A method for power grid investment optimization based on big data analysis

Abstract

The present invention relates to the technical field of power grid investment optimization, and specifically discloses a power grid investment optimization method based on big data analysis, the method comprising: monitoring meteorological data of a power planning area, processing to obtain a time series function of power generation of new energy sites in the power planning area, predicting the demand load based on historical load data of the power planning area, and comprehensively analyzing to obtain the demand construction scale data of the energy storage system in the power planning area; obtaining new energy vehicle usage data in the power planning area, and comprehensively analyzing to obtain virtual energy storage compensation parameters in the power planning area; and optimizing the demand construction scale data of the energy storage system in the power planning area based on the virtual energy storage compensation parameters in the power planning area. The present invention comprehensively considers the charging demand and discharge capacity of electric vehicles, determines the optimal construction scale of the energy storage system, and provides a more scientific basis for power grid investment optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid investment optimization, and in particular to a power grid investment optimization method based on big data analysis. Background Art

[0002] Grid investment optimization plays a vital role in the current power system, aiming to improve the operation efficiency, safety and economy of the grid through rational allocation of resources.

[0003] For example, the invention patent with publication number CN117252707B is a method and device for optimizing power grid project investment. This involves collecting and analyzing power parameters to identify existing grid issues; identifying business needs and a library of proposed projects based on these issues; analyzing these business needs and the library of proposed projects to determine project construction objectives, which are then divided and quantified; using the quantified indicators to construct an investment portfolio optimization model; and inputting the quantified indicator data into the investment portfolio optimization model to obtain a power grid project investment portfolio optimization plan.

[0004] For example, the invention patent with announcement number CN113793022B is a method and system for generating a power grid investment planning scheme based on distributed cloud energy storage. By obtaining the current status of the power system of the power grid, the power grid is planned and the power balance analysis is performed on the power grid to generate a predicted power distribution point, capacity and required power generation of the power grid; at the same time, combined with the actual situation of the power grid, a plan for the installation of power grid substations and transmission lines and a distributed cloud energy storage platform architecture plan are generated; and multiple power grid investment planning schemes are formulated; operational data analysis is performed on the multiple power grid investment planning schemes, and the optimal power grid investment planning scheme is obtained based on the results of the operational data analysis.

[0005] Based on the above solution, it was found that there are still some shortcomings in the current optimization of power grid investment. Specifically, traditional power grid investment optimization mainly focuses on power balance. By predicting future power demand and supply, new energy stations and transmission lines are planned. This method ensures the stable operation of the power grid to a certain extent, but does not pay enough attention to the construction and optimization of energy storage systems, which to a certain extent inhibits the flexibility and stability of the power grid. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the present invention provides a power grid investment optimization method based on big data analysis, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides a power grid investment optimization method based on big data analysis, including: monitoring the meteorological data of the power planning area, processing to obtain the time series function of the power generation of new energy sites in the power planning area, and predicting the demand load based on the historical load data of the power planning area, and comprehensively analyzing to obtain the energy storage system demand construction scale data in the power planning area.

[0008] Obtain new energy vehicle usage data in the power planning area, and conduct comprehensive analysis to obtain virtual energy storage compensation parameters in the power planning area.

[0009] The energy storage system demand construction scale data in the power planning area is optimized according to the virtual energy storage compensation parameters in the power planning area.

[0010] As a further method, the processing obtains a time series function of the power generation of new energy stations in the power planning area. The specific process is: deploying a number of environmental monitoring points, collecting the solar radiation and wind speed in the power planning area at each environmental monitoring point, and obtaining the power generation impact weight factors corresponding to the set solar radiation and wind speed from the power planning database, and comprehensively analyzing to obtain the power generation evaluation index of the power planning area.

[0011] The power generation evaluation indicators of the power planning area are compared one by one with the estimated power generation corresponding to each power generation evaluation indicator interval stored in the power planning database to obtain the estimated power generation of the power planning area. At the same time, the historical data of the power generation of the new energy stations in the power planning area are obtained, and the time series function of the power generation of the new energy stations in the power planning area is obtained through curve fitting.

[0012] As a further method, the demand load is predicted based on the historical load data of the power planning area. The specific process is: based on the historical load data of the power planning area, the historical load time series function of the power planning area is obtained by curve fitting.

[0013] Deploy several historical monitoring time points, obtain the historical load at each historical monitoring time point, and obtain the demand load in the power planning area after processing.

[0014] As a further method, the comprehensive analysis obtains the energy storage system demand construction scale data in the power planning area. The specific analysis process is: comparing and analyzing the time series function of the power generation of the new energy stations in the power planning area with the historical load time series function, obtaining the historical monitored power supply and demand difference, and extracting the maximum value of the historical monitored power supply and demand difference.

[0015] The power supply and demand difference threshold is extracted from the power planning database. If the power supply and demand difference in a certain time period is greater than or equal to the power supply and demand difference threshold, the time period is marked as the demand power scheduling time period. The historical demand power scheduling time periods are counted, and the summed result is marked as the historical scheduling duration of the energy storage system.

[0016] Comprehensive analysis yields an energy storage system dispatch demand assessment index for the power planning area, and matching this with the energy storage system demand construction scale data for the power planning area.

[0017] As a further method, the comprehensive analysis obtains the virtual energy storage compensation parameters of the power planning area. The specific analysis process is: the new energy vehicle usage data of the power planning area, including the number of operating new energy vehicles in the power planning area and user vehicle usage habit data.

[0018] Based on the user's car usage habit data, the virtual energy storage regulation capacity evaluation index of the power planning area is obtained after processing, and the virtual energy storage compensation parameters of the power planning area are obtained through comprehensive analysis.

[0019] As a further method, the matching obtains the energy storage system demand construction scale data for the power planning area. The specific process is: comparing the energy storage system scheduling demand degree assessment index for the power planning area with the energy storage system demand construction scale data corresponding to each energy storage system scheduling demand degree assessment index interval stored in the power planning database one by one, to obtain the energy storage system demand construction scale data for the power planning area, wherein the energy storage system demand construction scale data includes the energy storage capacity and energy storage power of the energy storage system.

[0020] As a further method, the energy storage system demand construction scale data of the power planning area is optimized according to the virtual energy storage compensation parameters of the power planning area. The specific process is: the virtual energy storage compensation parameters of the power planning area are compared one by one with the optimizable energy storage capacity and optimizable energy storage power corresponding to each virtual energy storage compensation parameter interval stored in the power planning database to obtain the optimizable energy storage capacity and optimizable energy storage power of the power planning area, and the energy storage system demand construction scale data of the power planning area is optimized according to the optimizable energy storage capacity and optimizable energy storage power of the power planning area.

[0021] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0022] (1) The present invention provides a grid investment optimization method based on big data analysis, which comprehensively considers factors such as the charging demand and discharge capacity of electric vehicles and the power balance of the grid, determines the optimal construction scale of the energy storage system, and can more accurately predict future power demand and supply conditions, providing a more scientific basis for grid investment optimization.

[0023] (2) By analyzing historical load data, the present invention can evaluate the stability of the power system in different time periods, help to discover potential system bottlenecks and failure points, and provide a basis for the optimization and transformation of the power system.

[0024] (3) By analyzing the difference between electricity supply and demand, the present invention can accurately grasp the degree of imbalance between electricity supply and demand, thereby formulating targeted adjustment strategies, more accurately predicting future electricity demand, optimizing electricity resource allocation, and improving electricity utilization efficiency.

[0025] (4) By analyzing the historical demand for power dispatch time, the present invention can discover the law of changes in power demand and provide a more scientific basis for power production, transmission and distribution. At the same time, by analyzing the historical demand for power dispatch time, the response capability of the power system in different seasons and different time periods can be evaluated, providing strong support for the planning, construction and operation of the power system, helping to predict future supply and demand trends and avoid power shortages or surpluses. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0027] Figure 1 Schematic diagram of the method of the present invention.

[0028] Figure 2 Schematic diagram of a functional relationship curve between the maximum value of the historical monitored power supply and demand difference and the energy storage system scheduling demand evaluation index involved in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0030] Reference Figure 1 As shown, the first aspect of the present invention provides a power grid investment optimization method based on big data analysis, including: monitoring the meteorological data of the power planning area, processing to obtain the time series function of the power generation of the new energy sites in the power planning area, and predicting the demand load based on the historical load data of the power planning area, and comprehensively analyzing to obtain the energy storage system demand construction scale data in the power planning area.

[0031] Specifically, the time series function of the power generation of new energy stations in the power planning area is processed. The specific process is: deploy a number of environmental monitoring points, collect the solar radiation and wind speed at each environmental monitoring point in the power planning area, and obtain the power generation impact weight factors corresponding to the set solar radiation and wind speed from the power planning database, and comprehensively analyze to obtain the power generation evaluation indicators of the power planning area.

[0032] In this embodiment, the power planning database is used to store data related to grid investment optimization, including power generation impact weighting factors corresponding to solar radiation and wind speed, historical minimum solar radiation, historical minimum wind speed, estimated power generation corresponding to each power generation assessment index interval, load forecast impact weighting factors corresponding to historical minimum, maximum, and average load values, power supply and demand difference thresholds, energy storage system dispatch demand assessment impact factors corresponding to historical power supply and demand differences, historical energy storage system dispatch duration, and expected power supply and demand differences, critical power supply and demand differences, critical historical energy storage system dispatch duration, virtual energy storage regulation capacity impact factors corresponding to battery capacity and charging rate, critical battery capacity, critical charging rate, number of new energy vehicle users and virtual energy storage compensation impact factors corresponding to virtual energy storage regulation capacity assessment indicators, critical number of new energy vehicle users, energy storage system demand construction scale data corresponding to each energy storage system dispatch demand assessment index interval, and optimizable energy storage capacity and optimizable energy storage power corresponding to each virtual energy storage compensation parameter interval. The data in the database can be obtained through experimental fitting.

[0033] In a specific embodiment, the historical minimum solar radiation and the historical minimum wind speed of the power planning area are extracted from the power planning database, and a comprehensive analysis is performed to obtain the power generation evaluation index of the power planning area. The specific numerical expression is:

[0034] ;

[0035] Where, represents the power generation evaluation index of the power planning area, j represents the number of each environmental monitoring point, j=1,2,3,...,m, m represents the total number of environmental monitoring points, represents the solar radiation at the jth environmental monitoring point, represents the wind speed at the jth environmental monitoring point, Indicates the minimum historical solar radiation. Indicates the historical minimum wind speed. Indicates the weight factor affecting the power generation corresponding to the set solar radiation. Indicates the power generation impact weight factor corresponding to the set wind speed.

[0036] Table 1 Example of power generation evaluation index data

[0037]

[0038] As shown in Table 1, the value of the power generation assessment index is determined by both solar radiation and wind speed. The greater the solar radiation and wind speed, the greater the corresponding power generation assessment index, indicating a higher potential power generation level in the power planning area. It will be appreciated that in this embodiment, the power generation assessment index is used to quantitatively assess the power generation level in the power planning area.

[0039] The formula comprehensively considers the impact of two key factors, solar radiation and wind speed, on power generation, and adjusts their influence using weighting factors, making the assessment results more comprehensive and accurate. By comparing current solar radiation and wind speed with their historical minimums, data standardization is achieved, ensuring consistent evaluation criteria across different times and locations, enhancing the fairness and comparability of the assessment. The formula also uses a nonlinear hyperbolic tangent function to appropriately adjust the sensitivity of the assessment results to the input data, preventing excessive influence from extreme data and improving the stability and reliability of the results.

[0040] It should be understood that in this embodiment, the power generation impact weight factors corresponding to solar radiation and wind speed range from 0 to 1. A mapping set is established based on historical power generation data to determine the impact of solar radiation and wind speed on power generation.

[0041] It should be understood that in this embodiment, the solar radiation can be monitored by a solar radiometer. Solar radiation is one of the main determinants of the power generation of a photovoltaic power generation system. By monitoring the solar radiation in real time, the output power of the photovoltaic power generation system can be predicted more accurately.

[0042] In this embodiment, wind speed can be monitored using an anemometer. Wind energy is a key component of renewable energy, and wind speed is a key factor in assessing wind energy resource potential and determining wind farm site selection. By monitoring wind speed, the power generation potential and efficiency of a wind farm can be assessed, and the layout and operation strategy of wind turbines can be optimized. In photovoltaic power generation, although wind speed is not the primary factor directly affecting power generation, changes in wind speed may affect the temperature and heat dissipation of photovoltaic panels, indirectly affecting the performance of the photovoltaic system. Therefore, monitoring wind speed helps to more comprehensively evaluate and optimize the operation of photovoltaic systems.

[0043] The power generation evaluation indicators of the power planning area are compared one by one with the estimated power generation corresponding to each power generation evaluation indicator interval stored in the power planning database to obtain the estimated power generation of the power planning area. At the same time, the historical data of the power generation of the new energy stations in the power planning area are obtained, and the time series function of the power generation of the new energy stations in the power planning area is obtained through curve fitting.

[0044] It should be understood that the estimated power generation in this embodiment refers to the expected total power generation in the power planning area within a set time period in the future.

[0045] In a specific embodiment, the time series function of the power generation of the new energy station can be fitted with a polynomial to obtain the power generation autoregressive model, and the mathematical expression can be written as , where represents the power generation in the power planning area at time t, yes The mathematical model, t represents the time variable, the value range of t is [t1, t2], t1 represents the starting time point of the historical data, Indicates the end time point of historical data. express The parameter vector is used to describe all the preset parameters in the power generation autoregressive model.

[0046] In a specific embodiment, by analyzing the historical data of the power generation of new energy stations, the operating performance of the new energy stations can be evaluated and the operation and maintenance strategy can be optimized. At the same time, the power generation of the new energy stations can be estimated, which helps to optimize the scheduling plan of conventional regulating power sources and ensure the adequacy of power supply in the power system.

[0047] Specifically, the demand load is predicted based on the historical load data of the power planning area. The specific process is: based on the historical load data of the power planning area, the historical load time series function of the power planning area is obtained by curve fitting.

[0048] In a specific embodiment, the historical load time series function can be fitted with a polynomial to obtain a historical load autoregressive model, and the mathematical expression can be written as , where represents the historical load of the power planning area at time t, yes The mathematical model of express The parameter vector is used to describe all the preset parameters in the historical load autoregressive model.

[0049] Deploy several historical monitoring time points, obtain the historical load at each historical monitoring time point, and obtain the demand load in the power planning area after processing.

[0050] In a specific embodiment, the load forecast influence weight factors corresponding to the set historical load minimum value, historical load maximum value, and historical load average value are obtained from the power planning database, and the demand load of the power planning area is obtained through comprehensive analysis. The specific numerical expression is:

[0051] ;

[0052] Where, Indicates the demand load of the power planning area, i represents the number of each historical monitoring time point, i=1,2,3,...,n, n represents the total number of historical monitoring time points, represents the historical load at the i-th historical monitoring time point, Indicates the load forecast impact weight factor corresponding to the set historical load minimum value, Indicates the load forecast impact weight factor corresponding to the set historical load maximum value, Indicates the load forecast impact weight factor corresponding to the set historical load average value, Indicates the minimum historical load value at the historical monitoring time point. Indicates the maximum historical load value at the historical monitoring time point. is the symbol for obtaining the minimum value, is the symbol for obtaining the maximum value.

[0053] It should be understood that the demand load in this embodiment refers to the estimated total demand load in the power planning area within a set time period in the future.

[0054] In this embodiment, the load forecast impact weight factors corresponding to the historical load minimum value, historical load maximum value, and historical load average value range from 0 to 1. A mapping set can be established based on historical load data to determine the impact of the historical load minimum value, historical load maximum value, and historical load average value on the demand load forecast.

[0055] In one specific embodiment, by analyzing historical load data, the stability of the power system over different time periods can be assessed, helping to identify potential system bottlenecks and failure points, and providing a basis for power system optimization and transformation. By predicting demand load, the power system can better allocate power load and schedule the operation of related equipment, avoiding potential safety hazards such as power shortages or surpluses and power failures, thereby improving the safety and reliability of the power system.

[0056] Specifically, a comprehensive analysis is conducted to obtain the demand construction scale data of the energy storage system in the power planning area. The specific analysis process is as follows: the time series function of the power generation of the new energy stations in the power planning area is compared with the time series function of the historical load, the difference between the historical monitored power supply and demand is obtained, and the maximum value of the historical monitored power supply and demand difference is extracted.

[0057] It should be understood that in this embodiment, the absolute value of the difference between power generation and load is marked as the power supply and demand difference. The historical monitored power supply and demand difference refers to the absolute value of the difference between historical power generation and historical load. The specific mathematical expression is: , where represents the historical monitored power supply and demand difference in the power planning area at time t, represents the power generation in the power planning area at time t, Represents the historical load of the power planning area at time t.

[0058] The power supply and demand difference threshold is extracted from the power planning database. If the power supply and demand difference in a certain time period is greater than or equal to the power supply and demand difference threshold, the time period is marked as the demand power scheduling time period. The historical demand power scheduling time periods are counted, and the summed result is marked as the historical scheduling duration of the energy storage system.

[0059] Comprehensive analysis yields an energy storage system dispatch demand assessment index for the power planning area, and matching this with the energy storage system demand construction scale data for the power planning area.

[0060] In a specific embodiment, the energy storage system scheduling demand assessment factor corresponding to the set historical power supply and demand difference, the historical scheduling duration of the energy storage system, and the expected power supply and demand difference is obtained from the power planning database. The critical power supply and demand difference and the critical historical scheduling duration of the energy storage system are extracted from the power planning database. A comprehensive analysis is performed to obtain the energy storage system scheduling demand assessment index for the power planning area. The specific numerical expression is:

[0061] ;

[0062] Where, Represents the energy storage system dispatch demand evaluation index in the power planning area, Indicates the maximum value of the historical monitored power supply and demand difference, Indicates the historical scheduling duration of the energy storage system, Indicates the estimated power generation in the power planning area, represents the demand load in the power planning area, represents the critical power supply and demand difference, represents the historical scheduling duration of the critical energy storage system, Indicates the impact factor of the energy storage system dispatch demand assessment corresponding to the set historical power supply and demand difference, Indicates the impact factor of the energy storage system scheduling demand assessment corresponding to the set historical scheduling duration of the energy storage system, Indicates the impact factor of the energy storage system scheduling demand assessment corresponding to the set expected power supply and demand difference.

[0063] like Figure 2 As shown, when When , the functional relationship between the maximum value of the historical monitoring power supply and demand difference and the energy storage system dispatch demand evaluation index is shown in curve a; when When , the functional relationship between the maximum value of the historical monitoring power supply and demand difference and the energy storage system dispatch demand evaluation index is shown in curve b; when The functional relationship between the maximum value of the historically monitored power supply and demand difference and the energy storage system dispatch demand assessment index is shown in curve c. The energy storage system dispatch demand assessment index is determined by the historical power supply and demand difference, the historical energy storage system dispatch duration, and the expected power supply and demand difference. The larger the historical power supply and demand difference, the historical energy storage system dispatch duration, and the expected power supply and demand difference, the larger the corresponding energy storage system dispatch demand assessment index, indicating a larger scale of energy storage system construction.

[0064] In this embodiment, the expected power supply and demand difference refers to the absolute value of the difference between the demand load and the estimated power generation in the power planning area.

[0065] In this embodiment, the energy storage system dispatch demand assessment index is used to quantitatively assess the energy storage system's need for power dispatch, making the assessment more quantitative and intuitive, and facilitating targeted planning and adjustments based on the assessment results. The formula comprehensively considers the historical power supply and demand differential, the energy storage system's historical dispatch duration, and the expected power supply and demand differential, enabling a more comprehensive and accurate assessment of the energy storage system's dispatch demand within the power planning area. Flexible adjustments to the influencing factors in the formula based on actual needs can reflect the varying weights and importance of different factors in the assessment. Furthermore, the use of a logarithmic function for calculations ensures the continuity and smoothness of the calculation results.

[0066] It should be understood that in this embodiment, the energy storage system scheduling demand degree assessment impact factors corresponding to the historical power supply and demand difference, the historical scheduling duration of the energy storage system, and the expected power supply and demand difference range from 0 to 1. A mapping table can be established based on historical data on the energy storage system scale to determine the impact of the historical power supply and demand difference, the historical scheduling duration of the energy storage system, and the expected power supply and demand difference on the energy storage system scale.

[0067] In one specific embodiment, by analyzing the power supply-demand gap, the imbalance between power supply and demand can be accurately determined, enabling the development of targeted adjustment strategies, more accurately forecasting future power demand, optimizing power resource allocation, and improving power utilization efficiency. Furthermore, analyzing the power supply-demand gap helps promptly identify potential problems in the power system, such as equipment failures and uneven loads, enabling measures to be taken to address them and improve power system stability.

[0068] In this embodiment, by analyzing historical demand-based power dispatch times, patterns in power demand can be identified, providing a more scientific basis for power production, transmission, and distribution. This analysis of historical demand-based power dispatch times can be used to assess the power system's ability to respond in different seasons and time periods, providing strong support for power system planning, construction, and operation, and helping to predict future supply and demand trends and avoid power shortages or surpluses.

[0069] Obtain new energy vehicle usage data in the power planning area, and conduct comprehensive analysis to obtain virtual energy storage compensation parameters in the power planning area.

[0070] Specifically, the virtual energy storage compensation parameters of the power planning area are obtained through comprehensive analysis. The specific analysis process is as follows: the new energy vehicle usage data of the power planning area, including the number of operating new energy vehicles in the power planning area and user vehicle usage habit data.

[0071] In this embodiment, an operating new energy vehicle refers to a new energy vehicle that is in service and has complete driving capabilities and functionality.

[0072] Based on the user's car usage habit data, the virtual energy storage regulation capacity evaluation index of the power planning area is obtained after processing, and the virtual energy storage compensation parameters of the power planning area are obtained through comprehensive analysis.

[0073] In a specific embodiment, the user's vehicle usage habit data includes the battery capacity and charging rate of each operating new energy vehicle in the power planning area. The virtual energy storage regulation capability influencing factor corresponding to the set battery capacity and charging rate is obtained from the power planning database. The critical battery capacity and critical charging rate are also obtained from the power planning database. The virtual energy storage regulation capability evaluation index of the power planning area is analyzed and obtained. The specific numerical expression is:

[0074] ;

[0075] Where, represents the evaluation index of the virtual energy storage regulation capacity of the power planning area, r represents the number of each operating new energy vehicle, r=1,2,3,...,h, h represents the total number of operating new energy vehicles, represents the battery capacity of the rth new energy vehicle in operation, represents the battery capacity of the rth new energy vehicle in operation, represents the critical battery capacity, represents the critical charging rate, Indicates the virtual energy storage regulation capability impact factor corresponding to the set battery capacity, Indicates the impact factor of the virtual energy storage regulation capability corresponding to the set charging rate.

[0076] It should be understood that the value range of the virtual energy storage regulation capability influencing factor corresponding to the battery capacity and charging rate is between 0 and 1. A mapping set can be established based on the virtual energy storage regulation historical data to determine the impact of the battery capacity and charging rate on the virtual energy storage regulation capability.

[0077] The virtual energy storage regulation capability evaluation index is used to quantitatively evaluate the power regulation capability of new energy vehicles as virtual energy storage systems within the power planning area. The virtual energy storage regulation capability evaluation index is jointly determined by the battery capacity and charging rate. The larger the battery capacity and charging rate, the larger the corresponding virtual energy storage regulation capability evaluation index, indicating that the new energy vehicle has a stronger power regulation capability as a virtual energy storage system.

[0078] It should be understood that this embodiment analyzes battery capacity and charging rate. The larger the battery capacity, the more power it can store and discharge, and the greater its contribution to grid regulation. The charging and discharging speed of a tram's battery determines how quickly it can respond to grid demand. Trams with fast charging and discharging capabilities can participate in grid regulation more quickly.

[0079] In a specific embodiment, the virtual energy storage compensation impact factor corresponding to the set number of new energy vehicle users and the virtual energy storage regulation capability evaluation index is obtained from the power planning database, and the critical number of new energy vehicle users is obtained from the power planning database. A comprehensive analysis is performed to obtain the virtual energy storage compensation parameter of the power planning area. The specific numerical expression is:

[0080] ;

[0081] Where, represents the virtual energy storage compensation parameter of the power planning area, Indicates the number of new energy vehicles in operation in the power planning area, represents the critical number of new energy vehicle users, It represents the evaluation index of virtual energy storage regulation capability in the power planning area. Indicates the virtual energy storage compensation impact factor corresponding to the set number of new energy vehicle users, Indicates the virtual energy storage compensation impact factor corresponding to the set virtual energy storage regulation capability evaluation index.

[0082] It should be understood that in this embodiment, the value range of the virtual energy storage compensation impact factor corresponding to the number of new energy vehicle users and the virtual energy storage regulation capability evaluation index is between 0 and 1. A mapping set can be established based on historical vehicle-grid interaction data to determine the impact of the number of new energy vehicle users and the virtual energy storage regulation capability evaluation index on virtual energy storage compensation.

[0083] In this embodiment, the virtual energy storage compensation parameter is used to quantitatively assess the degree to which the scale of new energy vehicles in the power planning area optimizes the energy storage system. The virtual energy storage compensation parameter is determined by the number of new energy vehicle users and the virtual energy storage regulation capacity assessment index. A larger number of new energy vehicle users and the virtual energy storage regulation capacity assessment index correspond to a larger virtual energy storage compensation parameter, indicating a higher degree of optimization of the energy storage system construction by new energy vehicles acting as virtual energy storage.

[0084] Specifically, the energy storage system demand construction scale data of the power planning area is matched. The specific process is: the energy storage system scheduling demand degree assessment index of the power planning area is compared one by one with the energy storage system demand construction scale data corresponding to each energy storage system scheduling demand degree assessment index interval stored in the power planning database, so as to obtain the energy storage system demand construction scale data of the power planning area, wherein the energy storage system demand construction scale data includes the energy storage capacity and energy storage power of the energy storage system.

[0085] The energy storage system demand construction scale data in the power planning area is optimized according to the virtual energy storage compensation parameters in the power planning area.

[0086] Specifically, the energy storage system demand construction scale data of the power planning area is optimized according to the virtual energy storage compensation parameters of the power planning area. The specific process is: the virtual energy storage compensation parameters of the power planning area are compared one by one with the optimizable energy storage capacity and optimizable energy storage power corresponding to each virtual energy storage compensation parameter interval stored in the power planning database to obtain the optimizable energy storage capacity and optimizable energy storage power of the power planning area, and the energy storage system demand construction scale data of the power planning area is optimized according to the optimizable energy storage capacity and optimizable energy storage power of the power planning area.

[0087] It should be understood that the optimizable energy storage capacity and optimizable energy storage power in this embodiment refer to the scale of the energy storage system that can be replaced when the new energy vehicle acts as virtual energy storage in the vehicle-grid interaction. The corresponding energy storage system investment cost is reduced according to the scale of the energy storage system that can be replaced, thereby achieving grid investment optimization.

[0088] In a specific embodiment, the present invention provides a grid investment optimization method based on big data analysis, which comprehensively considers factors such as the charging needs and discharge capacity of electric vehicles and the power balance of the power grid to determine the optimal construction scale of the energy storage system. This can more accurately predict future power demand and supply conditions, providing a more scientific basis for grid investment optimization.

[0089] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A power grid investment optimization method based on big data analysis, characterized in that: include: Meteorological data in the planned power area is monitored and processed to obtain a time series function of the power generation capacity of renewable energy stations in the planned power area. Demand load is then predicted based on historical load data in the planned power area. Comprehensive analysis is then performed to obtain the required construction scale data for the energy storage system in the planned power area. Obtain new energy vehicle usage data in the power planning area and conduct comprehensive analysis to obtain virtual energy storage compensation parameters in the power planning area; Optimize the energy storage system construction scale data required in the power planning area based on the virtual energy storage compensation parameters in the power planning area; The comprehensive analysis yields data on the required construction scale of energy storage systems in the power planning area. The specific analysis process is as follows: Compare and analyze the time series function of the power generation of new energy stations in the power planning area with the time series function of the historical load, obtain the historical monitored power supply and demand difference, and extract the maximum value of the historical monitored power supply and demand difference; Extracting a power supply and demand difference threshold from the power planning database. If the power supply and demand difference in a certain time period is greater than or equal to the power supply and demand difference threshold, the time period is marked as the demand power dispatch time period. Historical demand power dispatch time periods are counted, and the summed result is marked as the historical dispatch duration of the energy storage system. Comprehensive analysis yields an energy storage system dispatch demand assessment index for the power planning area, which is then matched with the energy storage system construction scale data for the power planning area. The comprehensive analysis obtains the virtual energy storage compensation parameters of the power planning area. The specific analysis process is as follows: New energy vehicle usage data in the power planning area, including the number of new energy vehicles in operation in the power planning area and user vehicle usage habits data; Based on the user's car usage habit data, the virtual energy storage regulation capacity evaluation index of the power planning area is obtained after processing, and the virtual energy storage compensation parameters of the power planning area are obtained through comprehensive analysis.

2. The method for optimizing power grid investment based on big data analysis according to claim 1, characterized in that: The above processing obtains the time series function of the power generation of the new energy stations in the power planning area. The specific process is as follows: Deploy several environmental monitoring points to collect solar radiation and wind speed data at each monitoring point in the power planning area. Obtain the power generation impact weight factors corresponding to the set solar radiation and wind speed data from the power planning database, and conduct a comprehensive analysis to obtain the power generation evaluation index for the power planning area. The power generation evaluation indicators of the power planning area are compared one by one with the estimated power generation corresponding to each power generation evaluation indicator interval stored in the power planning database to obtain the estimated power generation of the power planning area. At the same time, the historical data of the power generation of the new energy stations in the power planning area are obtained, and the time series function of the power generation of the new energy stations in the power planning area is obtained through curve fitting.

3. The method for optimizing power grid investment based on big data analysis according to claim 1, characterized in that: The specific process of predicting the demand load based on the historical load data of the power planning area is as follows: According to the historical load data of the power planning area, the historical load time series function of the power planning area is obtained by curve fitting; Deploy several historical monitoring time points, obtain the historical load at each historical monitoring time point, and obtain the demand load in the power planning area after processing.

4. The method for optimizing power grid investment based on big data analysis according to claim 3, characterized in that: The matching process to obtain the energy storage system construction scale data required in the power planning area is as follows: The energy storage system dispatch demand assessment index of the power planning area is compared one by one with the energy storage system demand construction scale data corresponding to each energy storage system dispatch demand assessment index interval stored in the power planning database to obtain the energy storage system demand construction scale data of the power planning area, where the energy storage system demand construction scale data includes the energy storage capacity and energy storage power of the energy storage system.

5. The method for optimizing power grid investment based on big data analysis according to claim 4, characterized in that: The specific process of optimizing the energy storage system construction scale data required in the power planning area according to the virtual energy storage compensation parameters in the power planning area is as follows: The virtual energy storage compensation parameters of the power planning area are compared one by one with the optimizable energy storage capacity and optimizable energy storage power corresponding to each virtual energy storage compensation parameter interval stored in the power planning database to obtain the optimizable energy storage capacity and optimizable energy storage power of the power planning area. Based on the optimizable energy storage capacity and optimizable energy storage power of the power planning area, the energy storage system demand construction scale data of the power planning area is optimized.

6. The method for optimizing power grid investment based on big data analysis according to claim 1, characterized in that: The processing obtains the virtual energy storage regulation capability evaluation index of the power planning area, and the specific process is as follows: The user vehicle usage habit data, including the battery capacity and charging rate of each operating new energy vehicle in the power planning area, is comprehensively analyzed to obtain a virtual energy storage regulation capacity evaluation index for the power planning area.

7. The method for optimizing power grid investment based on big data analysis according to claim 1, characterized in that: The comprehensive analysis to obtain the energy storage system dispatch demand assessment index for the power planning area also includes: The energy storage system dispatch demand assessment factor corresponding to the set historical power supply and demand difference, the historical dispatch duration of the energy storage system, and the expected power supply and demand difference is obtained from the power planning database. The critical power supply and demand difference and the critical historical dispatch duration of the energy storage system are extracted from the power planning database. A comprehensive analysis is performed to obtain the energy storage system dispatch demand assessment index for the power planning area. The specific numerical expression is: ； Where, Represents the energy storage system dispatch demand evaluation index in the power planning area, Indicates the maximum value of the historical monitored power supply and demand difference, Indicates the historical scheduling duration of the energy storage system, Indicates the estimated power generation in the power planning area, represents the demand load in the power planning area, represents the critical power supply and demand difference, represents the historical scheduling duration of the critical energy storage system, Indicates the impact factor of the energy storage system dispatch demand assessment corresponding to the set historical power supply and demand difference, Indicates the impact factor of the energy storage system scheduling demand assessment corresponding to the set historical scheduling duration of the energy storage system, Indicates the impact factor of the energy storage system scheduling demand assessment corresponding to the set expected power supply and demand difference.

8. The method for optimizing power grid investment based on big data analysis according to claim 1, characterized in that: The comprehensive analysis to obtain virtual energy storage compensation parameters for the power planning area also includes: The virtual energy storage compensation influencing factors corresponding to the set number of new energy vehicle users and the virtual energy storage regulation capability evaluation index are obtained from the power planning database. The critical number of new energy vehicle users is also obtained from the power planning database. A comprehensive analysis is performed to obtain the virtual energy storage compensation parameters for the power planning area. The specific numerical expression is: ； Where, represents the virtual energy storage compensation parameter of the power planning area, Indicates the number of new energy vehicles in operation in the power planning area, represents the critical number of new energy vehicle users, It represents the evaluation index of virtual energy storage regulation capability in the power planning area. Indicates the virtual energy storage compensation impact factor corresponding to the set number of new energy vehicle users, Indicates the virtual energy storage compensation impact factor corresponding to the set virtual energy storage regulation capability evaluation index.

Images