A method and system for evaluating power grid assets

Abstract

The present invention provides a power grid asset evaluation method and system, which relates to the technical field of power grid management; the method includes: obtaining the asset operation status of each asset in the power grid according to the real-time monitoring data of the power grid, and performing data fusion to obtain a data set of the asset within a preset time period; performing feature extraction on the data set to obtain relevant data of the asset at the same time within the preset time period; and predicting the operating environment of the asset within the preset time period to obtain at least one operating environment of the asset within the preset time period; and then obtaining the operating efficiency of the asset under the operating environment; according to the operating efficiency and the preset standard efficiency, obtaining the maintenance requirements of the asset under the operating environment; according to the operating efficiency and the maintenance requirements, obtaining the asset evaluation of the asset within the preset time period. The present invention analyzes the operating efficiency of assets in a negative electricity price environment, improves the accuracy and reliability of power grid asset evaluation, and thus optimizes the operation and maintenance of the power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid management, and in particular to a power grid asset evaluation method and system. Background Art

[0002] Currently, the assessment of power grid assets is usually based on the physical condition and performance data of the assets, and the health level and utilization efficiency analysis is carried out to determine the current operating efficiency and potential maintenance needs of the assets. In addition, the scale structure of the assets is also considered during the assessment process to analyze whether their layout and configuration in the power grid are optimized.

[0003] In the existing technology, the emergence of new energy has led to major changes in the assets of the power grid. The volatility of new energy can easily lead to an oversupply of electricity in the power grid during certain periods, resulting in an oversupply of electricity, which affects the operating power of the assets, thereby causing a drop in electricity prices and even negative electricity prices. A negative electricity price environment will lead to misjudgment of the actual current operating conditions of the assets, thereby affecting the judgment of the current operating efficiency of the assets and potential maintenance needs. At the same time, a negative electricity price environment will also affect the determination of the power grid's revenue and asset valuation. Summary of the invention

[0004] The technical problem solved by the present invention is how to improve the accuracy of power grid asset evaluation in a negative electricity price environment.

[0005] In order to solve the above problems, the present invention provides a power grid asset evaluation method and system.

[0006] In a first aspect, the present invention provides a method for evaluating power grid assets, comprising:

[0007] According to the real-time monitoring data of the power grid, the asset operation status of each asset in the power grid is obtained, and the asset operation status includes the power supply, power demand, power grid load, voltage data and current data of the asset;

[0008] Performing data fusion on the power supply, power demand, grid load, voltage data and current data of the asset to obtain a data set of the asset within a preset time period;

[0009] Extract features from the data set to obtain the load rate, voltage fluctuation, current fluctuation, and power supply stability of the asset at the same time in the preset time period;

[0010] Predicting the operating environment of the asset within the preset time period according to the load rate of the asset, the voltage fluctuation, the current fluctuation, and the power supply stability, and obtaining at least one operating environment of the asset within the preset time period;

[0011] Obtaining the operating efficiency of the asset under the operating environment according to the power supply, the power demand, the grid load, the voltage data and the current data having the same time series of the asset in the time period corresponding to each operating environment;

[0012] According to the operating efficiency and the preset standard efficiency, the maintenance requirement of the asset under the operating environment is obtained;

[0013] An asset evaluation result of the asset within the preset time period is obtained according to the operating efficiency and the maintenance requirements.

[0014] Optionally, the performing data fusion on the power supply, the power demand, the grid load, the voltage data and the current data of the asset to obtain a data set of the asset within a preset time period includes:

[0015] Performing data cleaning on the power supply, the power demand, the grid load, the voltage data, and the current data according to a preset preprocessing method;

[0016] Performing time calibration on the cleaned power supply, power demand, grid load, voltage data and current data to obtain the power supply, power demand, grid load, voltage data and current data having the same time series;

[0017] The power supply, the power demand, the grid load, the voltage data and the current data having the same time series are encoded by an encoder to obtain the data set;

[0018] The step of time-calibrating the cleaned power supply, power demand, grid load, voltage data, and current data to obtain the power supply, power demand, grid load, voltage data, and current data having the same time series includes:

[0019] Obtaining timestamps corresponding to the power supply, the power demand, the grid load, the voltage data, and the current data after cleaning;

[0020] According to the timestamp, the cleaned power supply, the power demand, the grid load, the voltage data and the current data are respectively sorted in the time sequence of the preset time period to obtain the power supply, the power demand, the grid load, the voltage data and the current data with the same time series.

[0021] Optionally, the feature extraction of the data set to obtain the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period includes:

[0022] Determine the load rate of the asset at the same time within the preset time period according to the power supply and the grid load of the data set;

[0023] Performing feature extraction on the voltage data and the current data of the data set to obtain standard deviations of the voltage data and the current data;

[0024] According to the standard deviation of the voltage data and the current data, respectively obtain the voltage fluctuation and the current fluctuation of the asset at the same time within the preset time period;

[0025] Performing feature extraction on the power supply, the power demand, the grid load, the voltage data, and the current data having the same time series in the data set to obtain a power supply interruption feature of the asset within the preset time period;

[0026] The power supply stability is determined according to the power supply interruption characteristics.

[0027] Optionally, predicting the operating environment of the asset within the preset time period according to the load rate, the voltage fluctuation, the current fluctuation, and the power supply stability of the asset to obtain at least one operating environment of the asset within the preset time period includes:

[0028] Inputting the load rate, the voltage fluctuation, the current fluctuation and the power supply stability of the asset into a deep learning model;

[0029] Through the feature fusion layer, the load rate, the voltage fluctuation, the current fluctuation and the power supply stability of the asset are subjected to feature fusion to obtain a comprehensive feature vector;

[0030] The comprehensive feature vector is sequentially passed through a time series processing layer, a dimension reduction layer, and an attention mechanism layer to obtain at least one operating environment of the asset within the preset time period.

[0031] Optionally, obtaining the operating efficiency of the asset in the operating environment according to the power supply, the power demand, the grid load, the voltage data, and the current data of the asset in the same time series in a time period corresponding to each operating environment includes:

[0032] Determine whether there are other operating environments within the time period corresponding to the operating environment of the asset;

[0033] If yes, then according to the duration of each of the operating environments in the time period, obtain the weight ratio of each of the operating environments;

[0034] The operating efficiency of each operating environment is obtained by combining the efficiency formula with the weight proportion of the operating environment.

[0035] Optionally, obtaining the operating efficiency of the asset in the operating environment according to the power supply, the power demand, the grid load, the voltage data, and the current data of the asset in the same time series in a time period corresponding to each operating environment includes:

[0036] Inputting the power supply, power demand, grid load, voltage data and current data of the asset in the same time series in each time period corresponding to the operating environment into the prediction model corresponding to the operating environment;

[0037] The operating efficiency of the asset under the operating environment is obtained through the output of the prediction model.

[0038] Optionally, obtaining the maintenance requirement of the asset under the operating environment according to the operating efficiency and a preset standard efficiency includes:

[0039] Determine whether there are other operating environments within the time period corresponding to the operating environment of the asset;

[0040] If yes, then taking the average of the differences between the operating efficiencies of all the operating environments of the asset within the time period and the preset standard efficiency as the efficiency difference of the asset in the operating environment;

[0041] If not, taking the difference between the operating efficiency of the asset under the operating environment and the preset standard efficiency as the efficiency difference of the asset under the operating environment;

[0042] The maintenance requirement of the asset under the operating environment is determined according to the efficiency difference of the asset under the operating environment.

[0043] Optionally, determining the maintenance requirement of the asset in the operating environment according to the efficiency difference of the asset in the operating environment includes:

[0044] Sorting the assets in the power grid according to the efficiency difference value under each operating environment to obtain a maintenance priority for each asset;

[0045] The maintenance requirement of each of the assets in the operating environment is determined according to the maintenance priority.

[0046] Optionally, obtaining the asset evaluation of the asset within the preset time period according to the operating efficiency and the maintenance requirement includes:

[0047] Determine the energy consumption of the asset according to the operating efficiency of the asset in the preset time period, and obtain the energy cost of the asset in the preset time period in combination with the market price;

[0048] Determining the maintenance cost of the asset within the preset time period according to the maintenance demand;

[0049] The operating cost and the operating quality of the asset within the preset time period are determined based on the energy cost and the maintenance cost, wherein the asset evaluation result includes the operating cost and the operating quality.

[0050] In a second aspect, the present invention provides a power grid asset evaluation system, comprising:

[0051] A monitoring unit, configured to obtain an asset operation status of each asset in the power grid according to real-time monitoring data of the power grid, wherein the asset operation status includes power supply, power demand, power grid load, voltage data, and current data of the asset;

[0052] A data fusion unit, configured to fuse the power supply, the power demand, the grid load, the voltage data and the current data of the asset to obtain a data set of the asset within a preset time period;

[0053] A feature extraction unit, used to extract features from the data set to obtain the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period;

[0054] an operating environment prediction unit, configured to predict the operating environment of the asset within the preset time period according to the load rate of the asset, the voltage fluctuation, the current fluctuation, and the power supply stability, and obtain at least one operating environment of the asset within the preset time period;

[0055] An operation efficiency prediction unit, used to obtain the operation efficiency of the asset under the operation environment according to the power supply, the power demand, the grid load, the voltage data and the current data having the same time series of the asset in a time period corresponding to each operation environment;

[0056] A comparison unit, configured to obtain a maintenance requirement of the asset under the operating environment according to the operating efficiency and a preset standard efficiency;

[0057] An evaluation unit is used to obtain an asset evaluation result of the asset within the preset time period according to the operating efficiency and the maintenance requirements.

[0058] The power grid asset evaluation method and system of the present invention obtain the type, location and operating status of the asset through real-time monitoring data, ensuring the comprehensiveness and accuracy of the basic data for evaluation. Then, the data fusion technology is used to make the data of different sources and types consistent in time and space to obtain a data set, which enhances the reliability of the data. Feature extraction based on the data set further refines the understanding of the asset operating status, and obtains the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period, providing a more in-depth analysis feature for the evaluation. By introducing time series analysis and deep learning technology to predict the operating environment of the asset in the preset time period, the evaluation can dynamically capture the performance of the asset in different operating environments, especially in the negative electricity price environment. By analyzing the operating status time series data of new energy facilities, the operating efficiency of the asset in a specific time period can be more accurately predicted. Due to the particularity of the power market under the negative electricity price environment, the operating efficiency and maintenance requirements of the asset may change accordingly. Through the analysis specifically for the operating environment, the performance of the asset in the negative electricity price environment can be more accurately evaluated. In addition, the operating efficiency is compared with the preset standard efficiency to clarify the maintenance requirements of the asset, thereby providing more targeted maintenance and optimization suggestions for power grid managers. Ultimately, combined with operating efficiency and maintenance needs, this method can provide a comprehensive asset valuation result that takes into account not only the technical performance of the assets, but also economic and environmental factors, especially the analysis of the operating efficiency of assets under a negative electricity price environment, which improves the accuracy and reliability of grid asset valuation, helps to make more informed decisions, and optimizes the operation and maintenance of the grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 One of the flow charts of the power grid asset evaluation method according to an embodiment of the present invention;

[0060] Figure 2 This is a second flowchart of the power grid asset evaluation method according to an embodiment of the present invention;

[0061] Figure 3 This is a flowchart of the power grid asset evaluation method according to an embodiment of the present invention;

[0062] Figure 4 This is a fourth flowchart of the power grid asset evaluation method according to an embodiment of the present invention;

[0063] Figure 5 This is a fifth flowchart of the power grid asset evaluation method according to an embodiment of the present invention;

[0064] Figure 6 The structure diagram of the power grid asset evaluation system according to the embodiment of the present invention is shown in FIG. DETAILED DESCRIPTION

[0065] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be interpreted as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0066] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0067] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to"; the term "based on" means "based at least in part on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0068] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0069] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0070] like Figure 1 As shown, the power grid asset evaluation method provided by the embodiment of the present invention includes:

[0071] S100: According to the real-time monitoring data of the power grid, the asset operation status of each asset in the power grid is obtained, and the asset operation status includes the power supply, power demand, power grid load, voltage data and current data of the asset.

[0072] Specifically, real-time monitoring of the power grid is key to ensuring safe, stable and efficient operation of the grid. By monitoring the operating status of each asset in the grid, the operating status of the grid can be understood in a timely manner and adjusted accordingly. In general, power supply refers to the amount of electricity that the grid can provide. It is usually determined by power plants or power imported from other regions through the grid; monitoring power supply helps ensure that the grid can meet demand and avoid power shortages. Power demand refers to the total amount of electricity from grid users (including industrial, commercial and residential users); power demand changes with time, weather, economic activities and other factors; real-time monitoring of demand helps predict and adjust power supply to meet changing demand. Grid load refers to the amount of electricity that the grid needs to handle in a specific time. High loads can cause the grid to be overloaded, and loads need to be managed by adjusting power generation or distribution to prevent equipment damage or power outages. Voltage is a measure of the potential difference in the power system, usually measured in volts (V); monitoring voltage data is critical to ensuring that power equipment is working properly; voltage that is too high or too low can cause equipment damage or reduced efficiency. Current is the amount of charge passing through a conductor per unit time, usually measured in amperes (A); monitoring current data helps detect abnormal conditions in the power grid, such as overloads or short circuits, which may cause damage to the grid.

[0073] S200: Performing data fusion on the power supply, the power demand, the grid load, the voltage data and the current data of the asset to obtain a data set of the asset within a preset time period.

[0074] Specifically, through data fusion technology, key parameters such as power supply, power demand, grid load, voltage and current data can be integrated to form a comprehensive data set within a preset time period. This data set not only provides a detailed view of real-time monitoring, but also helps identify patterns and trends in grid operation through analysis and prediction models, thereby achieving more effective resource allocation, risk management and decision support. Through this comprehensive approach, the reliability and efficiency of the power grid are significantly improved, while providing a solid data foundation for future grid optimization and upgrades.

[0075] S300: Extract features from the data set to obtain the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period.

[0076] Specifically, by identifying and extracting key information from the original data set, this information can represent the important characteristics or patterns of the data; for power grid monitoring data sets, feature extraction can help us better understand the operation status of the power grid within a preset time period. In general, the load rate is the ratio between the load of the power grid and the maximum power supply capacity; by calculating the load of the power grid at each time point in the preset time period and the maximum power supply capacity, the load rate feature can be obtained; this feature reflects the load level of the power grid at different time points. Voltage fluctuation refers to the degree of fluctuation of voltage data within a preset time period; voltage fluctuation is quantified by calculating the standard deviation or variance of voltage data; voltage fluctuation reveals the stability of power grid voltage; current fluctuation is similar to voltage fluctuation, measured by analyzing the standard deviation or variance of current data; current fluctuation reflects the stability of current in the power grid and possible overload risks; power supply stability is evaluated by analyzing the difference between power supply and demand; if the supply is always greater than or equal to the demand, the power grid can be considered stable; in addition, the supply fluctuation index, such as the standard deviation of the supply, can be calculated to further evaluate the stability of power supply. Exemplarily, statistical analysis methods, such as calculating the mean, median, maximum, minimum, standard deviation, etc., can be used to extract basic features of the data. Apply time series analysis, such as the Autoregressive Integrated Moving Average (ARIMA) model, to predict and analyze the changing trends of power grid parameters. Use machine learning algorithms, such as principal component analysis (PCA) or cluster analysis, to identify potential patterns and correlations in the data. Through feature extraction, a deep understanding of the power grid operation status can be obtained, and more accurate and timely operational decisions can be made based on this information.

[0077] S400: Predicting the operating environment of the asset within the preset time period based on the load rate, the voltage fluctuation, the current fluctuation and the power supply stability of the asset, and obtaining at least one operating environment of the asset within the preset time period.

[0078] Specifically, by carefully analyzing the load factor, voltage fluctuation, current fluctuation, and power supply stability of grid assets, a prediction model can be constructed to accurately predict the operating environment of assets within a preset time period. First, through feature extraction, we identify the load factor as a key indicator to measure the load level of the grid, and the voltage and current fluctuations reflect the stability of the grid. At the same time, the power supply stability provides intuitive information on whether the grid can continue to meet demand. Using these features, statistical methods and machine learning algorithms, such as regression analysis or deep learning techniques, can be applied to build a prediction model. When training the model, historical data is used to learn the association between these features and the grid operating environment, and parameter tuning is performed to improve the accuracy of the prediction. In addition, cross-validation is used to ensure the generalization ability of the model and avoid overfitting. Ultimately, the model is able to predict the operating environment that the grid may encounter in different time periods, such as peak load periods, voltage instability periods, or potential power supply shortages. These prediction results can provide valuable information for, for example, grid operators, allowing them to plan and adjust the grid's operating strategy in advance to cope with possible challenges and ensure efficient and stable operation of the grid.

[0079] S500: Obtain the operating efficiency of the asset in the operating environment based on the power supply, the power demand, the grid load, the voltage data and the current data of the asset in the same time series within the corresponding time period of each operating environment.

[0080] Specifically, by conducting time series analysis on power supply, power demand, grid load, voltage data, and current data of power grid assets under specific operating environments, the operating efficiency of assets can be evaluated; this evaluation is based on in-depth analysis of data in the corresponding time period of each operating environment, identifying the balance of power supply and demand, grid load bearing capacity, voltage stability, and current fluctuations. By calculating the ratios and differences of these parameters, the operating efficiency of the power grid can be quantified. For example, by comparing power supply and demand, it can be determined whether the power grid is efficiently meeting user needs. At the same time, the matching degree between grid load and power supply capacity, as well as the stability of voltage and current, are key factors in evaluating the operating efficiency of the power grid. These analysis results not only reflect the performance of the power grid under different operating environments, but also provide a basis for the optimization and improvement of the power grid, ensuring that the power grid can operate with the highest efficiency and reliability.

[0081] S600: Obtaining maintenance requirements of the asset under the operating environment according to the operating efficiency and a preset standard efficiency.

[0082] Specifically, by comparing the actual operating efficiency of grid assets under specific operating conditions with the preset standard efficiency, the maintenance needs of the assets can be determined; if the actual operating efficiency is lower than the preset standard, this may indicate that the grid has performance degradation or potential problems, such as equipment aging, overload or technical defects. After identifying these differences, targeted maintenance plans can be formulated, including equipment upgrades, system optimization or preventive maintenance measures to improve the operating efficiency of the grid and ensure its long-term stability; this data-driven maintenance strategy helps reduce unexpected failures, extend asset life, and ultimately achieve a dual improvement in cost-effectiveness and service quality.

[0083] S700: Obtaining an asset evaluation result of the asset within the preset time period according to the operating efficiency and the maintenance requirement.

[0084] Specifically, a comprehensive asset evaluation is conducted by comprehensively analyzing the operating efficiency and maintenance needs of power grid assets within a preset time period. This evaluation takes into account the performance of assets in actual operation, including the balance of power supply and demand, the adaptability of grid load, the stability of voltage and current, and the comparison results with the preset standard efficiency. During the evaluation process, any situation where the operating efficiency is lower than expected will be identified and matched with maintenance needs to determine the necessary improvement measures. Not only can the current performance status of the asset be understood, but also corresponding maintenance and upgrade plans can be formulated based on this to ensure that the asset can continue to operate in an efficient and stable manner. Ultimately, asset evaluation provides key information about the health status, performance potential and future investment direction of power grid assets, providing solid data support for the decision-making of power grid operators.

[0085] The power grid asset evaluation method of the present invention obtains the type, location and operating status of the asset through real-time monitoring data, ensuring the comprehensiveness and accuracy of the basic evaluation data. Then, the data fusion technology is used to make the data of different sources and types consistent in time and space to obtain a data set, which enhances the reliability of the data. Feature extraction based on the data set further refines the understanding of the asset operating status, and obtains the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period, providing a more in-depth analysis feature for the evaluation. By introducing time series analysis and deep learning technology to predict the operating environment of the asset in the preset time period, the evaluation can dynamically capture the performance of the asset in different operating environments, especially in the negative electricity price environment. By analyzing the operating status time series data of new energy facilities, the operating efficiency of the asset in a specific time period can be more accurately predicted. Due to the particularity of the power market under the negative electricity price environment, the operating efficiency and maintenance requirements of the asset may change accordingly. Through the analysis specifically for the operating environment, the performance of the asset under the negative electricity price environment can be more accurately evaluated. In addition, the operating efficiency is compared with the preset standard efficiency to clarify the maintenance requirements of the asset, thereby providing more targeted maintenance and optimization suggestions for power grid managers. Ultimately, combined with operating efficiency and maintenance needs, this method can provide a comprehensive asset valuation result that takes into account not only the technical performance of the assets, but also economic and environmental factors, especially the analysis of the operating efficiency of assets under a negative electricity price environment, which improves the accuracy and reliability of grid asset valuation, helps to make more informed decisions, and optimizes the operation and maintenance of the grid.

[0086] Optionally, combined Figure 2 As shown, the power supply, power demand, grid load, voltage data and current data of the asset are fused to obtain a data set of the asset within a preset time period, including:

[0087] S210: performing data cleaning on the power supply, the power demand, the grid load, the voltage data, and the current data according to a preset preprocessing method;

[0088] S220: performing time calibration on the cleaned power supply, power demand, grid load, voltage data, and current data to obtain the power supply, power demand, grid load, voltage data, and current data having the same time series;

[0089] S230: encoding the power supply, the power demand, the grid load, the voltage data and the current data having the same time series through an encoder to obtain the data set;

[0090] The step of time-calibrating the cleaned power supply, power demand, grid load, voltage data, and current data to obtain the power supply, power demand, grid load, voltage data, and current data having the same time series includes:

[0091] Obtaining timestamps corresponding to the power supply, the power demand, the grid load, the voltage data, and the current data after cleaning;

[0092] According to the timestamp, the cleaned power supply, the power demand, the grid load, the voltage data and the current data are respectively sorted in the time sequence of the preset time period to obtain the power supply, the power demand, the grid load, the voltage data and the current data with the same time series.

[0093] Specifically, according to the preset preprocessing method, the power supply, power demand, grid load, voltage data and current data are firstly thoroughly cleaned to remove outliers and noise to ensure the accuracy and reliability of the data. Subsequently, the cleaned data is time-calibrated, and the timestamp of each set of data is obtained, and the data is sorted according to the time order of the preset time period to ensure that all data sets are synchronized in the time dimension to form a comprehensive data set with the same time series. In this embodiment, the timestamp refers to the precise time information associated with each power supply, power demand, grid load, voltage data and current data point; this time information is usually expressed in the form of date and time, ensuring that the data points can be sorted and analyzed in the order in which they actually occur. The time calibration process involves obtaining these timestamps and rearranging the data points according to them to ensure that data from different sources or types can be compared and integrated on the same timeline. By ensuring that all data points are arranged in a unified time series, analysis errors caused by time inconsistency can be avoided. Synchronized time series data makes the analysis results more reliable and helps to more accurately identify patterns and trends in grid operation. Accurate time series data supports better decision making, such as adjusting power supply during peak load periods on the grid. Time-calibrated data provides high-quality input for forecasting models, helping to improve the accuracy of predicting the future state of the grid. Time calibration ensures the responsiveness of real-time monitoring systems, allowing grid operators to respond promptly to any changes in the state of the grid. As can be seen from the above, timestamps are the basis for achieving data synchronization and ensuring analysis accuracy.

[0094] In this optional embodiment, the synchronized time series data can more accurately reflect the real-time status of the power grid, thereby improving the accuracy of the prediction model. Accurate data can guide power grid operators to more effectively allocate power resources to meet power demand in different time periods. By accurately monitoring the status of the power grid, potential operating problems can be discovered and resolved in a timely manner, thereby enhancing the stability and reliability of the power grid. By optimizing the matching of power supply and demand, unnecessary energy waste can be reduced, thereby reducing operating costs. Providing higher quality data support to power grid operators helps to make more scientific and reasonable operational decisions.

[0095] Optionally, combined Figure 3 As shown, the feature extraction of the data set is performed to obtain the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period, including:

[0096] S310: Determine the load rate of the asset at the same time in the preset time period according to the power supply and the grid load of the data set;

[0097] S320: performing feature extraction on the voltage data and the current data of the data set to obtain standard deviations of the voltage data and the current data;

[0098] S330: Obtaining the voltage fluctuation and the current fluctuation of the asset at the same time within the preset time period according to the standard deviation of the voltage data and the current data;

[0099] S340: extracting features from the power supply, the power demand, the grid load, the voltage data, and the current data having the same time series in the data set to obtain a power supply interruption feature of the asset within the preset time period;

[0100] S350: Determine the power supply stability according to the power supply interruption characteristics.

[0101] Specifically, in the power grid monitoring system, the data set is first processed accurately; in the data cleaning stage, the preset preprocessing method is used to remove outliers, fill missing values, and correct inconsistent data to ensure the accuracy of power supply, power demand, power grid load, voltage data, and current data. Subsequently, the time calibration process ensures that all data points are aligned in a unified time series. This step involves extracting the timestamp of each data point and reordering it in chronological order to ensure the synchronization of the data; the encoding process converts the cleaned and calibrated data into a format suitable for further analysis through a specific encoder. In the feature extraction stage, the load rate is calculated to measure the load level of the power grid, and the volatility is quantified by the standard deviation of the voltage and current data. These features reflect the stability of the power grid operation. The extraction of power outage features further identifies factors that may affect the continuity of power supply.

[0102] In this optional embodiment, data cleaning improves data quality and provides a solid foundation for subsequent analysis; time calibration ensures the consistency of different data sources, making comparison and comprehensive analysis across data types possible; the encoding process further enhances the processability of the data, creating conditions for feature extraction and model training; by calculating the load rate, the load status of the power grid can be monitored in real time, and overload risks can be discovered in a timely manner; the standard deviation of voltage and current provides a quantitative indicator of power grid volatility, which helps to evaluate the stability of the power grid; the extraction of power outage features can reveal the potential vulnerable links of the power grid and provide a basis for preventive maintenance and emergency response. Ultimately, these comprehensive measures will improve the operating efficiency of the power grid, reduce the failure rate, enhance the reliability of power supply, and provide decision support for the long-term stable operation of the power grid.

[0103] Optionally, combined Figure 4 As shown, the operating environment of the asset within the preset time period is predicted according to the load rate, the voltage fluctuation, the current fluctuation and the power supply stability of the asset, and at least one operating environment of the asset within the preset time period is obtained, including:

[0104] S410: Inputting the load rate, the voltage fluctuation, the current fluctuation, and the power supply stability of the asset into a deep learning model;

[0105] S420: performing feature fusion on the load rate, the voltage fluctuation, the current fluctuation, and the power supply stability of the asset through a feature fusion layer to obtain a comprehensive feature vector;

[0106] S430: The comprehensive feature vector is sequentially passed through a time series processing layer, a dimension reduction layer, and an attention mechanism layer to obtain at least one operating environment of the asset within the preset time period.

[0107] Specifically, in the deep learning model for power grid monitoring, the input data includes the load rate of assets, voltage fluctuations, current fluctuations, and power supply stability; these data are first sent to the feature fusion layer, which is responsible for integrating different features to form a comprehensive feature vector; the comprehensive feature vector captures the key information of the power grid operation status. Subsequently, the comprehensive feature vector passes through the time series processing layer, which is specially designed to handle time dependencies and can identify long-term and short-term patterns in power grid operation. Next, the dimensionality reduction layer is used to reduce the dimension of the data while retaining the most important information as much as possible, which helps to improve the computational efficiency and generalization ability of the model. Finally, the attention mechanism layer enables the model to focus on the most important part of the data and enhance the ability to identify key features of the power grid operation environment; the model predicts the output to obtain at least one operating environment of the power grid asset within a preset time period.

[0108] In this optional embodiment, firstly, the integration of the feature fusion layer enables the model to consider information of multiple dimensions at the same time, thereby improving the comprehensiveness of the understanding of the power grid status; secondly, the introduction of the time series processing layer enables the model to capture the temporal dynamics of the power grid operation, which is crucial for predicting short-term and long-term trends; the application of the dimensionality reduction layer reduces the computational burden of the model, and at the same time, by removing redundant information, it may improve the prediction accuracy of the model; the focusing effect of the attention mechanism layer enables the model to more accurately identify the key factors affecting the power grid operation; combining the effects of these processing layers, the deep learning model can provide more accurate and reliable predictions of the power grid operation environment, which helps power grid operators take preventive measures in advance and optimize the power grid operation strategy, thereby improving the stability of the power grid and the reliability of power supply. In addition, this deep learning-based method of this embodiment can also adapt to changes in the power grid operation mode, and has good adaptability and scalability.

[0109] Optionally, combined Figure 5 As shown, the operation efficiency of the asset in the operation environment is obtained according to the power supply, the power demand, the grid load, the voltage data and the current data of the asset in the same time series in the time period corresponding to each operation environment, including:

[0110] S510: Determine whether there are other operating environments within the time period corresponding to the operating environment of the asset;

[0111] S520: If yes, obtaining a weight ratio of each of the operating environments according to the duration of each of the operating environments in the time period;

[0112] S530: Obtain the operating efficiency of each of the operating environments by combining an efficiency formula with the weight proportions of the operating environments.

[0113] Specifically, first, the prediction results of the deep learning model are used to identify different operating environments that may appear within a preset time period; if there are multiple operating environments, the duration of each environment needs to be calculated, and the weight ratio of each operating environment is determined based on this; the weight ratio reflects the relative importance or duration ratio of each operating environment in the entire time period; finally, the operating efficiency of each operating environment is calculated by combining the efficiency formula and the weight ratio of each operating environment.

[0114] In this technical solution, the efficiency formula is a calculation method that comprehensively considers multiple factors and is used to evaluate the performance of power grid assets under specific operating conditions. In this embodiment, the efficiency formula includes the following key components: Power supply (Ps): the amount of power provided by the power grid within a specific time; Power demand (Pd): the amount of power that the power grid needs to meet within a specific time; Power grid load (Load): the total amount of power in the power grid at a specific time point; Voltage stability (Vs): the stability index of the power grid voltage, measured by the standard deviation of the voltage data; Current stability (Is): the stability index of the power grid current, measured by the standard deviation of the current data; Power supply stability (Ss): the stability of the power supply of the power grid, measured by the number or duration of power outages.

[0115] Taking the above factors into consideration, the efficiency formula is expressed as:

[0116] Operation efficiency (η) = f (Ps, Pd, Load, Vs, Is, Ss)

[0117] Among them, f is a function that integrates these factors, including weighted average, minimum-maximum normalization or other mathematical processing methods. The weight proportion w represents the duration ratio of each operating environment in the total time period, which can be combined into the efficiency formula to reflect the contribution of different operating environments to the overall efficiency.

[0118] Therefore, the formula can be further expanded as:

[0119] ;

[0120] Wherein, η: represents the operating efficiency, which is the target value to be calculated in this embodiment; : Weight ratio, which indicates the duration ratio of each operating environment within the preset time period, and is used to adjust the calculation of operating efficiency to reflect the importance of the grid operating status in different time periods. a, b, c, d, e: are the weights assigned to different performance indicators, which are used to indicate the importance of each indicator when calculating efficiency; the choice of weights depends on the grid operator's priority for different performance indicators. Ps: Power supply, which indicates the total amount of electricity provided by the grid in a specific time period; Pd: Power demand, which indicates the total amount of electricity that the grid needs to meet in a specific time period; Ps / Pd: The ratio of supply to demand, which reflects the grid's ability to meet demand; ideally, this ratio should be close to or equal to 1, indicating a balance between supply and demand; : The reciprocal of the grid load plus 1, which is used to reflect the impact of the grid load on efficiency. The higher the load, the smaller this value is, indicating lower efficiency. Vs: Voltage stability, which is measured by the standard deviation of the voltage data. The smaller the standard deviation, the more stable the voltage. : The reciprocal of voltage stability, used to reflect the impact of voltage fluctuations on efficiency; add a small positive number here To avoid the denominator being zero; Is: current stability, similar to voltage stability, here it is measured by the standard deviation of current data; : The inverse of current stability, used to reflect the impact of current fluctuations on efficiency; Ss: Power supply stability, measured by the number or duration of power supply interruptions, reflects the continuity and reliability of power supply.

[0121] The entire formula combines these performance indicators in a weighted sum manner and multiplies them by the weight ratio w to calculate the operating efficiency of each operating environment. This efficiency value can provide a quantitative assessment for power grid operators, helping them understand the performance of the power grid in different operating environments and make corresponding optimization decisions.

[0122] In this optional embodiment, by identifying multiple operating environments, the grid operator can more fully understand the performance of the grid under different conditions; by calculating the weight ratio of each environment, it helps to identify which environments are the main states in the operation of the grid and which are secondary or abnormal states; this distinction is crucial for priority management and resource allocation; and combined with the efficiency formula and weight ratio, the operating efficiency of the grid can be more accurately evaluated. This embodiment takes into account the duration of different environments and provides a weighted average efficiency indicator, which more truly reflects the overall performance of the grid. This evaluation can help operators identify the causes of inefficiency, optimize the grid's operating strategy, and improve the stability and reliability of power supply. In addition, this embodiment can also be used for long-term planning and investment decisions to improve the long-term sustainability and economic benefits of the grid.

[0123] Optionally, obtaining the operating efficiency of the asset in the operating environment according to the power supply, the power demand, the grid load, the voltage data, and the current data of the asset in the same time series in a time period corresponding to each operating environment includes:

[0124] Inputting the power supply, power demand, grid load, voltage data and current data of the asset in the same time series in each time period corresponding to the operating environment into the prediction model corresponding to the operating environment;

[0125] The operating efficiency of the asset under the operating environment is obtained through the output of the prediction model.

[0126] Specifically, in this embodiment, the selection of the prediction model depends on whether the operating environment of the power grid assets is normal or abnormal; in the normal operating environment, the time series model is used as a prediction tool to analyze and predict the power supply, power demand, power grid load, voltage and current data; this model can capture the periodic and trend characteristics of the power grid operation. On the contrary, in the abnormal operating environment, such as when a fault or abnormal fluctuation occurs, the same time series model is used to predict and identify these abnormal situations in order to respond in time. Regardless of the operating environment, the time series model receives data with the same time series as input, which includes power supply, power demand, power grid load, voltage and current, which together constitute a comprehensive view of the operating status of the power grid. Through the output of the model, the operating efficiency of the power grid under different operating environments can be predicted.

[0127] In this optional embodiment, the above technical solution can achieve accurate prediction and evaluation of the power grid operation efficiency. Under normal operating conditions, the time series model can predict the stable operating state of the power grid based on historical data, and provide a reference for future power supply and demand balance for power grid operators. Under abnormal operating conditions, the model can identify and predict potential anomalies, helping operators to quickly locate problems and take preventive or repair measures. This flexible model application strategy enables timely and relevant operating efficiency forecasts to be obtained regardless of the state of the power grid. This helps to improve the reliability and stability of the power grid, reduce unexpected power outages, optimize the allocation and use of power resources, and ultimately achieve a dual improvement in cost-effectiveness and service quality. In addition, by continuously learning and adapting to power grid operation data, the time series model can continuously improve its prediction accuracy, providing solid data support and decision-making basis for the long-term sustainable development of the power grid.

[0128] Optionally, obtaining the maintenance requirement of the asset under the operating environment according to the operating efficiency and a preset standard efficiency includes:

[0129] Determine whether there are other operating environments within the time period corresponding to the operating environment of the asset;

[0130] If yes, then taking the average of the differences between the operating efficiencies of all the operating environments of the asset within the time period and the preset standard efficiency as the efficiency difference of the asset in the operating environment;

[0131] If not, taking the difference between the operating efficiency of the asset under the operating environment and the preset standard efficiency as the efficiency difference of the asset under the operating environment;

[0132] The maintenance requirement of the asset under the operating environment is determined according to the efficiency difference of the asset under the operating environment.

[0133] Specifically, the efficiency of power grid assets in different operating environments is evaluated and compared with the preset standard efficiency to determine the maintenance needs. First, the system determines whether there are multiple different operating environments for power grid assets within a given time period; if there are multiple environments, the system will calculate the difference between the operating efficiency and the preset standard efficiency in each operating environment, and take the average of these differences as the efficiency difference; detailed analysis and efficiency evaluation of each operating environment. If the power grid asset is only in a single operating environment during the time period, the difference between the operating efficiency in that environment and the preset standard efficiency is directly calculated as the efficiency difference, which is used to reflect the gap between the actual operating efficiency of the power grid asset and the ideal or expected efficiency. Finally, based on the calculated efficiency difference, the system determines the maintenance needs of the power grid asset, such as: preventive maintenance, troubleshooting or other optimization measures.

[0134] In this optional embodiment, by comparing with the preset standard efficiency, the efficiency level of the power grid assets under different or single operating environments can be accurately evaluated; the calculation of the efficiency difference provides a clear quantitative indicator for determining maintenance needs, which helps power grid operators identify areas that need improvement or attention; by identifying the efficiency difference, maintenance work can be scheduled in advance, reducing unexpected failures and unplanned downtime, and improving the reliability of the power grid; after clarifying the maintenance needs, resources can be more effectively allocated to where they are most needed, improving the efficiency and effectiveness of maintenance work; and through preventive maintenance and timely troubleshooting, long-term maintenance costs and economic losses caused by operational interruptions can be reduced. Timely response to maintenance needs helps to maintain the efficient operation of the power grid, thereby improving the stability and quality of power supply and enhancing user satisfaction. This embodiment provides a systematic method for power grid operators to determine and prioritize maintenance work by quantitatively analyzing and evaluating the operating efficiency of power grid assets, thereby improving the overall performance and long-term sustainability of the power grid.

[0135] Optionally, determining the maintenance requirement of the asset in the operating environment according to the efficiency difference of the asset in the operating environment includes:

[0136] Sorting the assets in the power grid according to the efficiency difference value under each operating environment to obtain a maintenance priority for each asset;

[0137] The maintenance requirement of each of the assets in the operating environment is determined according to the maintenance priority.

[0138] Specifically, this embodiment determines the maintenance priority of assets by quantitatively analyzing the efficiency difference of each asset in the power grid under different operating environments. First, the operating efficiency of each asset under a specific operating environment is calculated and compared with the preset standard efficiency to obtain the efficiency difference; these efficiency differences reflect the gap between the operating efficiency of the asset and the ideal state. Then, all assets are sorted according to these efficiency differences, and assets with larger efficiency differences will receive higher priorities, which means that they require more urgent maintenance or optimization; this importance sorting process can help power grid operators identify and concentrate resources to solve those problems that have the greatest impact on power grid performance. Finally, based on the maintenance priority, specific maintenance needs are determined for each asset, which may include equipment upgrades, system optimization, fault repair, or other improvement measures.

[0139] In this optional embodiment, through the quantitative analysis of the efficiency difference, the maintenance priority of each asset is clearly determined, helping operators to rationally plan maintenance resources. At the same time, it ensures that limited maintenance resources are first used for those assets that need them most, thereby improving the efficiency of resource use. Prioritizing the resolution of asset problems with large efficiency differences helps reduce power grid failures and outages and improve the overall stability of the power grid. Through preventive maintenance and timely optimization, long-term maintenance costs and economic losses caused by failures are reduced. The determination of maintenance priorities and timely response help maintain the efficient operation of the power grid and improve the reliability of power supply. Provide data-driven decision support for power grid operators to make maintenance plans more scientific and accurate. This embodiment not only improves the operating efficiency and stability of the power grid by systematically analyzing and sorting the maintenance needs of power grid assets, but also provides support for the long-term sustainable development of the power grid.

[0140] Optionally, obtaining the asset evaluation of the asset within the preset time period according to the operating efficiency and the maintenance requirement includes:

[0141] Determine the energy consumption of the asset according to the operating efficiency of the asset in the preset time period, and obtain the energy cost of the asset in the preset time period in combination with the market price;

[0142] Determining the maintenance cost of the asset within the preset time period according to the maintenance demand;

[0143] The operating cost and the operating quality of the asset within the preset time period are determined based on the energy cost and the maintenance cost, wherein the asset evaluation result includes the operating cost and the operating quality.

[0144] Specifically, based on the operating efficiency of the grid assets within a preset time period, the energy consumption of the assets is calculated through the efficiency formula, and then combined with the market price, the energy consumption is converted into energy cost, while considering factors such as electricity price fluctuations and peak and valley electricity prices. Then, based on maintenance needs, the maintenance cost of the assets is evaluated and calculated, which may include preventive maintenance, fault repair, equipment replacement and other costs. Finally, the energy cost is added to the maintenance cost to obtain the total operating cost of the asset within the preset time period. At the same time, the operating quality can be comprehensively evaluated by considering factors such as power supply reliability, efficiency and maintenance response time.

[0145] In this optional embodiment, by clearly understanding the energy cost and maintenance cost of the grid assets, a clear direction for cost control is provided for the grid operator. By identifying high-cost assets or links, operators can take measures to optimize energy use and maintenance strategies and reduce unnecessary expenses. By evaluating the operating efficiency, operators can identify the causes of inefficiency and take measures to improve efficiency and reduce energy waste; accurate maintenance cost assessment helps to formulate a more reasonable maintenance plan and balance the needs of preventive maintenance and emergency repairs. Understanding energy costs and maintenance costs can help operators better manage financial risks and formulate strategies to deal with market price fluctuations. By optimizing energy use and maintenance work, the reliability and power supply quality of the grid are improved, and user satisfaction and trust are enhanced; data-based decision support is provided for grid operators to help them formulate more scientific and reasonable operation and financial plans. This embodiment not only helps to improve the economic efficiency and operation quality of the grid through a comprehensive evaluation of the energy consumption, cost and maintenance needs of grid assets, but also provides strong data support for the long-term planning and management of the grid.

[0146] Combination Figure 6 As shown, an embodiment of the present invention provides a power grid asset evaluation system 600, including:

[0147] The monitoring unit 610 is used to obtain the asset operation status of each asset in the power grid according to the real-time monitoring data of the power grid, and the asset operation status includes the power supply, power demand, power grid load, voltage data and current data of the asset;

[0148] A data fusion unit 620 is used to perform data fusion on the power supply, the power demand, the grid load, the voltage data and the current data of the asset to obtain a data set of the asset within a preset time period;

[0149] A feature extraction unit 630 is used to extract features from the data set to obtain the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period;

[0150] An operating environment prediction unit 640 is used to predict the operating environment of the asset within the preset time period according to the load rate of the asset, the voltage fluctuation, the current fluctuation and the power supply stability, and obtain at least one operating environment of the asset within the preset time period;

[0151] The operation efficiency prediction unit 650 is used to obtain the operation efficiency of the asset in the operation environment according to the power supply, the power demand, the grid load, the voltage data and the current data of the asset in the same time series in the corresponding time period of each operation environment;

[0152] A comparison unit 660, configured to obtain a maintenance requirement of the asset under the operating environment according to the operating efficiency and a preset standard efficiency;

[0153] The evaluation unit 670 is used to obtain an asset evaluation result of the asset within the preset time period according to the operating efficiency and the maintenance requirement.

[0154] The power grid asset evaluation method and system of the present invention obtain the type, location and operating status of the asset through real-time monitoring data, ensuring the comprehensiveness and accuracy of the basic evaluation data. Then, the data fusion technology is used to make the data of different sources and types consistent in time and space to obtain a data set, which enhances the reliability of the data. Feature extraction based on the data set further refines the understanding of the asset operation status, and obtains the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period, providing a more in-depth analysis feature for the evaluation. By introducing time series analysis and deep learning technology to predict the operating environment of the asset in the preset time period, the evaluation can dynamically capture the performance of the asset in different operating environments, especially in the negative electricity price environment. By analyzing the operating status time series data of new energy facilities, the operating efficiency of the asset in a specific time period can be more accurately predicted. Due to the particularity of the power market under the negative electricity price environment, the operating efficiency and maintenance requirements of the asset may change accordingly. Through the analysis specifically for the operating environment, the performance of the asset in the negative electricity price environment can be more accurately evaluated. In addition, the operating efficiency is compared with the preset standard efficiency to clarify the maintenance requirements of the asset, thereby providing more targeted maintenance and optimization suggestions for power grid managers. Ultimately, combined with operating efficiency and maintenance needs, this method can provide a comprehensive asset valuation result that takes into account not only the technical performance of the assets, but also economic and environmental factors, especially the analysis of the operating efficiency of assets under a negative electricity price environment, which improves the accuracy and reliability of grid asset valuation, helps to make more informed decisions, and optimizes the operation and maintenance of the grid.

[0155] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. In the present application, the unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present invention. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0156] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A method for evaluating power grid assets, characterized in that: include: According to the real-time monitoring data of the power grid, the asset operation status of each asset in the power grid is obtained, and the asset operation status includes the power supply, power demand, power grid load, voltage data and current data of the asset; Performing data fusion on the power supply, power demand, grid load, voltage data and current data of the asset to obtain a data set of the asset within a preset time period; Extract features from the data set to obtain the load rate, voltage fluctuation, current fluctuation, and power supply stability of the asset at the same time in the preset time period; According to the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset, the operating environment of the asset within the preset time period is predicted to obtain at least one operating environment of the asset within the preset time period, specifically including: inputting the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset into a deep learning model; Through the feature fusion layer, the load rate, the voltage fluctuation, the current fluctuation and the power supply stability of the asset are subjected to feature fusion to obtain a comprehensive feature vector; The comprehensive feature vector is sequentially passed through a time series processing layer, a dimension reduction layer, and an attention mechanism layer to obtain at least one operating environment of the asset within the preset time period; According to the power supply, power demand, grid load, voltage data and current data of the asset in the same time series in each time period corresponding to the operating environment, the operating efficiency of the asset in the operating environment is obtained; specifically including: determining whether there are other operating environments in the time period corresponding to the operating environment of the asset; If yes, then according to the duration of each of the operating environments in the time period, obtain the weight ratio of each of the operating environments; The operating efficiency of each operating environment is obtained by combining the weight ratio of the operating environment with the efficiency formula; Wherein, the efficiency formula is: Among them, η: represents the operating efficiency, that is, the target value to be calculated; : represents the weight ratio, that is, the duration ratio of each operating environment within the preset time period; a, b, c, d, e: represents the weights assigned to different performance indicators, which are used to indicate the importance of each indicator in calculating efficiency; Ps: represents the power supply, that is, the total amount of power provided by the power grid in a specific time period; Pd: represents the power demand, that is, the total amount of power that the power grid needs to meet in a specific time period; Ps / Pd: represents the ratio of supply to demand; : The reciprocal of the grid load plus 1, which is used to reflect the impact of the grid load on efficiency; the higher the load, the smaller this value is, indicating lower efficiency; Vs: represents voltage stability; : The reciprocal of voltage stability, used to reflect the impact of voltage fluctuations on efficiency; add a small positive number here To avoid the denominator being zero; Is: current stability; : The inverse of current stability, used to reflect the impact of current fluctuations on efficiency; Ss: power supply stability; According to the operating efficiency and the preset standard efficiency, the maintenance requirement of the asset under the operating environment is obtained; An asset evaluation result of the asset within the preset time period is obtained according to the operating efficiency and the maintenance requirements.

2. The power grid asset evaluation method according to claim 1, characterized in that: The performing data fusion on the power supply, the power demand, the grid load, the voltage data and the current data of the asset to obtain a data set of the asset within a preset time period includes: Performing data cleaning on the power supply, the power demand, the grid load, the voltage data, and the current data according to a preset preprocessing method; Performing time calibration on the cleaned power supply, power demand, grid load, voltage data and current data to obtain the power supply, power demand, grid load, voltage data and current data having the same time series; The power supply, the power demand, the grid load, the voltage data and the current data having the same time series are encoded by an encoder to obtain the data set; The step of time-calibrating the cleaned power supply, power demand, grid load, voltage data, and current data to obtain the power supply, power demand, grid load, voltage data, and current data having the same time series includes: Obtaining timestamps corresponding to the power supply, the power demand, the grid load, the voltage data, and the current data after cleaning; According to the timestamp, the cleaned power supply, the power demand, the grid load, the voltage data and the current data are respectively sorted in the time sequence of the preset time period to obtain the power supply, the power demand, the grid load, the voltage data and the current data with the same time series.

3. The power grid asset evaluation method according to claim 2, characterized in that: The feature extraction of the data set to obtain the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period includes: Determine the load rate of the asset at the same time within the preset time period according to the power supply and the grid load of the data set; Performing feature extraction on the voltage data and the current data of the data set to obtain standard deviations of the voltage data and the current data; According to the standard deviation of the voltage data and the current data, respectively obtain the voltage fluctuation and the current fluctuation of the asset at the same time within the preset time period; Performing feature extraction on the power supply, the power demand, the grid load, the voltage data, and the current data having the same time series in the data set to obtain a power supply interruption feature of the asset within the preset time period; The power supply stability is determined according to the power supply interruption characteristics.

4. The power grid asset evaluation method according to claim 1, characterized in that: The obtaining, according to the operating efficiency and the preset standard efficiency, the maintenance requirement of the asset under the operating environment includes: Determine whether there are other operating environments within the time period corresponding to the operating environment of the asset; If yes, then taking the average of the differences between the operating efficiencies of all the operating environments of the asset within the time period and the preset standard efficiency as the efficiency difference of the asset in the operating environment; If not, taking the difference between the operating efficiency of the asset under the operating environment and the preset standard efficiency as the efficiency difference of the asset under the operating environment; The maintenance requirement of the asset under the operating environment is determined according to the efficiency difference of the asset under the operating environment.

5. The power grid asset evaluation method according to claim 4, characterized in that: The determining, according to the efficiency difference of the asset in the operating environment, the maintenance requirement of the asset in the operating environment includes: Sorting the assets in the power grid according to the efficiency difference value under each operating environment to obtain a maintenance priority for each asset; The maintenance requirement of each of the assets in the operating environment is determined according to the maintenance priority.

6. The power grid asset evaluation method according to claim 1, characterized in that: The obtaining, according to the operating efficiency and the maintenance requirement, an asset evaluation result of the asset within the preset time period includes: Determine the energy consumption of the asset according to the operating efficiency of the asset in the preset time period, and obtain the energy cost of the asset in the preset time period in combination with the market price; Determining the maintenance cost of the asset within the preset time period according to the maintenance demand; The operating cost and the operating quality of the asset within the preset time period are determined based on the energy cost and the maintenance cost, wherein the asset evaluation result includes the operating cost and the operating quality.

7. A power grid asset assessment system, characterized in that: include: A monitoring unit, configured to obtain an asset operation status of each asset in the power grid according to real-time monitoring data of the power grid, wherein the asset operation status includes power supply, power demand, power grid load, voltage data, and current data of the asset; A data fusion unit, used for fusing the power supply, the power demand, the grid load, the voltage data and the current data of the asset to obtain a data set of the asset within a preset time period; A feature extraction unit, used to extract features from the data set to obtain the load rate, voltage fluctuation, current fluctuation and power supply stability of the asset at the same time in the preset time period; An operating environment prediction unit is used to predict the operating environment of the asset within the preset time period according to the load rate, the voltage fluctuation, the current fluctuation and the power supply stability of the asset, and obtain at least one operating environment of the asset within the preset time period, specifically comprising: inputting the load rate, the voltage fluctuation, the current fluctuation and the power supply stability of the asset into a deep learning model; Through the feature fusion layer, the load rate, the voltage fluctuation, the current fluctuation and the power supply stability of the asset are subjected to feature fusion to obtain a comprehensive feature vector; The comprehensive feature vector is sequentially passed through a time series processing layer, a dimension reduction layer, and an attention mechanism layer to obtain at least one operating environment of the asset within the preset time period; The operation efficiency prediction unit is used to obtain the operation efficiency of the asset under the operation environment according to the power supply, power demand, grid load, voltage data and current data of the asset in the same time series in each time period corresponding to the operation environment, specifically including: determining whether there are other operation environments in the time period corresponding to the operation environment of the asset; If yes, then according to the duration of each of the operating environments in the time period, obtain the weight ratio of each of the operating environments; The operating efficiency of each operating environment is obtained by combining the weight ratio of the operating environment with the efficiency formula; Wherein, the efficiency formula is: Among them, η: represents the operating efficiency, that is, the target value to be calculated; : represents the weight ratio, that is, the duration ratio of each operating environment within the preset time period; a, b, c, d, e: represents the weights assigned to different performance indicators, which are used to indicate the importance of each indicator in calculating efficiency; Ps: represents the power supply, that is, the total amount of power provided by the power grid in a specific time period; Pd: represents the power demand, that is, the total amount of power that the power grid needs to meet in a specific time period; Ps / Pd: represents the ratio of supply to demand; : The reciprocal of the grid load plus 1, which is used to reflect the impact of the grid load on efficiency; the higher the load, the smaller this value is, indicating lower efficiency; Vs: represents voltage stability; : The reciprocal of voltage stability, used to reflect the impact of voltage fluctuations on efficiency; add a small positive number here To avoid the denominator being zero; Is: current stability; : The inverse of current stability, used to reflect the impact of current fluctuations on efficiency; Ss: power supply stability; A comparison unit, configured to obtain a maintenance requirement of the asset under the operating environment according to the operating efficiency and a preset standard efficiency; An evaluation unit is used to obtain an asset evaluation result of the asset within the preset time period according to the operating efficiency and the maintenance requirements.

Images