A power management method, system, terminal device and storage medium

Abstract

The application relates to the field of information technology, in particular to a power management method and system, a terminal device and a storage medium. The method comprises the following steps: analyzing a supply-demand evaluation model, obtaining a related fluctuation threshold of an evaluation coefficient corresponding to a supply-demand power data class; adding real-time collection data corresponding to the supply-demand power data class to the corresponding supply-demand evaluation model to generate a corresponding real-time evaluation coefficient; if the real-time evaluation coefficient exceeds the related fluctuation threshold, determining whether a numerical difference between the real-time evaluation coefficient and the related fluctuation threshold meets a preset iteration numerical standard; if the numerical difference between the real-time evaluation coefficient and the related fluctuation threshold meets the preset iteration numerical standard, generating a corresponding iteration supply-demand evaluation model according to the real-time collection data and the real-time evaluation coefficient. The power management method and system, the terminal device and the storage medium provided by the application can improve the data analysis effect in power management.

Description

Technical Field

[0001] This application relates to the field of information technology, and in particular to a power management method, system, terminal equipment, and storage medium. Background Technology

[0002] Power management refers to the management methods for effectively monitoring, scheduling, and optimizing power systems to achieve goals such as the rational utilization of power resources, reduction of energy consumption, and improvement of power supply reliability.

[0003] The main contents of power management include the following aspects: Load management: Through monitoring and controlling various loads in the power system, rational allocation and scheduling of power demand are achieved to reach optimal load balance and optimization. Energy management: Through monitoring, analysis, and optimization of energy, energy consumption is reduced and energy resources are rationally utilized, including energy procurement, storage, distribution, and use. Power supply management: Through monitoring and scheduling of power supply, the stable operation and reliable power supply of the power system are ensured, including power transmission, distribution, storage, and backup. Fault management: Through monitoring, predicting, and handling potential faults in the power system, timely measures are taken for repair and recovery to ensure the reliability and security of the power system. Data analysis and intelligent management: By employing technologies such as big data analytics, artificial intelligence, and machine learning, data in the power system is processed and analyzed to extract valuable information and knowledge to support decision-making and optimize power management.

[0004] In practical applications, the operating status and demand changes of the power system are dynamic. However, current power management methods can only perform simple trend analysis based on historical data and cannot accurately predict changes in power demand and supply, resulting in poor data analysis performance in power management. Summary of the Invention

[0005] To improve the effectiveness of data analysis in power management, this application provides a power management method, system, terminal equipment, and storage medium.

[0006] In a first aspect, this application provides a power management method, comprising the following steps:

[0007] Obtain historical power data;

[0008] The historical power data is divided according to a preset classification standard to form corresponding power supply side characteristic data groups and power consumption side characteristic data groups.

[0009] Based on the relationship between power supply and demand, the corresponding power supply and demand data classes in the power supply side characteristic data group and the power consumption side characteristic data group are associated to form a corresponding supply and demand assessment model.

[0010] The supply and demand assessment model is analyzed to obtain the relevant fluctuation threshold of the assessment coefficient corresponding to the supply and demand power data class;

[0011] Add the real-time collected data corresponding to the power supply and demand data category to the corresponding power supply and demand assessment model to generate the corresponding real-time assessment coefficients.

[0012] If the real-time evaluation coefficient exceeds the relevant fluctuation threshold, then it is determined whether the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard.

[0013] If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, then a corresponding iterative supply and demand evaluation model is generated based on the real-time collected data and the real-time evaluation coefficient.

[0014] Based on the power assessment data corresponding to the iterative supply and demand assessment model, a corresponding power supply and demand optimization strategy is generated.

[0015] By adopting the above technical solution, historical power data is divided according to preset classification standards to form corresponding power supply-side characteristic data groups and power consumption-side characteristic data groups. This allows for the acquisition of various supply and demand characteristics of the current power system data, providing an accurate basis for subsequent data analysis. Subsequently, based on the current power supply and demand relationship of the power system, the data in the power supply-side and power consumption-side characteristic data groups are specifically categorized according to their supply and demand attributes into specific supply and demand power data categories. Corresponding supply and demand assessment models are then formed. These models provide the corresponding supply and demand assessment analysis for each specific supply and demand power data category. To further integrate with the actual operating status of the current power system and better predict power demand and supply, the real-time collected data corresponding to each supply and demand power data category is added to the aforementioned supply and demand assessment model, generating... The corresponding real-time evaluation coefficients are then used to update the supply and demand evaluation model in real time to accurately reflect the actual operating status of the power system. If the real-time evaluation coefficients exceed the relevant fluctuation thresholds (i.e., the current real-time data is in an abnormal fluctuation state), the difference between the real-time evaluation coefficients and the relevant fluctuation thresholds is again checked against a preset iterative numerical standard. If it does, an iterative supply and demand evaluation model is generated based on the current real-time data and the real-time evaluation coefficients. Then, based on the power evaluation data in the iterative supply and demand evaluation model, an optimization strategy suitable for the current operating status of the power system is formulated. By combining historical power system data and current dynamic changes in power system supply and demand, a more suitable iterative supply and demand evaluation model is generated, thereby improving the data analysis effect in power management.

[0016] Optionally, forming a corresponding supply and demand assessment model by associating the power supply-side characteristic data group and the corresponding power supply and demand data classes in the power consumption-side characteristic data group according to the power supply and demand relationship includes the following steps:

[0017] Based on the power supply and demand relationship, the corresponding power supply and demand data classes in the power supply side feature data group and the power consumption side feature data group are aligned according to time to generate corresponding aligned data classes;

[0018] Perform correlation analysis on the aligned data class to generate corresponding correlation coefficients;

[0019] By combining the aligned data class and the corresponding correlation coefficient, a corresponding supply and demand assessment model is formed.

[0020] By adopting the above technical solutions, aligning power supply and demand data according to time helps to more accurately analyze the supply and demand relationship of the power system in different time periods. Further correlation analysis of the aligned data helps to uncover the inherent connection between power supply and power consumption data, providing more possibilities for the optimization of the power system, and thus providing more accurate and comprehensive data support analysis for the optimization and management of the power system.

[0021] Optionally, parsing the supply and demand assessment model to obtain the relevant fluctuation thresholds of the assessment coefficients corresponding to the supply and demand electricity data class includes the following steps:

[0022] Analyze the supply and demand assessment model to determine whether there are any fluctuation factors affecting the supply and demand electricity data.

[0023] If the power supply and demand data class contains the fluctuation influencing factors, then obtain the safe fluctuation threshold of the fluctuation influencing factors relative to the power supply and demand data class;

[0024] By combining the target fluctuation threshold and the safety fluctuation threshold corresponding to the power supply and demand data class, the relevant fluctuation threshold of the evaluation coefficient corresponding to the power supply and demand data class is formed.

[0025] By adopting the above technical solution, it is possible to determine whether there are fluctuation factors affecting the power supply and demand data, so as to identify potential unstable factors in the power system. If they exist, the target fluctuation threshold corresponding to the power supply and demand data and the safe fluctuation threshold corresponding to the fluctuation factors are combined to form relevant fluctuation thresholds. This allows for accurate determination of the evaluation coefficient of the power supply and demand data, thereby reducing evaluation bias caused by unstable factors.

[0026] Optionally, after analyzing the supply and demand assessment model and determining whether there are fluctuation factors affecting the supply and demand electricity data, the following steps are also included:

[0027] If the power supply and demand data category contains the fluctuation influencing factors, determine whether there are multiple fluctuation influencing factors.

[0028] If there are multiple factors affecting the fluctuations, then each of the factors affecting the fluctuations will be subjected to a multiple linear regression analysis with the power supply and demand data class to generate the degree of fluctuation contribution of each factor affecting the fluctuations relative to the power supply and demand data class.

[0029] By adopting the above technical solutions and using multiple linear analysis, the impact of each fluctuation factor on power supply and demand data can be quantified more accurately. This allows for a better understanding of the mechanisms by which various factors operate in the power system, as well as better identification and prediction of relevant risks in the power system. This provides data support for risk prevention in the power system. Furthermore, based on the contribution of each fluctuation factor, changes in various risk factors can be monitored in real time, providing a more reliable basis for the dynamic adjustment and management of the power system.

[0030] Optionally, if the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, then generating the corresponding iterative supply and demand evaluation model based on the real-time collected data and the real-time evaluation coefficient includes the following steps:

[0031] If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, then the target fluctuation item corresponding to the real-time collected data is obtained;

[0032] If the target fluctuation term has multiple fluctuation inducing factors, then the correlation coefficients between each fluctuation inducing factor are calculated to form the corresponding correlation coefficient matrix;

[0033] The correlation coefficient matrix is ​​subjected to eigenvalue decomposition to generate corresponding eigenvalues ​​and eigenvectors;

[0034] Calculate the weight coefficients corresponding to the feature vectors based on the feature values;

[0035] By combining the target fluctuation term and the weighting coefficient, the corresponding real-time evaluation coefficient is generated as the iterative supply and demand evaluation model.

[0036] By adopting the above technical solution, the weight coefficients corresponding to the eigenvectors are calculated based on the eigenvalues. This allows for the reasonable allocation of the weights of each fluctuation-inducing factor in the real-time evaluation coefficients, thereby better reflecting the degree of influence of each factor on the power system. Subsequently, by combining the target fluctuation term and the weight coefficients, the corresponding real-time evaluation coefficients are generated as an iterative supply and demand evaluation model. Based on this iterative supply and demand evaluation model, the power system can be dynamically adjusted and optimized, thereby improving the operating efficiency and stability of the power system.

[0037] Optionally, generating a corresponding power supply and demand optimization strategy based on the power assessment data corresponding to the iterative supply and demand assessment model includes the following steps:

[0038] Obtain the target power supply and demand indicators corresponding to the power assessment data;

[0039] Analyze the current power supply and demand data based on the target power supply and demand indicators to obtain the corresponding abnormal adjustment items;

[0040] Based on the abnormal adjustment item, the corresponding power supply and demand optimization strategy is generated.

[0041] By adopting the above technical solutions and analyzing the current power supply and demand data based on the target power supply and demand indicators, abnormal situations in the power system can be detected in a timely manner, providing data support for power system risk prevention. Furthermore, based on the abnormal adjustment items, corresponding power supply and demand optimization strategies can be generated, providing more reasonable strategy suggestions for power system scheduling and optimization, and improving the operating efficiency and stability of the power system.

[0042] Optionally, after generating the corresponding power supply and demand optimization strategy based on the abnormal adjustment item, the following steps are also included:

[0043] Implement the power supply and demand optimization strategy and generate corresponding target monitoring instructions;

[0044] Execute the target monitoring command to obtain the corresponding power optimization parameters;

[0045] Based on the power optimization parameters and the current power operation status, an adjustment plan corresponding to the power supply and demand optimization strategy is generated.

[0046] By adopting the above technical solutions, the implementation of power supply and demand optimization strategies can be monitored in real time. The optimization strategies can be dynamically adjusted according to the actual optimization situation of the power system, thereby improving the dispatch flexibility of the power system, enabling more rational allocation of power resources, improving the resource utilization rate of the power system, and reducing energy waste.

[0047] Secondly, this application provides a power management system, comprising:

[0048] The acquisition module is used to acquire historical power data;

[0049] The segmentation module is used to segment the historical power data according to a preset classification standard to form corresponding power supply side feature data groups and power consumption side feature data groups.

[0050] The association module is used to associate the power supply side feature data group and the corresponding power supply and demand data class in the power consumption side feature data group according to the power supply and demand relationship, so as to form a corresponding supply and demand assessment model;

[0051] The parsing module is used to parse the supply and demand assessment model and obtain the relevant fluctuation threshold of the assessment coefficient corresponding to the supply and demand power data class;

[0052] The loading module is used to add the real-time collected data corresponding to the power supply and demand data class to the corresponding power supply and demand assessment model and generate the corresponding real-time assessment coefficients.

[0053] The iterative analysis module is used to determine whether the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard if the real-time evaluation coefficient exceeds the relevant fluctuation threshold.

[0054] If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, the iterative model generation module is used to generate a corresponding iterative supply and demand evaluation model based on the real-time collected data and the real-time evaluation coefficient.

[0055] The power optimization module is used to generate corresponding power supply and demand optimization strategies based on the power assessment data corresponding to the iterative supply and demand assessment model.

[0056] By adopting the above technical solution, historical power data is divided according to preset classification standards by the segmentation module, forming corresponding power supply-side characteristic data groups and power consumption-side characteristic data groups. This allows for the acquisition of various supply and demand characteristics of the current power system data, providing an accurate basis for subsequent data analysis. Subsequently, based on the current power supply and demand relationship of the power system, the data in the power supply-side and power consumption-side characteristic data groups are specifically categorized, i.e., classified into specific supply and demand power data categories according to their supply and demand attributes. A corresponding supply and demand assessment model is formed through the association module. This model allows for the acquisition of corresponding supply and demand assessment analyses for each specific supply and demand power data category. To further integrate with the actual operating status of the current power system and better predict power demand and supply, the real-time collected data corresponding to the supply and demand power data categories is added to the supply and demand assessment model through the loading module, generating corresponding... The real-time evaluation coefficient is then used to update the supply and demand assessment model in real time to accurately reflect the actual operating status of the power system. If the real-time evaluation coefficient exceeds a relevant fluctuation threshold (i.e., the current real-time data is in an abnormal fluctuation state), the difference between the real-time evaluation coefficient and the relevant fluctuation threshold is again checked against a preset iterative numerical standard. If it does, the iterative analysis module generates a corresponding iterative supply and demand assessment model based on the current real-time data and the real-time evaluation coefficient. Then, based on the power assessment data in the iterative supply and demand assessment model, the power optimization module formulates an optimization strategy suitable for the current operating status of the power system. By combining historical power system data and current dynamic changes in power system supply and demand, a more suitable iterative supply and demand assessment model is generated, thereby improving the data analysis effect in power management.

[0057] Thirdly, this application provides a terminal device, which adopts the following technical solution:

[0058] A terminal device includes a memory and a processor, wherein the memory stores computer instructions that can run on the processor, and the processor loads and executes the computer instructions using the aforementioned power management method.

[0059] By adopting the above technical solution, a power management method is used to generate computer instructions, which are then stored in a memory for loading and execution by a processor. This allows for the creation of terminal devices based on the memory and processor, making them convenient to use.

[0060] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0061] A computer-readable storage medium storing computer instructions, which, when loaded and executed by a processor, employ the aforementioned power management method.

[0062] By adopting the above technical solution, a power management method is used to generate computer instructions, which are then stored in a computer-readable storage medium for loading and execution by a processor. The computer-readable storage medium facilitates the reading and storage of the computer instructions.

[0063] In summary, this application includes at least one of the following beneficial technical effects: Historical power data is divided according to preset classification standards to form corresponding power supply-side characteristic data groups and power consumption-side characteristic data groups. This allows for the acquisition of various supply and demand characteristics of the current power system data, providing an accurate basis for subsequent data analysis. Then, based on the current power supply and demand relationship of the power system, the data in the power supply-side characteristic data groups and power consumption-side characteristic data groups are specifically categorized, i.e., classified into specific supply and demand power data categories according to their supply and demand attributes. Corresponding supply and demand assessment models are then formed. Through these models, corresponding supply and demand assessment analyses for each specific supply and demand power data category can be obtained. To further integrate with the actual operating status of the current power system and better predict power demand and supply, the real-time collected data corresponding to the supply and demand power data categories is added to the corresponding supply and demand assessment models. The system first estimates the supply and demand model and generates corresponding real-time evaluation coefficients. Then, in order to update the supply and demand evaluation model in real time to accurately reflect the actual operating status of the power system, if the real-time evaluation coefficient exceeds the relevant fluctuation threshold (i.e., the current real-time collected data is in an abnormal fluctuation state), it checks again whether the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard. If it does, an iterative supply and demand evaluation model is generated based on the current real-time collected data and real-time evaluation coefficients of the power system. Then, an optimization strategy suitable for the current operating status of the power system is formulated based on the power evaluation data in the iterative supply and demand evaluation model. By combining historical data of the power system and the current dynamic changes in power system supply and demand, a more suitable iterative supply and demand evaluation model is generated, thereby improving the data analysis effect in power management. Attached Figure Description

[0064] Figure 1 This is a flowchart illustrating steps S101 to S108 of a power management method provided in this application.

[0065] Figure 2 This is a flowchart illustrating steps S201 to S203 of a power management method provided in this application.

[0066] Figure 3 This is a flowchart illustrating steps S301 to S303 of a power management method provided in this application.

[0067] Figure 4This is a flowchart illustrating steps S401 to S402 of a power management method provided in this application.

[0068] Figure 5 This is a flowchart illustrating steps S501 to S505 of a power management method provided in this application.

[0069] Figure 6 This is a flowchart illustrating steps S601 to S603 of a power management method provided in this application.

[0070] Figure 7 This is a flowchart illustrating steps S701 to S703 of a power management method provided in this application.

[0071] Figure 8 This is a schematic diagram of a power management system provided in this application.

[0072] Explanation of reference numerals in the attached figures:

[0073] 1. Acquisition Module; 2. Division Module; 3. Association Module; 4. Parsing Module; 5. Loading Module; 6. Iterative Analysis Module; 7. Iterative Model Generation Module; 8. Power Optimization Module. Detailed Implementation

[0074] The following is in conjunction with the appendix Figure 1-8 This application will be described in further detail.

[0075] This application discloses a power management method, such as... Figure 1 As shown, it includes the following steps:

[0076] S101. Obtain historical power data;

[0077] S102. Divide historical power data according to preset classification standards to form corresponding power supply side characteristic data groups and power consumption side characteristic data groups;

[0078] S103. Based on the power supply and demand relationship, form the corresponding power supply and demand assessment model by associating the power supply side characteristic data group and the power consumption side characteristic data group with the power supply and demand relationship;

[0079] S104. Analyze the supply and demand assessment model and obtain the relevant fluctuation thresholds of the assessment coefficients corresponding to the supply and demand power data categories;

[0080] S105. Add the real-time collected data corresponding to the power supply and demand data category to the corresponding power supply and demand assessment model to generate the corresponding real-time assessment coefficients;

[0081] S106. If the real-time evaluation coefficient exceeds the relevant fluctuation threshold, determine whether the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard.

[0082] S107. If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, then generate the corresponding iterative supply and demand evaluation model based on the real-time collected data and the real-time evaluation coefficient.

[0083] S108. Generate corresponding power supply and demand optimization strategies based on the power assessment data corresponding to the iterative supply and demand assessment model.

[0084] In step S101, historical power data refers to various types of data generated during the historical operation of the power system. This data can be used to analyze the operating status, performance, and causes of faults of the power system, providing a reference for the optimization, scheduling, and management of the power system.

[0085] For example, historical power data includes: load data, including historical load data, load characteristics, load forecasts, etc., used to analyze changes in power system demand and load characteristics; power generation data, including the output, power generation, and operating status of various generating units, used to analyze the utilization of power generation resources and power generation efficiency; power market data, including power trading volume, electricity price, market participants, etc., used to analyze the operation and development trend of the power market; and user data, including user electricity consumption, electricity consumption characteristics, electricity demand, etc., used to analyze user demand and electricity consumption behavior.

[0086] In step S102, the preset classification standard refers to the standard for classifying historical power data based on the characteristics of corresponding data from the power supply side and the power consumption side of the power system. Specifically, the power supply side characteristic data group includes characteristic data from the power supply side of the power system, and the power consumption side characteristic data group includes characteristic data from the power consumption side of the power system.

[0087] Analyzing the characteristic data sets on both the power supply and consumption sides provides a comprehensive understanding of the power system's operational status, offering valuable information and support for its planning, operation, scheduling, and management. Furthermore, this division into power supply and consumption characteristic data sets helps in better understanding the power system's supply-demand balance, providing a reference for optimizing power resource allocation and improving power system efficiency.

[0088] Specifically, the power supply side characteristic data group includes the following characteristic data: generator set operation data, including generator set output power, voltage, current, frequency and other data; transmission line data, including transmission line current, voltage, power loss and other data; substation data, including substation voltage, current, power and other data; power load data, including power load size, trend, seasonality, periodicity and other data; generator set operation status data, including generator set switch status, fault information and other data.

[0089] The electricity consumption-side characteristic data set includes the following: electricity load data, including the size, trend, seasonality, and periodicity of electricity load; electrical equipment data, including the power, current, and voltage of each electrical device; electricity consumption behavior data, including changes in electricity consumption behavior and habits; and weather data, such as temperature, humidity, and wind speed, which can affect electricity demand. This data can be acquired through sensors, monitoring equipment, smart meters, and other means. This data can be used to analyze the operating status of the power system and changes in demand, helping to optimize energy management and demand response on the supply side (power generation and transmission) and the demand side (electricity consumption).

[0090] In step S103, the electricity supply and demand relationship refers to the balance between electricity production, transmission, and consumption within a power system. In the electricity market, the supply side mainly includes power generation companies and transmission companies, responsible for producing and transmitting electricity; the demand side mainly includes various electricity customers such as industrial, commercial, and residential users, responsible for consuming electricity. The degree of balance in the electricity supply and demand relationship directly affects the stable operation of the power system and the healthy development of the electricity market.

[0091] Among them, power supply and demand data refers to a type of data used to describe and analyze the relationship between power supply and demand. A power supply and demand assessment model is a mathematical model based on this type of data, used to evaluate the supply and demand balance of the power system. These models typically employ statistical and machine learning methods to assess the power system's supply and demand balance by analyzing relevant data from both the power supply and consumption side characteristic data sets.

[0092] For example, based on the generator output power data in the power supply-side characteristic data group and the total load power data in the power consumption-side characteristic data group, a corresponding supply-demand balance assessment model is formed. By monitoring the supply-demand balance assessment model, the power supply and demand status of the power system can be assessed and analyzed. Among them, the power supply and demand data corresponding to the generator output power data and the total load power data are the supply and demand status data categories.

[0093] For example, based on the transmission line current data in the power supply-side characteristic data group and the power consumption-side characteristic data group, a corresponding transmission loss assessment model can be formed. This model allows for the evaluation and analysis of the power system's transmission losses. The power supply and demand data categories corresponding to the transmission line current data and the power consumption-side current data constitute the transmission loss data category.

[0094] For example, based on the generator operating status data in the power supply-side characteristic data group and the electrical equipment status data in the power consumption-side characteristic data group, a corresponding fault assessment model can be formed. This model can then be used to evaluate and analyze fault diagnosis and maintenance of the power system. Specifically, the power supply and demand data corresponding to the generator operating status data and the electrical equipment status data constitute the fault diagnosis and maintenance data category.

[0095] In step S104, by parsing the above supply and demand assessment model, the values ​​of the assessment coefficients corresponding to each supply and demand power data category can be obtained. The assessment coefficients corresponding to each supply and demand power data category refer to the quality assessment scores corresponding to each supply and demand power data category.

[0096] For example, in the category of power supply and demand data, the load factor is an evaluation coefficient. The load factor refers to the ratio of the actual load of the power system to the maximum load within a certain period. The load factor reflects the balance of the power system load. The higher the load factor, the higher the utilization rate of the power system and the more uniform the load distribution. The corresponding evaluation coefficient is also higher. For example, if the maximum load of the power system in a day is 1000MW and the average load of the day is 800MW, then the load factor is 80%, and the corresponding evaluation coefficient is 8. The value range of the evaluation coefficient is 1-10.

[0097] The relevant fluctuation threshold is a numerical standard used to determine whether the fluctuation of the evaluation coefficient exceeds the normal range. The threshold is set based on historical data and experience to judge whether the fluctuation of the evaluation coefficient is within an acceptable range. When the evaluation coefficient exceeds the threshold, it means that there is a problem with the supply and demand balance of the power system.

[0098] In step S105, in order to predict changes in power demand and supply based on the actual operating status of the current power system, the real-time collected data corresponding to the power supply and demand data categories in the current power system are added to the generated supply and demand assessment model to obtain the corresponding real-time assessment coefficients.

[0099] For example, real-time data collection is the real-time reserve capacity rate, which refers to the ratio of the reserve capacity to the maximum load in the power system at the current moment. The higher the real-time reserve capacity, the greater the real-time safety margin of the power system, and the higher the corresponding real-time assessment coefficient, which can better cope with emergencies.

[0100] Specifically, the general steps of the supply and demand assessment model to analyze and process real-time collected data to obtain corresponding real-time assessment coefficients include: data preprocessing, which involves preprocessing the real-time collected power supply and demand data, including data cleaning, data interpolation, and data smoothing, to eliminate differences in the data and improve data quality; and feature extraction, which involves extracting features related to the assessment of power supply and demand data from the preprocessed data, i.e., feature matching, such as real-time load, real-time power generation, and real-time reserves. For example, features such as actual load (10000MW), maximum load (12000MW), and reserve capacity (2000MW) at a certain moment can be extracted from the real-time collected data.

[0101] Secondly, model calculations are performed. Based on the extracted features, real-time assessment coefficients are calculated using the corresponding supply and demand assessment model. For example, real-time load factor = actual load / maximum load = 10,000MW / 12,000MW = 0.833, and real-time reserve capacity factor = reserve capacity / maximum load = 2,000MW / 12,000MW = 0.1667. The results are then output, and the calculated real-time assessment coefficients are provided for reference and analysis by power system dispatchers or market participants.

[0102] In step S106, it is determined whether the real-time evaluation coefficient exceeds the relevant fluctuation threshold. The purpose is to determine whether the power system needs to be adjusted to cope with changes in real-time supply and demand. When the real-time evaluation coefficient exceeds the relevant fluctuation threshold, it indicates that the power system may face the risk of supply and demand imbalance.

[0103] Secondly, the preset iterative data standard is a pre-set value used to determine whether the difference between the real-time evaluation coefficient and the relevant fluctuation threshold has reached a level that requires adjustment of the power system. This value can be set based on historical data, experience and system characteristics to ensure that the power system can make timely adjustments when facing the risk of supply and demand imbalance.

[0104] Specifically, when the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, it indicates a significant change in the power system's supply and demand situation, necessitating system adjustments. At this point, an iterative supply and demand evaluation model is generated based on the real-time collected data and the real-time evaluation coefficient to optimize the power system. The iterative supply and demand evaluation model is a dynamically adjusted model that predicts the power system's supply and demand situation based on real-time data and evaluation coefficients, providing a basis for system adjustments.

[0105] For example, in the example above, the preset iteration value standard is set to 0.03. When the difference between the real-time evaluation coefficient and the relevant fluctuation threshold is greater than 0.03, it is considered that the power system needs to be adjusted, such as increasing power generation or adjusting load distribution, in order to maintain the stable operation of the power system.

[0106] Furthermore, if the real-time evaluation coefficient does not exceed the relevant fluctuation threshold, it indicates that the current power supply and demand data of the power system are in a balanced or safe operating range. In order to effectively protect the power system, the system acquires and monitors various power data of the power system in real time.

[0107] In step S107, the iterative supply and demand assessment model is a dynamically adjusted model that predicts the supply and demand status of the power system based on real-time data and assessment coefficients, and provides a basis for adjusting the system.

[0108] Specifically, the steps for generating an iterative supply and demand assessment model can be roughly divided into: real-time data acquisition, which involves collecting real-time operating data of the power system, such as power generation, load, and transmission line status; real-time assessment system calculation, which involves calculating real-time assessment coefficients of the power system based on real-time data, such as supply-demand ratio and load factor; numerical difference assessment, which involves comparing the numerical differences between the real-time assessment coefficients and relevant fluctuation thresholds to determine whether the preset iterative numerical standards have been met; generating an iterative supply and demand assessment model, which involves generating an iterative supply and demand assessment model based on real-time data and real-time assessment coefficients if the numerical differences meet the preset iterative numerical standards; and adjusting the power system, which involves making corresponding adjustments to the power system based on the results of the iterative supply and demand assessment model, such as increasing power generation and adjusting load distribution, to maintain the stable operation of the system.

[0109] Furthermore, if the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold does not meet the preset iterative numerical standard, the system continues to acquire the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold corresponding to the power supply and demand data class in the power system.

[0110] In step S108, a corresponding power supply and demand optimization strategy is generated based on the power assessment data corresponding to the iterative supply and demand assessment model in order to achieve supply and demand balance, improve system efficiency, and reduce operating costs in the power system.

[0111] The power assessment data corresponding to the iterative supply and demand assessment model refers to a series of key data obtained in the power system through iterative calculation and analysis of the supply and demand relationship. For example, load data includes the total system load, the load of each region, load fluctuations, etc. Based on this data, the distribution and changing trends of power demand can be analyzed.

[0112] Specifically, the steps for generating power supply and demand optimization strategies can be roughly divided into: analyzing and evaluating the model, i.e., analyzing the power system's operating status based on the power assessment data obtained from the iterative supply and demand assessment model, such as supply and demand balance, load distribution, and equipment operating status; determining optimization objectives, i.e., determining the power system's optimization objectives based on the assessment data analysis results, such as improving power supply reliability, reducing operating costs, and reducing line losses; formulating optimization strategies, i.e., developing corresponding power supply and demand optimization strategies for the optimization objectives, including adjusting generation plans, optimizing load allocation, and improving equipment utilization; implementing optimization strategies, i.e., applying the formulated optimization strategies to the power system to adjust the system. For example, adjusting generator output, dispatching loads, and optimizing transmission lines according to the optimization strategies; and monitoring optimization effects, i.e., continuously monitoring the power system's operating status after implementing the optimization strategies and evaluating the actual effects of the optimization strategies. If necessary, the optimization strategies can be adjusted according to the actual situation.

[0113] The power management method provided in this embodiment divides historical power data according to preset classification standards to form corresponding power supply-side characteristic data groups and power consumption-side characteristic data groups. This allows for the acquisition of various supply and demand characteristics of the current power system data, providing an accurate basis for subsequent data analysis. Then, based on the current power supply and demand relationship of the power system, the data in the power supply-side and power consumption-side characteristic data groups are specifically categorized, i.e., classified into specific supply and demand power data classes according to their supply and demand attributes. Corresponding supply and demand assessment models are then formed. These models provide supply and demand assessment analyses for each specific supply and demand power data class. To further integrate with the actual operating status of the current power system and better predict power demand and supply, the real-time collected data corresponding to each supply and demand power data class is added to the aforementioned supply and demand assessment model. The corresponding real-time evaluation coefficients are generated. Then, in order to update the supply and demand evaluation model in real time to reflect the actual operation of the power system, if the real-time evaluation coefficients exceed the relevant fluctuation thresholds (i.e., the current real-time collected data is in an abnormal fluctuation state), it is determined again whether the numerical difference between the real-time evaluation coefficients and the relevant fluctuation thresholds meets the preset iterative numerical standard. If it does, an iterative supply and demand evaluation model is generated based on the current real-time collected data and real-time evaluation coefficients of the power system. Then, an optimization strategy suitable for the current operation of the power system is formulated based on the power evaluation data in the iterative supply and demand evaluation model. By combining the historical data of the power system and the current dynamic changes in the supply and demand of the power system, a more suitable iterative supply and demand evaluation model is generated, thereby improving the data analysis effect in power management.

[0114] In one embodiment of this example, such as Figure 2As shown, step S103, which involves forming a corresponding supply and demand assessment model by associating the power supply-side characteristic data group and the power consumption-side characteristic data group with the power supply and demand relationship, includes the following steps:

[0115] S201. Align the corresponding power supply and demand data classes in the power supply side characteristic data group and the power consumption side characteristic data group according to time based on the power supply and demand relationship, and generate the corresponding aligned data class;

[0116] S202. Perform correlation analysis on the aligned data classes and generate the corresponding correlation coefficients;

[0117] S203. Combine the aligned data class and the corresponding correlation coefficient to form the corresponding supply and demand assessment model.

[0118] In step S201, within the power system, the power supply side characteristic data set mainly includes information such as generator output, generation cost, and generation efficiency, while the power consumption side characteristic data set mainly includes information such as total system load, load in each region, and load fluctuation. To better analyze the supply and demand relationship of the power system, these two sets of data need to be aligned according to time to generate corresponding aligned data classes.

[0119] The aligned data class is a data structure that integrates power supply-side characteristic data sets and power consumption-side characteristic data sets. By aligning these two sets of data according to time granularity, it facilitates the analysis of the supply and demand relationship of the power system. The aligned data class contains power supply-side characteristic data and power consumption-side characteristic data at the same time, which helps to more accurately assess the operating status of the power system and provides a basis for power system monitoring, forecasting, and scheduling.

[0120] Specifically, the process of generating aligned data classes mainly includes the following steps: determining the time granularity, i.e., selecting an appropriate time granularity, such as hour, day, month, etc., based on actual needs and data characteristics; data preprocessing, i.e., cleaning, filling missing values, and handling outliers of the raw data to ensure the accuracy and completeness of the data; time alignment, i.e., aligning the data in the power supply side feature data group and the power consumption side feature data group according to the selected time granularity, i.e., analyzing the power supply data and power consumption data at the same moment together; generating aligned data classes, i.e., integrating the aligned data into a new data class that contains the power supply side feature data and power consumption side feature data at the same moment.

[0121] In step S201, correlation analysis is a statistical method used to measure the strength of the relationship between two or more variables. In a power system, the aligned data class contains characteristic data of the power supply side and the power consumption side at the same time. By performing correlation analysis on these data, the interrelationship between the power supply side and the power consumption side can be revealed, providing a basis for the optimized operation of the power system.

[0122] The correlation coefficient is a commonly used index in association analysis, used to measure the strength of the linear relationship between two variables. For example, the correlation coefficient ranges from -1 to 1, where 1 represents a perfect positive correlation, -1 represents a perfect negative correlation, and 0 represents no correlation. In aligned data classes, the correlation coefficient between power supply-side characteristic data and power consumption-side characteristic data can be calculated to assess the degree of their association.

[0123] For example, if the data is aligned to power generation and load, the correlation between power generation and load can be analyzed by examining the Pearson correlation coefficient between them.

[0124] Specifically, data obtained from the power system's corresponding power data monitoring equipment showed that: in the first hour, the power generation was 1000 MW and the load was 900 MW; in the second hour, the power generation was 1100 MW and the load was 950 MW; in the third hour, the power generation was 1200 MW and the load was 1000 MW; in the fourth hour, the power generation was 1300 MW and the load was 1050 MW; and in the fifth hour, the power generation was 1400 MW and the load was 1100 MW.

[0125] Secondly, calculate the mean of power generation and load: mean power generation = 1200, mean load = 1000. Then calculate the covariance of power generation and load: covariance = 10000. Next, calculate the standard deviation of power generation and load: = 141.42, load standard deviation = = 70.71. The Pearson correlation coefficient = covariance / (standard deviation of power generation * standard deviation of load) = 10000 / (141.42 * 70.71) = 0.999, indicating a strong positive correlation between power generation and load. This means that when power generation increases, the load will increase accordingly, and vice versa.

[0126] In step S203, the supply and demand assessment model is a method based on aligned data classes and correlation coefficients, used to assess the relationship between the power supply side and the power consumption side. This model can predict the future supply and demand balance of the power system.

[0127] This involves aligning data types and correlation coefficients to construct a corresponding supply and demand assessment model. This model can be based on methods such as linear regression or time series analysis. By comparing the model's prediction results with actual data, the accuracy and reliability of the model can be evaluated. Furthermore, based on the evaluation results, the model can be adjusted and optimized.

[0128] For example, if power generation and load data of a certain region's power system are collected over a period of time and the correlation coefficient between them is calculated to be 0.999, a supply and demand assessment model, such as a linear regression model, can then be constructed.

[0129] Specifically, the process involves dividing the data into training and testing sets: the aligned data classes are divided into training and testing sets. The training set is used to build the model, and the testing set is used to evaluate it. A linear regression model is then constructed using the training set data. This model can be represented as y = ax + b, where y represents load, x represents power generation, and a and b are model parameters. Model prediction is performed using the testing set data to calculate the predicted load values. These predicted values ​​are then compared with the actual values ​​to evaluate the model's accuracy. Finally, the model is optimized based on the evaluation results. For example, other regression methods can be used, or more feature variables can be added.

[0130] The power management method provided in this embodiment aligns power supply and demand data according to time, which helps to analyze the supply and demand relationship of the power system in different time periods more accurately. Furthermore, the correlation analysis of the aligned data helps to uncover the inherent connection between the power supply side and the power consumption side data, providing more possibilities for the optimization of the power system, thereby providing more accurate and comprehensive data support analysis for the optimization and management of the power system.

[0131] In one embodiment of this example, such as Figure 3 As shown, step S104, which involves parsing the supply and demand assessment model and obtaining the relevant fluctuation thresholds of the assessment coefficients corresponding to the supply and demand electricity data categories, includes the following steps:

[0132] S301. Analyze the supply and demand assessment model to determine whether there are fluctuation factors affecting the supply and demand electricity data.

[0133] S302. If there are fluctuation factors affecting the power supply and demand data, obtain the safe fluctuation threshold of the fluctuation factors relative to the power supply and demand data.

[0134] S303. Combining the target fluctuation threshold and the safety fluctuation threshold corresponding to the power supply and demand data categories, a relevant fluctuation threshold for the evaluation coefficient corresponding to the power supply and demand data categories is formed.

[0135] In practical applications, power supply and demand data may be affected by a variety of fluctuations, which may cause changes in the supply and demand relationship.

[0136] For example, seasonal factors, such as temperature and holidays, often influence electricity demand. During summer and winter, electricity demand may increase due to the use of air conditioning and heating equipment. Therefore, when analyzing electricity supply and demand data, it is necessary to consider the impact of seasonal factors on the supply-demand relationship.

[0137] For example, weather factors also significantly impact electricity supply and demand. The output of wind and solar power is affected by wind speed and sunshine duration. Furthermore, extreme weather events (such as typhoons and torrential rains) can damage power infrastructure, affecting power supply capacity. Therefore, when analyzing electricity supply and demand data, the impact of weather factors on the supply-demand relationship must be considered.

[0138] In step S301, if analyzing the supply and demand assessment model reveals a significant discrepancy between the model's predictions and actual data—in other words, fluctuations exist in the supply and demand electricity data—a series of analyses can be conducted on the fluctuating data to determine the specific factors influencing these fluctuations. For example, weather factors can be analyzed: collecting weather data related to electricity supply and demand, such as wind speed and sunshine duration. Analyzing the correlation between these data and the supply and demand relationship helps determine the extent of the impact of weather factors on the supply and demand electricity data.

[0139] In steps S302 to S303, the safety fluctuation threshold refers to the maximum allowable fluctuation range of power supply and demand data categories affected by fluctuation factors without affecting the normal operation of the power system.

[0140] Secondly, the relevant fluctuation thresholds for the evaluation coefficient are formed by combining the target fluctuation threshold and the safety fluctuation threshold of the power supply and demand data. The target fluctuation threshold refers to the fluctuation range that the power supply and demand data should achieve to achieve a specific goal (such as energy saving, cost reduction, etc.). The evaluation coefficient is an indicator that reflects the degree of fluctuation of the power supply and demand data and is used to measure the stability and reliability of the power system.

[0141] Among them, the relevant fluctuation threshold is a comprehensive assessment of the fluctuation range of supply and demand power data, taking into account both the safety fluctuation threshold and the target fluctuation threshold. By comparing the actual fluctuation with the relevant fluctuation threshold, it can be determined whether the power system's operating status is stable and whether it has achieved the expected goals.

[0142] For example, power supply and demand data in a power system can fluctuate due to factors such as weather and equipment failures. First, a safe fluctuation threshold is determined based on system operating requirements and safety standards. Then, a target fluctuation threshold is determined based on goals such as energy conservation and cost reduction. Finally, by combining the safe and target fluctuation thresholds, relevant fluctuation thresholds are obtained. By monitoring the fluctuations in power supply and demand data in real time and comparing them with these relevant fluctuation thresholds, the stability and operational effectiveness of the power system can be evaluated.

[0143] The power management method provided in this embodiment determines whether there are fluctuation influencing factors in the power supply and demand data category, so as to identify possible unstable factors in the power system. If they exist, the method further combines the target fluctuation threshold corresponding to the power supply and demand data category and the safe fluctuation threshold corresponding to the fluctuation influencing factor to form a relevant fluctuation threshold. This allows for accurate determination of the evaluation coefficient of the power supply and demand data category, thereby reducing the evaluation deviation caused by unstable factors.

[0144] In one embodiment of this example, such as Figure 4 As shown, after step S301, which involves parsing the supply and demand assessment model and determining whether there are fluctuations affecting the supply and demand electricity data, the following steps are also included:

[0145] S401. If there are fluctuations in the power supply and demand data, determine whether there are multiple fluctuation factors.

[0146] S402. If there are multiple factors affecting fluctuations, then each factor affecting fluctuations will be subjected to multiple linear regression analysis with the power supply and demand data class to generate the degree of fluctuation contribution of each factor affecting fluctuations relative to the power supply and demand data class.

[0147] In steps S401 to S402, if there are multiple fluctuation factors affecting the power supply and demand data, these factors need to be analyzed to understand their degree of influence on the power supply and demand data.

[0148] Multiple linear regression analysis is a statistical method used to study the relationship between multiple independent variables (fluctuation influencing factors) and a dependent variable (supply and demand electricity data). Using this method, the contribution of each fluctuation influencing factor to the fluctuation of the supply and demand electricity data category can be obtained, that is, the magnitude of each factor's influence on the fluctuation of the supply and demand electricity data category.

[0149] For example, the power supply and demand data of a power system is affected by multiple factors such as weather, equipment failure, and load changes. To analyze the degree of influence of these factors on the power supply and demand data, these factors can be used as independent variables, and the power supply and demand data as the dependent variable, to conduct a multiple linear regression analysis. The analysis yields the regression coefficients for each factor, which reflect the contribution of each factor to the fluctuations in the power supply and demand data. For instance, the regression coefficient for weather is 0.5, for equipment failure is 0.3, and for load changes is 0.2. This means that weather has the greatest impact on the fluctuations in the power supply and demand data, followed by equipment failure, and finally load changes.

[0150] The power management method provided in this embodiment, based on multiple linear analysis, can more accurately quantify the impact of various fluctuation factors on power supply and demand data, thereby better understanding the mechanism of action of various factors in the power system, and better identifying and predicting relevant risks in the power system, providing data support for risk prevention in the power system. In addition, based on the contribution of each fluctuation factor, the changes of each risk factor can be monitored in real time, providing a more reliable basis for the dynamic adjustment and management of the power system.

[0151] In one embodiment of this example, such as Figure 5 As shown, step S107, which involves generating the corresponding iterative supply and demand assessment model based on the real-time collected data and the real-time evaluation coefficient if the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, includes the following steps:

[0152] S501. If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, then obtain the target fluctuation item corresponding to the real-time collected data;

[0153] S502. If the target volatility term has multiple volatility-inducing factors, calculate the correlation coefficients between the various volatility-inducing factors and construct the corresponding correlation coefficient matrix;

[0154] S503. Perform eigenvalue decomposition on the correlation coefficient matrix to generate corresponding eigenvalues ​​and eigenvectors;

[0155] S504. Calculate the weight coefficients corresponding to the eigenvectors based on the eigenvalues;

[0156] S505. Combine the target fluctuation term and weight coefficients to generate the corresponding real-time evaluation coefficients as an iterative supply and demand evaluation model.

[0157] In step S501, the preset iterative numerical standard is a numerical threshold set during the power system fluctuation analysis and control process. It is used to measure whether the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold is within an acceptable range. When the numerical difference is within the preset iterative numerical standard range, it indicates that the current numerical difference is within the acceptable range of the power system. However, it is necessary to iteratively update the current supply and demand evaluation model in order to obtain power supply and demand data that are more closely related to reality.

[0158] The target fluctuation term refers to the analysis of the impact of various fluctuation factors on power supply and demand data in the power system, under the condition of meeting preset iterative numerical standards. The target fluctuation term is typically calculated using real-time collected data, including but not limited to multiple fluctuation factors such as weather, equipment failure, and load changes. These factors may affect the supply and demand balance of the power system, leading to system fluctuations.

[0159] For example, in the supply and demand assessment model, the user load is set at 1000 MW as the electricity consumption benchmark. However, in the summer, the user's electricity consumption surges and the electricity load is maintained at 1500 MW for a long time. In order to make the analysis of the power system more in line with reality, it is necessary to iteratively update the electricity consumption benchmark analysis rules in the current supply and demand assessment model, that is, to set the electricity load at 1500 MW as the electricity consumption benchmark.

[0160] For example, if the preset iteration numerical standard is that the difference between the real-time evaluation coefficient and the relevant fluctuation threshold is greater than 0.05, and the difference between the real-time evaluation coefficient and the relevant fluctuation threshold is 0.06, then it can be determined that the preset iteration numerical standard is met. At this time, the target fluctuation items corresponding to the real-time collected data include multiple fluctuation influencing factors such as weather, equipment failure, and load change. Through multiple linear regression analysis, the degree of influence of the above fluctuation influencing factors on the power supply and demand data can be obtained. For example, the degree of influence of weather factors is 0.5, the degree of influence of equipment failure factors is 0.3, and the degree of influence of load change factors is 0.2. These degrees of influence are the target fluctuation items.

[0161] In steps S502 to S504, if the target fluctuation item has multiple fluctuation inducing factors, in order to better analyze the interrelationships between these factors, the correlation coefficients between the various fluctuation inducing factors can be calculated and a corresponding correlation coefficient matrix can be constructed.

[0162] The correlation coefficient matrix is ​​a symmetric matrix used to describe the linear relationship between various fluctuation-inducing factors. The correlation coefficient ranges from -1 to 1, where 1 represents a perfect positive correlation, -1 represents a perfect negative correlation, and 0 represents no correlation. The correlation coefficient matrix can analyze the degree of association between various fluctuation-inducing factors. By analyzing the correlation coefficient matrix, we can identify which factors have strong correlations, thus enabling targeted measures to reduce the impact of fluctuations. Furthermore, the correlation coefficient matrix can also be used for multiple linear regression analysis to predict fluctuation changes in power systems.

[0163] Secondly, eigenvalue decomposition of the aforementioned correlation coefficient matrix is ​​a dimensionality reduction method that extracts information from multiple fluctuation-inducing factors into fewer principal components, thus simplifying the problem. Eigenvalue decomposition generates corresponding eigenvalues ​​and eigenvectors. Eigenvalues ​​represent the importance of each principal component, and eigenvectors represent the direction of each principal component. By calculating the weight coefficients corresponding to the eigenvectors based on the eigenvalues, the contribution of each principal component to the original fluctuation-inducing factors can be obtained.

[0164] For example, the target fluctuation term in a power system includes three fluctuation-inducing factors: weather change, equipment failure, and load change. Eigenvalue decomposition of their correlation coefficient matrix yields eigenvalues ​​λ1, λ2, and λ3, and corresponding eigenvectors v1, v2, and v3. Assuming λ1 is the largest eigenvalue, then v1 represents the direction of the first principal component. The weight coefficients corresponding to the eigenvectors can be calculated based on the eigenvalues: weight coefficient = eigenvalue / sum of eigenvalues. This yields the corresponding weight coefficients w1, w2, and w3, where w1 has the largest value. Therefore, the first principal component, i.e., w1, contributes the most to the original fluctuation-inducing factors.

[0165] Furthermore, the iterative supply and demand assessment model is a method for assessing the supply and demand status of a power system based on real-time assessment coefficients. By updating the assessment coefficients in real time and comparing them with thresholds, it enables real-time monitoring and adjustment of the supply and demand status of the power system.

[0166] Specifically, the corresponding iterative supply and demand assessment model can be generated in the following ways: Identifying target fluctuation terms: Collect fluctuation-inducing factors affecting the supply and demand of the power system, such as weather changes, equipment failures, and load changes, and use these factors as target fluctuation terms; Calculating weighting coefficients: For each target fluctuation term, calculate its weighting coefficient using methods such as eigenvalue decomposition and principal component analysis; the weighting coefficients are used to measure the degree of influence of each fluctuation-inducing factor on the supply and demand situation; Generating real-time assessment coefficients: Multiply the target fluctuation term by its corresponding weighting coefficient to obtain the real-time assessment coefficient, which is used to monitor and assess the supply and demand situation of the power system in real time; Setting thresholds: Based on historical data and experience, set a reasonable threshold to determine whether the supply and demand situation of the power system is good; Real-time monitoring and assessment: Compare the real-time assessment coefficient with the threshold. If the real-time assessment coefficient exceeds the threshold, it indicates that there may be problems with the supply and demand situation, and measures need to be taken to adjust it; Adjustment and optimization: Based on the changes in the real-time assessment coefficient, take corresponding measures to adjust the operating parameters of the power system to achieve supply and demand balance; Iterative updates: Continuously update the target fluctuation terms and weighting coefficients over time so that the iterative supply and demand assessment model can better adapt to the actual operating conditions of the power system.

[0167] The power management method provided in this embodiment calculates the weight coefficients corresponding to the eigenvectors based on the eigenvalues. This allows for the reasonable allocation of the weights of various fluctuation-inducing factors in the real-time evaluation coefficients, thereby better reflecting the degree of influence of each factor on the power system. Subsequently, by combining the target fluctuation term and the weight coefficients, the corresponding real-time evaluation coefficients are generated as an iterative supply and demand evaluation model. Based on this iterative supply and demand evaluation model, the power system can be dynamically adjusted and optimized, thereby improving the operating efficiency and stability of the power system.

[0168] In one embodiment of this example, such as Figure 6As shown, step S108, which generates the corresponding power supply and demand optimization strategy based on the power assessment data corresponding to the iterative supply and demand assessment model, includes the following steps:

[0169] S601. Obtain the target power supply and demand indicators corresponding to the power assessment data;

[0170] S602. Analyze the current power supply and demand data based on the target power supply and demand indicators, and obtain the corresponding abnormal adjustment items;

[0171] S603. Generate corresponding power supply and demand optimization strategies based on abnormal adjustment items.

[0172] In steps S601 to S602, obtaining the target power supply and demand indicators corresponding to the power assessment data refers to extracting key indicators related to power supply and demand from the power system's operational data to assess the power system's supply and demand status. These indicators typically include load, power generation, transmission line capacity, and energy storage capacity.

[0173] Among these, analyzing current power supply and demand data based on target power supply and demand indicators to obtain corresponding abnormal adjustment items refers to identifying abnormal factors that may lead to supply and demand imbalances by comparing actual operating data with target indicators. These abnormal adjustment items are used to guide the power system in taking appropriate measures to adjust and achieve supply and demand balance.

[0174] Secondly, abnormal adjustment items refer to situations in which the power system deviates from the target supply and demand indicators due to various uncertainties during actual operation. For example, sudden equipment failures, extreme weather, load fluctuations, etc., may cause the actual power supply and demand situation to deviate from the expected target.

[0175] In step S603, after identifying the abnormal factors of the aforementioned abnormal regulation items, corresponding measures and plans are formulated to achieve power supply and demand balance and optimized operation of the power system. Power supply and demand optimization strategies target abnormal regulation items in the power system and adjust and optimize the operating parameters of the power system to achieve power supply and demand balance and improve system operating efficiency. Power supply and demand optimization strategies typically include adjusting generation plans, optimizing power dispatch, activating backup equipment, and utilizing energy storage devices.

[0176] For example, after identifying abnormal regulation items in the power system load fluctuations, corresponding power supply and demand optimization strategies can be generated, including: utilizing energy storage devices (such as batteries, pumped storage, etc.) to release stored electrical energy to meet short-term peak load demands. Simultaneously, during off-peak periods, excess electrical energy can be stored using energy storage devices to improve the efficiency of power resource utilization.

[0177] The power management method provided in this embodiment analyzes the current power supply and demand data based on target power supply and demand indicators, which can promptly detect anomalies in the power system, provide data support for power system risk prevention, and generate corresponding power supply and demand optimization strategies based on abnormal adjustment items. This can provide more reasonable strategy suggestions for power system scheduling and optimization, and improve the operating efficiency and stability of the power system.

[0178] In one embodiment of this example, such as Figure 7 As shown, after step S603, which generates the corresponding power supply and demand optimization strategy based on the abnormal adjustment item, the following steps are also included:

[0179] S701. Implement power supply and demand optimization strategies and generate corresponding target monitoring instructions;

[0180] S702. Execute the target monitoring command to obtain the corresponding power optimization parameters;

[0181] S703. Based on the power optimization parameters and the current power operation status, generate adjustment schemes corresponding to the power supply and demand optimization strategy.

[0182] In steps S701 to S702, the target monitoring instructions are a series of monitoring tasks designed to ensure the effectiveness and real-time performance of the power supply and demand optimization strategy. By executing these monitoring instructions, real-time operating data of the power system, i.e., power optimization parameters, can be obtained, so as to evaluate and adjust the optimization strategy.

[0183] For example, after implementing an optimization strategy for utilizing energy storage devices, corresponding monitoring instructions can be generated to monitor the charging and discharging status of the energy storage devices, so as to ensure that the energy storage devices can play a role when the load fluctuates and improve the utilization efficiency of power resources.

[0184] In step S703, the current power operation status refers to the actual operating status of the power system at a certain moment, including equipment operating status, power demand, and power supply. After collecting real-time operating data and optimization parameters of the power system, corresponding adjustment plans can be formulated based on the current operating status of the power system to optimize the power supply and demand balance and improve the operating efficiency of the power system.

[0185] Specifically, the above-mentioned optimization parameters and the current power operation status are analyzed to identify the problems and deficiencies in the current power system, such as supply and demand imbalance, equipment overload, and excessive power loss. Then, based on the above analysis results, corresponding adjustment measures are formulated, such as adjusting the power generation plan, optimizing power dispatch, and utilizing energy storage equipment. Subsequently, the above adjustment measures are integrated into a complete adjustment plan, including specific operating steps, time arrangements, and responsible persons.

[0186] The power management method provided in this embodiment monitors the implementation of power supply and demand optimization strategies in real time. It can dynamically adjust the optimization strategies according to the actual optimization situation of the power system, thereby improving the dispatch flexibility of the power system, enabling more rational allocation of power resources, improving the resource utilization rate of the power system, and reducing energy waste.

[0187] This application discloses a power management system, such as... Figure 8 As shown, it includes:

[0188] Module 1 is used to acquire historical power data;

[0189] The segmentation module 2 is used to segment historical power data according to preset classification standards to form corresponding power supply side characteristic data groups and power consumption side characteristic data groups;

[0190] The association module 3 is used to associate the corresponding power supply and demand data classes in the power supply side characteristic data group and the power consumption side characteristic data group according to the power supply and demand relationship, and form the corresponding supply and demand assessment model.

[0191] Module 4 is used to parse the supply and demand assessment model and obtain the relevant fluctuation threshold of the assessment coefficient corresponding to the supply and demand power data class.

[0192] Loading module 5 is used to add real-time collected data corresponding to the power supply and demand data category to the corresponding power supply and demand assessment model and generate the corresponding real-time assessment coefficients.

[0193] If the real-time evaluation coefficient exceeds the relevant fluctuation threshold, the iterative analysis module 6 is used to determine whether the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard.

[0194] If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, the iterative model generation module 7 is used to generate the corresponding iterative supply and demand evaluation model based on the real-time collected data and the real-time evaluation coefficient.

[0195] The power optimization module 8 is used to generate corresponding power supply and demand optimization strategies based on the power assessment data corresponding to the iterative supply and demand assessment model.

[0196] The power management system provided in this embodiment divides historical power data according to preset classification standards using the division module 2, forming corresponding power supply-side characteristic data groups and power consumption-side characteristic data groups. This allows for the acquisition of various supply and demand characteristics of the current power system data, providing an accurate basis for subsequent data analysis. Then, based on the current power supply and demand relationship of the power system, the data in the power supply-side and power consumption-side characteristic data groups are specifically categorized, i.e., classified into specific supply and demand power data categories according to their supply and demand attributes. A corresponding supply and demand assessment model is formed through the association module 3. The supply and demand assessment model then provides the corresponding supply and demand assessment analysis for each specific supply and demand power data category. To further integrate with the actual operating status of the current power system and better predict power demand and supply, the real-time collected data corresponding to the supply and demand power data categories is added to the supply and demand assessment model through the loading module 5, generating... The corresponding real-time evaluation coefficient is then used to update the supply and demand evaluation model in real time to accurately reflect the actual operating status of the power system. If the real-time evaluation coefficient exceeds the relevant fluctuation threshold (i.e., the current real-time data is in an abnormal fluctuation state), the difference between the real-time evaluation coefficient and the relevant fluctuation threshold is again checked to see if it meets the preset iterative numerical standard. If it does, the iterative analysis module 6 generates the corresponding iterative supply and demand evaluation model based on the current real-time data and the real-time evaluation coefficient of the power system. Then, based on the power evaluation data in the iterative supply and demand evaluation model, the power optimization module 8 formulates an optimization strategy suitable for the current operating status of the power system. By combining historical power system data and current dynamic changes in power system supply and demand, a more suitable iterative supply and demand evaluation model is generated, thereby improving the data analysis effect in power management.

[0197] It should be noted that the power management system provided in this application embodiment also includes various modules and / or corresponding sub-modules corresponding to the logical functions or logical steps of any of the above power management methods, achieving the same effect as each logical function or logical step, which will not be elaborated here.

[0198] This application also discloses a terminal device, including a memory, a processor, and computer instructions stored in the memory and capable of running on the processor, wherein the processor executes the computer instructions using any of the power management methods described in the above embodiments.

[0199] The terminal device can be a computer device such as a desktop computer, a laptop computer, or a cloud server. The terminal device includes, but is not limited to, a processor and a memory. For example, the terminal device may also include input / output devices, network access devices, and buses.

[0200] The processor can be a central processing unit (CPU). Of course, depending on the actual use, it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it.

[0201] The memory can be an internal storage unit of the terminal device, such as a hard disk or RAM of the terminal device, or an external storage device of the terminal device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD), or flash memory card (FC) equipped on the terminal device. Furthermore, the memory can be a combination of internal storage units and external storage devices of the terminal device. The memory is used to store computer instructions and other instructions and data required by the terminal device. The memory can also be used to temporarily store data that has been output or will be output. This application does not limit this.

[0202] In this terminal device, any one of the power management methods in the above embodiments can be stored in the memory of the terminal device and loaded and executed on the processor of the terminal device for convenient use.

[0203] This application also discloses a computer-readable storage medium, which stores computer instructions, wherein when the computer instructions are executed by a processor, any of the power management methods described in the above embodiments are employed.

[0204] The computer instructions can be stored in a computer-readable medium. The computer instructions include computer instruction code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer instruction code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.

[0205] In this embodiment, any one of the power management methods described above can be stored in the computer-readable storage medium and loaded and executed on the processor to facilitate the storage and application of the above methods.

[0206] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A power management method, characterized in that, Includes the following steps: Obtain historical power data; The historical power data is divided according to a preset classification standard to form corresponding power supply side characteristic data groups and power consumption side characteristic data groups. Based on the relationship between power supply and demand, the corresponding power supply and demand data classes in the power supply side characteristic data group and the power consumption side characteristic data group are associated to form a corresponding supply and demand assessment model. The supply and demand assessment model is analyzed to obtain the relevant fluctuation threshold of the assessment coefficient corresponding to the supply and demand power data class; Add the real-time collected data corresponding to the power supply and demand data category to the corresponding power supply and demand assessment model to generate the corresponding real-time assessment coefficients. If the real-time evaluation coefficient exceeds the relevant fluctuation threshold, then it is determined whether the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard. If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, then a corresponding iterative supply and demand evaluation model is generated based on the real-time collected data and the real-time evaluation coefficient. Based on the power assessment data obtained from the iterative supply and demand assessment model, a corresponding power supply and demand optimization strategy is generated. The process of forming a corresponding supply and demand assessment model by associating the power supply-side characteristic data group and the power consumption-side characteristic data group with the power supply and demand relationship includes the following steps: Based on the power supply and demand relationship, the corresponding power supply and demand data classes in the power supply side feature data group and the power consumption side feature data group are aligned according to time to generate corresponding aligned data classes; Perform correlation analysis on the aligned data class to generate corresponding correlation coefficients; By combining the aligned data class and the corresponding correlation coefficient, a corresponding supply and demand assessment model is formed.

2. The power management method according to claim 1, characterized in that, The steps to analyze the supply and demand assessment model and obtain the relevant fluctuation thresholds of the assessment coefficients corresponding to the supply and demand electricity data categories include: Analyze the supply and demand assessment model to determine whether there are any fluctuation factors affecting the supply and demand electricity data. If the power supply and demand data class contains the fluctuation influencing factors, then obtain the safe fluctuation threshold of the fluctuation influencing factors relative to the power supply and demand data class; By combining the target fluctuation threshold and the safety fluctuation threshold corresponding to the power supply and demand data class, the relevant fluctuation threshold of the evaluation coefficient corresponding to the power supply and demand data class is formed.

3. The power management method according to claim 2, characterized in that, After analyzing the supply and demand assessment model and determining whether there are fluctuation factors affecting the supply and demand electricity data, the following steps are also included: If the power supply and demand data category contains the fluctuation influencing factors, determine whether there are multiple fluctuation influencing factors; If there are multiple factors affecting the fluctuations, then each of the factors affecting the fluctuations will be subjected to a multiple linear regression analysis with the power supply and demand data class to generate the degree of fluctuation contribution of each factor affecting the fluctuations relative to the power supply and demand data class.

4. The power management method according to claim 1, characterized in that, If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, then generating the corresponding iterative supply and demand evaluation model based on the real-time collected data and the real-time evaluation coefficient includes the following steps: If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, then the target fluctuation item corresponding to the real-time collected data is obtained; If the target fluctuation term has multiple fluctuation inducing factors, then the correlation coefficient between each fluctuation inducing factor is calculated to form the corresponding correlation coefficient matrix; The correlation coefficient matrix is ​​subjected to eigenvalue decomposition to generate corresponding eigenvalues ​​and eigenvectors; Calculate the weight coefficients corresponding to the feature vectors based on the feature values; By combining the target fluctuation term and the weighting coefficient, the corresponding real-time evaluation coefficient is generated as the iterative supply and demand evaluation model.

5. The power management method according to claim 1, characterized in that, Based on the power assessment data corresponding to the iterative supply and demand assessment model, the corresponding power supply and demand optimization strategy is generated, including the following steps: Obtain the target power supply and demand indicators corresponding to the power assessment data; Analyze the current power supply and demand data based on the target power supply and demand indicators to obtain the corresponding abnormal adjustment items; Based on the abnormal adjustment item, the corresponding power supply and demand optimization strategy is generated.

6. The power management method according to claim 5, characterized in that, After generating the corresponding power supply and demand optimization strategy based on the abnormal adjustment item, the following steps are also included: Implement the power supply and demand optimization strategy and generate corresponding target monitoring instructions; Execute the target monitoring command to obtain the corresponding power optimization parameters; Based on the power optimization parameters and the current power operation status, an adjustment plan corresponding to the power supply and demand optimization strategy is generated.

7. A power management system, characterized in that, include: Acquisition module (1) is used to acquire historical power data; The partitioning module (2) is used to partition the historical power data according to the preset classification standard to form corresponding power supply side feature data group and power consumption side feature data group; The association module (3) is used to associate the power supply side characteristic data group and the power consumption side characteristic data group with the corresponding power supply and demand data class according to the power supply and demand relationship, so as to form a corresponding supply and demand assessment model; The parsing module (4) is used to parse the supply and demand assessment model and obtain the relevant fluctuation threshold of the assessment coefficient corresponding to the supply and demand power data class; The loading module (5) is used to add the real-time collected data corresponding to the power supply and demand data class to the corresponding power supply and demand assessment model and generate the corresponding real-time assessment coefficients. If the real-time evaluation coefficient exceeds the relevant fluctuation threshold, the iterative analysis module (6) is used to determine whether the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard. If the numerical difference between the real-time evaluation coefficient and the relevant fluctuation threshold meets the preset iterative numerical standard, the iterative model generation module (7) is used to generate a corresponding iterative supply and demand evaluation model based on the real-time collected data and the real-time evaluation coefficient. The power optimization module (8) is used to generate a corresponding power supply and demand optimization strategy based on the power assessment data obtained from the iterative supply and demand assessment model. The process of forming a corresponding supply and demand assessment model by associating the power supply-side characteristic data group and the power consumption-side characteristic data group with the power supply and demand relationship includes the following steps: Based on the power supply and demand relationship, the corresponding power supply and demand data classes in the power supply side feature data group and the power consumption side feature data group are aligned according to time to generate corresponding aligned data classes; Perform correlation analysis on the aligned data class to generate corresponding correlation coefficients; By combining the aligned data class and the corresponding correlation coefficient, a corresponding supply and demand assessment model is formed.

8. A terminal device, comprising a memory and a processor, characterized in that, The memory stores computer instructions that can run on the processor, and when the processor loads and executes the computer instructions, it employs a power management method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are loaded and executed by the processor, a power management method as described in any one of claims 1 to 6 is employed.

Images