Digital Energy Virtual Power Plant Big Data Computing Power Center Management System

Abstract

The present invention discloses a digital energy virtual power plant big data computing power center management system, which relates to the technical field of power dispatching management. The digital energy virtual power plant big data computing power center management system includes: a data acquisition module for continuously acquiring power control time series data of several power areas of the virtual power plant to be controlled; a data analysis module analyzes the power control time series data to obtain the power production capacity index, power reserve index, and power consumption intensity index of each area in each time period, and calculates the power supply and demand index; the prediction analysis module predicts the power supply and demand index of each area in the next time period based on the power supply and demand index. The present invention dispatches and manages the virtual power plant through the power supply and demand index of each power area in the next time period in the dispatching management module, thereby ensuring the efficient use of power resources, thereby improving the balance of power supply and demand, thereby improving the overall efficiency of the power system, and then reducing the additional costs caused by insufficient power supply or waste.

Description

Technical Field

[0001] The present invention relates to the technical field of power dispatching management, and specifically to a management system for a big data computing power center of a digital energy virtual power plant. Background Technique

[0002] A virtual power plant aggregates and coordinates multiple distributed energy systems, energy storage devices, load regulation and other resources through information technology, communication technology and intelligent algorithms, thus forming a "virtual power resource pool" that can participate in dispatching and market transactions in the power market like a traditional power plant. Through real-time monitoring and predictive analysis of various energy resources, the virtual power plant can make flexible dispatching and optimization decisions according to factors such as power market demand and real-time load fluctuations, thereby improving the economy and reliability of the power system.

[0003] The core of digital energy technology is informatization, intelligence and networking. It realizes real-time monitoring and analysis of power production, transmission, distribution and consumption through technical means such as sensors, the Internet of Things, cloud computing, and big data. In the application scenario of a virtual power plant, digital energy technology makes the dispatching of distributed energy more accurate and efficient, and big data technology enables the virtual power plant to extract valuable information from a large amount of power data. Based on this information, the virtual power plant can achieve more accurate power dispatching.

[0004] The prior art, such as the patent application with the publication number CN118572708A, discloses a method and system for power equipment operation management based on edge computing, which relates to the technical field of power production equipment management. The method includes: interacting the distribution of power production equipment in the target area with the data center configuration to determine the reference distribution network; performing twin simulation and management mechanism configuration to build a twin power network; matching the derived power data and operation processing tasks with the computing power center to determine the target computing power center; performing task processing and determining the equipment operation and management data; performing equipment operation and maintenance management and transmitting back the management response data; determining whether the management response data meets the expected standard. If not, perform equipment feedback management based on the expected deviation degree. In the prior art, problems such as network delay, large data transmission volume, and waste of computing resources occur in the operation management of power production equipment due to relying on the central server for data processing and analysis, and rational and accurate control of power production equipment operation management is achieved.

[0005] Based on the above solutions, it is found that the limitations of the existing technology at least include the following problems. The existing technology lacks a dynamic monitoring and intelligent scheduling mechanism for real-time data during the operation of power equipment in the power area, which easily leads to management lags in high-load or abnormal states of the equipment, making it difficult to respond promptly to power demand fluctuations, thereby affecting the efficiency and stability of the overall power system. In addition, the existing technology is difficult to effectively cope with changes in power operation data processing requirements, resulting in waste or insufficiency of computing resources, thus affecting management efficiency and response speed. Summary of the Invention

[0006] In view of the deficiencies of the existing technology, the present invention provides a management system for the big data computing power center of a digital energy virtual power plant, which solves the problems of the existing technology lacking real-time data monitoring and intelligent scheduling, resulting in resource waste and response lags.

[0007] To achieve the above objectives, the present invention is realized through the following technical solutions: A management system for the big data computing power center of a digital energy virtual power plant, including: a data acquisition module for continuously acquiring power control time-series data of several power areas of the virtual power plant to be controlled, where the power control time-series data includes power production time-series data, power storage time-series data, and power consumption time-series data; a data analysis module for separately analyzing the power control time-series data of each power area of the virtual power plant to be controlled to obtain the power production index, power energy reserve index, and power consumption intensity index of each time period of each power area of the virtual power plant to be controlled, and performing comprehensive analysis to obtain the power supply and demand index of each time period of each power area of the virtual power plant to be controlled; a prediction analysis module for predicting and analyzing the power supply and demand index of each time period of each power area of the virtual power plant to be controlled to obtain the power supply and demand index of the next time period of each power area of the virtual power plant to be controlled; and a scheduling management module for performing scheduling management based on the power supply and demand index of the next time period of each power area of the virtual power plant to be controlled.

[0008] Furthermore, the power production time-series data includes the power generation power value, operation efficiency value, equipment stability index, output fluctuation index, and power load index of each time period, and the specific steps for obtaining the power production index of each time period of each power area of the virtual power plant to be controlled are as follows: performing normalization processing on the power generation power value, operation efficiency value, equipment stability index, output fluctuation index, and power load index of each time period of each power area of the virtual power plant to be controlled; and performing comprehensive analysis based on the power generation power value, operation efficiency value, equipment stability index, output fluctuation index, and power load index of each time period of each power area of the virtual power plant to be controlled after normalization processing to obtain the power production index of each time period of each power area of the virtual power plant to be controlled.

[0009] Further, the specific steps for obtaining the equipment stability index and output fluctuation index of each time period in each power area of the virtual power plant to be controlled are as follows: Obtain the operating temperature value, operating pressure value, operating vibration value, operating rotation speed value, operating temperature reference value, operating pressure reference value, operating vibration reference value, and operating rotation speed reference value of each time period in each power area of the virtual power plant to be controlled, and conduct comprehensive analysis respectively to obtain the operating temperature difference index, operating pressure difference index, operating vibration difference index, and operating rotation speed difference index of each power area of the virtual power plant to be controlled; and conduct comprehensive analysis on the operating temperature difference index, operating pressure difference index, operating vibration difference index, and operating rotation speed difference index of each power area of the virtual power plant to be controlled to obtain the equipment stability index of each time period in each power area of the virtual power plant to be controlled; obtain the output power value of each time point in each time period in each power area of the virtual power plant to be controlled, and conduct comprehensive analysis to obtain the output fluctuation index of each time period in each power area of the virtual power plant to be controlled.

[0010] Further, the specific formula for calculating the power production index of each time period in each power area of the virtual power plant to be controlled is as follows: ; where is the power production index of the th power area of the virtual power plant to be controlled in the th time period, is the power generation power value of the th power area of the virtual power plant to be controlled in the th time period after normalization, is the power generation adjustment coefficient stored in the database, is the operating efficiency value of the th power area of the virtual power plant to be controlled in the th time period after normalization, is the operating adjustment coefficient stored in the database, is the equipment stability index of the th power area of the virtual power plant to be controlled in the th time period, is the stability adjustment coefficient stored in the database, is the power load index of the th power area of the virtual power plant to be controlled in the th time period, is the load adjustment coefficient stored in the database, is the output fluctuation index of the th power area of the virtual power plant to be controlled in the th time period, is the output fluctuation adjustment coefficient stored in the database, 1, 2, 3, …, , is the number of power regions, 1, 2, 3, …, , is the number of time periods.

[0011] Furthermore, the power storage time series data includes the state of charge index, charge and discharge power index, internal impedance value, and thermal distribution gradient value for each time period. The specific steps for obtaining the power energy reserve index for each time period of each power region of the virtual power plant to be controlled are as follows: Standardize the state of charge index, charge and discharge power index, internal impedance value, and thermal distribution gradient value for each time period of each power region of the virtual power plant to be controlled; Based on the standardized state of charge index, charge and discharge power index, internal impedance value, and thermal distribution gradient value for each time period of each power region of the virtual power plant to be controlled, conduct a comprehensive analysis to obtain the power storage interaction correction index and the initial power storage index for each time period of each power region of the virtual power plant to be controlled; Obtain the power decay factor for each time period of each power region of the virtual power plant to be controlled, and conduct a comprehensive analysis in combination with the power storage interaction correction index and the initial power storage index to obtain the power energy reserve index for each time period of each power region of the virtual power plant to be controlled.

[0012] Furthermore, the specific steps for obtaining the power decay factor for each time period of each power region of the virtual power plant to be controlled are as follows: Obtain the cycle number value, charge and discharge rate value, deep discharge value, battery health index, as well as the cycle number reference value, charge and discharge rate reference value, deep discharge reference value, and battery health reference index for each time period of each power region of the virtual power plant to be controlled, and conduct a difference analysis to obtain the cycle difference, charge and discharge rate difference, deep discharge difference, and battery health index difference for each time period of each power region of the virtual power plant to be controlled; Standardize the cycle difference, charge and discharge rate difference, deep discharge difference, and battery health index difference for each time period of each power region of the virtual power plant to be controlled, and conduct a comprehensive analysis to obtain the power decay factor for each time period of each power region of the virtual power plant to be controlled.

[0013] Further, the power consumption time-series data includes the power consumption value, frequency fluctuation index, and load mutation rate index for each time period. The specific steps for obtaining the power consumption intensity index for each time period of each power region of the virtual power plant to be controlled are as follows: Normalize the power consumption value, frequency fluctuation index, and load mutation rate index for each time period of each power region of the virtual power plant to be controlled; Based on the normalized power consumption value, frequency fluctuation index, and load mutation rate index for each time period of each power region of the virtual power plant to be controlled, perform a comprehensive analysis to obtain the initial power consumption index for each time period of each power region of the virtual power plant to be controlled; Obtain the environmental correction factor and power quality index for each time period of each power region of the virtual power plant to be controlled, and perform a comprehensive analysis in combination with the initial power consumption index to obtain the power consumption intensity index for each time period of each power region of the virtual power plant to be controlled.

[0014] Further, the specific formula for calculating the power supply-demand index for each time period of each power region of the controlled virtual power plant is as follows: ; where is the power supply-demand index for the th time period of the th power region of the virtual power plant to be controlled, is the power production index for the th time period of the th power region of the virtual power plant to be controlled, is the power production adjustment coefficient stored in the database, is the power reserve index for the th time period of the th power region of the virtual power plant to be controlled, is the power reserve adjustment coefficient stored in the database, is the power consumption intensity index for the th time period of the th power region of the virtual power plant to be controlled, is the power consumption adjustment coefficient stored in the database, is the power consumption correction coefficient stored in the database, 1, 2, 3, …, , is the number of power regions, 1, 2, 3, …, , is the number of time periods.

[0015] Furthermore, the specific steps for obtaining the power supply and demand index for the next time period of each power area of the virtual power plant to be controlled are as follows: perform a change analysis on the power supply and demand index for each time period of each power area of the virtual power plant to be controlled, obtain several groups of power supply and demand index change rates of each power area of the virtual power plant to be controlled, and perform a comprehensive analysis to obtain the power supply and demand change fluctuation index of each power area of the virtual power plant to be controlled; perform a comprehensive analysis on the power supply and demand change fluctuation index of each power area of the virtual power plant to be controlled, the power supply and demand index for each time period, and the change rate of each group of power supply and demand index, obtain the predicted power supply and demand index for each power area of the virtual power plant to be controlled, and regard it as the power supply and demand index for the next time period of each power area of the virtual power plant to be controlled.

[0016] Furthermore, the specific steps for scheduling management based on the power supply and demand index of each power area of the virtual power plant to be controlled in the next time period are as follows: the power supply and demand index of each power area of the virtual power plant to be controlled in the next time period is judged and analyzed respectively with the power supply and demand index threshold interval preset for the corresponding power area; if the power supply and demand index of each power area of the virtual power plant to be controlled in the next time period is lower than the lower limit of the power supply and demand index threshold interval preset for the corresponding power area, it is marked as a power shortage area, and arranged in ascending order to generate a power supply and demand shortage table, and priority scheduling is performed based on the power supply and demand shortage table; if the power supply and demand index of each power area of the virtual power plant to be controlled in the next time period is within the power supply and demand index threshold interval preset for the corresponding power area, it is marked as a power balance area and no scheduling is performed; if the power supply and demand index of each power area of the virtual power plant to be controlled in the next time period is lower than the upper limit of the power supply and demand index threshold interval preset for the corresponding power area, it is marked as a power surplus area, and arranged in descending order to generate a power supply and demand surplus table, and priority scheduling is performed based on the power supply and demand surplus table.

[0017] The present invention has the following beneficial effects:

[0018] (1) The digital energy virtual power plant big data computing center management system can effectively optimize the dispatch of power resources by accurately predicting and analyzing the power supply and demand index of each power area. It calculates the power supply and demand index of each power area by comprehensively analyzing the power production, storage and consumption data, and makes predictions based on this index to ensure that power demand can be accurately met in different time periods. For example, when the supply and demand index of a power area is lower than the preset lower limit, the system marks it as a "power shortage area" and gives priority to dispatching areas with insufficient power resources, thereby ensuring the efficient use of power resources, thereby improving the balance of power supply and demand, and further improving the overall efficiency of the power system, thereby reducing the additional costs caused by insufficient power supply or waste.

[0019] (2) The management system of the digital energy virtual power plant big data computing power center can accurately predict the fluctuations in power demand through the comprehensive analysis of continuous real-time data by the prediction analysis module, thereby formulating a scheduling plan in advance. Furthermore, when the power demand decreases, the system can automatically adjust the distribution of excess power to ensure the stable operation of the power grid. Subsequently, the virtual power plant can quickly respond to emergencies, enhance the flexibility and contingency of the power system, and ensure the continuity and security of power supply.

[0020] (3) The management system of the digital energy virtual power plant big data computing power center can comprehensively grasp the health status of equipment by accurately calculating and real-time monitoring multi-dimensional data of equipment operation in the power area. Thus, potential faults of the equipment can be identified and processed in advance before they occur, effectively avoiding equipment downtime or damage caused by overload or unstable operation. Moreover, the precise scheduling of the system can ensure that the equipment operates in a stable state, thereby reducing maintenance costs and extending the service life of the equipment, and improving the overall safety and stability of the power system.

[0021] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a block diagram of the management system of the digital energy virtual power plant big data computing power center of the present invention.

[0023] Figure 2 It is a specific step flowchart for obtaining the power production index of each time period in each power area of the virtual power plant to be controlled in the management system of the digital energy virtual power plant big data computing power center of the present invention.

[0024] Figure 3 It is a specific step flowchart for obtaining the electric energy reserve index of each time period in each power area of the virtual power plant to be controlled in the management system of the digital energy virtual power plant big data computing power center of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0025] Please refer to Figure 1, an embodiment of the present invention provides a technical solution: a digital energy virtual power plant big data computing power center management system, including: a data acquisition module, configured to continuously acquire power control time-series data of several power regions of a virtual power plant to be controlled, where the power control time-series data includes power production time-series data, power storage time-series data, and power consumption time-series data; a data analysis module, configured to perform data analysis on the power control time-series data of each power region of the virtual power plant to be controlled respectively, obtain the power production index, power reserve index, and power consumption intensity index of each time period of each power region of the virtual power plant to be controlled, and perform comprehensive analysis to obtain the power supply and demand index of each time period of each power region of the virtual power plant to be controlled. The specific formula is as follows: ; where is the power supply and demand index of the th power region of the virtual power plant to be controlled at the th time period, is the power production index of the th power region of the virtual power plant to be controlled at the th time period, is the power production adjustment coefficient stored in the database, is the power reserve index of the th power region of the virtual power plant to be controlled at the th time period, is the power reserve adjustment coefficient stored in the database, is the power consumption intensity index of the th power region of the virtual power plant to be controlled at the th time period, is the power consumption adjustment coefficient stored in the database, is the power consumption correction coefficient stored in the database, 1, 2, 3,..., , is the number of power regions, 1, 2, 3,..., , is the number of time periods; a prediction analysis module, configured to perform prediction analysis on the power supply and demand index of each time period of each power region of the virtual power plant to be controlled, and obtain the power supply and demand index of the next time period of each power region of the virtual power plant to be controlled; a scheduling management module, configured to perform scheduling management based on the power supply and demand index of the next time period of each power region of the virtual power plant to be controlled.

[0026] It should be noted that , , , It can be obtained through the following steps: Using historical data, combined with the power production capacity index, power energy reserve index, and power energy consumption intensity index, conduct statistical regression analysis to quantify the specific impact of each factor on the power supply and demand index, thereby fitting the initial weight values. Secondly, use the sensitivity analysis method to adjust the value range of each coefficient and observe its impact on the power supply and demand assessment results to ensure the stability and rationality of the model. Based on the power regional characteristics and actual situation, correct and optimize the preliminarily fitted coefficients, and finally determine the coefficient values applicable to a specific power region.

[0027] Specifically, as Figure 2 shown, the power production time series data includes the power generation power value, operation efficiency value, equipment stability maintenance index, output power fluctuation index, and power load index for each time period, and the specific steps to obtain the power production capacity index for each time period of each power region of the virtual power plant to be controlled are as follows: Normalize the power generation power value, operation efficiency value, equipment stability maintenance index, output power fluctuation index, and power load index for each time period of each power region of the virtual power plant to be controlled; Based on the normalized power generation power value, operation efficiency value, equipment stability maintenance index, output power fluctuation index, and power load index for each time period of each power region of the virtual power plant to be controlled, conduct comprehensive analysis to obtain the power production capacity index for each time period of each power region of the virtual power plant to be controlled.

[0028] Among them, the power generation power value is the average value of the output power of all power production equipment in this power region during this time period, and the output power of each power production equipment can be obtained through a power sensor.

[0029] The operation efficiency value is the average value of the efficiency of all power production equipment in this power region during this time period in converting input energy (such as fuel) into electric energy. It can be obtained by obtaining the electric energy output (which can be obtained through an electric energy metering device, such as a watt-hour meter or an electric energy meter) and the fuel consumption (which can be obtained through a fuel flow meter), performing ratio processing, and performing average processing based on the ratio processing result. The obtained result is the operation efficiency value.

[0030] The power load index is the average value of the ratio between the actual load demand (i.e., the actual power generation power, which can be obtained through a power sensor) and the maximum power generation capacity (the maximum power generation power, i.e., the rated power generation power, which can be obtained from the specifications of the power generation equipment stored in the database) of all power production equipment in this power region during this time period.

[0031] The specific formula for calculating the power production capacity index for each time period of each power region of the virtual power plant to be controlled is as follows: ; where is the th The power production index for a certain period is the power generation value of the th period of the th power region of the virtual power plant to be controlled after normalization, is the power generation adjustment coefficient stored in the database, is the operating efficiency value of the th period of the th power region of the virtual power plant to be controlled after normalization, is the operation adjustment coefficient stored in the database, is the equipment stability index of the th period of the th power region of the virtual power plant to be controlled after normalization, is the stability adjustment coefficient stored in the database, is the power load index of the th period of the th power region of the virtual power plant to be controlled after normalization, is the load adjustment coefficient stored in the database, 1, 2, 3, …, , is the number of power regions, 1, 2, 3, …, , is the number of periods.

[0032] It should be noted that , , , , can be obtained through the following steps: Based on the historical data of the region, determine the initial influence weights of each variable (power generation value, operating efficiency value, equipment stability index, output fluctuation index, power load index) on the power production index through statistical regression analysis. Then, use the sensitivity analysis method to adjust the value range of the coefficients to evaluate the stability and applicability of these parameters to the formula output. Next, further fit the weights through model optimization (such as machine learning algorithms) to ensure that the formula can accurately reflect the actual power production status, and fine-tune the coefficients based on the characteristics of different power regions to ensure its applicability to specific power production assessment requirements.

[0033] The specific implementation example of calculating the power production index of the first time period in the first power area of the virtual power plant to be controlled is as follows. The following data is available:

[0034] The power generation power value (unit: MW) of the first time period in the first power area of the virtual power plant to be controlled is: 85.000.

[0035] The operating efficiency value of the first time period in the first power area of the virtual power plant to be controlled is: 0.865.

[0036] The equipment stability index of the first time period in the first power area of the virtual power plant to be controlled is: 0.924.

[0037] The output fluctuation index (unit: MW) of the first time period in the first power area of the virtual power plant to be controlled is: 1.562.

[0038] The power load index of the first time period in the first power area of the virtual power plant to be controlled is: 0.864.

[0039] Normalize the above data to obtain:

[0040] The power generation power value of the first time period in the first power area of the virtual power plant to be controlled after normalization is approximately: 0.834.

[0041] The operating efficiency value of the first time period in the first power area of the virtual power plant to be controlled after normalization is approximately: 0.893.

[0042] The equipment stability index of the first time period in the first power area of the virtual power plant to be controlled after normalization is approximately: 0.876.

[0043] The output fluctuation index of the first time period in the first power area of the virtual power plant to be controlled after normalization is approximately: 0.562.

[0044] The power load index of the first time period in the first power area of the virtual power plant to be controlled after normalization is approximately: 0.813.

[0045] The power generation adjustment coefficient stored in the database is approximately: 0.271.

[0046] The operation adjustment coefficient stored in the database is approximately: 0.214.

[0047] The stability adjustment coefficient stored in the database is approximately: 0.246.

[0048] The load adjustment coefficient stored in the database is approximately: 2.567.

[0049] The output fluctuation adjustment coefficient stored in the database is approximately: 0.762.

[0050] Substitute the above data into the specific formula for calculating the power production index of each time period in each power area of the virtual power plant to be controlled, and we get:

[0051] The power production index of the first time period in the first power area of the virtual power plant to be controlled ≈ 0.394.

[0052] In this implementation plan, through the comprehensive analysis of multiple key parameters such as power generation power, operation efficiency, equipment stability index, and power load index, the power production status of each power area can be accurately evaluated. And through the normalization processing of various indicators and the introduction of adjustment coefficients, the consistency and fairness among different power areas, different equipment, and different time periods are ensured, making the production capacity evaluation results more objective and accurate. Secondly, by using historical data for statistical regression analysis and combining sensitivity analysis to adjust each coefficient, the influence of different factors on power production can be quantified, and through intelligent model optimization, the power production evaluation system can self-adjust and optimize according to the actual situation, thus realizing precise power resource allocation and scheduling. Finally, by adjusting the coefficients according to the characteristics of different power areas, the adaptability of the system to diverse power equipment and operating environments is ensured, so as to cope with the special needs and changes in different regions, equipment types, and different environments, and provide customized power production evaluation results, thereby avoiding the limitations of a single model in a complex power system, and the introduction of adjustment coefficients ensures the stability and rationality of the model, thus reducing the prediction error caused by overfitting of the system or improper parameter selection.

[0053] Specifically, the specific steps to obtain the equipment stability index and output fluctuation index for each time period of each power area of the virtual power plant to be controlled are as follows: Obtain the operating temperature value, operating pressure value, operating vibration value, operating rotation speed value, operating temperature reference value, operating pressure reference value, operating vibration reference value, and operating rotation speed reference value for each time period of each power area of the virtual power plant to be controlled, and conduct comprehensive analysis respectively (that is, the ratio of the absolute value of the difference between these values and the corresponding reference value to the corresponding reference value, such as the absolute value of the difference between the operating temperature value and the operating temperature reference value / the operating temperature reference value), to obtain the operating temperature difference index, operating pressure difference index, operating vibration difference index, and operating rotation speed difference index for each power area of the virtual power plant to be controlled; and conduct comprehensive analysis (i.e., weighted processing) on the operating temperature difference index, operating pressure difference index, operating vibration difference index, and operating rotation speed difference index for each power area of the virtual power plant to be controlled to obtain the equipment stability index for each time period of each power area of the virtual power plant to be controlled; Obtain the output power value at each time point for each time period of each power area of the virtual power plant to be controlled, and conduct comprehensive analysis (i.e., standard deviation processing) to obtain the output fluctuation index for each time period of each power area of the virtual power plant to be controlled.

[0054] Among them, the operating temperature value is the average value of the operating temperatures of all power production equipment in this power area during this time period, and the temperature value of each power production equipment can be obtained through a temperature sensor.

[0055] The operating pressure value is the average value of the operating pressures of all power production equipment in this power area during this time period, and the pressure value of each power production equipment can be obtained through a pressure sensor.

[0056] The operating vibration value is the average value of the vibration amplitudes of all power production equipment in this power area during this time period, and the vibration amplitude of each power production equipment can be obtained through a vibration sensor.

[0057] The operating rotation speed value is the average value of the rotation speeds of the rotors of all power production equipment in this power area during this time period, and the rotation speed of the rotor of each power production equipment can be obtained through a rotation speed sensor.

[0058] The steps to obtain the operating temperature reference value are as follows: Obtain the historical operating temperature values of all power production equipment in several historical same time periods of this power area, and conduct average value processing to obtain this operating temperature reference value.

[0059] And the steps to obtain the operating pressure reference value, operating vibration reference value, and operating rotation speed reference value are logically consistent with the steps to obtain the operating temperature reference value.

[0060] The output power value can be obtained through a power monitoring instrument (such as a real-time power meter).

[0061] In this implementation scheme, by obtaining key parameters such as the operating temperature, pressure, vibration, and rotational speed of power equipment in real time and comparing them with reference values, the working state of the equipment can be accurately monitored. Furthermore, abnormal fluctuations or unstable states of the equipment can be detected in real time, which helps to timely identify potential fault risks, comprehensively grasp the health status of the equipment, and ensure the long-term stable operation of power equipment. Secondly, the comprehensive analysis of the equipment stability index and the output fluctuation index can timely reflect whether there are risks of equipment decline or load fluctuation, helping maintenance personnel to discover problems earlier, avoiding downtime or production interruption caused by equipment failures, effectively reducing the frequency and severity of failures, reducing maintenance costs, and improving the operating safety of the equipment. Finally, through the analysis of the equipment stability index and the output fluctuation index, the system can help determine whether the equipment is in the optimal operating state, optimize the scheduling arrangement of power production, improve equipment efficiency, avoid production imbalance caused by equipment problems, and ensure the high efficiency and safety of the entire power production process.

[0062] Specifically, as Figure 3 shown, the power storage time-series data includes the state-of-charge index, charge-discharge power index, internal impedance value, and thermal distribution gradient value for each time period. The specific steps to obtain the power energy reserve index for each time period of each power area of the virtual power plant to be controlled are as follows: Standardize the state-of-charge index, charge-discharge power index, internal impedance value, and thermal distribution gradient value for each time period of each power area of the virtual power plant to be controlled; Based on the standardized state-of-charge index, charge-discharge power index, internal impedance value, and thermal distribution gradient value for each time period of each power area of the virtual power plant to be controlled, conduct comprehensive analysis respectively to obtain the power storage interaction correction index for each time period of each power area of the virtual power plant to be controlled (that is, multiply the standardized state-of-charge index, charge-discharge power index, internal impedance value, and thermal distribution gradient value for each time period of each power area), and the initial power storage index (that is, weight the standardized state-of-charge index, charge-discharge power index, internal impedance value, and thermal distribution gradient value for each time period of each power area); Obtain the power decline factor for each time period of each power area of the virtual power plant to be controlled, and conduct comprehensive analysis in combination with the power storage interaction correction index and the initial power storage index to obtain the power energy reserve index for each time period of each power area of the virtual power plant to be controlled.

[0063] Among them, the charge index is the average value of the ratio of the remaining power to the maximum capacity of all energy storage devices in this power region during this time period. The remaining power of each energy storage device can be obtained through the battery management system (which calculates the remaining power of the battery in real time according to parameters such as the current, voltage, and temperature of the device, and usually uses the voltage change of the battery to estimate the remaining power of the battery), and the maximum capacity of each energy storage device can be obtained through the device specification stored in the database.

[0064] The charge-discharge power index is the average value of the ratio of the input power to the output power of all energy storage devices in this power region during this time period. The input power of each energy storage device can be obtained by calculating the charging current (which can be obtained through a current sensor), charging voltage (which can be obtained through a voltage sensor), and charging power factor (which can be obtained through a power factor meter) during the charging process (i.e., charging current * charging voltage * charging power factor). The output power of each energy storage device can be obtained by calculating the discharge current (which can be obtained through a current sensor), discharge voltage (which can be obtained through a voltage sensor), and discharge power factor (which can be obtained through a power factor meter) during the discharge process (i.e., discharge current * discharge voltage * discharge power factor).

[0065] The internal impedance value is the average value of the internal resistances of all energy storage devices in this power region during this time period, and the internal resistance of each energy storage device can be obtained through an impedance analyzer.

[0066] The thermal distribution gradient value is the average value of the standard deviations of the internal temperature values (i.e., the temperature at this key position, which can be obtained through a temperature sensor) at each key position (such as different cells of the battery module, the top and bottom of the battery pack) of all energy storage devices in this power region during this time period.

[0067] And the specific formula for calculating the power energy reserve index of each time period of each power region of the virtual power plant to be controlled is as follows: ; among them, is the power energy reserve index of the th power region of the virtual power plant to be controlled in the th time period, is the power storage interaction correction index of the th power region of the virtual power plant to be controlled in the th time period, is the storage correction adjustment coefficient stored in the database, is the power initial storage index of the th power region of the virtual power plant to be controlled in the th time period, is the initial adjustment coefficient stored in the database, is the composite adjustment coefficient stored in the database, is the power decay factor for the th power area of the virtual power plant to be controlled during the th time period, is the decay adjustment coefficient stored in the database, 1, 2, 3, …, , is the number of power areas, 1, 2, 3, …, , is the number of time periods.

[0068] It should be noted that the term in the formula is used to adjust the combined effect of the power storage interaction correction index and the initial power storage index, avoiding the final power reserve index being too high or too low.

[0069] 、 、 、 can be obtained through the following steps: Based on historical data, determine the initial influence weights of each variable (power storage interaction correction index, initial power storage index, power decay factor) on the power reserve index through statistical regression analysis. Then, use the sensitivity analysis method to adjust the value range of the coefficient to evaluate the stability and applicability of these parameters to the formula output. Next, further fit the weights through model optimization (such as multi-objective optimization) to ensure that the formula can accurately reflect the actual power reserve state, and fine-tune the coefficient based on the characteristics of different power areas to ensure its applicability to specific power reserve assessment requirements.

[0070] The specific steps to obtain the power decay factor for each time period of each power area of the virtual power plant to be controlled are as follows: Obtain the cycle number value, charge and discharge rate value, deep discharge value, battery health index, as well as the cycle number reference value, charge and discharge rate reference value, deep discharge reference value, and battery health reference index for each time period of each power area of the virtual power plant to be controlled, and perform difference analysis to obtain the cycle difference, charge and discharge rate difference, deep discharge difference, and battery health index difference for each time period of each power area of the virtual power plant to be controlled; Standardize (i.e., remove the unit) the cycle difference, charge and discharge rate difference, deep discharge difference, and battery health index difference for each time period of each power area of the virtual power plant to be controlled, and perform comprehensive analysis (weighted processing based on the standardized processing results) to obtain the power decay factor for each time period of each power area of the virtual power plant to be controlled.

[0071] Among them, the cycle number value is the average number of times each energy storage device (such as a battery) in this power region during this time period undergoes a complete charge-discharge cycle, and the number of times each energy storage device undergoes a complete charge-discharge cycle can be obtained through a cycle number counter.

[0072] The charge-discharge rate value can be obtained through the following steps: Obtain the charging rate (i.e., charging voltage * charging current, where the charging voltage can be obtained through a voltage sensor and the charging current can be obtained through a current sensor) and the discharging rate (i.e., discharging voltage * discharging current, where the discharging voltage can be obtained through a voltage sensor and the discharging current can be obtained through a current sensor) of each energy storage device in this power region during this time period, and perform a weighting process. The average value can be processed on the weighting process result, and the obtained result is the charge-discharge rate value.

[0073] The deep discharge value is the average value of the ratio of the electricity consumed during the discharging process of each energy storage device in this power region during this time period (which can be obtained through the ampere-hour metering method, that is, monitoring the current change during the discharging process and performing integration to calculate the electricity consumed by the battery during this time period) to the maximum capacity of the battery (obtained through the device specification stored in the database).

[0074] The battery health index is the average value of the ratio between the current charging capacity of each energy storage device in this power region during this time period (which can be obtained through the ampere-hour metering method, that is, monitoring the current change during the charging process and performing integration to calculate the charging electricity of the battery during this time period) and the original capacity (obtained through the device specification stored in the database).

[0075] And the cycle number reference value can be obtained through the following steps: Obtain the historical cycle number values of all power production devices in several historical identical time periods in this power region, and perform an average value process to obtain the cycle number reference value.

[0076] The acquisition logics of the charge-discharge rate reference value, the deep discharge reference value, the battery health reference index, and the cycle number reference value are the same.

[0077] In this implementation plan, by comprehensively analyzing multiple key indicators such as the charge index, charge and discharge power index, internal impedance value, and thermal distribution gradient value, the reserve state of the power storage device is comprehensively and accurately evaluated. For example, the charge index and charge and discharge power index reflect the current power and power efficiency of the energy storage device, while the internal impedance value and thermal distribution gradient reveal the health status of the energy storage device. These indicators are standardized and combined with correction factors to ensure the accuracy of the power reserve index. Furthermore, the reserve state of each power area is understood in real time, thereby avoiding power shortages or surpluses and improving the accuracy and efficiency of power dispatching. Secondly, by monitoring data such as the charge status, charge and discharge efficiency, internal impedance, and temperature distribution of the battery, potential problems of the battery can be discovered in real time and maintained or adjusted in a timely manner, thereby extending the service life of the energy storage device, improving the operation efficiency of the device, reducing the risk of failures, and then reducing the device downtime and maintenance costs and ensuring the reliability of the power system. Finally, regression analysis is performed in combination with historical data, and the coefficients are adjusted through sensitivity analysis, so that the power reserve index can adapt to the specific conditions of different power areas, thereby making the system more flexible and adaptable, and then ensuring more accurate evaluation of the power reserve in each area and improving the comprehensive dispatching ability of the power system.

[0078] Specifically, the power consumption time series data includes the power consumption value, frequency fluctuation index, and load mutation rate index for each time period. The specific steps for obtaining the power consumption intensity index for each time period of each power area of the virtual power plant to be controlled are as follows: Normalize (i.e., remove the unit) the power consumption value, frequency fluctuation index, and load mutation rate index for each time period of each power area of the virtual power plant to be controlled; Based on the normalized power consumption value, frequency fluctuation index, and load mutation rate index for each time period of each power area of the virtual power plant to be controlled, perform comprehensive analysis (i.e., weighted processing) to obtain the initial power consumption index for each time period of each power area of the virtual power plant to be controlled; Obtain the environmental correction factor and power quality index for each time period of each power area of the virtual power plant to be controlled, and perform comprehensive analysis in combination with the initial power consumption index to obtain the power consumption intensity index for each time period of each power area of the virtual power plant to be controlled.

[0079] Among them, the power consumption value is the sum of the power consumed by all power devices in this power area during this time period, and the power consumed by each power device can be obtained through an intelligent electricity meter.

[0080] The frequency fluctuation index measures the degree of frequency fluctuation of the power grid (i.e., composed of a combination of power equipment) in this time period of this power area. That is, obtain the power grid frequency values at each location at each time point in this time period of this power area (which can be obtained through frequency sensors), perform standard deviation processing, and perform mean processing based on the standard deviation processing (i.e., for the standard deviation processing results at each time point). The obtained result is the frequency fluctuation index.

[0081] The load mutation rate index measures the severity of the power grid load change in this time period of this power area. It can be obtained by acquiring the power grid load values at each time point in this time period (i.e., the total power demand of each electrical equipment in the power grid, and the power demand of each electrical equipment can be obtained through an intelligent electricity meter), and performing standard deviation processing. The obtained result is the load mutation rate index.

[0082] The specific steps for obtaining the environmental correction factor for each time period of each power area of the virtual power plant to be controlled are as follows: Obtain the environmental temperature reference value, environmental humidity reference value, environmental air pressure reference value, environmental wind speed reference value, environmental temperature value, environmental humidity value, environmental air pressure value, and environmental wind speed value for each time period of each power area of the virtual power plant to be controlled, and perform comprehensive analysis respectively (i.e., the ratio of the absolute value of the difference between these values and the corresponding reference value to the corresponding reference value, such as |environmental temperature reference value - environmental temperature value| / environmental temperature reference value), to obtain the environmental temperature deviation index, environmental humidity deviation index, environmental air pressure deviation index, and environmental wind speed deviation index for each time period of each power area of the virtual power plant to be controlled, and perform weighted processing to obtain the environmental correction factor for each time period of each power area of the virtual power plant to be controlled.

[0083] And the environmental temperature reference value is obtained by acquiring the historical environmental temperature values in several identical time periods of this power area and performing mean processing to obtain this environmental temperature reference value.

[0084] The acquisition logics of the environmental humidity reference value, environmental air pressure reference value, and environmental wind speed reference value are the same as that of the environmental temperature reference value.

[0085] The environmental temperature value (i.e., the environmental temperature value within the power area), environmental humidity value, environmental air pressure value, and environmental wind speed value are obtained through a temperature sensor, humidity sensor, pressure sensor, and wind speed sensor in sequence.

[0086] The specific steps for obtaining the power quality index for each time period of each power area of the virtual power plant to be controlled are as follows: Obtain the voltage deviation rate value and current harmonic distortion rate value for each time period of each power area of the virtual power plant to be controlled, and perform comprehensive analysis (i.e., weighted processing) to obtain the power quality index for each time period of each power area of the virtual power plant to be controlled.

[0087] And the voltage deviation rate value is the average value of the ratio of the measured voltage to the rated voltage of each power device in this power region during this time period (i.e., the absolute value of the difference between the measured voltage and the rated voltage / the rated voltage, and the measured voltage can be obtained through a smart meter, and the rated voltage can be obtained through the device specification stored in the database).

[0088] The current harmonic distortion rate value is the total proportion of harmonic components in the current waveform in this power region during this time period, which can be obtained through a portable harmonic tester.

[0089] The specific formula for calculating the power consumption intensity index of each power region and each time period of the virtual power plant to be controlled is as follows: ; where is the power consumption intensity index of the th power region and the th time period of the virtual power plant to be controlled, is the initial power consumption index of the th power region and the th time period of the virtual power plant to be controlled, is the initial power consumption adjustment coefficient stored in the database, is the environmental correction factor of the th power region and the th time period of the virtual power plant to be controlled, is the environmental correction adjustment coefficient stored in the database, is the power quality index of the th power region and the th time period of the virtual power plant to be controlled, is the power quality adjustment coefficient stored in the database, is the comprehensive interaction adjustment coefficient stored in the database, 1, 2, 3, …, , is the number of power regions, 1, 2, 3, …, , is the number of time periods.

[0090] It should be noted that the term in the formula is used to adjust the superposition effect of the initial power consumption index, the environmental correction factor, and the power quality index, and to avoid the power consumption intensity index being too high or too low.

[0091] 、 、 、 It can be obtained through the following steps: Utilize historical data to evaluate the influence degree of each variable (such as the initial power consumption index, environmental correction factor, power quality index) on the power consumption intensity index through statistical modeling and regression analysis, so as to fit the initial weight values. Then, based on sensitivity analysis, adjust the value range of these coefficients to ensure that the formula has good adaptability to the changes in power consumption intensity in different power regions.

[0092] In this implementation plan, by comprehensively analyzing multi-dimensional data such as power consumption, frequency fluctuation, and load mutation, the power consumption intensity index of each time period and power region can be evaluated in detail. And normalization processing and weighted analysis ensure the balanced manifestation of each influencing factor in different power regions and time periods, which helps to accurately grasp the actual situation of power consumption, and then provides a more reliable basis for power dispatching and management. Secondly, by dynamically adjusting the influence of the initial power consumption index, environmental correction factor, and power quality index, the power distribution can be adjusted in real time according to the needs of different power regions, thereby reducing the situation of excessive or insufficient power concentration and ensuring the stable operation of the power system. Finally, through statistical modeling and regression analysis of historical data, the system can continuously optimize the calculation formula of the power consumption intensity index to ensure that it can accurately reflect the consumption characteristics of different power regions and time periods. Sensitivity analysis further ensures the robustness and adaptability of the model and can be dynamically adjusted according to the needs and environmental conditions of different regions, so as to ensure the adaptability and accuracy of the formula to power consumption changes, and then improve the decision-making efficiency of the power system and make it more intelligent.

[0093] Specifically, the specific steps to obtain the power supply and demand index of the next time period of each power region of the virtual power plant to be controlled are as follows: Conduct a change analysis on the power supply and demand index of each time period of each power region of the virtual power plant to be controlled to obtain several groups of power supply and demand index change rates of each power region of the virtual power plant to be controlled (specifically, the difference result of the power supply and demand index of the next time period minus the previous time period, divided by the time period) and conduct comprehensive analysis (i.e., standard deviation processing) to obtain the power supply and demand change fluctuation index of each power region of the virtual power plant to be controlled; Conduct comprehensive analysis on the power supply and demand change fluctuation index of each power region of the virtual power plant to be controlled, the power supply and demand index of each time period, and each group of power supply and demand index change rates to obtain the predicted power supply and demand index of each power region of the virtual power plant to be controlled, and regard it as the power supply and demand index of the next time period of each power region of the virtual power plant to be controlled.

[0094] The specific steps to calculate the predicted power supply and demand index of each power region of the virtual power plant to be controlled are as follows: ; where is the predicted power supply and demand index of the th power region of the virtual power plant to be controlled. is the power supply and demand index of the th power area of the virtual power plant to be controlled for the th time period, is the demand interaction coefficient stored in the database, is the change rate of the power supply and demand index of the th power area of the virtual power plant to be controlled, group, is the change rate adjustment coefficient stored in the database, is the power supply and demand change fluctuation index of the th power area of the virtual power plant to be controlled, is the fluctuation adjustment coefficient stored in the database, 1, 2, 3, …, , is the number of power areas, 1, 2, 3, …, , is the number of time periods, 1, 2, 3, …, , is the number of groups of the change rate of the power supply and demand index, and .

[0095] It should be noted that , , can be obtained through the following steps: Using historical data, combining with the change rate of the power supply and demand index and the power supply and demand change fluctuation index, conducting statistical regression analysis, quantifying the specific impact of each factor on the predicted power supply and demand index, so as to fit the initial weight value. Secondly, using the sensitivity analysis method, adjusting the value range of each coefficient, observing its impact on the evaluation result of the predicted power supply and demand index, ensuring the stability and rationality of the model, and based on the characteristics of the power area and the actual situation, correcting and optimizing the initially fitted coefficients, and finally determining the coefficient values applicable to a specific power area.

[0096] In this implementation plan, by analyzing the change rate of the power supply and demand index and comprehensively analyzing it in combination with the volatility index, the power supply and demand situation in the next time period can be predicted more accurately. Considering the dynamic change characteristics of power demand and supply, it can better reflect the power change trend in the future time period. Secondly, by predicting the power supply and demand index, reasonable resource allocation and scheduling can be made for future power demand, thus avoiding over-supply or shortage of power, and then improving the utilization efficiency of power resources, while reducing the risk of system overload and equipment failure. Especially for complex power grids and multiple power regions, effective allocation can be carried out under unbalanced load demands. Finally, through accurate power supply and demand prediction, power waste can be effectively avoided, and the costs of over-purchasing and over-supply can be reduced. By means of multi-dimensional comprehensive consideration such as data regression analysis, change rate analysis, and volatility index, the intelligent management of the power system is reflected, so as to respond in a timely manner in a complex dynamic change environment, and thus provide a new and accurate decision-making for future power management.

[0097] Specifically, the specific steps for dispatching management based on the power supply and demand index of each power region of the virtual power plant to be controlled in the next time period are as follows: Judge and analyze the power supply and demand index of each power region of the virtual power plant to be controlled in the next time period respectively with the preset power supply and demand index threshold interval of the corresponding power region; If the power supply and demand index of each power region of the virtual power plant to be controlled in the next time period is lower than the lower limit (i.e., the minimum value of the interval) of the preset power supply and demand index threshold interval of the corresponding power region, it is marked as a power shortage region, and an ascending order is carried out to generate a power supply and demand shortage table. At the same time, based on the power supply and demand shortage table, priority dispatching is carried out (that is, dispatching is carried out in turn according to the power shortage regions corresponding to each sequence of the power supply and demand shortage table. For example, the power region corresponding to the first sequence is preferentially dispatched, power from other surplus regions is dispatched to the power region corresponding to the first sequence, and its power generation capacity is increased, or power is dispatched from other power plants); If the power supply and demand index of each power region of the virtual power plant to be controlled in the next time period is within the preset power supply and demand index threshold interval of the corresponding power region, it is marked as a power balance region and no dispatching is carried out; If the power supply and demand index of each power region of the virtual power plant to be controlled in the next time period is lower than the upper limit (i.e., the maximum value of the interval) of the preset power supply and demand index threshold interval of the corresponding power region, it is marked as a power surplus region, and a descending order is carried out to generate a power supply and demand surplus table. At the same time, based on the power supply and demand surplus table, priority dispatching is carried out (that is, dispatching is carried out in turn according to the power surplus regions corresponding to each sequence of the power supply and demand surplus table. For example, the power region corresponding to the first sequence is preferentially dispatched, power is transferred to other shortage regions, and the power output of the surplus region is adjusted, such as reducing power generation or transporting power through the power grid to other regions in need).

[0098] In this implementation scheme, by making a detailed judgment and analysis of the power supply and demand index of each power region, it is possible to accurately identify the regions with power shortages, balances, and surpluses, thereby providing an effective basis for the scheduling of the next time period, avoiding unnecessary power waste (in the surplus regions) and power shortages (in the shortage regions), improving the efficiency of the overall power system. Secondly, according to the shortage regions arranged in ascending order, it can ensure that the regions with the most urgent need for power are given priority in supply, minimizing the risks brought by power shortages, avoiding affecting the normal operation within the region due to insufficient power supply, and dispatching power from other surplus regions to the power shortage regions, or increasing the power generation capacity of these regions, which helps to better cope with sudden power demand fluctuations. Finally, the real-time scheduling of the system for different power regions can be dynamically adjusted according to the changing demands, ensuring that the power supply can always adapt to the demand fluctuations between regions, being able to respond to the changes in supply and demand in real time, and preventing the overload or instability of the power system.

[0099] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0100] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. Digital energy virtual power plant big data computing power center management system, characterized in that, Including: A data acquisition module, configured to continuously acquire power control time-series data of several power regions of a virtual power plant to be controlled, where the power control time-series data includes power production time-series data, power storage time-series data, and power consumption time-series data; A data analysis module, configured to perform data analysis on the power control time-series data of each power region of the virtual power plant to be controlled respectively, obtain the power production capacity index, electric energy reserve index, and electric energy consumption intensity index of each time period of each power region of the virtual power plant to be controlled, and perform comprehensive analysis to obtain the power supply-demand index of each time period of each power region of the virtual power plant to be controlled; A prediction analysis module, configured to perform prediction analysis on the power supply-demand index of each time period of each power region of the virtual power plant to be controlled, and obtain the power supply-demand index of the next time period of each power region of the virtual power plant to be controlled; A dispatching management module, configured to perform dispatching management based on the power supply-demand index of the next time period of each power region of the virtual power plant to be controlled; The specific formula for calculating the power production capacity index of each time period of each power region of the virtual power plant to be controlled is as follows: ； Among them, is the power production index of the th time period of the th power area of the virtual power plant to be controlled, , , , , are, in sequence, the power generation power value, operation efficiency value, equipment stability index, power load index, and output fluctuation index of the th power area of the virtual power plant to be controlled after normalization processing for the th time period, , , , , are, in sequence, the power generation adjustment coefficient, operation adjustment coefficient, stability adjustment coefficient, load adjustment coefficient, and output fluctuation adjustment coefficient stored in the database, 1, 2, 3, …, , is the number of power areas, 1, 2, 3, …, , is the number of time periods.

2. The digital energy virtual power plant big data computing power center management system according to claim 1, wherein The power production time-series data includes the power generation power value, operation efficiency value, equipment stability index, output fluctuation index, and power load index of each time period, and the specific steps for obtaining the power production capacity index of each time period of each power region of the virtual power plant to be controlled are as follows: Perform normalization processing on the power generation power value, operation efficiency value, equipment stability index, output fluctuation index, and power load index of each time period of each power region of the virtual power plant to be controlled; Based on the power generation power value, operation efficiency value, equipment stability index, output fluctuation index, and power load index of each time period of each power region of the virtual power plant to be controlled after normalization processing, perform comprehensive analysis to obtain the power production capacity index of each time period of each power region of the virtual power plant to be controlled.

3. The digital energy virtual power plant big data computing power center management system according to claim 2, wherein The specific steps for obtaining the equipment stability index and output fluctuation index of each time period of each power region of the virtual power plant to be controlled are as follows: Obtain the operation temperature value, operation pressure value, operation vibration value, operation rotation speed value, operation temperature reference value, operation pressure reference value, operation vibration reference value, and operation rotation speed reference value of each time period of each power region of the virtual power plant to be controlled, and perform comprehensive analysis respectively to obtain the operation temperature difference index, operation pressure difference index, operation vibration difference index, and operation rotation speed difference index of each power region of the virtual power plant to be controlled; And perform comprehensive analysis on the operation temperature difference index, operation pressure difference index, operation vibration difference index, and operation rotation speed difference index of each power region of the virtual power plant to be controlled to obtain the equipment stability index of each time period of each power region of the virtual power plant to be controlled; Obtain the output power value of each time point of each time period of each power region of the virtual power plant to be controlled, and perform comprehensive analysis to obtain the output fluctuation index of each time period of each power region of the virtual power plant to be controlled.

4. The digital energy virtual power plant big data computing power center management system according to claim 1, characterized in that The power storage time series data includes the state of charge index, charge and discharge power index, internal impedance value, and thermal distribution gradient value for each time period. The specific steps to obtain the power energy reserve index for each time period of each power area of the virtual power plant to be controlled are as follows: Perform standardization processing on the state of charge index, charge and discharge power index, internal impedance value, and thermal distribution gradient value for each time period of each power area of the virtual power plant to be controlled; Based on the standardized state of charge index, charge and discharge power index, internal impedance value, and thermal distribution gradient value for each time period of each power area of the virtual power plant to be controlled, perform comprehensive analysis to obtain the power storage interaction correction index and power initial storage index for each time period of each power area of the virtual power plant to be controlled; Obtain the power decay factor for each time period of each power area of the virtual power plant to be controlled, and perform comprehensive analysis in combination with the power storage interaction correction index and power initial storage index to obtain the power energy reserve index for each time period of each power area of the virtual power plant to be controlled.

5. The digital energy virtual power plant big data computing power center management system according to claim 4, characterized in that, The specific steps to obtain the power decay factor for each time period of each power area of the virtual power plant to be controlled are as follows: Obtain the number of cycles value, charge and discharge rate value, deep discharge value, battery health index, and the reference value of the number of cycles, charge and discharge rate reference value, deep discharge reference value, and battery health reference index for each time period of each power area of the virtual power plant to be controlled, and perform difference analysis to obtain the cycle difference, charge and discharge rate difference, deep discharge difference, and battery health index difference for each time period of each power area of the virtual power plant to be controlled; Perform standardization processing on the cycle difference, charge and discharge rate difference, deep discharge difference, and battery health index difference for each time period of each power area of the virtual power plant to be controlled, and perform comprehensive analysis to obtain the power decay factor for each time period of each power area of the virtual power plant to be controlled.

6. The digital energy virtual power plant big data computing power center management system according to claim 1, wherein The power consumption time series data includes the power energy consumption value, frequency fluctuation index, and load mutation rate index for each time period. The specific steps to obtain the power energy consumption intensity index for each time period of each power area of the virtual power plant to be controlled are as follows: Perform normalization processing on the power energy consumption value, frequency fluctuation index, and load mutation rate index for each time period of each power area of the virtual power plant to be controlled; Based on the normalized power energy consumption value, frequency fluctuation index, and load mutation rate index for each time period of each power area of the virtual power plant to be controlled, perform comprehensive analysis to obtain the initial power consumption index for each time period of each power area of the virtual power plant to be controlled; Obtain the environmental correction factor and power quality index for each time period of each power area of the virtual power plant to be controlled, and perform comprehensive analysis in combination with the initial power consumption index to obtain the power energy consumption intensity index for each time period of each power area of the virtual power plant to be controlled.

7. The digital energy virtual power plant big data computing power center management system according to claim 1, characterized in that, The specific formula for calculating the power supply and demand index for each time period of each power area of the controlled virtual power plant is as follows: ； Among them, is the power supply and demand index of the th time period of the th power area of the virtual power plant to be controlled. , , are, in sequence, the power production capacity index, power energy reserve index, and power energy consumption intensity index of the th time period of the th power area of the virtual power plant to be controlled. , , , are, in sequence, the power production capacity adjustment coefficient, power energy reserve adjustment coefficient, power energy consumption adjustment coefficient, and power energy consumption correction coefficient stored in the database. 1, 2, 3, …, , is the number of power areas. 1, 2, 3, …, , is the number of time periods.

8. The digital energy virtual power plant big data computing power center management system according to claim 1, characterized in that, The specific steps to obtain the power supply and demand index for the next time period of each power area of the virtual power plant to be controlled are as follows: Conduct a variation analysis on the power supply and demand index for each time period in each power region of the virtual power plant to be controlled, obtain several groups of power supply and demand index change rates for each power region of the virtual power plant to be controlled, and conduct a comprehensive analysis to obtain the power supply and demand change fluctuation index for each power region of the virtual power plant to be controlled; Conduct a comprehensive analysis on the power supply and demand change fluctuation index for each power region of the virtual power plant to be controlled, the power supply and demand index for each time period, and each group of power supply and demand index change rates to obtain the predicted power supply and demand index for each power region of the virtual power plant to be controlled, and regard it as the power supply and demand index for the next time period in each power region of the virtual power plant to be controlled.

9. The digital energy virtual power plant big data computing power center management system according to claim 1, characterized in that, The specific steps for dispatching management based on the power supply and demand index for the next time period in each power region of the virtual power plant to be controlled are as follows: Respectively conduct a judgment analysis on the power supply and demand index for the next time period in each power region of the virtual power plant to be controlled and the preset power supply and demand index threshold range for the corresponding power region; If the power supply and demand index for the next time period in each power region of the virtual power plant to be controlled is lower than the lower limit of the preset power supply and demand index threshold range for the corresponding power region, mark it as a power shortage area, conduct an ascending order arrangement, generate a power supply and demand shortage table, and conduct priority dispatching based on the power supply and demand shortage table; If the power supply and demand index for the next time period in each power region of the virtual power plant to be controlled is within the preset power supply and demand index threshold range for the corresponding power region, mark it as a power balance area and do not conduct dispatching; If the power supply and demand index for the next time period in each power region of the virtual power plant to be controlled is higher than the upper limit of the preset power supply and demand index threshold range for the corresponding power region, mark it as a power surplus area, conduct a descending order arrangement, generate a power supply and demand surplus table, and conduct priority dispatching based on the power supply and demand surplus table.

Images