Power supply planning method and system considering boundary uncertainty, and storage medium

Abstract

The invention relates to a power supply planning method considering boundary uncertainty. The method comprises the following steps: step 1, inputting power supply construction and load conditions of original partitions in long-term planning as basic parameters of a model; 2, sampling uncertainty according to a Monte Carlo simulation method to generate a scene tree of future electricity consumption and load, and generating a possible value set under different time nodes in the future; 3, establishing a rolling optimization power supply structure planning model based on a model prediction control thought; the method has the advantages that the power supply structure planning model is constructed, model prediction control is introduced, pre-planning is realized, and the influence is reduced through an online rolling strategy.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system planning and operation, and specifically relates to a power supply planning method, system and storage medium considering boundary uncertainty. Background Art

[0002] With the proposal of the dual carbon goals and the deepening of energy structure transformation, the penetration rate of renewable energy has continued to increase. The access of large-scale renewable energy has not only significantly improved the economic benefits of the power grid, but also greatly promoted energy conservation and emission reduction. However, the randomness, volatility and intermittency of renewable energy output have increased the uncertainty of the boundary conditions on the power supply side. At the same time, the promotion of load-side electricity substitution and demand-side response has also greatly increased the uncertainty of load boundary conditions. The volatility of boundary conditions such as power construction costs in medium- and long-term planning has also greatly increased the uncertainty of planning schemes. The above three types of uncertainty increase the volatility of the power supply and demand balance of the power grid, increase the difficulty of system planning, and have an adverse impact on the safe and stable development of the power grid. If the power structure planning that avoids uncertainty obtains the optimal result, it often not only fails to achieve the "optimal" effect, but may also cause an unreasonable power structure. Future load and electricity consumption data are important boundary conditions in long-term planning, and power structure planning under uncertainty is of great significance. Current research on considering uncertainty focuses on robust methods, stochastic optimization methods and scenario planning methods. However, in these traditional power structure planning methods, the future boundary conditions of the optimization process are often determined before the uncertainty occurs, and as the planning cycle increases, the reliability of the prediction results of the long-term boundary conditions decreases significantly, so their practicality and scope of application are greatly limited. Therefore, it is very necessary to provide a power planning method, system and storage medium that considers boundary uncertainty by constructing a power structure planning model, introducing model predictive control, realizing pre-planning, and reducing the impact through online rolling strategies. Summary of the Invention

[0003] The purpose of the present invention is to overcome the shortcomings of the existing technology and provide a power planning method, system and storage medium that consider boundary uncertainty by constructing a power structure planning model, introducing model predictive control, realizing pre-planning, and reducing the impact through an online rolling strategy.

[0004] The object of the present invention is achieved by providing a power supply planning method considering boundary uncertainty, the method comprising the following steps:

[0005] Step 1: Input the power supply construction and load conditions of each zone in the long-term plan as the basic parameters of the model;

[0006] Step 2: Generate a scenario tree of future power consumption and load by sampling uncertainty using the Monte Carlo simulation method, and generate a set of possible values ​​at different time nodes in the future;

[0007] Step 3: Establish a rolling optimization power structure planning model based on model predictive control.

[0008] The step 3 of establishing a rolling optimization power structure planning model based on the model predictive control concept specifically includes the following steps:

[0009] Step 3.1: Establish a power structure pre-planning model based on model predictive control;

[0010] Step 3.2: Build an online rolling optimization power structure model;

[0011] Step 3.3: Design an online rolling optimization process for power structure.

[0012] The establishment of the power structure pre-planning model based on model predictive control in step 3.1 is specifically as follows: the objective function of the power structure pre-planning is the expected total cost TC in the kth planning period K Minimum, where the total cost includes the expected cost of power supply investment and construction SC k , expected cost of investment and construction of inter-regional transmission lines LC k , expected operation and maintenance cost OM k 、Expected cost of power fuel FC k and the expected cost of transmission and distribution losses TE k :MinTC K (N)=SC k (N)+LC k (N)+OM k (N)+FC k (N)+TE k (N)(1).

[0013] The boundary conditions for establishing the power structure pre-planning model based on model predictive control in step 3.1 are specifically: considering various constraints in actual power system operation, such as installed capacity constraints, power balance constraints, and natural resource constraints, and modifying traditional constraints in combination with the model predictive control algorithm: AG r,g,y,s (k) = AG r,g,y-1,s (k)+G r,g,y-1,s (k)-RG r,g,y-1,s (k)(9), the above formula describes the installed capacity constraints of various power sources, where, are the upper and lower limits of the newly built capacity of the g-th type power source in the r-th region at the y-th time node in the k-th iteration respectively; are the upper and lower limits of the retired capacity of the g-th type power supply in the r-th region at the y-th time node in the k-th iteration; G r,g,y,s (k) is the decommissioned capacity;

[0014]

[0015] The above formula describes the constraints of inter-regional transmission lines, where: is the amount of electricity transmitted by the transmission line between the two regions in the kth iteration; is the maximum operating hours of the transmission line between the two regions; is the minimum operating hours of the transmission line between two regions; The above formula describes the natural resource endowment constraint, where The upper limit of natural resource installed capacity for category g power source in region r; PS r,g,y,s (k) is the power generation of the g-type power source in the r-th region at the y-th time node of the k-th iteration; The upper limit of natural resource power generation for category g power source in region r;

[0016] The above formula describes the power balance constraint within the region, where: They represent the upper and lower limits of the operating hours of the g-type power supply in the r-th area at the y-th time node; PD r,y Indicates the rth time node at the yth time i Electricity consumption in the region; LD r,y Indicates the rth time node at the yth time i Regional load; PR is the reserve factor of the system load; FS r,g,y Indicates the power factor of the g-type power supply in the r-th area at the y-th time node; Indicates the power factor of the transmission line between two areas.

[0017] The construction of the online rolling optimization power structure model in step 3.2 is specifically as follows: the entire planning period is divided into T time nodes, and the power structure planning model in step 3.1 is solved to obtain the construction capacity of various power sources in the region with a time span of N and the construction capacity construction plan of the inter-regional interconnection line:

[0018] After the iterative cycle shown below, the power structure evolution path result is obtained: G r,g,k,s =G r,g,1,s (k),k=1,2,...,(T-N+1)(20), AG r,g,k,s =AG r,g,1,s (k),k=1,2,...,(T-N+1)(22),

[0019] Gr,g,T-N+1+i,s =G r,g,i+1,s (T-N+1),i=1,2,...,N-1(24),

[0020] AG r,g,T-N+1+i,s =AG r,g,i,s (T-N+1),i=1,2,...,N-1(26),

[0021] The design of the online rolling optimization process of the power structure in step 3.3 is specifically as follows: based on the pre-planning decision sequence obtained from the power structure pre-planning model, a current time node decision is generated, and new initial conditions and boundary conditions are further generated based on the current time node decision, until the online cyclic power planning of all time nodes is completed to obtain the final decision sequence.

[0022] A power supply planning system considering boundary uncertainty includes a data acquisition module, a topology construction module, a planning prediction module, and a planning update module. The power supply structure planning system considering planning boundary uncertainty is used to execute the above-mentioned power supply planning method considering boundary uncertainty.

[0023] The data acquisition module is used to obtain grid network parameters, power supply installed capacity parameters, inter-regional transmission line capacity and power, and natural resources in each region;

[0024] The topology building module is used to build a power planning prediction model based on the power grid network parameters and power supply and transmission line parameters output by the data acquisition module;

[0025] The planning and prediction module is used to predict power supply planning based on regional power balance, unexpected planning, peak load reserve, and network balance constraints, combined with the data acquisition module and the topology construction module;

[0026] The planning update module is used to perform rolling optimization at the current time node according to the prediction sequence of the planning prediction module to obtain a new power supply planning decision.

[0027] A storage medium includes a computer-readable storage medium and a computer program / instruction, wherein the computer-readable storage medium is used to store the computer program / instruction; the computer program / instruction is used to control the above-mentioned power planning system considering boundary uncertainty to realize data calling and power structure evolution route.

[0028] The computer-readable storage medium is any available medium that can be stored by a computing device or a data center data storage device containing one or more available media.

[0029] The usable medium is a magnetic medium, an optical medium or a semiconductor medium.

[0030] The beneficial effects of the present invention are as follows: the present invention is a power supply planning method considering boundary uncertainty, proposes a power supply structure planning theory, and considers the grid planning problem of load and power consumption boundary uncertainty. In use, first, the lowest expected cost of the system during the planning period is taken as the goal, and constraints such as power balance and natural resources based on the model predictive control idea are introduced to establish a power supply structure pre-planning model, and pre-plan the power supply structure under the expected values ​​of future boundary conditions to obtain a pre-planning decision sequence; further, through an online rolling optimization model, based on the pre-planning decision sequence, the current decision result is obtained and the initial and boundary conditions of the next round of pre-planning are updated; the present invention has the advantages of constructing a power supply structure planning model, introducing model predictive control, realizing pre-planning, and reducing the impact through an online rolling strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 Based on the flow chart.

[0032] Figure 2 This is a flow chart of the online rolling optimization power supply structure of the present invention. DETAILED DESCRIPTION

[0033] The present invention will be further described below with reference to the accompanying drawings.

[0034] Example 1

[0035] like Figure 1-2 As shown, a power planning method considering boundary uncertainty includes the following steps:

[0036] Step 1: Input the power supply construction and load conditions of each zone in the long-term plan as the basic parameters of the model;

[0037] Step 2: Generate a scenario tree of future power consumption and load by sampling uncertainty using the Monte Carlo simulation method, and generate a set of possible values ​​at different time nodes in the future;

[0038] Step 3: Establish a rolling optimization power structure planning model based on model predictive control.

[0039] The step 3 of establishing a rolling optimization power structure planning model based on the model predictive control concept specifically includes the following steps:

[0040] Step 3.1: Establish a power structure pre-planning model based on model predictive control;

[0041] In this embodiment, a power structure pre-planning model based on model predictive control is established, specifically: the objective function of power structure pre-planning is the expected total cost TC in the kth planning period KMinimum, where the total cost includes the expected cost of power supply investment and construction SC k , expected cost of investment and construction of inter-regional transmission lines LC k , expected operation and maintenance cost OM k 、Expected cost of power fuel FC k and the expected cost of transmission and distribution losses TE k :MinTC K (N)=SC k (N)+LC k (N)+OM k (N)+FC k (N)+TE k (N)(1), where

[0042]

[0043] Where p y,s is the probability of the sth scenario occurring at the yth time node; SC r,g,y is the unit construction cost of the g-type power source in the r-th area at the y-th time node; is the cost of constructing a unit capacity transmission line between two regions at time node y; OM r,g,y F is the operation and maintenance cost of the g-type power supply in the r-th area at the y-th time node; r,g,y is the fuel cost of the g-type power source in the r-th area at the y-th time node; G is the transmission and distribution loss per unit capacity between the two regions at the yth time node; r,g,y,s (k) is the newly built capacity of the g-type power source in the r-th area at the y-th time node in the k-th iteration; AG r,g,y,s (k) is the built power capacity of the g-type power source in the r-th region at the y-th time node in the k-th iteration; The capacity of the new transmission line between the two regions at the yth time node in the kth iteration; is the capacity of the transmission lines built between the two regions at the yth time node in the kth iteration; N is the number of time nodes in the planning period; T is the total planning duration; T g T is the service life of the g-type power supply; L is the service life of the transmission line; i is the capital discount rate;

[0044] The boundary conditions for establishing a power structure pre-planning model based on model predictive control are as follows: considering various constraints in actual power system operation, such as installed capacity constraints, power balance constraints, and natural resource constraints, and modifying traditional constraints in combination with the model predictive control algorithm:

[0045] AG r,g,y,s (k) = AGr,g,y-1,s (k)+G r,g,y-1,s (k)-RG r,g,y-1,s (k)(9), the above formula describes the installed capacity constraints of various power sources, where, are the upper and lower limits of the newly built capacity of the g-th type power source in the r-th region at the y-th time node in the k-th iteration respectively; are the upper and lower limits of the retired capacity of the g-th type power supply in the r-th region at the y-th time node in the k-th iteration; G r,g,y,s (k) is the decommissioned capacity;

[0046]

[0047] The above formula describes the constraints of inter-regional transmission lines, where: is the amount of electricity transmitted by the transmission line between the two regions in the kth iteration; is the maximum operating hours of the transmission line between the two regions; is the minimum operating hours of the transmission line between two regions; The above formula describes the natural resource endowment constraint, where The upper limit of natural resource installed capacity for category g power source in region r; PS r,g,y,s (k) is the power generation of the g-type power source in the r-th region at the y-th time node of the k-th iteration; The upper limit of natural resource power generation for category g power source in region r;

[0048] The above formula describes the power balance constraint within the region, where: They represent the upper and lower limits of the operating hours of the g-type power supply in the r-th area at the y-th time node; PD r,y Indicates the rth time node at the yth time i Electricity consumption in the region; LD r,y Indicates the rth time node at the yth time i Regional load; PR is the reserve factor of the system load; FS r,g,y Indicates the power factor of the g-type power supply in the r-th area at the y-th time node; Indicates the power factor of the transmission line between two areas.

[0049] Step 3.2: Build an online rolling optimization power structure model;

[0050] In this embodiment, an online rolling optimization power structure model is established. Specifically, the entire planning period is divided into T time nodes, and the power structure planning model in step 3.1 is solved to obtain the construction capacity of various power sources in the region with a time span of N and the construction capacity construction plan of the inter-regional interconnection line:

[0051] After the iterative cycle shown below, the power structure evolution path result is obtained: G r,g,k,s =G r,g,1,s (k),k=1,2,...,(T-N+1)(20), AG r,g,k,s =AG r,g,1,s (k),k=1,2,...,(T-N+1)(22),

[0052] G r,g,T-N+1+i,s =G r,g,i+1,s (T-N+1),i=1,2,...,N-1(24),

[0053] AG r,g,T-N+1+i,s =AG r,g,i,s (T-N+1),i=1,2,...,N-1(26),

[0054] Step 3.3: Design an online rolling optimization process for power structure.

[0055] In this embodiment, an online rolling optimization process for the power structure is designed, specifically: a pre-planning decision sequence obtained from a power structure pre-planning model is used to generate a current time node decision, and new initial conditions and boundary conditions are further generated based on the current time node decision until the online cyclic power planning of all time nodes is completed, a final decision sequence is obtained, and a computer-readable storage medium is provided for storing a computer program or instruction. When the computer program or instruction is executed by a processing device, the above-mentioned data call and power structure evolution route are realized.

[0056] In this embodiment, an example analysis is performed to illustrate in more detail the effectiveness of the method of the present invention in effectively reducing the system cost and system carbon emissions of power planning. The method of the present invention is used to plan the power structure. The test system includes seven regions: Northwest, Southwest, North China, Northeast, Central China, South China, and East China. The power investment and construction types include thermal power, gas power generation, photovoltaic power generation, wind power generation, hydropower generation, and energy storage. The future power demand of each region can be referred to Table 1. The initial installed capacity and investment and construction costs of various power sources can be referred to Tables 2 and 3.

[0057] Table 4 shows a comparison of the economic efficiency of the method of the present invention compared to two traditional methods: the total system cost and the cost under the maximum and minimum scenarios of the two planning methods are shown in Table 3. The expected cost under this application is 2.52 trillion yuan, which is about 10.71% lower than that of Solution 2; the total cost under the maximum load scenario is 2.75 trillion yuan, a decrease of about 11.00%, and the cost under the minimum load scenario is 2.42 trillion yuan, a decrease of about 8.68%. This shows that the power supply planning obtained by using the present invention can achieve lower optimization results and has higher reliability and flexibility.

[0058] Table 5 compares the low-carbon performance of the proposed method compared to two traditional methods. The expected carbon emissions and carbon emissions under the maximum and minimum scenarios for both planning methods are significantly reduced. The proposed method expects carbon emissions to be approximately 22.45% of that in 2020, a decrease of approximately 5.51% compared to Option 2. The total cost under the maximum load scenario is reduced by approximately 3.33%, and the cost under the minimum load scenario is reduced by approximately 5.15%.

[0059] In summary, the method of the present invention can effectively reduce the system cost and system carbon emissions of power supply planning.

[0060] Table 1

[0061]

[0062]

[0063] Table 2

[0064]

[0065] Table 3

[0066]

[0067] Table 4

[0068]

[0069] Table 5

[0070]

[0071] The present invention is a power supply planning method that takes boundary uncertainty into consideration, and proposes a power supply structure planning theory. It considers the grid planning problem with uncertainty in load and power consumption boundaries. In use, on the basis of a given scenario tree, boundary conditions based on the model predictive control idea are introduced, and a power supply structure pre-planning model and an online rolling optimization power supply structure model are established. The example shows that compared with the traditional multi-stage random planning method, the planning method proposed by the present invention is more suitable for planning under uncertainty in future boundaries. The power supply structure planning model proposed by the present invention and the traditional multi-stage random planning model are explained and compared in detail. The results show that the method of the present invention can not only obtain better planning results, but also fully consider the uncertainty of boundary conditions and respond flexibly. The present invention has the advantages of constructing a power supply structure planning model, introducing model predictive control, realizing pre-planning, and reducing the impact through an online rolling strategy.

[0072] Example 2

[0073] like Figure 1-2 As shown, the power supply planning system considering boundary uncertainty includes a data acquisition module, a topology construction module, a planning prediction module and a planning update module. The power supply structure planning system considering planning boundary uncertainty is used to execute the above-mentioned power supply planning method considering boundary uncertainty;

[0074] The data acquisition module is used to obtain grid network parameters, power supply installed capacity parameters, inter-regional transmission line capacity and power, and natural resources in each region;

[0075] The topology building module is used to build a power planning prediction model based on the power grid network parameters and power supply and transmission line parameters output by the data acquisition module;

[0076] The planning and prediction module is used to predict power supply planning based on regional power balance, unexpected planning, peak load reserve, and network balance constraints, combined with the data acquisition module and the topology construction module;

[0077] The planning update module is used to perform rolling optimization at the current time node according to the prediction sequence of the planning prediction module to obtain a new power supply planning decision.

[0078] In this embodiment, the data acquisition module is connected to the topology construction module, the planning prediction module is connected to the data acquisition module and the topology construction module respectively, and the planning update module is connected to the data acquisition module, the topology construction module and the planning prediction module respectively.

[0079] The present invention is a power supply planning method that takes boundary uncertainty into consideration, and proposes a power supply structure planning theory. It considers the power grid planning problem with uncertainty in load and power consumption boundaries. In use, the lowest expected cost of the system during the planning period is first taken as the goal, and constraints such as power balance and natural resources based on the model predictive control idea are introduced to establish a power supply structure pre-planning model, and pre-plan the power supply structure under the expected values ​​of future boundary conditions to obtain a pre-planning decision sequence; further, through an online rolling optimization model, based on the pre-planning decision sequence, the current decision result is obtained and the initial and boundary conditions of the next round of pre-planning are updated; the present invention has the advantages of constructing a power supply structure planning model, introducing model predictive control, realizing pre-planning, and reducing the impact through an online rolling strategy.

[0080] Example 2

[0081] like Figure 1-2 As shown, a storage medium includes a computer-readable storage medium and a computer program / instruction, wherein the computer-readable storage medium is used to store the computer program / instruction; the computer program / instruction is used to control the above-mentioned power planning system considering boundary uncertainty to realize data calling and power structure evolution route.

[0082] The computer-readable storage medium is any available medium that can be stored by a computing device or a data center data storage device containing one or more available media.

[0083] The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state drive).

[0084] The present invention is a power supply planning method that takes boundary uncertainty into consideration, and proposes a power supply structure planning theory. It considers the power grid planning problem with uncertainty in load and power consumption boundaries. In use, the lowest expected cost of the system during the planning period is first taken as the goal, and constraints such as power balance and natural resources based on the model predictive control idea are introduced to establish a power supply structure pre-planning model, and pre-plan the power supply structure under the expected values ​​of future boundary conditions to obtain a pre-planning decision sequence; further, through an online rolling optimization model, based on the pre-planning decision sequence, the current decision result is obtained and the initial and boundary conditions of the next round of pre-planning are updated; the present invention has the advantages of constructing a power supply structure planning model, introducing model predictive control, realizing pre-planning, and reducing the impact through an online rolling strategy.

Claims

1. A power structure planning method considering planning boundary uncertainty, characterized by: The method comprises the following steps: Step 1: Input the power supply construction and load conditions of each zone in the long-term plan as the basic parameters of the model; Step 2: Generate a scenario tree of future power consumption and load by sampling uncertainty using the Monte Carlo simulation method, and generate a set of possible values ​​at different time nodes in the future; Step 3: Establish a rolling optimization power structure planning model based on model predictive control.

2. The power structure planning method considering planning boundary uncertainty according to claim 1, characterized in that: The step 3 of establishing a rolling optimization power structure planning model based on the model predictive control concept specifically includes the following steps: Step 3.1: Establish a power structure pre-planning model based on model predictive control; Step 3.2: Build an online rolling optimization power structure model; Step 3.3: Design an online rolling optimization process for power structure.

3. The power structure planning method considering planning boundary uncertainty according to claim 2, characterized in that: The establishment of the power structure pre-planning model based on model predictive control in step 3.1 is specifically as follows: the objective function of the power structure pre-planning is the expected total cost TC in the kth planning period K Minimum, where the total cost includes the expected cost of power supply investment and construction SC k , expected cost of investment and construction of inter-regional transmission lines LC k , expected operation and maintenance cost OM k 、Expected cost of power fuel FC k and the expected cost of transmission and distribution losses TE k : MinTC K (N)=SC k (N)+LC k (N)+OM k (N)+FC k (N)+TE k (N)(1)。 4. The power structure planning method considering planning boundary uncertainty according to claim 3, characterized in that: The boundary conditions for establishing the power structure pre-planning model based on model predictive control in step 3.1 are as follows: considering various constraints in actual power system operation, such as installed capacity constraints, power balance constraints, and natural resource constraints, and modifying traditional constraints in combination with the model predictive control algorithm: AG r,g,y,s (k) = AG r,g,y-1,s (k)+G r,g,y-1,s (k)-RG r,g,y-1,s (k)(9), the above formula describes the installed capacity constraints of various power sources, where, are the upper and lower limits of the newly built capacity of the g-th type power source in the r-th region at the y-th time node in the k-th iteration respectively; are the upper and lower limits of the retired capacity of the g-th type power supply in the r-th region at the y-th time node in the k-th iteration; G r,g,y,s (k) is the decommissioned capacity; The above formula describes the constraints of inter-regional transmission lines, where: is the amount of electricity transmitted by the transmission line between the two regions in the kth iteration; is the maximum operating hours of the transmission line between the two regions; is the minimum operating hours of the transmission line between two regions; The above formula describes the natural resource endowment constraint, where The upper limit of natural resource installed capacity for category g power source in region r; PS r,g,y,s (k) is the power generation of the g-type power source in the r-th region at the y-th time node of the k-th iteration; The upper limit of natural resource power generation for category g power source in region r; The above formula describes the power balance constraint within the region, where: They represent the upper and lower limits of the operating hours of the g-type power supply in the r-th area at the y-th time node; PD r,y Indicates the rth time node at the yth time i Electricity consumption in the region; LD r,y Indicates the rth time node at the yth time i Regional load; PR is the reserve factor of the system load; FS r,g,y Indicates the power factor of the g-type power supply in the r-th area at the y-th time node; Indicates the power factor of the transmission line between two areas.

5. The power structure planning method considering planning boundary uncertainty according to claim 2, characterized in that: The online rolling optimization power structure model in step 3.2 is specifically constructed as follows: the entire planning period is divided into T time nodes, and the power structure planning model in step 3.1 is solved to obtain the construction capacity of various power sources in the region with a time span of N and the construction capacity construction plan of the inter-regional interconnection line: After the iterative cycle shown below, the power structure evolution path result is obtained: G r,g,k,s =G r,g,1,s (k),k=1,2,...,(T-N+1)(20), AG r,g,k,s =AG r,g,1,s (k),k=1,2,...,(T-N+1)(22), G r,g,T-N+1+i,s =G r,g,i+1,s (T-N+1),i=1,2,...,N-1(24), AG r,g,T-N+1+i,s =AG r,g,i,s (T-N+1),i=1,2,...,N-1(26), 6. The power structure planning method considering planning boundary uncertainty according to claim 2, characterized in that: The design of the online rolling optimization process of the power structure in step 3.3 is specifically as follows: based on the pre-planning decision sequence obtained from the power structure pre-planning model, a current time node decision is generated, and new initial conditions and boundary conditions are further generated based on the current time node decision, until the online cyclic power planning of all time nodes is completed to obtain the final decision sequence.

7. A power structure planning system that considers planning boundary uncertainty, comprising a data acquisition module, a topology construction module, a planning prediction module, and a planning update module, characterized in that: The power structure planning system considering planning boundary uncertainty is used to execute the power structure planning method considering planning boundary uncertainty according to any one of claims 1 to 6; The data acquisition module is used to obtain grid network parameters, power supply installed capacity parameters, inter-regional transmission line capacity and power, and natural resources in each region; The topology building module is used to build a power planning prediction model based on the power grid network parameters and power supply and transmission line parameters output by the data acquisition module; The planning and prediction module is used to predict power supply planning based on regional power balance, unexpected planning, peak load reserve, and network balance constraints, combined with the data acquisition module and the topology construction module; The planning update module is used to perform rolling optimization at the current time node according to the prediction sequence of the planning prediction module to obtain a new power supply planning decision.

8. A storage medium, characterized in that: It includes a computer-readable storage medium and a computer program / instruction, wherein the computer-readable storage medium is used to store the computer program / instruction; the computer program / instruction is used to control a power structure planning system that considers planning boundary uncertainty as described in any one of claims 1 to 7 to realize data calling and power structure evolution route.

9. A storage medium according to claim 8, characterized in that: The computer-readable storage medium is any available medium that can be stored by a computing device or a data center data storage device containing one or more available media.

10. A storage medium according to claim 9, characterized in that: The usable medium is a magnetic medium, an optical medium or a semiconductor medium.

Images