CN113705874A - New energy power grid evolution prediction method and device, computer equipment and storage medium - Google Patents

Abstract

The present application relates to a new energy grid evolution prediction method, device, computer equipment and storage medium. The method includes: determining a set of key indicators corresponding to the target area; the set of key indicators includes power generation resource indicators, energy storage indicators, power demand side indicators, flexible resource indicators, and fuel price indicators that affect the development of power grids in the target area; Perform numerical prediction processing on each indicator in the indicator set to obtain a sample set of key indicators; use the power grid evolution prediction algorithm to process the sample set of key indicators to obtain multiple sets of evolution data corresponding to the target area; the evolution data includes the power generation resource structure corresponding to the target area. Evolution data and evolution data of the flexible resource structure corresponding to the target area. The method can realize automatic and intelligent prediction of the evolution path of the power grid, exclude the influence of human factors, ensure the accuracy of the generated evolution path, and make the predicted evolution path of the power grid have a certain global coverage.

Description

New energy grid evolution prediction method, device, computer equipment and storage medium

technical field

The present application relates to the field of electric power technology, and in particular to a new energy grid evolution prediction method, device, computer equipment and storage medium.

Background technique

As flexibility resources (eg, thermal power plant flexibility retrofit, pumped hydro, battery storage, compressed air storage, load-shifting demand-side response, load-shedding demand-side response) continue to participate in the evolution of the grid, The evolution of the power grid will face many uncertain factors, so that the evolution of the power grid has deep uncertainty. It poses a great challenge to identify the key driving factors of power grid evolution and the path of power grid evolution.

In traditional technologies, human experience is mainly used to predict the possible evolution path of the power grid. It is mainly to predict a variety of possible evolution paths in advance based on prior experience, and regard these possible evolution paths as the approximate evolution and development paths of the future system.

However, the traditional power grid evolution path prediction method is greatly affected by human factors, and only a few possible evolution paths of the power grid are predicted, and these paths are regarded as the approximate evolution and development paths of the future system, which makes the prediction results lack universality. It is difficult to guarantee the accuracy of the evolution path with existing technologies.

SUMMARY OF THE INVENTION

The present application provides a new energy power grid evolution prediction method, device, computer equipment and storage medium, which can improve the global coverage of the predicted power grid evolution path and ensure the accuracy of the predicted evolution path to a certain extent.

In a first aspect, a power grid evolution prediction method is provided, the method includes: determining a key index set corresponding to a target area; the key index set includes a power generation resource index affecting the development of the target area power grid, an energy storage index affecting the target area power grid development, Demand side indicators, flexible resource indicators that affect the development of the target regional power grid, and fuel price indicators that affect the development of the target regional power grid; perform numerical prediction processing on each indicator in the key indicator set to obtain a key indicator sample set; use the power grid The evolution prediction algorithm processes the key index sample set to obtain multiple sets of evolution data corresponding to the target area; the evolution data includes the evolution data of the power generation resource structure corresponding to the target area and the evolution data of the flexible resource structure corresponding to the target area.

With reference to the first aspect, in a possible implementation manner of the first aspect, performing numerical prediction processing on each indicator in the key indicator set to obtain a key indicator sample set, including: for each indicator in the key indicator set , determine the upper and lower limit values of each indicator in the forecast period, and assign values to each indicator in the key indicator set according to the upper and lower values of each indicator; use Monte Carlo method to assign values Random sampling is performed on the subsequent set of key indicators to obtain the value of each indicator in each forecast period, and a sample set of key indicators is determined according to the value of each indicator in each forecast period.

In combination with the first aspect, in a possible implementation manner of the first aspect, a power grid evolution prediction algorithm is used to process the key indicator sample set to obtain multiple sets of evolution data corresponding to the target area, including: inputting the key indicator sample set into the power grid evolution prediction The objective function in the algorithm uses the constraints in the power grid evolution prediction algorithm to constrain the key indicator sample set; according to the output of the objective function and the result of the constraint processing, multiple sets of evolution data corresponding to the target area are determined; among them, the objective function is: The sum of the investment cost, the fixed operation and maintenance cost of the power grid, and the variable operation cost of the power grid in each forecast period of the power grid evolution is optimal; the constraints include: the construction constraints of the power grid and the operating cost constraints of the power grid.

In combination with the first aspect, in a possible implementation manner of the first aspect, the investment cost is the capital cost invested in the construction of power generation resources and flexible resources in the power system; the fixed operation and maintenance cost of the power grid is the cost of equipment constructed in the power system. The cost of capital invested in routine maintenance; the variable operating cost of the grid is the cost of the fuel consumed by the power generation resources in the power system.

With reference to the third aspect, in a possible implementation manner of the third aspect, the construction constraints of the power grid include at least one of the following: investment capacity constraints of various resources on each power grid node in each prediction period, total investment capacity constraints, Renewable energy permeability constraints in the final stage of grid evolution and carbon emissions constraints in the final stage of grid evolution; the operating cost constraints of the grid are the capital costs required to maintain the normal operation of various power generation resources in the power system.

In combination with the first aspect, in a possible implementation manner of the first aspect, for any key indicator in the key indicator set, the degree of difference of the key indicator in different evolution data is calculated, and the largest degree of difference is used as the key The impact factor of the indicator; one or more key indicators whose impact factor is greater than the preset threshold in the key indicator set is determined as the key driving factor of the grid evolution in the target area; the key driving factor is used to predict the evolution data.

In combination with the first aspect, in a possible implementation manner of the first aspect, the flexible resource development index of the target area is calculated, and the flexible resource development index includes flexible resource capacity demand, flexible resource marginal capacity demand, battery energy storage Emergence point and dominant point of battery energy storage; among them, the flexible resource capacity demand is the flexible resource capacity of the system under different renewable energy power penetration rates, and the flexible resource marginal capacity demand is under different renewable energy power penetration rates. , the flexible resource capacity increment corresponding to the preset value of the penetration rate increase, the battery energy storage occurrence point is the corresponding renewable energy power penetration rate when the battery energy storage appears in the power system, and the battery energy storage dominant point is the battery energy storage capacity Renewable energy electricity penetration rate corresponding to the preset proportion of flexible resource capacity.

In a second aspect, a power grid evolution prediction device is provided, the device includes: a determination module for determining a key index set corresponding to a target area; the key index set includes a power generation resource index affecting the development of the target area power grid, a power generation resource index affecting the target area power grid The developed energy storage index, the electricity demand side index that affects the development of the target regional power grid, the flexible resource index, and the fuel price index that affects the development of the target regional power grid;

The numerical processing module is used to perform numerical prediction processing on each index in the key index set, and obtain the key index sample set;

The evolution data generation module is used to process the key index sample set by using the power grid evolution prediction algorithm to obtain multiple sets of evolution data corresponding to the target area; the evolution data includes the evolution data of the power generation resource structure corresponding to the target area and the flexibility resources corresponding to the target area. Structural evolution data.

In a third aspect, there is provided a computer apparatus including a memory and a processor, the memory having a computer program stored thereon. When the processor executes the computer program, the steps of the method described in the first aspect or any one possible implementation manner of the first aspect are implemented.

In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method described in the first aspect or any possible implementation manner of the first aspect is implemented. step.

The present application provides a new energy power grid evolution prediction method, device, computer equipment and storage medium, which can determine the key index set corresponding to the target area, and perform numerical prediction processing on each index in the key index set to obtain key index samples Finally, the power grid evolution prediction algorithm can also be used to process the key index sample set to obtain multiple sets of evolution data corresponding to the target area; the evolution data is used to characterize the evolution trend and evolution path of the power grid. The set of key indicators includes power generation resource indicators that affect the development of the target regional power grid, energy storage indicators that affect the development of the target regional power grid, demand side indicators that affect the development of the target regional power grid, flexible resource indicators, and indicators that affect the development of the target regional power grid. Fuel price indicator. It can be seen that the computer in the present application can realize the automatic intelligent prediction of the power grid evolution path based on the power grid evolution prediction algorithm, which solves the problem that the prior art relies on manual power grid evolution path prediction, resulting in the difficulty of guaranteeing the accuracy of the evolution path. Based on the power grid evolution prediction algorithm, the influence of human factors on the power grid evolution prediction can be excluded. In addition, the set of key indicators in this application basically covers various indicators that affect the development of the power grid, specifically including some indicators related to flexible resource allocation. When predicting the power grid path, uncertain factors such as flexible resource allocation are fully considered. Therefore, based on The set of key indicators and the power grid evolution prediction algorithm can obtain a more comprehensive evolution path, and the predicted power grid evolution path has a certain global coverage.

Description of drawings

1 is a schematic flowchart of a method for predicting the evolution of a power grid in one embodiment;

2 is a schematic flowchart of a numerical prediction processing method in one embodiment;

3 is a schematic flowchart of an evolutionary data analysis method in one embodiment;

Fig. 4 is the setting diagram of the flexibility transformation path of thermal power unit in one embodiment;

5 is a schematic diagram of key driving factor identification based on a time-varying pattern in one embodiment;

6 is a schematic diagram of the current installed capacity and load conditions in the northwest region in one embodiment;

7 is a schematic diagram of a system evolution path and its distribution in one embodiment;

FIG. 8 is a schematic diagram of the demand for flexibility resources under different renewable energy power penetration rates in one embodiment;

9 is a schematic diagram of the statistics of battery energy storage in a large number of evolution paths in one embodiment;

10 is a schematic diagram of a clustering result of renewable energy permeability evolution data in one embodiment;

11 is a graph of mean values of key indicators corresponding to different category paths in one embodiment;

12 is a graph of the average distance between classes of each key indicator in one embodiment;

13 is a frame diagram of the generation and analysis of massive evolution paths in one embodiment;

14 is a schematic structural diagram of a power grid evolution prediction device in one embodiment;

FIG. 15 is a schematic diagram of a power grid evolution data analysis structure in one embodiment;

FIG. 16 is a schematic diagram of a grid evolution data adjustment structure in one embodiment;

Figure 17 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

An embodiment of the present application provides a method for predicting the evolution of a power grid, which is applied to computer equipment, and as shown in Figure 1, the method includes the following steps:

Step 101: Determine a set of key indicators corresponding to the target area; the set of key indicators includes a power generation resource index that affects the development of the power grid in the target area, an energy storage index that affects the development of the power grid in the target area, and an electricity demand side index that affects the development of the power grid in the target area, and flexibility Resource indicators, and fuel price indicators that affect the development of power grids in the target area;

In order to realize the automatic prediction of the evolution path of the power grid in the embodiment of the present application, it is necessary to determine multiple uncertain factors that affect the development of the power grid, so as to predict the evolution path of the power grid based on these uncertain factors, so that the predicted evolution path can take into account the uncertainty. influence of factors. In the specific implementation, when predicting the evolution of the power grid in a certain region, some key indicators that affect the evolution of the power grid in that region can be determined. For example, when predicting the evolution of the power grid in the target area, first determine the set of key indicators of the target area, and the set of key indicators includes some key indicators that affect the evolution direction of the power grid in the target area.

In a possible implementation manner, the set of key indicators includes power generation resource indicators, energy storage indicators, electricity demand side indicators, flexible resource indicators, and fuel price indicators that affect the development of the target regional power grid.

Wherein, the power generation resource index can be the investment parameters of various power generation resources in the target area, and the investment parameters can represent the investment details of the corresponding power generation resources, for example, can be the investment prices of various power generation resources. Exemplarily, the power generation resources may be coal power, gas power, hydropower, wind power, photovoltaic, solar thermal.

The energy storage index can be the energy storage efficiency of flexible resources in the target area, and the energy storage efficiency can represent the emergency capability of the power system, such as lithium battery energy storage efficiency and compressed air energy storage efficiency. Among them, lithium battery energy storage mainly uses the chemical reaction of chemical substances in lithium ion batteries to store or release electricity, and compressed air energy storage mainly uses the surplus electricity when the grid load is low to compress air and store it in high-voltage sealed facilities. The peak of electricity consumption is released to drive the gas turbine to generate electricity.

The power demand side index can be the power demand response of the power system in the target area, and the power demand response can represent the reliability of the power system operation. For example, it can be the investment price of the power demand side response, the compensation price of the power demand side response, The capacity potential of demand-side response for electricity use. Wherein, the investment price of the electricity demand side response is the capital invested by the power system to ensure the balance of supply and demand and the reliability of the system operation when the user needs it or the power is in short supply. Exemplarily, the investment price of the electricity demand side response can be It is the unit investment price of transfer demand-side response and the unit investment price of reduction demand-side response; the compensation price of electricity demand-side response is that the user reduces the electricity demand when the system needs or power is in short supply, so as to obtain direct compensation or other discounts Electricity price, exemplarily, the compensation price of the electricity demand side response can be the unit compensation price of the transfer demand side response, the unit compensation price of the reduction demand side response; In times of stress, the maximum electric power that can be provided to users or power equipment. Exemplarily, the capacity potential of electricity demand side response can be a transfer demand side response capacity potential, a reduction type demand side response capacity potential.

The flexible resource index can be the investment parameters of various flexible resources in the target area, and the investment parameters can represent the investment details of the corresponding flexible resources. Investment capacity (the maximum amount the power system can invest in flexible resources during each forecast period). Exemplarily, the investment price of the flexible resource may be the investment price of a pumped hydro energy storage unit, the investment price of a lithium battery energy storage unit, and the investment price of a compressed air energy storage unit; wherein, the pumped storage energy is the electric energy used by the power system when the power load is at a low valley. A hydropower station that pumps water to the upper reservoir and releases it to the lower reservoir to generate electricity during peak power load periods. That is, when the electrical power consumed by the electrical equipment in the power system is small, the remaining electrical power is used to pump water to the upper reservoir, and the electrical energy is converted into the potential energy of water; when the electrical power consumed by the electrical equipment in the power system is large, the water is discharged. To the lower reservoir, the potential energy of water is converted into electricity. The maximum investment capacity of flexible resources in each forecast period can be the maximum investment capacity of lithium battery energy storage in each stage, and the maximum investment capacity of compressed air energy storage in each stage. Among them, the maximum investment capacity of lithium battery energy storage in each stage is the maximum capital that the power system can invest in lithium battery energy storage in each forecast period; the maximum investment capacity of compressed air energy storage in each stage is each forecast period. The maximum capital that the power system can invest in compressed air energy storage equipment during a period of time.

The fuel price indicator may be the price of fuel consumed when various power generation resources in the target area are operating. Exemplarily, the fuel price may be the price of coal-electric fuel and the price of gas-electric fuel.

The following Table 1 provides a set of key indicators in this embodiment of the application, including 21 key indicators (uncertainty factors) that affect the development and evolution of the power grid.

In the specific implementation, the set of key indicators in the target area can be determined according to the actual development of the power grid in the target area. The computer device may receive the set of key indicators input by the user, or the set of key indicators may be pre-stored in the computer device.

Table 1

Step 102, performing numerical prediction processing on each key indicator in the key indicator set to obtain a key indicator sample set;

In the embodiment of the present application, in order to determine the evolution data corresponding to the target area based on the set of key indicators, it is necessary to perform assignment processing on each index in the set of key indicators. For example, numerical prediction processing can be performed on each key indicator in the key indicator set to obtain a key indicator sample set.

In the specific implementation, each key index in the key index set can be quantified, and the quantized result can be sampled by random sampling to obtain the key index sample set. Among them, quantification may be to determine the possible values of each indicator, and sampling may be to sample the possible values of each indicator. The data obtained by one sampling is a set of key indicator samples, and the data obtained by multiple sampling is the key indicator sample set.

In a possible implementation method, the uncertain factors that have been determined to affect the development of the power grid are quantified. The quantitative data can be obtained by analyzing and predicting historical data, or it can be determined according to other relevant documents; The uncertainty factors that affect the development of the power grid can be sampled, and the random sampling method can be used for sampling.

Step 103: Use the power grid evolution prediction algorithm to process the key index sample set to obtain multiple sets of evolution data corresponding to the target area; the evolution data includes the evolution data of the power generation resource structure corresponding to the target area and the evolution data of the flexible resource structure corresponding to the target area.

In the prior art, the evolution path of the power grid is manually predicted based on human experience. In the embodiment of the present application, the computer device can obtain the evolution path of the power grid through an automatic processing algorithm. For example, when the power grid evolution prediction is performed on the target area, the key index sample set corresponding to the area can be processed according to the power grid evolution prediction algorithm, and multiple sets of evolution data corresponding to the area can be obtained.

In the specific implementation, the key index sample set is input into the power grid evolution prediction algorithm, and the reasonable evolution of each index sample under certain constraints can be determined. Therefore, the power grid evolution data of the region can be constructed according to the evolved index samples.

In a possible implementation, the evolution data is used to represent the evolution trend of the power grid, or the evolution path of the power grid. Multiple sets of evolution data can determine multiple grid evolution paths in the target area. Exemplarily, the evolution data may include evolution data of the power generation resource structure corresponding to the target area and evolution data of the flexible resource structure corresponding to the target area.

Among them, the evolution data is used to represent the evolution trend, which can be the change trend of the power generation resource structure and flexible resource structure corresponding to the target area in the next few years. The structure of power generation resources refers to the allocation of various power generation resources deployed in the target area, which can specifically be the percentage of the construction quantity of various power generation resources in the target area to the total construction quantity. The flexible resource structure refers to the configuration of various flexible resources deployed in the target area, which can be the percentage of the construction quantity of various flexible resources in the target area to the total construction quantity.

In the power grid evolution prediction method provided by the embodiment of the present application, the computer can realize the automatic intelligent prediction of the power grid evolution path based on the power grid evolution prediction algorithm, which solves the problem that the prior art relies on manual power grid evolution path prediction, which leads to the accuracy of the evolution path. difficult to guarantee issues. The power grid evolution prediction algorithm can exclude the influence of human factors on the power grid evolution prediction. In addition, the set of key indicators in this application basically covers various indicators that affect the development of the power grid, specifically including some indicators related to flexible resource allocation. When predicting the power grid path, uncertain factors such as flexible resource allocation are fully considered. Therefore, based on The set of key indicators and the power grid evolution prediction algorithm can obtain a more comprehensive evolution path, and the predicted power grid evolution path has a certain global coverage.

In the aforementioned step 102, the computer device may obtain the key indicator sample set by quantifying and sampling the key indicator set. For example, the specific implementation of "performing numerical prediction processing on each indicator in the set of key indicators to obtain a sample set of key indicators" mentioned above includes the steps shown in Figure 2:

Step 201: For each indicator in the key indicator set, determine the upper limit value and lower limit value of each indicator in the forecast period, and determine the upper limit value and lower limit value of each indicator for each indicator in the key indicator set according to the upper limit value and lower limit value of each indicator. Perform assignment processing.

In order to generate specific power grid evolution data in the embodiment of the present application, it is necessary to perform quantitative processing on the set of key indicators, and to represent the set of key indicators with specific data. For example, each indicator in the set of key indicators can be assigned a value to obtain the set of key indicators after the assignment.

In the specific implementation, each key indicator in the key indicator set is divided into multiple prediction periods, and the upper and lower limit values (upper and lower bounds) of each key indicator in each prediction period are determined, with multiple The key indicator set is represented in the form of stages (multiple forecast periods) and interval (upper limit value and lower limit value interval), and the assignment of the key indicator set is completed;

In a possible implementation manner, each key indicator in the key indicator set is divided into multiple forecast periods. For example, referring to Table 2, it can be divided into 5 forecast periods from 2025 to 2050, and each forecast period is 5 years; During the period, the upper and lower values of each year can remain unchanged, and the upper and lower values of each key indicator in the forecast period can be obtained by analyzing and predicting historical data, or based on other Relevant literature identified.

Table 2

Step 202: Use the Monte Carlo method to randomly sample the set of key indicators after the assignment processing, obtain the value of each indicator in each forecast period, and determine the sample set of key indicators according to the value of each indicator in each forecast period .

In the embodiment of the present application, in order to perform algorithm-based processing on the set of key indicators, it is necessary to sample the set of key indicators that have been assigned values to obtain a sample set of key indicators.

In the specific implementation, for each forecast period of each key indicator, random sampling is performed within the interval between the upper limit value and the lower limit value of the forecast period, and a set of data obtained by random sampling is used as a set of key indicator samples. The data obtained by sampling is the key indicator sample set.

In a possible implementation, the set of key indicators after the assignment can be sampled, and the Monte Carlo method can be used for random sampling, and the result of sampling is the specific value of each key indicator within the upper and lower limit intervals of each forecast period, The specific value represents the data of the key indicator in the forecast period, the result of one sampling is a set of key indicator samples, and the set of key indicators after the assignment is randomly sampled multiple times to obtain the key indicator sample set.

As shown in Table 1 above, the 21 uncertain factors (set of key indicators) that affect the evolution and development of the power grid are determined for this application, and these 21 uncertain factors are divided into 5 forecast periods from 2025 to 2050. , each forecast period is 5 years, then determine the upper limit and lower limit of each uncertainty factor in each forecast period, and obtain the quantitative results of these 21 uncertainty factors; then for each uncertainty factor The factors are randomly sampled within the upper and lower limits of each forecast period, and the value obtained by sampling represents the data of the uncertainty factor in the forecast period. The result of one sampling is a set of key index samples. The collection is randomly sampled multiple times to obtain a sample set of key indicators.

Among them, the quantification results of the 21 uncertainty factors (set of key indicators) in Table 1 are shown in Table 2. Take the uncertainty factor of coal power unit investment price in Table 2 as an example: In the table, 2025 to 2030 is a forecast period, 2030 to 2035 is a forecast period, and there are 5 forecast periods from 2025 to 2050. ;559$/kW (1 US dollar per kilowatt) is the lowest unit investment price of coal power unit investment price between 2025 and 2030, which is the lower limit of the forecast period from 2025 to 2030, and 621$/kW is the coal power unit The highest unit investment price of the investment price between 2025 and 2030, which is the upper limit of the forecast period of 2025 to 2030. When sampling the investment price of coal power units in the forecast period from 2025 to 2030, a value between 559$/kW and 621$/kW is randomly selected as the investment price of coal power units in the forecast period from 2025 to 2030. 21 uncertainty factors are randomly sampled in each forecast period, and the sampling results obtained are a set of key indicator samples.

The embodiments of the present application provide a method for performing numerical prediction processing on each key indicator in the key indicator set to obtain a key indicator sample set. Specifically, for the set of key indicators that affect the evolution and development of the power grid in the target area, each key indicator in the set of key indicators is divided into multiple forecast periods, and the upper and lower limits (upper bounds) in each forecast period are determined. and lower bound) to complete the assignment of the set of key indicators; then, for each forecast period of each key indicator, random sampling is performed within the interval between the upper limit value and the lower limit value of the forecast period, and the random sampling is performed. A set of data is used as a set of key indicator samples, and the data obtained by multiple sampling is the key indicator sample set. It can be seen that the embodiment of the present application performs numerical prediction processing on the set of key indicators that affect the evolution and development of the power grid in the target area, quantifies and samples the set of key indicators, and obtains a sample set of key indicators, which represents the uncertainty affecting the evolution and development of the power grid in the form of specific numerical values. In order to facilitate the subsequent use in the power grid evolution prediction algorithm, a large number of power grid evolution paths can be generated. Compared with the prior art, which relies on human experience to predict the power grid evolution path, the embodiment of the present application relies on specific samples to predict the power grid evolution path, which reduces the influence of human factors and improves the accuracy of the power grid evolution path prediction.

In the aforementioned step 103, the computer equipment can use the power grid evolution prediction algorithm to process the key indicator sample set, and obtain multiple sets of evolution data corresponding to the target area.

The prior art mainly relies on human experience to predict the evolution path of the power grid, and the embodiment of the present application automatically generates the evolution path of the power grid through the power grid evolution prediction algorithm. For example, when predicting the power grid evolution in the target area, the key index sample set is input into the power grid evolution prediction algorithm to obtain multiple sets of evolution data corresponding to the area.

In the specific implementation, for each group of samples in the key indicator sample set, it is input into the objective function of the power grid evolution prediction algorithm, and then the output of the objective function is constrained by the constraint conditions, and the processed result is the corresponding Evolution data. That is, the output evolution data not only satisfy the objective function of the power grid evolution prediction algorithm, but also satisfy the constraints.

In a possible implementation, the power grid evolution prediction algorithm targets each group of samples in the key indicator sample set, and if the sample satisfies the objective function and constraint conditions, then outputs a set of evolution data according to the sample. Among them, the objective function is: the optimal sum of investment cost, fixed operation and maintenance cost of power grid, and variable operation cost of power grid in each stage of power grid evolution; constraints include: construction constraints of power grid evolution and power grid operating cost constraints.

The objective function mentioned above includes the investment cost of each stage of power grid evolution, the fixed power grid operation and maintenance cost, and the power grid variable operating cost. Among them, the investment cost of each stage of power grid evolution refers to: the capital cost used to build power generation resources and flexible resources in the power system during each forecast period; the fixed operation and maintenance cost of the power grid refers to: The capital cost invested in the routine maintenance of the equipment; the variable operation cost of the power grid refers to the cost of the fuel consumed by the power generation resources in the power system. In addition, the objective function should not only take into account the minimum sum of investment costs, fixed grid operation and maintenance costs, and grid variable operation costs at each stage of grid evolution, but also consider the time value of funds. When exploring the evolution path of the power grid in this application, the time interval delineated is from 2025 to 2050, and 5 years is used as a forecast period, and the time span is long, which makes the value of the same fund different in different forecast periods , i.e. 1 dollar in 2025 is not the same value as 1 dollar in 2050 (e.g. 1 dollar in 2025 can buy 2 dollars in 2050). Therefore, when the objective function considers the various capital costs invested in each stage of the power grid evolution, it is also necessary to unify the capital value of each forecast period into the same forecast period, that is, to consider the time value of funds.

The constraints mentioned above include the construction constraints of the grid evolution in the target area and the operating cost constraints of the grid evolution. Among them, the construction constraints of the power grid evolution refer to: in the power system, the constraints on the investment capacity of various units and the constraints on the evolution goals; it specifically includes the following four aspects: the constraints of various resources on each grid node in each prediction stage Investment capacity constraints, total investment capacity constraints, renewable energy penetration constraints in the final stage of grid evolution, and carbon emissions constraints in the final stage of grid evolution. Among them, the investment capacity constraint of each stage of power grid evolution refers to the capital cost invested in constructing various resources in the power system of each province during each forecast period; the total investment capacity constraint refers to: during the entire forecast period, the entire The capital cost of building various resources in the power system; the renewable energy penetration rate constraint refers to: the final stage of evolution (the forecast period from 2045 to 2050) needs to reach the preset renewable energy penetration rate ( Renewable energy generation); carbon emissions constraints refer to: The maximum carbon emissions that are limited by the final stage of evolution (the forecast period from 2045 to 2050).

The power grid operating cost constraint refers to the capital cost required for the normal operation of various resources (generating equipment) in the power grid system. Among them, the thermal power unit considers the operation constraints in the form of clusters; the hydropower unit considers the operation constraints in the form of three-stage output; the output of wind power, photovoltaic and solar thermal units is less than its maximum power generation capacity; energy storage considers its power, energy, and cycle constraints. ; Assuming that the power transmission between nodes is non-blocking, the power flow between nodes takes the traffic flow model into account to consider the operating constraints.

The following describes the objective function and constraints mentioned above in combination with the specific formula:

The objective function in the power grid evolution prediction algorithm is to minimize the sum of investment cost, fixed operation and maintenance cost, and variable operation cost in each evolution stage, and consider the time value of funds, as shown in equations (1) to (5):

min C ^INV +C ^OM +C ^OPR +C ^Target (1)

C ^Target = c ^VRE Q ^VRE +c ^Carb Q ^Carb (5)

Among them, Equation (1) represents the objective function; Equation (2) represents the total investment cost, including the sum of the investment costs of each stage and various types of resources; Equation (3) represents the total operation and maintenance cost, including The sum of fixed operation and maintenance costs; Equation (4) represents the total operation cost, including the operation cost of each stage, each type of resource estimated on a typical day, and the sum of the load shedding penalty cost; Equation (5) represents the long-term penalty cost, including The sum of the penalty cost of not meeting the renewable energy penetration rate and the penalty cost of not meeting the carbon emission standard.

表示某种资源在第n个预测时段的单位容量投资成本；

表示资源X在 第k个节点(以省为单位的电力系统)第n个预测时段的建设容量；Z表示每个 预测时段所包含的年份数目；f是年度单位固定运维成本；

表示资源X在第n 个预测时段的总容量；假设每个阶段内共有S个典型运行场景(模拟不同配比的各种类型的电源在电力系统中协同优化运行)，一年中对应于每个场景的天数 为ρ_s；

表示火电机组的单位发电成本；

表示火电机组的单位容量启动成本 (火电机组启动消耗的燃料的成本)，其中G表示火电机组类型，包括煤电和 气电机组；

表示节点k上火电机组在预测时段n典型场景s下时刻t的发电功 率；

表示节点k上火电机组在预测时段n典型场景s下时刻t的开机容量；

表示储能设备的单位运行成本，其中ES表示储能设备类型，包括抽水蓄能、电 池储能和压缩空气储能；

表示储能的充电功率；

表示储能的放电功率；

表示需求侧响应的单位补偿成本，其中DR表示需求侧响应的类型，包括负荷 削减型和负荷转移型；

表示需求侧响应的响应功率；

表示切负荷(事故 情况下，为维持电力系统的功率平衡和稳定性，将部分负荷从电网上断开)的 单位惩罚成本；

表示切负荷功率；c^VRE表示可再生能源渗透率目标未完成时， 与目标相比单位缺额量的惩罚成本；c^Carb表示碳排放目标未完成时，与目标相比 单位缺额量的惩罚成本；Q^VRE表示对应的可再生能源电量缺额量；Q^Carb表示对应 的碳排放减排缺额量。Among them, C ^INV represents the total investment cost of multiple forecast periods; C ^OM represents the fixed operation and maintenance cost of multiple forecast periods; C ^OPR represents the variable operation cost of multiple forecast periods; C ^Target represents the penalty cost of the gap with the preset target, The preset target can be renewable energy electricity penetration rate or carbon emissions; d is the annual discount rate, which is the annual interest rate that converts future assets into present value; X represents various power generation resources and flexible resources;

Represents the unit capacity investment cost of a certain resource in the nth forecast period;

Represents the construction capacity of resource X in the nth forecast period of the kth node (power system in the unit of province); Z represents the number of years included in each forecast period; f is the annual unit fixed operation and maintenance cost;

Represents the total capacity of resource X in the nth forecast period; assuming that there are S typical operating scenarios in each stage (simulating the coordinated optimal operation of various types of power sources with different ratios in the power system), corresponding to each The number of days for each scene is ρ _s ;

Indicates the unit power generation cost of the thermal power unit;

Represents the startup cost per unit capacity of thermal power units (the cost of fuel consumed for startup of thermal power units), where G represents the type of thermal power units, including coal-fired and gas-fired power units;

Represents the generation power of the thermal power unit on node k at time t under typical scenario s in forecast period n;

Represents the startup capacity of the thermal power unit on node k at time t under typical scenario s in forecast period n;

Represents the unit operating cost of energy storage equipment, where ES represents the type of energy storage equipment, including pumped hydro storage, battery energy storage and compressed air energy storage;

Represents the charging power of the energy storage;

Represents the discharge power of the energy storage;

Represents the unit compensation cost of demand-side response, where DR represents the type of demand-side response, including load reduction and load transfer;

represents the response power of the demand-side response;

Represents the unit penalty cost of load shedding (disconnecting part of the load from the grid in order to maintain the power balance and stability of the power system in the event of an accident);

Represents load shedding power; c ^VRE represents the penalty cost per unit of shortfall compared with the target when the renewable energy penetration rate target is not fulfilled; c ^Carb represents the penalty cost per unit of shortfall compared with the target when the carbon emission target is not fulfilled; Q ^VRE represents the corresponding shortfall of renewable energy electricity; Q ^Carb represents the corresponding shortfall of carbon emission reduction.

The constraints in the power grid evolution prediction algorithm are the power grid construction constraints and power grid operating cost constraints, such as equations (6) to (9):

Equation (6) constrains the investment capacity of each resource on each node in each stage; Equation (7) represents the relationship between the investment capacity and the total capacity; Equation (8) constrains the renewable energy penetration rate that needs to be achieved in the final stage of evolution target; Equation (9) constrains the carbon emission cap target in the final stage of evolution.

表示资源X在n阶段k节点上的投资容量上限，；

表示在 最后一个阶段N内，风电的发电功率；

表示在最后一个阶段N内，光伏的 发电功率；

表示在最后一个阶段N内，光热的发电功率；ζ表示可再生能 源电量渗透率目标；D_k,n＝N,t,s表示负荷功率；e^G表示火电单位发电对应的碳排放 量；V^Carb表示碳排放上限的目标值。in,

Represents the upper limit of the investment capacity of resource X on node k in n stages,;

Indicates the power generated by wind power in the last stage N;

Indicates the photovoltaic power generation in the last stage N;

Represents the solar thermal power generation in the last stage N; ζ represents the renewable energy penetration rate target; D _k,n=N,t,s represents the load power; e ^G represents the carbon emission corresponding to the unit power generation of thermal power; V ^Carb represents the target value of the carbon cap.

The embodiment of the present application provides a method for generating a large amount of evolution data by performing processing based on the power grid evolution prediction algorithm on the key indicator sample set. Specifically, for each group of samples in the key indicator sample set, if the sample satisfies the objective function (the optimal sum of investment costs in each stage of grid evolution, grid fixed operation and maintenance costs, and grid variable operation costs) and constraints (Construction constraints of grid evolution and grid operating cost constraints), then output a set of evolution data according to the sample. It can be seen that, in the embodiment of the present application, the key indicator sample set is processed based on the power grid evolution prediction algorithm, and a large amount of evolution data is generated. Compared with the prior art relying on artificial prediction of several power grid evolution development paths, the embodiment of the present application automatically generates a large number of evolution paths based on reliable specific data and a power grid evolution prediction algorithm, which can eliminate the influence of human factors on the power grid evolution prediction. This improves the accuracy of power grid evolution path prediction.

In the method provided by the embodiment of the present application, the evolution data obtained by the automatic prediction can also be analyzed to determine some key driving factors affecting the evolution of the power grid, which are used to predict the evolution data of the power grid and provide guidance for the actual evolution of the subsequent power grid. Specifically, the method provided in the embodiment of the present application also includes the steps shown in Figure 3:

Step 301: For any index in the key index set, calculate the degree of difference of the index in different evolution data, and use the largest degree of difference as the influence factor of the index.

In order to determine some key indicators (key driving factors) that have a greater impact on the evolution and development of the power grid in the embodiment of the present application, it is necessary to use a specific numerical value to represent the degree of influence of these key indicators on the evolution of the power grid.

In the specific implementation, the difference degree of the key index in different evolution data is calculated, and the largest difference degree is used as the influence factor of the key index, indicating the degree of influence of the key index on the evolution of the power grid.

Calculate the degree of difference of key indicators in different evolution data, the specific process is as formula (10) ~ (13):

y _i =[y _i,1 ,y _i,2 ,...,y _i,N ] (10)

Equation (10) represents the time series composed of multi-stage values; Equation (11) represents the mean value of each key indicator in the corresponding subspace; Equation (12) represents the standardization of the time series of the key indicators; Equation (13) ) represents the average distance of the normalized time series between different clusters.

表示同属于第r类的演 化路径对应的关键指标；Ψ_i表示关键指标的整个取值空间；

表示关键指标在 一个聚类中的取值空间；

表示标准化后的时间序列；μ_i,n表示关键指标在整个 取值空间中对应第n个预测时段内的均值；σ_i,n表示关键指标在整个取值空间中 对应第n个预测时段内的标准差。Dist_i表示关键指标在不同聚类演化路径间的平 均距离。Among them, y _i represents the i-th key indicator; y _i,1 , _yi,2 ,...,y _i,N represents the value of the i-th key indicator from the forecast period 1 to the forecast period N; R represents the massive The number of path clusters;

Represents the key indicators corresponding to the evolution path belonging to the rth class; Ψ _i represents the entire value space of the key indicators;

Represents the value space of key indicators in a cluster;

represents the normalized time series; μ _i,n represents the average value of the key indicators in the entire value space corresponding to the nth forecast period; σ _i,n represents the key indicators in the entire value space corresponding to the nth forecast period standard deviation of . Dist _i represents the average distance of key indicators between different cluster evolution paths.

The final calculated average distance is the degree of difference of the key indicator in different evolution data, and the maximum degree of difference is taken as the influence factor of the key indicator,

Step 302: In the key index set, one or more indexes whose impact factor is greater than a preset threshold are determined as the key driving factors for the evolution of the power grid in the target area.

In order to determine one or more key driving factors that have a greater impact on the evolution and development of the power grid from the key index set, it is necessary to preset a threshold for the impact factor corresponding to each key index, and set the impact factor greater than the preset threshold. Key metrics, identified as a key driver.

Step 303 , predict the subsequently generated evolution data according to the key driving factors.

The key driving factors that have a greater impact on the evolution and development of the power grid are determined, and when the power grid evolution data of the target area is subsequently generated, the power grid evolution data can be predicted by adjusting these key driving factors.

The embodiments of the present application provide a method for determining some key indicators (key driving factors) that have a greater impact on the evolution and development of the power grid in the key indicator set. Specifically, first determine the time series of any key indicator consisting of multi-stage values, and then cluster the generated massive paths to determine the value space of the key indicator in the same cluster, and calculate the key indicator in the same cluster. The mean value of the value space, based on the mean value, standardize the time series of the key indicators, calculate the distance of the standardized parameters between different clusters, as the degree of difference of the key index in different evolution data, these differences are calculated. Sort, take the largest difference as the impact factor of the index; obtain the impact factor of each key index in the key index set, compare the impact factor with the preset threshold, and compare the impact factor greater than the preset threshold to the corresponding key The index is determined as the key driving factor of the power grid evolution in the target area; in the subsequent power grid evolution and development process, the subsequent power grid evolution path (evolution data) can be adjusted by affecting the key driving factors.

In the method provided by the embodiment of the present application, the flexible resource development index of the target area can also be calculated, including: flexible resource capacity demand, flexible resource marginal capacity demand, battery energy storage emergence point, and battery energy storage dominant point. Adjust multiple sets of evolution data according to the development index of flexible resources, and also plan the evolution data generated subsequently according to the development index;

In the embodiment of the present application, in order to adjust the evolution data generated by the power grid evolution prediction algorithm, it is necessary to obtain the distribution of flexible resources and battery energy storage in the power system, and determine the development index of flexible resources. Specifically, the flexible resource capacity demand, flexible resource marginal capacity demand, battery energy storage emergence point and battery energy storage dominant point of the target area are calculated according to the formula.

Among them, the demand for flexible resource capacity is the flexible resource capacity of the system under different renewable energy power penetration rates, that is, under different renewable energy power generation targets, the installed capacity of flexible resources that needs to be achieved (generating unit Rated power); the marginal capacity demand of flexible resources is the increment of flexible resource capacity corresponding to the preset value of penetration rate increase under different renewable energy power penetration rates, that is, under different renewable energy power generation targets, the The increase of renewable energy power generation by 1 percentage point corresponds to the increase in the installed capacity of flexible resources; the appearance point of battery energy storage is the penetration rate of renewable energy corresponding to the appearance of battery energy storage in the power system. The dominant point is the penetration rate of renewable energy corresponding to the preset proportion of battery energy storage capacity to flexible resource capacity. The preset ratio can be 50%.

Calculation of flexible resource capacity, such as formula (14):

表示灵活性资源容量；ζ₀表示某一特定水平的可再生能源电量 渗透率。in,

Represents flexible resource capacity; ζ ₀ represents the penetration rate of renewable energy at a certain level.

The calculation of the marginal capacity of flexible resources is shown in formula (15):

表示灵活性资源的容量增量；Δζ表示可再生能源渗透率增量。in,

represents the capacity increment of flexible resources; Δζ represents the renewable energy penetration increment.

The calculation of the occurrence point of battery energy storage, such as formula (16):

The calculation of the dominant point of battery energy storage is shown in formula (17):

表示电池储能的总容量。in

Indicates the total capacity of battery energy storage.

The embodiments of the present application provide a method for calculating a flexible resource development index of a target area. Specifically, according to the formula, calculate the flexible resource capacity demand, flexible resource marginal capacity demand, battery energy storage emergence point and battery energy storage dominant point of the target area, and adjust the flexible resources according to the calculation results to achieve the expected The renewable energy power penetration rate set target can also be used to judge the current distribution (occurrence frequency) of battery energy storage resources in the power system through the renewable energy power penetration rate, which increases the flexibility of the power system; When the electricity penetration rate of renewable energy changes abnormally, the reliability of the power system can be increased to a certain extent by adjusting the flexible resources to interfere with the electricity penetration rate of renewable energy.

The embodiment of the present invention takes the northwest region (for example, including Shaanxi, Gansu, Qinghai, Ningxia, and Xinjiang) as an example to describe the power grid evolution prediction method provided in the present application in detail. Specifically, consider grid evolution data from 2020 to 2050. The current installed capacity and load of each province in the Northwest Power Grid are shown in Figure 4, with wind power and photovoltaic installed capacity accounting for 38.8%. Assuming an annual growth rate of local load of 3%, the outbound load capacity remains the same.

Applied to the above-mentioned specific scenario, the power grid evolution prediction method provided in the embodiment of the present application includes the following steps:

S1. According to historical documents, determine the value range of multiple uncertain factors in each prediction stage, and complete the assignment of these uncertain factors.

Among them, the uncertain factors can also be called key indicators, and multiple uncertain factors constitute the set of key indicators mentioned above.

S2. Divide 5 years as a forecast period, and set the target of renewable energy penetration in the final state of evolution (2050) to 80%.

S3. Sampling the uncertain factors after assignment for 2,500 times, and generate evolution data under the three thermal power flexibility transformation paths shown in Figure 4, generating a total of 7,500 pieces of evolution data. It should be noted that the setting of the renewable energy penetration rate target defines the power generation space of conventional power sources, and the carbon emissions of conventional power sources are relatively determined, that is, the renewable energy penetration rate target and the carbon emission target have a certain degree of correlation. , so this chapter does not set carbon emission targets separately.

The evolution path of carbon emissions of the system is shown in Figure 7(d), and the annual carbon emissions show a trend of peaking first and then decreasing. From the average path, the annual carbon emissions will still increase by about 12%, and under the target of 80% renewable energy penetration rate, the final annual carbon emissions will drop by 57% compared with 2020. The increase in carbon emissions in the early stage of evolution is due to the fact that the reduction in carbon emissions brought about by the growth of renewable energy in the early stage is difficult to offset the increase in carbon emissions brought about by the increase in load growth and thermal power generation.

Figure 6 shows the demand of flexible resources (flexible resource capacity, flexible resource marginal capacity) under different renewable energy penetration rates under the massive evolution path. The evolution data involved in the statistics are all generated under the thermal power deep transformation path. With the increase in the penetration rate of renewable energy, not only the demand for flexibility resource capacity increases, but also the marginal capacity demand for flexibility resources is on the rise. A penetration rate between 70-80% requires about 23 times the flexibility capacity than a penetration rate between 10-20%, while for marginal flexibility needs, the corresponding increase is about 11 times. Therefore, when the penetration rate of renewable energy is high, more resources are required to further increase the penetration rate, and the position of flexible resources in the system will become more and more important.

Figure 7 shows the statistics of battery energy storage in the massive evolution path. It can be seen that battery energy storage may intervene in the early stage of the development of a low proportion of renewable energy, and it is most likely to intervene in the system when the penetration rate of renewable energy is between 40 and 45%. The energy penetration rate is between 60 and 65% to become the dominant flexibility resource.

As mentioned above, the evolution of power grid is affected by different factors such as technology, market, and public. This application first shows the identification process shown in Figure 5 by taking the identification of key drivers of renewable energy penetration evolution at the technical level as an example, and then analyzes the key drivers that affect various aspects of grid evolution.

For the renewable energy permeability evolution path, firstly, a large number of generated paths are clustered, and here they are clustered into 4 categories, as shown in Figure 8. These four categories correspond to the four modes of permeability evolution: fast growth mode, slow growth mode, fast growth before and slow growth, slow growth before and fast growth. The key indicators corresponding to each type of evolution data are averaged and standardized, as shown in Figure 9. It can be seen that the unit investment cost of renewable energy, the cost of battery energy storage, and the coal price curve are quite different between different categories, indicating that the penetration rate of renewable energy is more sensitive to these indicators. Calculate the average distance of each index curve and sort, the result is shown in Figure 10. It can be seen that the influencing factors are coal price, unit investment cost of wind power, maximum investable capacity of battery energy storage in each stage, unit investment cost of photovoltaic, unit investment cost of battery energy storage, which is consistent with the results in Figure 9.

Based on the above process, the key indicators that affect the evolution path of different aspects are further analyzed, and the calculated values of the average distance indicators are listed in Table 3. In all aspects of evolution, the main influencing factors are basically the same, including the unit investment cost of renewable energy and energy storage, coal price, and the maximum investable capacity of battery energy storage in each forecast period. But the relative importance of these factors varies slightly in various respects. In terms of technology, the maximum investable capacity of battery energy storage at each stage is the most important factor, reflecting that the configuration of battery energy storage is an economical choice, and its configuration capacity is closely related to its maximum configurable upper limit. On the market and public side, the most important influencing factor is the price of coal.

table 3

From the above calculation process, it can be seen that the annual carbon emissions will still increase by about 12%, and the carbon emissions in 2050 will drop by 57% compared with 2020. Both the flexibility demand and marginal flexibility demand of the system will increase with the increase of the penetration rate of renewable energy. Among them, battery energy storage is most likely to intervene in the system when the penetration rate of renewable energy is between 40% and 45%. The rate between 60 and 65% has become the dominant flexibility resource. The main drivers affecting grid evolution include unit investment costs of renewable energy and energy storage, coal prices, and the maximum investable capacity of battery storage at each stage. This method has clear calculation ideas, good generality, and is suitable for popularization.

FIG. 13 is a frame diagram of the generation and analysis of massive evolution paths of the present application. Specifically, first, determine the uncertainty factors (key index set) that affect the evolution and development of the power grid in the target area, then divide the uncertainty factors into multiple prediction periods, and determine the upper and lower limit values of each prediction period, Complete the quantification of uncertainty factors; then randomly sample each uncertainty factor within the upper limit value and lower limit value range of each forecast period to obtain key indicator samples, which are input into the evolution The path generation module (power grid evolution prediction algorithm) judges that if the key index sample satisfies the objective function and constraint conditions, a set of evolution data will be generated correspondingly; finally, a large number of generated evolution data are analyzed to obtain a comparative analysis of the impact on the evolution and development of the power grid. Large key drivers; achievable, and also calculate flexibility resource development metrics, used to tune the generated grid evolution data.

It should be understood that although the various steps in the flowcharts of Figures 1-3 are shown in sequence as indicated by the arrows, these steps are not necessarily performed sequentially in the sequence indicated by the arrows. Unless explicitly stated herein, there is no strict order in the execution of these steps, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIGS. 1-3 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but may be executed at different times. The execution of these steps or stages The order is also not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the steps or phases within the other steps.

In one embodiment, as shown in FIG. 14, a power grid evolution prediction device is provided, including:

A determination module 1401 is used to determine a set of key indicators corresponding to the target area; the set of key indicators includes a power generation resource index that affects the development of the target area's power grid, an energy storage index that affects the development of the target area's power grid, and an electricity demand side index that affects the development of the target area's power grid , flexible resource indicators, and fuel price indicators that affect the development of power grids in the target area;

Numerical processing module 1402, for performing numerical prediction processing on each index in the key index set to obtain a key index sample set;

The evolution data generation module 1403 is used to process the key index sample set by using the power grid evolution prediction algorithm to obtain multiple sets of evolution data corresponding to the target area; the evolution data includes the evolution data of the power generation resource structure corresponding to the target area and the flexibility resources corresponding to the target area Structural evolution data.

In one embodiment, the numerical processing module 1402 is specifically configured to perform numerical prediction processing on each index in the key index set to obtain a key index sample set, including:

For each indicator in the key indicator set, determine the upper limit value and lower limit value of each indicator in the forecast period, and assign each indicator in the key indicator set according to the upper limit value and lower limit value of each indicator. ;

The Monte Carlo method is used to randomly sample the set of key indicators after the assignment processing, and the value of each indicator in each forecast period is obtained, and the key indicator sample set is determined according to the value of each indicator in each forecast period.

In one embodiment, the evolution data generation module 1403 is specifically used to input the key indicator sample set into the objective function in the power grid evolution prediction algorithm, and use the constraints in the power grid evolution prediction algorithm to perform constraint processing on the key indicator sample set;

Determine multiple sets of evolution data corresponding to the target area according to the output of the objective function and the result of the constraint processing;

Among them, the objective function is: the optimal sum of the investment cost of the power grid evolution in each forecast period, the fixed operation and maintenance cost of the power grid, and the variable operation cost of the power grid; the constraints include: the construction constraints of the power grid and the operating cost constraints of the power grid.

In one embodiment, the investment cost is the capital cost invested in the construction of power generation resources and flexible resources in the power system; the grid fixed operation and maintenance cost is the capital cost invested in routine maintenance of the equipment built in the power system; the power grid variable The operating cost is the cost of the fuel consumed when the power generation resource in the power system operates.

In one embodiment, the construction constraints of the power grid include at least one of the following:

Investment capacity constraints, total investment capacity constraints, renewable energy penetration rate constraints in the final stage of grid evolution, and carbon emission constraints in the final stage of grid evolution for various resources on each power grid node in each forecast period;

The operating cost constraint of the power grid is the capital cost required to maintain the normal operation of various power generation resources in the power system.

In one embodiment, as shown in FIG. 15 , the power grid evolution prediction apparatus further includes a power grid evolution data analysis module 1404.

The power grid evolution data analysis module is specifically used to, for any key index in the key index set, calculate the degree of difference of the key index in different evolution data, and take the largest degree of difference as the impact factor of the key index;

In the key indicator set, one or more key indicators whose impact factor is greater than the preset threshold are determined as the key driving factors of the grid evolution in the target area; the key driving factors are used to predict the grid evolution data.

In one embodiment, as shown in FIG. 16 , the power grid evolution prediction apparatus further includes a power grid evolution data adjustment module 1405.

The power grid evolution data adjustment module is specifically used to calculate the flexible resource development index of the target area. The flexible resource development index includes flexible resource capacity demand, flexible resource marginal capacity demand, battery energy storage emergence point and battery energy storage dominant point;

Adjust multiple sets of evolution data according to the development index of flexible resources, and plan the subsequent evolution data according to the development index;

Among them, the flexible resource capacity requirement is the flexible resource capacity of the system under different renewable energy electricity penetration rates, and the flexible resource marginal capacity requirement is the penetration rate increase under different renewable energy electricity penetration rates, corresponding to the preset value. The capacity increment of flexible resources, the occurrence point of battery energy storage is the corresponding renewable energy power penetration rate when battery energy storage appears in the power system, and the dominant point of battery energy storage is the preset proportion of battery energy storage capacity to flexible resource capacity The corresponding renewable energy electricity penetration rate.

For the specific limitations of the power grid evolution prediction device, please refer to the limitations on the power grid evolution prediction method above, which will not be repeated here. Each module in the above-mentioned power grid evolution prediction device can be implemented in whole or in part by software, hardware and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above modules.

In one embodiment, a computer device is provided, and the computer device may be a server, and its internal structure diagram may be as shown in FIG. 17 . The computer device includes a processor, memory, and a network interface connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The nonvolatile storage medium stores an operating system, computer programs, and databases. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The computer device's database is used to store key indicator sets, key indicator sample sets, and evolution data. The network interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, the method for predicting the evolution of the power grid described in the embodiments of the present application is implemented.

Those skilled in the art can understand that the structure shown in FIG. 17 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. The specific computer device may be Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, a computer program is stored in the memory, and the processor implements the following steps when executing the computer program:

Determine the set of key indicators corresponding to the target area; the set of key indicators includes the power generation resource indicators affecting the development of the target regional power grid, the energy storage indicators affecting the development of the target regional power grid, the demand side indicators affecting the and fuel price indicators that affect the development of power grids in target regions;

Perform numerical prediction processing on each indicator in the key indicator set to obtain a key indicator sample set;

The power grid evolution prediction algorithm is used to process the key index sample set to obtain multiple sets of evolution data corresponding to the target area; the evolution data includes the evolution data of the power generation resource structure corresponding to the target area and the evolution data of the flexible resource structure corresponding to the target area.

In one embodiment, the processor, when executing a computer program, implements:

For each indicator in the key indicator set, determine the upper limit value and lower limit value of each indicator in the forecast period, and assign each indicator in the key indicator set according to the upper limit value and lower limit value of each indicator. ;

The Monte Carlo method is used to randomly sample the set of key indicators after the assignment processing, and the value of each indicator in each forecast period is obtained, and the key indicator sample set is determined according to the value of each indicator in each forecast period.

In one embodiment, the processor, when executing a computer program, implements:

Input the key index sample set into the objective function in the power grid evolution prediction algorithm, and use the constraints in the power grid evolution prediction algorithm to constrain the key index sample set;

Determine multiple sets of evolution data corresponding to the target area according to the output of the objective function and the result of the constraint processing;

Among them, the objective function is: the optimal sum of the investment cost of the power grid evolution in each forecast period, the fixed operation and maintenance cost of the power grid, and the variable operation cost of the power grid; the constraints include: the construction constraints of the power grid and the operating cost constraints of the power grid.

In one embodiment, the investment cost is the capital cost invested in the construction of power generation resources and flexible resources in the power system; the grid fixed operation and maintenance cost is the capital cost invested in routine maintenance of the equipment built in the power system; the power grid variable The operating cost is the cost of the fuel consumed when the power generation resource in the power system operates.

In one embodiment, the construction constraints of the power grid include at least one of the following:

Investment capacity constraints, total investment capacity constraints, renewable energy penetration rate constraints in the final stage of grid evolution, and carbon emission constraints in the final stage of grid evolution for various resources on each power grid node in each forecast period;

The operating cost constraint of the power grid is the capital cost required to maintain the normal operation of various power generation resources in the power system.

In one embodiment, the processor, when executing a computer program, implements:

For any key indicator in the key indicator set, calculate the degree of difference of the key indicator in different evolution data, and take the largest degree of difference as the impact factor of the key indicator;

In the key indicator set, one or more key indicators whose impact factor is greater than the preset threshold are determined as the key driving factors of the grid evolution in the target area; the key driving factors are used to predict the grid evolution data.

In one embodiment, the processor, when executing a computer program, implements:

Calculate the flexible resource development index of the target area, the flexible resource development index includes flexible resource capacity demand, flexible resource marginal capacity demand, battery energy storage emergence point and battery energy storage dominant point;

Adjust multiple sets of evolution data according to the development index of flexible resources, and plan the subsequent evolution data according to the development index;

Among them, the flexible resource capacity requirement is the flexible resource capacity of the system under different renewable energy electricity penetration rates, and the flexible resource marginal capacity requirement is the penetration rate increase under different renewable energy electricity penetration rates, corresponding to the preset value. The capacity increment of flexible resources, the occurrence point of battery energy storage is the corresponding renewable energy power penetration rate when battery energy storage appears in the power system, and the dominant point of battery energy storage is the preset proportion of battery energy storage capacity to flexible resource capacity The corresponding renewable energy electricity penetration rate.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage In the medium, when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the various embodiments provided in this application may include at least one of non-volatile and volatile memory. The non-volatile memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, and the like. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, the RAM may be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM).

The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims (10)

1. A power grid evolution prediction method, characterized in that the method comprises: A set of key indicators corresponding to the target area is determined; the set of key indicators includes a power generation resource index that affects the development of the power grid in the target area, an energy storage index that affects the development of the power grid in the target area, and an electricity demand that affects the development of the power grid in the target area side indicators, flexible resource indicators, and fuel price indicators that affect the development of the power grid in the target area; Perform numerical prediction processing on each indicator in the set of key indicators to obtain a sample set of key indicators; The key index sample set is processed by using a power grid evolution prediction algorithm to obtain multiple sets of evolution data corresponding to the target area; the evolution data includes the evolution data of the power generation resource structure corresponding to the target area and the flexible data corresponding to the target area. Evolutionary data on the structure of sexual resources. 2. The method according to claim 1, wherein, performing numerical prediction processing on each indicator in the set of key indicators to obtain a sample set of key indicators, comprising: For each indicator in the key indicator set, determine the upper limit value and lower limit value of each indicator within the forecast period, and determine the key indicator according to the upper limit value and lower limit value of each indicator Each indicator in the set is assigned a value; The Monte Carlo method is used to randomly sample the set of key indicators after the assignment processing, to obtain the value of each indicator in each forecast period, and determine the value of each indicator in each forecast period according to the value of each indicator in each forecast period. A sample set of the above key indicators. 3. The method according to claim 1, characterized in that, using a power grid evolution prediction algorithm to process the key indicator sample set to obtain multiple sets of evolution data corresponding to the target area, comprising: Inputting the key indicator sample set into the objective function in the power grid evolution prediction algorithm, and performing constraint processing on the key indicator sample set by using the constraints in the power grid evolution prediction algorithm; Determine multiple sets of evolution data corresponding to the target area according to the output of the objective function and the result of the constraint processing; The objective function is: the optimal sum of the investment cost of the grid evolution in each forecast period, the fixed grid operation and maintenance cost, and the grid variable operation cost; the constraints include: grid construction constraints and grid operating cost constraints. 4. The method according to claim 3, wherein the investment cost is the capital cost invested in the construction of power generation resources and flexible resources in the power system; the fixed operation and maintenance cost of the power grid is the cost of construction in the power system. The capital cost invested in routine maintenance of equipment; the variable operating cost of the power grid is the cost of fuel consumed by the power generation resources in the power system during operation. 5. The method according to claim 3, wherein the construction constraints of the power grid comprise at least one of the following: Investment capacity constraints, total investment capacity constraints, renewable energy penetration rate constraints in the final stage of grid evolution, and carbon emission constraints in the final stage of grid evolution for various resources on each grid node in each forecast period; The operating cost constraint of the power grid is the capital cost required to maintain the normal operation of various power generation resources in the power system. 6. The method of claim 1, wherein the method comprises: For any key indicator in the key indicator set, calculate the degree of difference of the key indicator in different evolution data, and use the largest degree of difference as the impact factor of the key indicator; In the set of key indicators, one or more key indicators whose impact factor is greater than a preset threshold are determined as key driving factors of the grid evolution in the target area; the key driving factors are used to predict grid evolution data. 7. The method of claim 1, wherein the method further comprises: calculating a flexible resource development index of the target area, where the flexible resource development index includes flexible resource capacity demand, flexible resource marginal capacity demand, battery energy storage emergence point, and battery energy storage dominant point; Wherein, the flexible resource capacity requirement is the flexible resource capacity of the system under different renewable energy power penetration rates, and the flexible resource marginal capacity requirement is the penetration rate growth forecast under different renewable energy power penetration rates. The flexible resource capacity increment corresponding to the value is set, the occurrence point of battery energy storage is the corresponding renewable energy power penetration rate when battery energy storage appears in the power system, and the dominant point of battery energy storage is the proportion of battery energy storage capacity. Renewable energy electricity penetration rate corresponding to the preset proportion of flexible resource capacity. 8. A power grid evolution prediction device, wherein the device comprises: A determination module, configured to determine a set of key indicators corresponding to the target area; the set of key indicators includes a power generation resource index that affects the development of the target area power grid, an energy storage index that affects the development of the target area power grid, and an index that affects the development of the target area power grid. The developed electricity demand side indicators, flexible resource indicators, and fuel price indicators affecting the development of the power grid in the target area; a numerical processing module, configured to perform numerical prediction processing on each index in the key index set to obtain a key index sample set; An evolution data generation module, configured to process the key indicator sample set using a power grid evolution prediction algorithm to obtain multiple sets of evolution data corresponding to the target area; the evolution data includes evolution data of the power generation resource structure corresponding to the target area and Evolution data of the flexible resource structure corresponding to the target area. 9. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein the processor implements the method according to any one of claims 1 to 7 when the processor executes the computer program. step. 10. A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images