aggregation: According to the hierarchical relationship of grid → equipment → site → group → region, the grid-level indicators are aggregated level by level to generate indicator results with multiple time dimensions such as daily, weekly, monthly, and yearly, and the hierarchical indicator results are stored in a structured manner.

[0020] As a further measure, the multi-dimensional operational indicators include, but are not limited to, 10MW power generation capacity, effective utilization hours, power generation equipment utilization rate, equipment failure downtime, photovoltaic combiner box branch failure rate, inverter operating conditions, inverter failure downtime, and environmental monitoring equipment operating conditions.

[0021] As a further solution, the steps of constructing an operational capability evaluation model based on multi-dimensional indicator results and calculating the comprehensive score of a single station include:

[0022] S301. Evaluation Model Construction:

[0023] From the multi-dimensional indicators of S200, core indicators for operational capability evaluation were selected, and an evaluation model for the operational capability of new energy power stations was constructed.

[0024] Dynamic weight values ​​are assigned to each core indicator, and these dynamic weight values ​​are determined by a combination of AHP and entropy weighting methods.

[0025] First, industry experts are invited to score the importance of the indicators to obtain subjective weights; then, the information entropy of the indicators is calculated based on recent historical data to obtain objective weights that reflect the degree of data dispersion; finally, the dynamic weight is subjective weight × 0.6 + objective weight × 0.4, balancing expert experience and data objectivity; at the same time, an environmental adjustment factor is configured to correct the impact of environmental differences on the indicators.

[0026] S302. Single site comprehensive score: The core indicator values ​​of a single site are obtained from S200 for a specified statistical period. The indicator values ​​are first normalized to the 0-1 range. Then, combined with dynamic weights and environmental adjustment factors, the comprehensive operational capability score of the site is calculated through a weighted average algorithm. The higher the score, the better the operational level.

[0027] The normalization formula for positive indicators in the process of normalizing the indicator value to the 0-1 range is as follows:

[0028] ;

[0029] This is the normalized value of the indicator; This is the actual performance of a positive indicator; This represents the maximum value of the positive indicator.

[0030] The formula for normalizing negative indices is:

[0031] ;

[0032] This is the normalized value of the negative index;

[0033] The formula for the overall score is:

[0034] ;

[0035] for Normalized values ​​of each indicator; Dynamic weights; Environmental adjustment factors; This represents the number of indicators involved in the calculation.

[0036] As a further solution, the steps of using the TOPSIS algorithm to conduct horizontal comparisons of similar sites and generate relative proximity and rankings include:

[0037] Construct a decision matrix by extracting the intersection of the core indicator datasets of the S200 and the core indicator datasets of the comparison group stations from the core indicator dataset of S200, that is, the core indicators that all stations in the comparison group have, to form a decision matrix of station × indicator.

[0038] Matrix standardization involves using range standardization to process the decision matrix and eliminate differences in dimensions and magnitudes.

[0039] Determine the ideal solution: the positive ideal solution is the maximum value of each indicator after standardization, and the negative ideal solution is the minimum value of each indicator after standardization.

[0040] Calculate the distances by using the Euclidean distance formula to determine the distances between each station and the positive and negative ideal solutions.

[0041] The stations are ranked according to the following formula: relative proximity = distance between station and negative ideal solution / (distance between station and positive ideal solution + distance between station and negative ideal solution). The proximity range is 0-1. The stations are ranked in descending order of proximity to obtain the station operation capability ranking.

[0042] As a further solution, the steps to ensure efficient data retrieval and long-term traceability through instantiated storage, tiered storage, and lifecycle management include:

[0043] S401. Result Instantiation Storage: The multi-time-dimensional and multi-level indicator results of S200 and the single-site comprehensive score and multi-site ranking results of S300 are stored in the form of a structured data table. The data table fields include: site number, indicator name, indicator value, statistical period, comprehensive score, ranking, and data generation time, etc., to ensure the consistency of the data structure.

[0044] S402. Tiered storage strategy, adopting a hybrid storage architecture of time-based tiering and access frequency-based tiering:

[0045] Hot data is stored in a columnar database and supports millisecond-level queries.

[0046] Warm data is stored in a distributed file system and retains index information, balancing query speed and storage cost;

[0047] Cold data is compressed using a high compression ratio algorithm of ≥80% and then stored on low-cost storage media to reduce long-term storage costs.

[0048] S403. Data lifecycle management, establishing a full-process data management mechanism:

[0049] Data updates are performed automatically based on daily incremental data, ensuring data timeliness.

[0050] Data backup: During daily off-peak hours, the system automatically backs up the previous day's metrics and evaluation results. The backup data is stored off-site and retained for one year to prevent data loss.

[0051] Data verification involves performing integrity checks on cold data every quarter, confirming that the data is not corrupted by comparing data hash values, and ensuring that historical data is traceable.

[0052] As a further embodiment, S500 includes:

[0053] S501. Multi-terminal visual interface construction: Based on data stored on S400, adaptable interfaces are built for different usage scenarios.

[0054] The large display screen presents an overall operation overview dashboard and a regional power generation heat distribution map. The overall operation overview dashboard displays core data such as the total number of connected power stations, total power generation, average comprehensive score, and failure rate in the form of digital cards. The regional power generation heat distribution map uses color depth to represent the 10MW power generation capacity of each region, with red representing high values ​​and blue representing low values, intuitively reflecting the differences in regional operation.

[0055] On the web platform, it provides trend comparison charts of power plant operation indicators and radar charts of equipment operation status. The trend comparison charts of power plant operation indicators support line charts / bar charts for comparison of multiple indicators such as 10MW power generation capacity and effective utilization hours. Data can be filtered by dragging the time axis to view daily / weekly / monthly / yearly data. The radar charts of equipment operation status display multi-dimensional indicators of a single power plant. It supports loading radar charts of 4 power plants at the same time for horizontal comparison, clearly presenting the advantages and disadvantages.

[0056] The mobile version simplifies the core functions of the web version, focuses on key metrics, and makes it easy for managers to view them anytime, anywhere.

[0057] S502. Interactive analysis function, which allows users to filter and drill down to adjust the displayed content through multiple dimensions, improving the flexibility of analysis:

[0058] Multi-dimensional filtering offers filtering by time, region, site type, and group. Once the filtering operation is triggered, the system retrieves the corresponding data from the S400 in real time to update the interface, with a response time of ≤2 seconds.

[0059] Data drill-down supports hierarchical drill-down from macro to micro levels;

[0060] S503. Customized decision-making report generation: Based on visual analysis results, the system supports the automatic generation of operational diagnostic reports, and users can customize report parameters.

[0061] Report type: Select monthly operations report, quarterly benchmarking report, annual summary report, etc.

[0062] Select the indicators to display for the range of indicators.

[0063] Time period: Specifies the time range that the report covers;

[0064] The system extracts corresponding data from the S400 and automatically generates Word / PDF format reports containing data tables, visualization charts, analysis conclusions, and optimization suggestions, directly providing data support for site resource allocation, operation and maintenance plan formulation, and operation strategy optimization.

[0065] Secondly, this invention provides a multi-dimensional comparative analysis and display system for the operation indicators of new energy power stations, including:

[0066] The data access and processing module is used to collect, clean, and standardize multi-source heterogeneous data.

[0067] The indicator calculation engine module is used for indicator calculation and multi-level aggregation based on spatial grids;

[0068] The intelligent analysis module is used to perform comprehensive evaluation of operational capabilities and horizontal comparative analysis;

[0069] The data storage management module is used to achieve persistent storage and lifecycle management of analysis results;

[0070] The visualization module is used to provide multi-dimensional, interactive data display and decision support functions.

[0071] The metrics calculation engine module includes:

[0072] The module comprises the following sub-modules: Raster Division Sub-module: Based on GIS map data, it supports custom raster specifications, automatically generates a raster map of the target area, and associates unique raster identifiers; Data Mapping Sub-module: Extracts latitude and longitude information from the standardized data pool, accurately maps data points to corresponding rasters using a spatial indexing algorithm, and generates a raster-data association table; Indicator Calculation Sub-module: Contains built-in aggregation functions to calculate raster-level baseline values; provides indicator calculation templates and supports custom indicator formula configuration; and combines industry standards and user needs to select core indicators and construct a core indicator dataset; Indicator Aggregation Sub-module: Aggregates indicators hierarchically by raster → equipment → site → group → region using a distributed computing framework, generating multi-time-dimensional indicator results, and synchronizing them to the intelligent analysis module and data storage management module.

[0073] The intelligent analysis module includes: a weight configuration submodule, which provides an AHP expert scoring interface, an entropy weight method data processing tool, and outputs dynamic weight values; it supports the configuration of environmental adjustment factors; a single-site scoring submodule, which obtains the core indicator values ​​of S200, incorporates a normalization algorithm and a weighted average algorithm, automatically calculates the comprehensive operational capability score of a single site, and supports custom score intervals; and a multi-site comparison submodule, which integrates the TOPSIS algorithm toolkit, supports the selection of comparison group sites, automatic extraction of the intersection of core indicator datasets, generates a decision matrix and completes standardization, ideal solution calculation, distance calculation and sorting, and outputs single-site scores and multi-site ranking results to the data storage and management module; it also supports the analysis of differences in comparison results.

[0074] The data storage management module includes: an instantiation storage submodule, which creates structured data tables, stores metrics and evaluation results, and supports batch data import and incremental updates; it provides a data consistency verification mechanism to ensure data integrity; a tiered storage submodule, which has a built-in data popularity identification algorithm to automatically classify data into hot, warm, and cold data and migrate them to the corresponding storage media; and it supports custom storage strategies.

[0075] The lifecycle management submodule provides a scheduled task scheduler to configure data update, backup, and verification tasks; supports backup data management; and provides a data lifecycle monitoring interface to display the data storage volume, access frequency, and backup status at each level.

[0076] The visualization module includes: an interface rendering submodule, which develops multi-terminal interfaces based on front-end frameworks (Vue / React), integrates ECharts / Highcharts visualization libraries, and enables dynamic rendering of components such as operation overview dashboards, heatmaps, trend charts, and radar charts; it supports customized interface styles; an interactive analysis submodule, which provides filtering controls, supports combinations of filtering conditions and real-time data updates; implements data drill-down functionality; provides data export functionality; and a report generation submodule, which has built-in report templates and supports user-defined report content; it automatically extracts data from the data storage management module and populates the templates to generate Word / PDF format reports, supporting online preview, download, and email sending; it also supports report history version management and querying.

[0077] In summary, due to the adoption of the above technical solution, the beneficial technical effects of the invention are as follows:

[0078] To address data fragmentation and build a unified data foundation, this invention utilizes S100 multi-source heterogeneous data fusion and standardization processing. Leveraging industrial internet security interfaces, it collects comprehensive operational data from multiple sites. After integrity verification, anomaly cleanup, and expired data removal, the data is standardized by a three-level classification: time, site, and equipment, and stored in a distributed cache forming a data pool. This solution effectively solves the shortcomings of existing technologies, such as inconsistent data formats, low data quality, and severe fragmentation across different sites. It provides unified, high-quality data support for subsequent indicator calculations and evaluation analyses, ensuring the comparability and usability of data from multiple sites.

[0079] This invention establishes a multi-dimensional evaluation and horizontal benchmarking system to achieve objective quantitative evaluation: Through S200 gridded spatial unit calculations, discrete data is transformed into multi-dimensional operational indicators such as 10MW power generation capacity, effective utilization hours, and equipment utilization rate, and these are summarized hierarchically to form multi-time-dimensional results. Then, through S300 dynamic weighting and the TOPSIS algorithm, combined with expert experience and data characteristics, dynamic weights are configured to correct for environmental differences and calculate the comprehensive score of a single power station. Simultaneously, the intersection of core indicators from multiple power stations is extracted for horizontal comparison, generating relative similarity and ranking. This technical solution overcomes the shortcomings of existing technologies that lack a multi-dimensional evaluation system and can only perform historical comparisons of single power stations. It achieves objective quantitative benchmarking of the operational capabilities of power stations of the same type and region, helping enterprises accurately identify their own strengths and weaknesses and providing a clear direction for operational optimization.

[0080] This invention achieves multi-terminal visualization and interactive decision-making, improving management efficiency: It utilizes S400 instantiated dynamic storage, employing a layered storage strategy for hot, warm, and cold data to ensure efficient querying and long-term traceability of indicators and evaluation results. Furthermore, it leverages S500 multi-dimensional visualization to construct a multi-terminal system encompassing large screens, web, and mobile devices. Data is presented intuitively in the form of overview dashboards, heatmaps, trend charts, and radar charts, supporting multi-dimensional filtering and drill-down analysis, and automatically generating customized decision reports. This solution overcomes the shortcomings of existing technologies, such as unintuitive result display, poor interactivity, and low decision-making efficiency. It allows managers to grasp the overall or partial operational status anytime, anywhere, quickly obtain data insights and optimization suggestions, and significantly improve the efficiency and accuracy of decision-making in the operation and management of new energy power plants. Attached Figure Description

[0081] Figure 1 This is a flowchart illustrating a method for comparing and analyzing operational indicators of new energy power plants from multiple dimensions. Detailed Implementation

[0082] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0083] To make the objectives, technical solutions, and advantages of the invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0084] This invention constructs a complete operational indicator analysis system through a progressive technical process: multi-source data fusion standardization → rasterized indicator calculation → dynamic weighting + TOPSIS evaluation → instantiated storage → multi-dimensional visualization. Based on S100 multi-source data fusion standardization, it solves data quality and format issues, providing a standardized data pool for subsequent steps. S200 rasterized indicator calculation, taking over the data pool, transforms discrete data into spatialized, aggregatable multi-dimensional indicators, achieving data-to-indicator transformation. S300 dynamic weighting and TOPSIS evaluation, based on indicator results, generates quantifiable single-site scores and multi-site rankings, solving the problem of objective benchmarking. S400 instantiated storage ensures efficient querying and long-term traceability of indicators and evaluation results, providing data support for display. S500 multi-dimensional visualization transforms data and evaluation results into an intuitive interactive interface, realizing data-to-decision implementation. Each step is closely linked through data input and output, forming a technical closed loop.

[0085] See Figure 1 The diagram illustrates a structural schematic of a method for multi-dimensional comparative analysis and display of operational indicators of new energy power stations provided by an embodiment of the present invention, which is described in detail below:

[0086] S100. Multi-source heterogeneous data fusion and standardization processing, as the data foundation of the entire technical process, collects real-time operational data from multiple sites through industrial internet security interfaces. After integrity verification, anomaly cleaning, and expired data cleanup, the data is standardized by time, site, and equipment and stored in a distributed cache to form a data pool. This provides high-quality, low-latency data input for S200 indicator calculations, specifically including:

[0087] Data acquisition relies on the secure interface of the industrial internet big data platform to acquire real-time operation data from multiple new energy power stations according to preset cycles (e.g., every 5 minutes) and frequencies. The data types cover millisecond-level telemetry and telecontrol data of equipment (e.g., wind turbine speed, inverter output power), power generation data (daily / monthly cumulative values), equipment fault logs (fault type, occurrence time, duration) and environmental monitoring data (wind speed, light intensity, component temperature), ensuring coverage of the entire operation scenario;

[0088] Data quality control involves first verifying the integrity of collected data by detecting the proportion of missing values. If the proportion of missing values ​​in a single data category exceeds 5%, a linear interpolation or mean-based completion process is triggered to ensure data integrity. Next, outlier cleaning is performed by identifying and removing abnormal data based on the equipment's rated parameters and historical data distribution. Finally, expired and invalid data is deleted according to the preset data retention strategy to avoid consuming storage resources.

[0089] Data standardization and storage involves classifying the cleaned data into three levels: date and time, site identifier (e.g., site number GF-05), and equipment category (e.g., wind turbine, photovoltaic combiner box). Data units are standardized (e.g., power unit is kW, power generation unit is kWh, temperature unit is ℃) to form a standardized data structure. The standardized data is stored in a distributed cache server (e.g., Redis cluster) to build a low-latency, highly available standardized data pool, which can be directly used by the S200 for indicator calculation.

[0090] S200. Based on the calculation of multi-dimensional indicators using gridded spatial units, it inherits the standardized data pool of S100, divides the target analysis area into basic grids, generates grid-level benchmark values ​​through data spatial mapping and grid aggregation operations, calculates multi-dimensional operational indicators and summarizes them at the equipment, station and regional levels to form multi-time dimension indicator results, and determines the core indicator dataset, providing quantifiable and comparable indicator inputs and the basis for the intersection of core indicator datasets for the comprehensive evaluation of S300.

[0091] S201. Grid division: Based on the target analysis area, basic grid units are divided according to standard specifications to ensure that each station and equipment can be accurately mapped to the corresponding grid through latitude and longitude, providing a spatial basis for subsequent regional indicator aggregation and avoiding data spatial misalignment;

[0092] S202. Data Spatial Mapping: Extract the latitude and longitude identifiers of each data point from the standardized data pool of S100, and accurately allocate the data points to the corresponding basic grids through Geographic Information System (GIS) positioning technology, so as to transform the discrete raw data into spatialized data with grid-data association, which facilitates subsequent data aggregation within the grid.

[0093] S203. Grid-level indicator calculation: Within each grid, spatial data is aggregated to generate grid-level indicator baseline values, such as the total monthly power generation within the grid and the average operating time of equipment within the grid. Based on the baseline values, multi-dimensional operation indicators are calculated, including but not limited to 10MW power generation capacity, effective utilization hours (power generation / installed capacity), power generation equipment utilization rate, equipment failure downtime, photovoltaic combiner box branch failure rate, inverter operating conditions, inverter failure downtime, environmental monitoring equipment operating conditions, etc., forming a grid-level operation indicator set. At the same time, from these multi-dimensional indicators, combined with industry standards and operational focus, core indicators are determined, such as 10MW power generation capacity, effective utilization hours, equipment utilization rate, failure downtime, inverter conversion efficiency, etc., constructing a core indicator dataset, which provides a foundation for the extraction of the intersection of core indicator datasets from multiple sites in S300.

[0094] The formula for calculating 10MW of power generation is:

[0095] ;

[0096] This indicates the power generation of the power plant, expressed in kWh. This indicates the total installed capacity of the power station, in kW.

[0097] S204. Indicator hierarchy aggregation: According to the hierarchical relationship of grid → equipment → site → group → region, the grid-level indicators are aggregated level by level to generate indicator results in multiple time dimensions such as day, week, month, and year; the hierarchical indicator results are stored in a structured manner, on the one hand synchronized to S300 as the core input for comprehensive evaluation, and on the other hand transmitted to S400 for persistent storage.

[0098] S300, based on dynamic weights and the TOPSIS algorithm, is a key component of the evaluation and analysis. It builds an operational capability evaluation model by taking the multi-dimensional indicator results and core indicator datasets from S200, configuring dynamic weights and environmental adjustment factors, and calculating the comprehensive score of a single site. The TOPSIS algorithm is used to make horizontal comparisons of similar sites, extract the intersection of core indicator datasets, and generate relative similarity and rankings, providing decision-making and benchmarkable evaluation results for the visualization of S500.

[0099] S301. Evaluation Model Construction: From the core indicators determined in S200, core indicators for operational capability evaluation are selected to construct an evaluation model for the operational capability of new energy power plants; dynamic weight values ​​are assigned to each core indicator, determined through a combination of the Analytic Hierarchy Process (AHP) and the entropy weight method.

[0100] First, several industry experts were invited to score the importance of the indicators to obtain subjective weights. Then, the information entropy of the indicators was calculated based on recent historical data to obtain objective weights that reflect the degree of data dispersion. The final dynamic weight is: subjective weight × 0.6 + objective weight × 0.4, balancing expert experience and data objectivity. At the same time, an environmental adjustment factor was configured to correct the impact of environmental differences on the indicators (e.g., for wind farms with wind speeds below 3 m / s, the 10 MW power generation capacity indicator is multiplied by an adjustment factor of 0.85; for photovoltaic power stations with solar irradiance below 200 W / m², the effective utilization hours are multiplied by an adjustment factor of 0.9).

[0101] S302. Single-site comprehensive score: Obtain the core indicator values ​​of a single site for a specified statistical period from S200. First, normalize the indicator values ​​to the 0-1 range. The normalization formula for the positive indicator is as follows:

[0102] ;

[0103] This is the normalized value of the indicator; This is the actual performance of a positive indicator; This represents the maximum value of the positive indicator.

[0104] The formula for normalizing negative indices is:

[0105] ;

[0106] This is the normalized value of the negative index;

[0107] The formula for the overall score is:

[0108] ;

[0109] for Normalized values ​​of each indicator; Dynamic weights; Environmental adjustment factors; The higher the score, the better the operational level, and this score is directly used by S500 to display the operational status of a single station.

[0110] A horizontal comparison of multiple sites was conducted, selecting sites of the same type and region as the comparison group, and the TOPSIS algorithm was used for analysis.

[0111] Construct a decision matrix by extracting the intersection of the core indicator datasets of the comparison group stations from the core indicator dataset of S200, that is, the core indicators that all stations in the comparison group have, to form a decision matrix of m stations × n indicators.

[0112] Matrix standardization involves using range standardization to process the decision matrix and eliminate differences in dimensions and magnitudes.

[0113] Determine the ideal solution: the positive ideal solution is the maximum value of each indicator after standardization, and the negative ideal solution is the minimum value of each indicator after standardization.

[0114] Calculate the distances by using the Euclidean distance formula to determine the distances between each station and the positive and negative ideal solutions.

[0115] Among them, the distance between the station and the ideal solution :

[0116] ;

[0117] For the first The first site to be evaluated The standardized values ​​of each indicator; For the first The positive ideal solution value of each index;

[0118] Distance between the station and the negative ideal solution :

[0119] ;

[0120] For the first The negative ideal solution value of each index;

[0121] Sort by relative proximity The proximity of each site is calculated, with a proximity range of 0-1. The sites are sorted in descending order of proximity to obtain the ranking of their operational capabilities. The comprehensive score and ranking results are synchronized to the S400 storage for the S500 to display the horizontal comparison results.

[0122] S400 inherits the indicator calculation results of S200 and the evaluation results of S300. Through instantiated storage, tiered storage (hot / warm / cold data) and lifecycle management, it ensures efficient data query and long-term traceability, providing stable data support for S500 visualization, while balancing storage efficiency and cost.

[0123] The results are instantiated and stored in the form of a structured data table, which stores the multi-time-dimensional and multi-level indicator results of S200 and the single-site comprehensive score and multi-site ranking results of S300. The data table fields include site number, indicator name, indicator value, statistical period, comprehensive score, ranking, and data generation time, to ensure that the data structure is consistent and that S500 can quickly retrieve the data through structured queries.

[0124] The tiered storage strategy employs a hybrid storage architecture that combines time-based tiering with access frequency tiering.

[0125] Hot data (accessed ≥ 1 time / day, such as daily metrics and real-time comprehensive scores for the past 3 months), is stored in a columnar database (such as HBase), supports millisecond-level queries, and meets the real-time display requirements of S500.

[0126] Warm data (accessed 0.1-1 times / day, such as monthly metrics and rankings for 3 months to 1 year), is stored in a distributed file system (such as HDFS) and retains index information, balancing query speed and storage cost.

[0127] Cold data (accessed less than 0.1 times / day, such as annual indicators or rankings over a year) is compressed using a high compression ratio algorithm (compression rate ≥ 80%) and stored on low-cost storage media (such as tape libraries) to reduce long-term storage costs.

[0128] Data lifecycle management, establishing a full-process data management mechanism:

[0129] Data updates are based on daily incremental data (such as the daily indicator calculation results and the daily evaluation results), and the corresponding level of stored data is automatically updated to ensure data timeliness.

[0130] Data backup: During daily off-peak hours, the system automatically backs up the previous day's metrics and evaluation results. The backup data is stored off-site and retained for one year to prevent data loss.

[0131] Data verification involves performing integrity checks on cold data every quarter, confirming that the data is not corrupted by comparing data hash values, and ensuring that historical data is traceable. This storage system directly provides S500 with real-time hot data query and historical cold data retrieval services, supporting the multi-time-dimensional analysis needs for visualization.

[0132] S500 inherits the metrics and evaluation results of S400 storage, and builds a multi-terminal visualization system through display screens, web terminals, and mobile terminals. It presents data intuitively in the form of overview dashboards, heat maps, trend charts, radar charts, etc., supports multi-dimensional filtering and drill-down analysis, generates customized decision reports, and completes the closed loop from technical analysis to business decision-making.

[0133] S501. Multi-terminal visual interface construction: Based on data stored on S400, adaptable interfaces are built for different usage scenarios.

[0134] The large display screen, deployed in the enterprise monitoring center, presents an overall operation overview dashboard (showing core data such as the total number of connected stations, total power generation, average comprehensive score, and failure rate in the form of digital cards) and a regional power generation heat distribution map;

[0135] The web version (compatible with computer browsers) provides trend comparison charts of site operation indicators and radar charts of equipment operation status.

[0136] Mobile version (compatible with mobile browsers / apps) simplifies core web functions, focuses on key metrics, and makes it easy for administrators to view information anytime, anywhere.

[0137] S502. Interactive analysis function, which allows users to filter and drill down to adjust the displayed content through multiple dimensions, improving the flexibility of analysis:

[0138] Multi-dimensional filtering offers filtering by time, region, site type, and group. Once the filtering operation is triggered, the system retrieves the corresponding data from the S400 in real time to update the interface, with a response time of ≤2 seconds.

[0139] Data drill-down supports hierarchical drill-down from macro to micro levels. For example, clicking on a province in a regional heat map allows you to drill down to view the distribution and indicators of facilities in various cities within that province; clicking on a trend chart of a facility allows you to drill down to view the real-time operating data of the facility's core equipment, meeting the needs of managers for in-depth analysis from global to local perspectives.

[0140] S503. Customized decision-making report generation: Based on visual analysis results, the system supports the automatic generation of operational diagnostic reports, and users can customize report parameters.

[0141] Report type: Select monthly operations report, quarterly benchmarking report, annual summary report, etc.

[0142] Select the indicators to display for the range of indicators.

[0143] Time period: Specifies the time range that the report covers;

[0144] The system extracts corresponding data from the S400 and automatically generates Word / PDF format reports containing data tables, visualization charts, analysis conclusions, and optimization suggestions. This provides data support for site resource allocation, operation and maintenance plan formulation, and operation strategy optimization, thus completing the final implementation of the technical process.

[0145] Secondly, this invention provides a multi-dimensional comparative analysis and display system for the operation indicators of new energy power stations, including:

[0146] The data access and processing module is used to collect, clean, and standardize multi-source heterogeneous data.

[0147] The indicator calculation engine module is used for indicator calculation and multi-level aggregation based on spatial grids;

[0148] The metrics calculation engine module includes:

[0149] The raster division submodule, based on GIS map data, supports custom raster specifications, automatically generates a raster map of the target area, and associates unique raster identifiers;

[0150] Data mapping submodule: Extracts latitude and longitude information from the standardized data pool, accurately maps data points to corresponding rasters using a spatial indexing algorithm, and generates a raster-data association table;

[0151] The indicator calculation submodule has built-in aggregation operation functions (summation, average, percentage, etc.) to calculate grid-level benchmark values; it provides indicator calculation templates and supports custom indicator formula configuration; at the same time, it combines industry standards and user needs to select core indicators and build a core indicator dataset.

[0152] The indicator aggregation submodule aggregates indicators by grid → equipment → site → group → region level, and uses a distributed computing framework (such as Spark) to generate multi-time dimension indicator results, which are then synchronized to the intelligent analysis module and data storage management module.

[0153] The intelligent analysis module is used to perform comprehensive evaluation of operational capabilities and horizontal comparative analysis;

[0154] The intelligent analysis module includes:

[0155] The weight configuration submodule provides an AHP expert scoring interface, an entropy weight method data processing tool, and outputs dynamic weight values; it also supports the configuration of environmental adjustment factors.

[0156] The single-site scoring submodule obtains the core indicator values ​​of S200, and has built-in normalization and weighted average algorithms to automatically calculate the comprehensive operational capability score of a single site. It supports custom score ranges (such as 0-1 points, 0-100 points).

[0157] The multi-site comparison submodule integrates the TOPSIS algorithm toolkit, supports the selection of comparison group sites, automatic extraction of the intersection of core indicator datasets, generation of decision matrices and completion of standardization, ideal solution calculation, distance calculation and sorting, and output of single-site scores and multi-site ranking results to the data storage and management module; at the same time, it supports the analysis of differences in comparison results.

[0158] The data storage management module is used to achieve persistent storage and lifecycle management of analysis results;

[0159] The data storage management module includes:

[0160] Instantiate the storage submodule to create structured data tables (based on MySQL / Hive), store metrics and evaluation results, support batch data import and incremental updates; provide data consistency verification mechanisms (such as primary key uniqueness verification) to ensure data integrity;

[0161] The tiered storage submodule has a built-in data popularity identification algorithm that automatically classifies data into hot, warm, and cold data and migrates them to the corresponding storage media; it also supports customizable storage strategies.

[0162] The lifecycle management submodule provides a scheduled task scheduler (such as Quartz), configures data update, backup, and verification tasks, supports backup data management, and provides a data lifecycle monitoring interface to display the data storage volume, access frequency, and backup status at each level.

[0163] The visualization module is used to provide multi-dimensional, interactive data display and decision support functions;

[0164] The visualization module includes:

[0165] The UI rendering submodule is based on a front-end framework (Vue / React) to develop multi-terminal interfaces. It integrates the ECharts / Highcharts visualization library to achieve dynamic rendering of components such as operation overview dashboards, heatmaps, trend charts, and radar charts; and supports customized interface styles.

[0166] The interactive analysis submodule provides filtering controls, supports combinations of filtering conditions and real-time data refresh; implements data drill-down functionality; and provides data export functionality.

[0167] The report generation submodule includes built-in report templates and supports user-defined report content. It automatically extracts data from the data storage management module and populates the template to generate Word / PDF reports, which can be previewed, downloaded, and sent via email. It also supports report history version management and querying.

[0168] The sequence number of each step in the above embodiments does not imply 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 invention.

[0169] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for multi-dimensional comparative analysis and display of operational indicators of new energy power stations, characterized in that, Includes the following steps: S100. Multi-source heterogeneous data fusion and standardization processing: Real-time operation data of multiple new energy power stations are collected through a secure interface at a preset cycle. After data quality control, the data is standardized by time, station and equipment and stored in a distributed cache to form a standardized data pool. S200. Based on the calculation of multi-dimensional indicators of gridded spatial units, it inherits the standardized data pool of S100, divides the target analysis area into basic grids, generates grid-level benchmark values ​​through data space mapping and grid aggregation operations, calculates multi-dimensional operation indicators and summarizes them according to equipment, station and region levels to form multi-time dimension indicator results, and determines the core indicator dataset at the same time. S300. Comprehensive evaluation of operational capabilities based on dynamic weights and TOPSIS algorithm: Based on multi-dimensional indicator results, construct an operational capability evaluation model and calculate the comprehensive score of a single site. The TOPSIS algorithm is used to make horizontal comparisons of similar sites to generate relative similarity and ranking. S400. Evaluation results are instantiated and dynamically stored. Based on the indicator calculation results of S200 and the evaluation results of S300, data is efficiently queried and traceable in the long term through instantiated storage, hierarchical storage and lifecycle management. S500 provides multi-dimensional visualization and decision support. Based on the indicators and evaluation results stored in S400, it builds a multi-terminal visualization system through display screens, web terminals, and mobile terminals. It presents data intuitively in the form of overview dashboards, heat maps, trend charts, radar charts, etc. It supports multi-dimensional filtering and drill-down analysis, generates customized decision reports, and completes the closed loop from technical analysis to business decision-making.

2. The method for multi-dimensional comparative analysis and display of operational indicators of new energy power stations according to claim 1, characterized in that, The real-time operational data includes millisecond-level telemetry and telecontrol data, power generation data, equipment fault logs, and environmental monitoring data, ensuring coverage of the entire operational scenario.

3. The method for multi-dimensional comparative analysis and display of operational indicators of new energy power stations according to claim 1, characterized in that, In the data quality control process, the collected data is first checked for completeness by detecting the proportion of missing values. If the proportion of missing values ​​for a single type of data exceeds 5%, a linear interpolation or mean-based completion process is triggered to ensure data integrity. Then, outlier cleaning is performed by identifying and removing outlier data based on the device's rated parameters and historical data distribution. Finally, according to the preset data retention strategy, expired and invalid data is deleted to avoid occupying storage resources.

4. The method for multi-dimensional comparative analysis and display of operational indicators of new energy power stations according to claim 1, characterized in that, The steps of dividing the target analysis area into basic grids, generating grid-level baseline values ​​through data spatial mapping and grid aggregation operations, calculating multi-dimensional operational indicators, and summarizing them at the equipment, site, and region levels to form multi-time-dimensional indicator results include: S201. Grid division: Based on the target analysis area, basic grid units are divided according to standard specifications to ensure that each station and equipment can be accurately mapped to the corresponding grid through latitude and longitude, providing a spatial basis for subsequent regional indicator aggregation and avoiding data spatial misalignment; S202. Data Spatial Mapping: Extract the latitude and longitude labels of each data point from the standardized data pool of S100, and accurately allocate the data points to the corresponding basic grids through Geographic Information System (GIS) positioning technology, so as to transform the discrete raw data into spatialized data with grid-data association, which facilitates subsequent data aggregation within the grid. S203. Grid-level indicator calculation: Within each grid, spatial data is aggregated and calculated to generate grid-level indicator benchmark values. Multi-dimensional operational indicators are calculated based on the benchmark values ​​to form a grid-level operational indicator set. At the same time, core indicators were identified from multi-dimensional indicators, combined with industry standards and operational priorities, and a core indicator dataset was constructed. S204. Indicator hierarchy aggregation: According to the hierarchical relationship of grid → equipment → site → group → region, the grid-level indicators are aggregated level by level to generate indicator results with multiple time dimensions such as daily, weekly, monthly, and yearly, and the hierarchical indicator results are stored in a structured manner.

5. The method for multi-dimensional comparative analysis and display of operation indicators of new energy power stations according to claim 4, characterized in that, The multi-dimensional operational indicators include, but are not limited to, 10MW power generation capacity, effective utilization hours, power generation equipment utilization rate, equipment failure downtime, photovoltaic combiner box branch failure rate, inverter operating conditions, inverter failure downtime, and environmental monitoring equipment operating conditions.

6. The method for multi-dimensional comparative analysis and display of operational indicators of new energy power stations according to claim 1, characterized in that, The steps for constructing an operational capability evaluation model based on multi-dimensional indicator results and calculating the comprehensive score of a single station include: S301. Evaluation Model Construction: From the multi-dimensional indicators of S200, core indicators for operational capability evaluation were selected, and an evaluation model for the operational capability of new energy power stations was constructed. Dynamic weight values ​​are assigned to each core indicator, determined by a combination of HP and entropy weighting methods: First, industry experts are invited to score the importance of the indicators to obtain subjective weights; then, the information entropy of the indicators is calculated based on recent historical data to obtain objective weights that reflect the degree of data dispersion; finally, the dynamic weight is subjective weight × 0.6 + objective weight × 0.4, balancing expert experience and data objectivity; at the same time, an environmental adjustment factor is configured to correct the impact of environmental differences on the indicators. S302. Single site comprehensive score: The core indicator values ​​of a single site are obtained from S200 for a specified statistical period. The indicator values ​​are first normalized to the 0-1 range. Then, combined with dynamic weights and environmental adjustment factors, the comprehensive operational capability score of the site is calculated through a weighted average algorithm. The higher the score, the better the operational level. In the process of normalizing the indicator value to the 0-1 range, the normalization formula for positive indicators is: Normalized indicator value = Actual value / Maximum indicator value; the normalization formula for negative indicators is: 1 - Actual value / Maximum indicator value. The overall score is calculated as Σ (normalized index value × dynamic weight × environmental adjustment factor).

7. The method for multi-dimensional comparative analysis and display of operational indicators of new energy power stations according to claim 1, characterized in that, The steps of using the TOPSIS algorithm to conduct horizontal comparisons of similar sites and generate relative similarity and rankings include: Construct a decision matrix by extracting the intersection of the core indicator datasets of the S200 and the core indicator datasets of the comparison group stations from the core indicator dataset of S200, that is, the core indicators that all stations in the comparison group have, to form a decision matrix of station × indicator. Matrix standardization involves using range standardization to process the decision matrix and eliminate differences in dimensions and magnitudes. Determine the ideal solution: the positive ideal solution is the maximum value of each indicator after standardization, and the negative ideal solution is the minimum value of each indicator after standardization. Calculate the distances by using the Euclidean distance formula to determine the distances between each station and the positive and negative ideal solutions. The stations are ranked according to the following formula: relative proximity = distance to negative ideal solution / (distance to positive ideal solution + distance to negative ideal solution). The proximity range is 0-1. The stations are ranked in descending order of proximity to obtain the station operation capability ranking.

8. The method for multi-dimensional comparative analysis and display of operation indicators of new energy power stations according to claim 1, characterized in that, The steps to ensure efficient data retrieval and long-term traceability through instantiated storage, tiered storage, and lifecycle management include: S401. Result Instantiation Storage: The multi-time-dimensional and multi-level indicator results of S200 and the single-site comprehensive score and multi-site ranking results of S300 are stored in the form of a structured data table. The data table fields include: site number, indicator name, indicator value, statistical period, comprehensive score, ranking, and data generation time, etc., to ensure the consistency of the data structure. S402. Tiered storage strategy, adopting a hybrid storage architecture of time-based tiering and access frequency-based tiering: Hot data is stored in a columnar database and supports millisecond-level queries. Warm data is stored in a distributed file system and retains index information, balancing query speed and storage cost; Cold data is compressed using a high compression ratio algorithm of ≥80% and then stored on low-cost storage media to reduce long-term storage costs. S403. Data lifecycle management, establishing a full-process data management mechanism: Data updates are performed automatically based on daily incremental data, ensuring data timeliness. Data backup: During daily off-peak hours, the system automatically backs up the previous day's metrics and evaluation results. The backup data is stored off-site and retained for one year to prevent data loss. Data verification involves performing integrity checks on cold data every quarter, confirming that the data is not corrupted by comparing data hash values, and ensuring that historical data is traceable.

9. The method for multi-dimensional comparative analysis and display of operational indicators of new energy power stations according to claim 1, characterized in that, The S500 includes: S501. Multi-terminal visual interface construction: Based on data stored on S400, adaptable interfaces are built for different usage scenarios. The large display screen presents an overall operation overview dashboard and a regional power generation heat distribution map. The overall operation overview dashboard displays core data such as the total number of connected power stations, total power generation, average comprehensive score, and failure rate in the form of digital cards. The regional power generation heat distribution map uses color depth to represent the 10MW power generation capacity of each region, with red representing high values ​​and blue representing low values, intuitively reflecting the differences in regional operation. On the web platform, it provides trend comparison charts of power plant operation indicators and radar charts of equipment operation status. The trend comparison charts of power plant operation indicators support line charts / bar charts for comparison of multiple indicators such as 10MW power generation capacity and effective utilization hours. Data can be filtered by dragging the time axis to view daily / weekly / monthly / yearly data. The radar charts of equipment operation status display multi-dimensional indicators of a single power plant. It supports loading radar charts of 4 power plants at the same time for horizontal comparison, clearly presenting the advantages and disadvantages. The mobile version simplifies the core functions of the web version, focuses on key metrics, and makes it easy for managers to view them anytime, anywhere. S502. Interactive analysis function, which allows users to filter and drill down to adjust the displayed content through multiple dimensions, improving the flexibility of analysis: Multi-dimensional filtering offers filtering by time, region, site type, and group. Once the filtering operation is triggered, the system retrieves the corresponding data from the S400 in real time to update the interface, with a response time of ≤2 seconds. Data drill-down supports hierarchical drill-down from macro to micro levels; S503. Customized decision-making report generation: Based on visual analysis results, the system supports the automatic generation of operational diagnostic reports, and users can customize report parameters. Report type: Select monthly operations report, quarterly benchmarking report, annual summary report, etc. Select the indicators to display for the range of indicators. Time period: Specifies the time range that the report covers; The system extracts corresponding data from the S400 and automatically generates Word / PDF format reports containing data tables, visualization charts, analysis conclusions, and optimization suggestions, directly providing data support for site resource allocation, operation and maintenance plan formulation, and operation strategy optimization.

10. The system for multi-dimensional comparative analysis and display of operational indicators of new energy power stations as described in claim 1, characterized in that, include: The data access and processing module is used to collect, clean, and standardize multi-source heterogeneous data. The indicator calculation engine module is used for indicator calculation and multi-level aggregation based on spatial grids; The intelligent analysis module is used to perform comprehensive evaluation of operational capabilities and horizontal comparative analysis; The data storage management module is used to achieve persistent storage and lifecycle management of analysis results; The visualization module is used to provide multi-dimensional, interactive data display and decision support functions.

Images