A power supply point planning method and device, a terminal device and a storage medium

Abstract

The application discloses a power supply point planning method and device, terminal equipment and storage medium, and belongs to the technical field of power grid planning. The method comprises the following steps: acquiring real-time operation data and a prediction planning strategy of a power grid to be planned; generating an initial power supply point planning scheme according to acquired architecture parameters and power supply characteristic parameters; determining the average change frequency of the prediction planning strategy for each point position in each scheme; evaluating the average change frequency to obtain a planning robustness coefficient; recording a point position with a planning robustness coefficient less than a preset robustness threshold as a failure point position; taking the sum of power difference values between expected power supply power of each failure point position and maximum dispatchable compensation power of a power grid side as total power shortage; simulating a constructed power grid transient stability simulation model with the total power shortage as a disturbance, obtaining a power grid stability margin index, and screening a final power supply point planning scheme from the scheme; and through implementation of the application, the problem that the prior art does not consider the influence of dynamic factors is solved.

Description

Technical Field

[0001] This invention relates to the field of power grid planning technology, and in particular to a power source deployment planning method, apparatus, terminal equipment, and storage medium. Background Technology

[0002] In power system planning, power source location planning is a crucial link in ensuring the safe and stable operation of the power grid. The rationality of its plan directly affects the power grid's power supply reliability, energy utilization efficiency, and socio-economic development. Currently, with the large-scale integration of renewable energy and the transformation and upgrading of the power system, the dynamics and uncertainties of power grid operation have significantly increased, placing higher demands on power source location planning.

[0003] Existing power source deployment planning methods mostly focus on optimizing the electrical characteristics and technical and economic indicators of the power grid itself. These technical solutions generally focus on the technical parameters and economic calculations within the power grid, without fully considering the impact of dynamic planning factors on the corresponding areas of the deployment locations. This results in deviations between the final planning scheme and the actual scenario, and makes it impossible to guarantee the long-term stable operation of the power source deployment. Summary of the Invention

[0004] This invention provides a power supply deployment planning method, apparatus, terminal equipment, and storage medium, which can effectively solve the problem that the prior art does not fully consider the influence of dynamic planning factors on the corresponding area of ​​the deployment location.

[0005] An embodiment of the present invention provides a power supply site planning method, comprising: Obtain the architecture parameters, power characteristic parameters, real-time operating data, and predictive planning strategies of the power grid to be planned; Several initial power supply placement planning schemes are generated based on the architecture parameters and the power characteristic parameters. For each location in the initial power supply layout plan, determine the average change frequency of the predictive planning strategy for the corresponding area. Based on the predictive planning strategy and the average change frequency, perform verification and evaluation to obtain the planning robustness coefficient of the location. Locations with a planned robustness coefficient less than a preset robustness threshold are marked as failure points. Based on the initial power supply layout planning scheme, real-time operation data, and architecture parameters, the power difference value of each failure point is calculated to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side. The sum of the power differences of each failure point is used as the total power deficit of the initial power supply layout planning scheme. A power grid transient stability simulation model is constructed based on the architecture parameters and real-time operating data. The transient stability simulation model is then subjected to transient stability simulation with the total power deficit as the disturbance condition to obtain the power grid stability margin index of the initial power source deployment planning scheme. The final power source deployment plan is obtained by selecting from the initial power source deployment plan based on the power grid stability margin index.

[0006] Furthermore, the forecasting and planning strategy includes forecast accuracy, load distribution requirements, and power supply capacity information; Based on the predictive planning strategy and the average frequency of change, the robustness coefficient of the site selection is obtained through verification and evaluation, including: Based on the predictive planning strategy corresponding to the location of the power supply points, a conflict verification was performed with the initial power supply point planning scheme. The predictive planning strategy with no spatial overlap of the power supply points and no conflict in the construction sequence was selected as the first strategy. The correlation between the first strategy and the power distribution of the power grid to be planned is verified, and the first strategy that will cause the change value of regional power load to be greater than the preset change threshold after implementation is selected as the feasible planning strategy. The single-strategy impact value is obtained by calculating the dot product of the average change frequency and the prediction accuracy value corresponding to the feasible planning strategy. The strategy change value is obtained by weighting the single-strategy impact value and the number of feasible planning strategies based on the entropy weight method. Based on the power supply capacity information and the load distribution demand assessment, the distribution planning coefficient is obtained. The normalized difference between the distribution planning coefficient and the strategy change value is used as the planning robustness coefficient of the distribution location.

[0007] Furthermore, based on the power supply capacity information and the load distribution demand assessment, the distribution planning coefficient is obtained, including: By comparing the power supply capacity information of the deployment locations with the load deployment requirements corresponding to the feasible planning strategies, if the rated power supply capacity of the power supply capacity information meets the load deployment requirements, the preset value is used as the deployment planning coefficient. If the rated power supply capacity of the power supply capacity information does not meet the load distribution requirements, the grid topology location corresponding to the distribution location is obtained based on the architecture parameters. The power dispatch response speed and power dispatch capacity value are evaluated based on the grid topology location. The dispatch flexibility is calculated by weighting the power dispatch response speed and power dispatch capacity value. Based on the location of the power grid topology, determine whether power grid power flow scheduling can meet the load distribution requirements. If so, the site planning coefficient is determined based on the scheduling flexibility; where scheduling flexibility and site planning coefficient are positively correlated. If not, the number of additional deployment points is estimated based on the power gap corresponding to the load deployment demand, the number of additional spaces is estimated based on the area around the deployment point location where additional deployment points can be added, and the deployment planning coefficient is calculated based on the difference between the number of additional deployment points and the number of additional spaces, according to the scheduling flexibility.

[0008] Furthermore, based on the initial power supply deployment plan, real-time operational data, and architecture parameters, the power difference value used to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side is calculated for each failure point, including: From the initial power supply layout plan, extract the rated power that each failure point is pre-assigned to, as the expected power supply for the failure point; Based on real-time operating data, the rated capacity, real-time output, and total system reserve capacity of adjacent non-failure points are obtained. The maximum additional power of adjacent non-failure points is calculated based on the rated capacity and real-time output. The maximum transmission capacity of supplementary power is calculated based on the line topology, line impedance, and line power flow limitations in the architecture parameters. The sum of the system's total reserve capacity and the maximum additional power is taken as the total power increment that the grid side can provide. The minimum value between the total power increment and the maximum transmission capacity of the supplementary power is taken as the maximum dispatchable compensation power of the grid side corresponding to the failure point. The difference between the expected power supply and the maximum dispatchable compensation power on the grid side is taken as the power difference at the failure point; where the maximum dispatchable compensation power on the grid side is greater than or equal to the expected power supply, the power difference at the failure point is recorded as 0.

[0009] Furthermore, using the total power deficit as a disturbance condition, transient stability simulation is performed on the power grid transient stability simulation model to obtain the power grid stability margin index of the initial power source deployment planning scheme, including: Power flow calculations are performed on the power grid transient stability simulation model based on real-time operating data to determine the initial steady-state operating points of the voltage, phase angle, generator output, and load power of each node in the power grid to be planned. The effectiveness of the power grid transient stability simulation model is verified based on the initial steady-state operating points and real-time operating data. After verifying the effectiveness of the power grid transient stability simulation model, transient stability simulation was performed using the total power deficit as a disturbance to obtain the dynamic change trajectory of generator power angle, bus voltage and system frequency during the simulation process; Based on the dynamic change trajectory, the calculated power angle stability margin, voltage stability margin, frequency stability margin, and critical cut-off time of the power grid to be planned are used as the power grid stability margin indicators corresponding to the initial power source layout planning scheme.

[0010] Furthermore, based on the grid stability margin index, the final power source deployment plan is obtained from the initial power source deployment plan, including: The grid stability margin index corresponding to each initial power source layout planning scheme is quantitatively weighted to obtain the comprehensive stability score of each initial power source layout planning scheme; wherein, the weighting weight is preset based on the power supply reliability level requirements of the grid to be planned. Based on the comprehensive stability score, all initial power supply site planning schemes are ranked, and the initial power supply site planning scheme with the highest ranking is selected as the final power supply site planning scheme. If two or more initial power supply layout plans have the same overall stability score and both are the maximum value, the plan with the longest critical clearing time shall be selected as the final power supply layout plan; if the critical clearing times are the same, the plan with the fewest failure points shall be selected as the final power supply layout plan.

[0011] Furthermore, the architecture parameters include line topology, line impedance, and load distribution; the power supply characteristic parameters include power supply type, power supply output curve, and power supply deployment cost. Based on the architecture parameters and the power characteristic parameters, several initial power supply placement plans are generated, including: Based on the line topology, the line impedance, and the load distribution, the boundary constraints of the power grid to be planned are determined. With the goal of minimizing operating costs, and under boundary constraints, a multi-objective optimization algorithm is used to generate several power supply point combinations based on the line topology, line impedance, load distribution, power supply type, and power supply output curve. An initial power supply layout plan is generated based on each power supply layout combination; each initial power supply layout plan includes the layout locations.

[0012] As an improvement to the above solution, another embodiment of the present invention provides a power supply site planning device, comprising: The data acquisition module is used to acquire the architecture parameters, power characteristic parameters, real-time operating data, and predictive planning strategies of the power grid to be planned. The initial power deployment planning scheme generation module is used to generate several initial power deployment planning schemes based on the architecture parameters and the power characteristic parameters. The planning robustness coefficient calculation module is used to determine the average change frequency of the predicted planning strategy for each location in each initial power supply location planning scheme, and to verify and evaluate the planning robustness coefficient of the location based on the predicted planning strategy and the average change frequency. The total power deficit determination module is used to mark the locations where the planned robustness coefficient is less than the preset robustness threshold as failure points. Based on the initial power supply layout planning scheme, real-time operation data and architecture parameters, it calculates the power difference value of each failure point to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side. The sum of the power differences of each failure point is used as the total power deficit of the initial power supply layout planning scheme. The power grid stability margin index evaluation module is used to construct a power grid transient stability simulation model based on architecture parameters and real-time operating data, and to perform transient stability simulation on the power grid transient stability simulation model with the total power deficit as the disturbance condition, so as to obtain the power grid stability margin index of the initial power source layout planning scheme. The final power distribution planning scheme determination module is used to select the final power distribution planning scheme from the initial power distribution planning scheme based on the power grid stability margin index.

[0013] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a power distribution planning method as described in the above embodiments.

[0014] Another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform a power distribution planning method as described in the above embodiment.

[0015] By implementing this invention, at least the following beneficial effects are achieved: This invention provides a power supply deployment planning method, apparatus, terminal equipment, and storage medium. The method can simultaneously acquire the predictive planning strategy of the power grid to be planned, and use it together with architecture parameters, power supply characteristic parameters, and real-time operating data as the planning basis. It places external dynamic planning factors alongside internal power grid parameters, overcoming the shortcomings of existing technologies that neglect the influence of external planning from the data input level. For each deployment location, it performs verification and evaluation based on the predictive planning strategy and its average change frequency to obtain a planning robustness coefficient, transforming the abstract regional dynamic planning influence into a quantifiable evaluation indicator, no longer relying solely on electrical performance and economics as the basis for deployment decisions. Then, deployment locations with unsatisfactory planning robustness coefficients or those susceptible to external dynamic planning influences are marked as failure points. Deployment locations that conflict with the actual scenario or are difficult to stably implement are eliminated in advance before scheme selection, avoiding a disconnect between the final scheme and actual needs. Finally, power deficits are calculated based on failure points, and transient stability simulations are conducted using real-time power grid operating data. The final scheme is selected using the power grid stability margin index, ensuring that the planning scheme not only meets internal electrical and economic requirements but also adapts to external planning changes and guarantees long-term stable operation. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a power supply site planning method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a power supply layout planning device provided in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] See Figure 1 To address the problem that existing technologies do not fully consider the dynamic planning factors affecting the corresponding areas of power supply deployment locations, an embodiment of the present invention provides a flowchart of a power supply deployment planning method, including: S1. Obtain the architecture parameters, power characteristic parameters, real-time operating data and predictive planning strategies of the power grid to be planned; Specifically, the architecture parameters are the physical and electrical structure and operational constraints of the power grid to be planned. These are the fundamental data for power grid planning, including line topology, line impedance, and load distribution. Line topology includes the connection relationships between grid nodes and lines; line impedance includes the resistance and reactance parameters of transmission and distribution lines; and load distribution includes the size and spatial distribution of active and reactive loads at each node within the planning area. Power source characteristic parameters are the inherent attribute parameters of various power sources to be connected to the grid, including power source type, power output curve, and power source deployment cost. Power source types include thermal power, hydropower, photovoltaic, wind power, and energy storage; power output curves include the daily and annual active power output variation patterns; and power source deployment cost includes the full lifecycle cost of power source construction, land acquisition, and operation and maintenance. Real-time operational data consists of real-time grid status data collected from the power grid energy management system (EMS) and the supervisory control and data acquisition system (SCADA), including node voltage, phase angle, real-time generator output, real-time load power, total system reserve capacity, and line power flow. This data is used to provide an accurate initial operating point for transient stability simulation.

[0019] Specifically, the forecasting planning strategy refers to the plans issued by the government's urban construction, natural resources, and transportation departments. These are medium- to long-term external dynamic plans, including land use change plans, large-scale infrastructure plans, industrial park plans, and road and transportation plans.

[0020] To illustrate, the system collects architecture parameters and power characteristic parameters from the power grid planning database; collects real-time operation data from the EMS / SCADA system; and collects the predictive planning strategies for the deployment area from local government planning departments. The average change frequency of each strategy is statistically analyzed simultaneously to achieve full acquisition of internal electrical parameters and external planning parameters.

[0021] S2. Generate several initial power supply layout planning schemes based on the architecture parameters and the power characteristic parameters. Specifically, the initial power supply deployment plan consists of multiple alternative power supply deployment schemes generated based on the internal grid architecture parameters and power supply characteristic parameters, including basic information such as deployment location, power supply capacity, and line access method.

[0022] To illustrate, with the constraints of grid safety operation and power supply demand satisfaction, and based on the architecture parameters and power characteristic parameters, several sets of compliant initial alternative schemes are generated using optimization algorithms, namely initial power supply deployment planning schemes. Each set of initial power supply deployment planning schemes specifies the deployment location, power capacity and access method.

[0023] Preferably, the architecture parameters include line topology, line impedance, and load distribution; the power supply characteristic parameters include power supply type, power supply output curve, and power supply deployment cost. Based on the architecture parameters and the power characteristic parameters, several initial power supply placement plans are generated, including: Based on the line topology, the line impedance, and the load distribution, the boundary constraints of the power grid to be planned are determined. With the goal of minimizing operating costs, and under boundary constraints, a multi-objective optimization algorithm is used to generate several power supply point combinations based on the line topology, line impedance, load distribution, power supply type, and power supply output curve. An initial power supply layout plan is generated based on each power supply layout combination; each initial power supply layout plan includes the layout locations.

[0024] Specifically, boundary constraints are mandatory constraints in power grid planning, including the N-1 safety criterion, line transmission capacity constraints, power source rated capacity constraints, site selection constraints, and construction sequence constraints. The multi-objective optimization algorithm balances the dual objectives of minimizing operating costs and maximizing power supply reliability; the power source site selection combination is the optimal combination of site location, power source capacity, and line access method, and is the core component of the initial scheme.

[0025] In a preferred embodiment of the present invention, based on line topology, impedance, and load distribution, boundary constraints across all dimensions—N-1 safety criteria, line transmission capacity, power supply capacity, land use, and timing—are clearly defined. With the dual optimization objectives of minimizing operating costs and maximizing power supply reliability, a multi-objective optimization algorithm is employed to generate several compliant power supply deployment combinations under these boundary constraints. Each power supply deployment combination corresponds to a complete initial plan, which includes deployment location, power supply capacity, line access method, and construction timing. Illustratively, the initial power supply deployment planning scheme can be generated using existing technologies.

[0026] S3. For each location in the initial power supply location planning scheme, determine the average change frequency of the prediction planning strategy for the corresponding area. Based on the prediction planning strategy and the average change frequency, perform verification and evaluation to obtain the planning robustness coefficient of the location. Specifically, the average frequency of change is the average frequency of adjustments, changes, and revisions to a single predictive planning strategy within the planning period, reflecting the stability of the planning strategy. A higher frequency indicates a greater risk of planning changes. The planning robustness coefficient quantifies the ability of site selection locations to withstand external planning changes, load fluctuations, and power grid disturbances, as well as their long-term stable operation capability. A higher value indicates a more stable site selection location and a lower implementation risk.

[0027] To illustrate, for each deployment location, a predictive planning strategy for the corresponding area is matched, and the average frequency of strategy change is determined. Effective strategies are screened through conflict verification and correlation verification. Combining the risk of strategy change and the flexibility of power supply at the deployment location, the planning robustness coefficient of that location is calculated.

[0028] Preferably, the forecasting and planning strategy includes forecast accuracy, load distribution requirements, and power supply capacity information; Based on the predictive planning strategy and the average frequency of change, the robustness coefficient of the site selection is obtained through verification and evaluation, including: Based on the predictive planning strategy corresponding to the location of the power supply points, a conflict verification was performed with the initial power supply point planning scheme. The predictive planning strategy with no spatial overlap of the power supply points and no conflict in the construction sequence was selected as the first strategy. The correlation between the first strategy and the power distribution of the power grid to be planned is verified, and the first strategy that will cause the change value of regional power load to be greater than the preset change threshold after implementation is selected as the feasible planning strategy. The single-strategy impact value is obtained by calculating the dot product of the average change frequency and the prediction accuracy value corresponding to the feasible planning strategy. The strategy change value is obtained by weighting the single-strategy impact value and the number of feasible planning strategies based on the entropy weight method. Based on the power supply capacity information and the load distribution demand assessment, the distribution planning coefficient is obtained. The normalized difference between the distribution planning coefficient and the strategy change value is used as the planning robustness coefficient of the distribution location.

[0029] Specifically, the prediction accuracy value represents the credibility and probability of the implementation of the predicted planning strategy. It is evaluated by the planning entity and historical implementation data, and ranges from 0 to 1, with higher values ​​indicating a higher likelihood of implementation. Load distribution requirements represent the new active and reactive load demands that the distribution location must meet after the implementation of the feasible planning strategy; it is the core verification basis for the power supply capacity of the distribution location. Power supply capacity information includes the current designed rated power, power supply range, and load supply limit of the distribution location; it represents the inherent power supply capacity of the distribution location itself. Conflict verification determines whether there is spatial overlap, construction timing conflict, or conflict with prohibited construction rules between the predicted planning strategy and the initial distribution plan. Correlation verification determines whether the implementation of the predicted planning strategy will cause significant changes in regional load or alter grid topology constraints. The single strategy impact value is the dot product of the average change frequency and the prediction accuracy value, characterizing the degree of impact of a single planning strategy on the distribution location. The strategy change value is calculated using the entropy weight method based on the single strategy impact value and the number of feasible strategies, quantifying the overall change risk of external planning. The distribution planning coefficient assesses the flexible adaptability of the distribution location's own power supply capacity to meet load demands. The normalized difference refers to the difference calculated after normalizing the location planning coefficients and the strategy change values, and is used as the planning robustness coefficient.

[0030] Schematic, by comparing the spatial coordinates, construction period, and planning rules of the predicted planning strategy with the initial site layout plan, strategies with overlapping site areas, conflicting construction schedules, or those containing labels prohibiting the construction of power facilities are eliminated, leaving the first strategy. Then, the impact of implementing the first strategy is analyzed, and strategies with regional power load changes exceeding a preset threshold (10%) or altering grid topology constraints are selected as feasible planning strategies; unrelated strategies such as those related to food safety and education policies are eliminated. Next, the average change frequency multiplied by the prediction accuracy is calculated to obtain the impact value of a single strategy; the total impact value of single strategies is weighted by the number of feasible strategies using the entropy weight method to obtain the strategy change value, with higher values ​​indicating greater risk of planning changes. Finally, the power supply capacity information of the site layout is compared with the load layout demand to evaluate the site layout planning coefficient; the site layout planning coefficient and the strategy change value are normalized, and the difference between the two is calculated, which is the planning robustness coefficient of the site layout location.

[0031] In a preferred embodiment of the present invention, geographic information system (GIS) data is used to perform collision detection between the spatial coordinate range of the predicted planning strategy and the spatial coordinate range of the proposed power supply location in the power supply deployment scheme. If the two overlap spatially, or are determined to be logically conflicting based on attribute tags such as "prohibited construction" in the strategy, the strategy is filtered out. The strategy without conflict after filtering is the first strategy. The first strategy is mapped to a feature vector (such as type, expected new load) and input into the association rule engine. If the strategy type is non-power related (such as food safety) and the expected new load is zero or below a threshold, it is determined to be unrelated and filtered out. Conversely, if the strategy belongs to land use change, large-scale infrastructure, or the resulting load change reaches a preset threshold, it is determined to be related and retained as a feasible planning strategy.

[0032] For each feasible planning strategy, the dot product of its prediction accuracy and average change frequency is calculated to obtain the single-strategy impact value. The dot product operation implies that the higher the prediction accuracy of a strategy and the higher its change frequency, the greater its impact on the placement plan's risk. Then, the entropy weight method is used to weight the single-strategy impact values ​​and the number of strategies for all feasible planning strategies. A larger number of feasible strategies implies a more complex future direction of change; the entropy weight method assigns a higher weight to the number of strategies, and the final calculated strategy change value reflects the overall uncertainty risk brought by all feasible planning strategies. After normalizing the strategy change value and the placement planning coefficient, the difference between the two is calculated. A larger strategy change value indicates higher external risk, resulting in a lower final planning robustness coefficient; conversely, a larger placement planning coefficient indicates stronger inherent resilience, resulting in a higher final planning robustness coefficient.

[0033] This embodiment employs a dual-verification strategy to accurately eliminate conflicts and irrelevant planning, avoiding invalid assessments and improving the accuracy of robustness calculations. It also digitally quantifies the risks of external planning changes, achieving standardized and quantifiable robustness assessments. By combining the dual-dimensional calculations of power supply flexibility and external risks, the assessment results closely align with actual engineering scenarios.

[0034] Preferably, the distribution planning coefficient is obtained based on the power supply capacity information and the load distribution demand assessment, including: By comparing the power supply capacity information of the deployment locations with the load deployment requirements corresponding to the feasible planning strategies, if the rated power supply capacity of the power supply capacity information meets the load deployment requirements, the preset value is used as the deployment planning coefficient. If the rated power supply capacity of the power supply capacity information does not meet the load distribution requirements, the grid topology location corresponding to the distribution location is obtained based on the architecture parameters. The power dispatch response speed and power dispatch capacity value are evaluated based on the grid topology location. The dispatch flexibility is calculated by weighting the power dispatch response speed and power dispatch capacity value. Based on the location of the power grid topology, determine whether power grid power flow scheduling can meet the load distribution requirements. If so, the site planning coefficient is determined based on the scheduling flexibility; where scheduling flexibility and site planning coefficient are positively correlated. If not, the number of additional deployment points is estimated based on the power gap corresponding to the load deployment demand, the number of additional spaces is estimated based on the area around the deployment point location where additional deployment points can be added, and the deployment planning coefficient is calculated based on the difference between the number of additional deployment points and the number of additional spaces, according to the scheduling flexibility.

[0035] Specifically, dispatch flexibility is a comprehensive indicator that characterizes the power dispatch response speed and dispatch carrying capacity under the power grid topology; a higher value indicates more convenient dispatch. The number of additional power stations is the number of new power stations required when both the existing power supply capacity and grid dispatch cannot meet load demand; the number of additional power stations in terms of space is the maximum number of new power stations that can be accommodated by the available land surrounding the new power station location. The difference between the number of additional power stations and the number of additional power stations represents the spatial expansion capacity of the dispatch area; a larger difference indicates greater expansion space.

[0036] Schematic, the rated power supply capacity of the deployment points is directly compared with the load deployment requirements. If the power supply capacity is greater than or equal to the load requirements, the deployment planning coefficient is set to the preset maximum value of 1.0. Then, based on the architecture parameters, the grid topology location of the deployment points is obtained. First, it is determined whether the load requirements can be met through grid power flow scheduling, and then the scheduling flexibility is calculated. If the scheduling meets the scenario, the scheduling flexibility is obtained by weighting the power dispatch response speed and power dispatch capability value using the entropy weight method. The scheduling flexibility is positively correlated with the deployment planning coefficient; the higher the flexibility, the larger the deployment planning coefficient. If the scheduling does not meet the scenario, the number of additional deployment points is estimated based on the power gap; the number of additional spaces is assessed based on the available additional area around the deployment points; then the difference in quantity is calculated, and the deployment planning coefficient is calculated by combining the scheduling flexibility and the difference in quantity. The larger the difference, the larger the deployment planning coefficient.

[0037] In a preferred embodiment of the present invention, the power supply capacity information (rated power supply capacity) of the deployment location is compared with the total load deployment demand brought about by all feasible planning strategies. If the rated power supply capacity is greater than or equal to the total load demand, it indicates that the current scheme itself can meet future demand, and the deployment planning coefficient can be directly set to the maximum value (e.g., 1). If the power supply capacity itself is insufficient, it is further determined whether it can be met through grid dispatch. First, the topological location of the deployment location in the grid is obtained based on the grid architecture parameters, such as node number and connection relationship. Then, the power dispatch response speed and power dispatch capability value are evaluated based on the topological location. For example, the closer the electrical distance, the larger the tie line capacity, and the higher the node degree, the higher the power dispatch capability value. The two are weighted and summed to obtain the dispatch flexibility, such as dispatch flexibility = a * power dispatch response speed + b * power dispatch capability value. Then, based on the grid topology location, power flow calculation is performed to analyze whether power from other areas can be transmitted to this point to make up for the gap by adjusting the output of adjacent nodes or switching lines. If it can be met by dispatch, the deployment planning coefficient is directly determined by the dispatch flexibility, and the two are positively correlated. For example, the site planning coefficient equals the dispatch flexibility. This means that even if the site's own capacity is insufficient, if the grid dispatch capability is strong, the planning coefficient for that site can still be high. If dispatch cannot meet the demand, it means that additional power sources (spatial expansion) must be added around the site location to satisfy the demand. First, based on the total power gap and the single-unit capacity of the standard power source, the number of additional sites needed is estimated (the number of additional sites). Then, spatial information around the site location is obtained, such as the area of ​​vacant land and the roof area of ​​available buildings. Combined with the single-site footprint of the power source facilities, the maximum number of additional sites that can be added is estimated (the number of additional spaces). Finally, dispatch flexibility and the difference in quantity are considered comprehensively. The site planning coefficient is positively correlated with dispatch flexibility and the difference between the number of additional spaces and the number of additional sites. For example, the site planning coefficient = dispatch flexibility + (the number of additional spaces - the number of additional sites). The larger the difference, the more physical space is available to compensate, and the higher the planning coefficient; if the difference is negative, it means that there is insufficient space, and the planning coefficient will be very low.

[0038] By implementing this embodiment, the quantitative scheduling capability and spatial expansion capability are improved, and the calculation of the site planning coefficient is more accurate and in line with reality; sites with scheduling difficulties and insufficient space are identified in advance, reducing the cost of later modification and replanning.

[0039] S4. Mark the locations where the planned robustness coefficient is less than the preset robustness threshold as failure points. Based on the initial power supply layout planning scheme, real-time operation data and architecture parameters, calculate the power difference value of each failure point to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side. The sum of the power differences of each failure point is used as the total power deficit of the initial power supply layout planning scheme. Specifically, the preset robustness threshold is a critical value of the planning robustness coefficient pre-set based on the power grid reliability level and regional importance, used to determine whether there is a risk of failure at the deployment location. A failure point refers to a deployment location whose planning robustness coefficient is lower than the preset robustness threshold, making it susceptible to failure to be put into operation or operate stably due to external planning changes, spatial constraints, or scheduling limitations. The expected power supply is the rated active power supply that the failure point is pre-set to bear in the initial power supply deployment plan, representing the design power supply capacity of that failure point. The maximum dispatchable compensation power is the maximum active power that the power grid can supplement to the failure point through system reserve capacity, additional power generation from adjacent normal points, and line transmission; it is the upper limit of the power grid's scheduling capacity to cope with point failures. The power difference is the difference between the expected power supply at the failure point and the maximum dispatchable compensation power on the grid side; this difference is considered an effective power deficit only when the expected power supply is greater than the compensation power. The total power deficit is the sum of the effective power differences of all failure points within the initial power supply deployment plan, and is the core indicator characterizing the power supply gap of the plan.

[0040] Indicatively, points with a planning robustness coefficient less than a preset robustness threshold are marked as failure points; the expected power supply of the failure points is extracted, and the maximum dispatchable compensation power is calculated by combining the system's reserve capacity, the power generation capacity of adjacent points, and the line transmission capacity; only the effective difference between the expected power and the compensation power is counted, and the summation is used to obtain the total power deficit of the scheme.

[0041] Preferably, based on the initial power supply layout plan, real-time operating data, and architecture parameters, the power difference value used to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side is calculated at each failure point, including: From the initial power supply layout plan, extract the rated power that each failure point is pre-assigned to, as the expected power supply for the failure point; Based on real-time operating data, the rated capacity, real-time output, and total system reserve capacity of adjacent non-failure points are obtained. The maximum additional power of adjacent non-failure points is calculated based on the rated capacity and real-time output. The maximum transmission capacity of supplementary power is calculated based on the line topology, line impedance, and line power flow limitations in the architecture parameters. The sum of the system's total reserve capacity and the maximum additional power is taken as the total power increment that the grid side can provide. The minimum value between the total power increment and the maximum transmission capacity of the supplementary power is taken as the maximum dispatchable compensation power of the grid side corresponding to the failure point. The difference between the expected power supply and the maximum dispatchable compensation power on the grid side is taken as the power difference at the failure point; where the maximum dispatchable compensation power on the grid side is greater than or equal to the expected power supply, the power difference at the failure point is recorded as 0.

[0042] Specifically, adjacent non-failure points are power supply locations around the failure point that meet the robustness coefficient requirements and are capable of normal operation; they are the core supplementary power sources after a failure point. Maximum additional power generation is the maximum active power that adjacent non-failure points can generate within their rated capacity limits. Maximum supplementary power transmission capacity is the upper limit of supplementary power that can be transmitted under the conditions of line topology, impedance, and power flow constraints, provided that the N-1 safety criterion is met. Total power increment is the sum of the system's total reserve capacity and the maximum additional power generation of adjacent non-failure points, representing the total supplementary power that the grid can provide.

[0043] Schematic, the rated active power supply of the failed points is extracted directly from the initial power supply layout plan as the expected power supply. Then, the maximum additional power supply to adjacent points is calculated. The rated capacity and real-time output of adjacent non-failed points are obtained from real-time operational data; the difference between the two is the maximum additional power supply. Next, the maximum transmission capacity of the supplementary power is calculated. Based on line topology, impedance, and power flow limitations, and strictly meeting the N-1 safety criterion, the maximum supplementary power that the line can transmit is calculated. Then, the maximum dispatchable compensation power is calculated: total power increment = total system reserve capacity + maximum additional power supply; maximum dispatchable compensation power = min(total power increment, maximum transmission capacity of supplementary power). Finally, the power difference is calculated. If the maximum dispatchable compensation power ≥ the expected power supply, the power difference is recorded as 0; otherwise, the power difference = expected power supply - maximum dispatchable compensation power.

[0044] By implementing this embodiment, only the effective power difference is counted, avoiding invalid calculations, and the data is more reliable; the calculation logic is based on real-time power grid operation data and dynamically adapts to the power grid operation status.

[0045] S5. Construct a power grid transient stability simulation model based on the architecture parameters and real-time operating data. Perform transient stability simulation on the power grid transient stability simulation model with the total power deficit as the disturbance condition to obtain the power grid stability margin index of the initial power supply layout planning scheme. Specifically, the power grid transient stability simulation model is a dynamic simulation model of the power system built based on power grid architecture parameters and component parameters. It can simulate the dynamic response of the power grid under disturbances such as power deficit and grid disconnection. The power grid stability margin index is a quantitative indicator characterizing the transient stability capability of the power grid under power deficit disturbances, including power angle stability margin, voltage stability margin, frequency stability margin, and critical disconnection time.

[0046] Specifically, a power grid transient stability simulation model is constructed based on power system simulation software.

[0047] Indicatively, a transient simulation model of the power grid is built based on the architecture parameters, and real-time operating data is imported to complete the model initialization and power flow calculation. Taking the total power deficit as the disturbance condition, the real scenario of the failure point exiting operation is simulated, and the system differential equation is solved by numerical integration method to obtain the power grid stability margin index.

[0048] Preferably, the transient stability simulation model of the power grid is performed using the total power deficit as a disturbance condition to obtain the power grid stability margin index of the initial power source deployment plan, including: Power flow calculations are performed on the power grid transient stability simulation model based on real-time operating data to determine the initial steady-state operating points of the voltage, phase angle, generator output, and load power of each node in the power grid to be planned. The effectiveness of the power grid transient stability simulation model is verified based on the initial steady-state operating points and real-time operating data. After verifying the effectiveness of the power grid transient stability simulation model, transient stability simulation was performed using the total power deficit as a disturbance to obtain the dynamic change trajectory of generator power angle, bus voltage and system frequency during the simulation process; Based on the dynamic change trajectory, the calculated power angle stability margin, voltage stability margin, frequency stability margin, and critical cut-off time of the power grid to be planned are used as the power grid stability margin indicators corresponding to the initial power source layout planning scheme.

[0049] Specifically, the initial steady-state operating point is the set of steady-state operating parameters when the power grid is undisturbed, including node voltage, phase angle, generator output, and load power. Validity verification is the process of verifying the consistency between the steady-state calculation results of the simulation model and the real-time operating data of the power grid, ensuring the accuracy of the model. The dynamic change trajectory refers to the curves showing the changes in generator power angle, bus voltage, and system frequency over time during the simulation process, and is the core basis for judging power grid stability. The critical clearing time is the maximum fault clearing time for the power grid to withstand power deficit disturbances without losing stability, and is a core indicator of power grid stability margin.

[0050] In a preferred embodiment of the present invention, power flow calculations are performed on the simulation model based on real-time operating data to determine the initial steady-state operating point. The simulation results are compared with the real-time data to verify the model's effectiveness and ensure its accuracy. After the simulation model verification is passed, a real fault scenario of the failure point exiting operation is simulated using the total power deficit as the disturbance condition. The system differential equations are solved by numerical integration using the improved Euler method or the trapezoidal method to obtain the dynamic change trajectories of generator power angle, bus voltage, and system frequency. Finally, based on the dynamic change trajectories, the power angle stability margin, voltage stability margin, frequency stability margin, and critical cut-off time are calculated and summarized into the grid stability margin index of the scheme.

[0051] In a preferred embodiment of the present invention, a power grid model is built on a simulation platform based on architecture parameters and real-time operating data. Power flow calculations are performed to obtain the initial steady-state operating point. Then, the steady-state results of the simulation model are compared with the real-time operating data, for example, comparing whether the voltage errors at each node are within the allowable range. If the error is large, the model parameters (such as the load model) need to be adjusted until the model passes the validity check. In the simulation model, disturbances caused by total power deficit are simulated. For example, if the total power deficit is 50MW, it can be set as suddenly disconnecting a 50MW generator at a certain node, or suddenly adding 50MW of load at a certain load node. Numerical integration methods (such as the improved Euler method or the Runge-Kutta method) are used to solve the differential-algebraic equations of the system to obtain the trajectories of generator power angle, bus voltage, and system frequency changing with time during the simulation. The dynamic change trajectories obtained from the simulation are analyzed. For example, observe whether the maximum power angle difference exceeds 180°; if not, the system power angle is stable. Observe whether the minimum voltage is lower than a preset threshold; if not, the system voltage is stable. Observe whether the minimum frequency is lower than a preset threshold; if not, the system frequency is stable. Simultaneously, through multiple simulations, the critical cut-off time at which the system just becomes unstable can be found. These analytical results are quantified into specific numerical indicators, serving as the grid stability margin indicators for this initial scheme.

[0052] By implementing this invention, we can simulate real failure and disturbance scenarios and verify the grid's ability to withstand disturbances in advance; and by using multi-dimensional stability indicators, we can comprehensively evaluate the grid operation stability of the solution.

[0053] S6. Based on the power grid stability margin index, the final power source layout plan is obtained by selecting from the initial power source layout plan.

[0054] Specifically, the final power supply deployment plan is the optimal feasible plan that takes into account external planning adaptability, grid operation stability, and engineering feasibility after robustness assessment, power deficit calculation, and transient simulation verification.

[0055] To illustrate, based on the grid stability margin index as the core criterion, the scheme with the highest stability margin and the lowest implementation risk is selected from multiple initial schemes as the final feasible power source deployment plan.

[0056] Preferably, the final power source deployment plan is obtained by selecting from the initial power source deployment plan based on the power grid stability margin index, including: The grid stability margin index corresponding to each initial power source layout planning scheme is quantitatively weighted to obtain the comprehensive stability score of each initial power source layout planning scheme; wherein, the weighting weight is preset based on the power supply reliability level requirements of the grid to be planned. Based on the comprehensive stability score, all initial power supply site planning schemes are ranked, and the initial power supply site planning scheme with the highest ranking is selected as the final power supply site planning scheme. If two or more initial power supply layout plans have the same overall stability score and both are the maximum value, the plan with the longest critical clearing time shall be selected as the final power supply layout plan; if the critical clearing times are the same, the plan with the fewest failure points shall be selected as the final power supply layout plan.

[0057] Specifically, the quantitative weighting process is the process of assigning preset weights to power angle, voltage, frequency stability margin, and critical cut-off time, and calculating a comprehensive score; the comprehensive stability score is the weighted total score of multi-dimensional stability margin indicators, and the higher the value, the better the grid stability of the scheme; the weighting weights are preset indicator weights based on the grid power supply reliability level, with the core indicator (critical cut-off time) having a higher weight.

[0058] In a preferred embodiment of the present invention, the stability margin indicators are weighted and summed according to preset weights based on the power grid reliability level (critical disconnection time is 0.3, power angle margin is 0.25, voltage margin is 0.25, and frequency margin is 0.2) to obtain a comprehensive stability score. The schemes with the highest comprehensive stability scores are ranked from highest to lowest, and the scheme with the highest score is selected as the final scheme. If the scores are the same, the scheme with the longest critical disconnection time is selected first; if the critical disconnection times are also the same, the scheme with the fewest failure points is selected.

[0059] In a preferred embodiment of the present invention, for each initial scheme, the calculated power grid stability margin indices are normalized, and then weights are preset for different indices according to the power supply reliability level requirements of the power grid to be planned. For example, for important urban power grids, voltage and frequency stability requirements may be higher, so they are given higher weights. A comprehensive stability score is obtained by weighted summation. Then, the comprehensive stability scores of all schemes are sorted in descending order, and the scheme with the highest score is the optimal scheme. If two or more schemes have the same comprehensive stability score and are tied for the highest, their critical clearing time (CCT) is further compared. The longer the CCT, the higher the system's tolerance to faults and the better the stability; therefore, the scheme with the longest CCT is selected. If the CCTs are also the same, the scheme with the fewest failure points is selected. This is because fewer failure points mean fewer risk points in the scheme itself, making its implementation more reliable.

[0060] By implementing this embodiment, the screening rules are quantified to avoid subjective judgment and ensure that the screening results are objective and fair; the hierarchical screening solves the problem of parallel solutions and adapts to actual engineering decision-making scenarios; and priority is given to ensuring power grid stability and improving power grid operation safety.

[0061] In a preferred embodiment of the present invention, taking the power supply layout planning of the 110kV main grid and 10kV distribution network in District D of G prefecture-level city as an example: the architecture parameters are 3 110kV lines, impedance 0.2Ω / km, and total load distribution of 200MW; the power supply characteristic parameters are 2 photovoltaic power stations (output curve 0-50MW during the day) and layout cost of 1500 yuan / kW; the real-time operation data are a total system reserve capacity of 30MW and a node voltage of 10.5kV; the predictive planning strategy is to build a new intelligent manufacturing industrial park in District D with an average change frequency of 0.1 times / year. Four initial power supply locations were generated, each containing 3-4 110kV power supply locations. The robustness coefficient of each location was evaluated with a preset threshold of 0.6. Location number 2 in Scheme 2 had a coefficient of 0.45 and was marked as a failure point. The expected power supply at the failure point was 40MW, with a maximum dispatchable compensation power of 25MW, a power difference of 15MW, and a total power deficit of 15MW. A simulation model was then built, simulating a 15MW disturbance. Scheme 2 had a stability margin of 0.72, and Scheme 1 had a stability margin of 0.89. Finally, Scheme 1 was selected as the final planning scheme. After implementation, there were no planning conflicts, the power grid operated stably, and the power supply reliability was high.

[0062] In another preferred embodiment of the invention, a power grid to be planned is assumed, whose architecture parameters and real-time operating data are known. Three initial planning schemes, A, B, and C, are generated. Calculations show that Scheme A has a location on a subway line planned for construction in the next three years, resulting in a very low planning robustness coefficient and being marked as a failure point, leading to a total power deficit of 50MW. Scheme B has fewer failure points, with a total power deficit of 20MW. Scheme C has no failure points, with a total power deficit of 0. Transient stability simulations are performed on the three schemes. Scheme A exhibits power angle instability under a 50MW disturbance; Scheme B experiences significant power angle fluctuations under a 20MW disturbance but eventually recovers to stability, with a slight voltage drop; Scheme C remains stable without disturbance. Ultimately, based on the stability margin index, Scheme B is selected as the final scheme. Although Scheme C has the best stability, its initial construction cost may be much higher than that of Scheme B. This embodiment, while ensuring acceptable stability, also considers other economic factors, demonstrating the intelligence of comprehensive optimization.

[0063] By implementing this embodiment, the limitations of traditional planning, which only focuses on internal electrical and economic indicators, are overcome. Regional dynamic planning is incorporated into the core evaluation system, and the planning scheme is highly matched with the actual engineering scenario. By identifying failure points in advance through the planning robustness coefficient, planning conflicts, site invalidation, and commissioning delays are avoided from the site selection stage, ensuring the stable operation of power supply sites throughout their entire life cycle. The total power deficit of failure points is calculated, and the calculation results are consistent with the actual dispatching capacity of the power grid, significantly improving data accuracy. Combined with power grid transient stability simulation to verify the feasibility of the scheme, the scheme ensures that the power grid remains stable under power deficit disturbances, reducing the risks of power angle loss of synchronism, voltage collapse, and frequency exceeding limits.

[0064] By implementing this embodiment, the predictive planning strategy of the power grid to be planned is obtained simultaneously, and used together with the architecture parameters, power characteristic parameters, and real-time operating data as the basis for planning. External dynamic planning factors are listed alongside internal power grid parameters, thus compensating for the shortcomings of existing technologies that ignore the impact of external planning from the data input level. For each deployment location, the predictive planning strategy and its average change frequency are used for verification and evaluation to obtain the planning robustness coefficient. The abstract regional dynamic planning impact is transformed into a quantifiable evaluation index, no longer relying solely on electrical performance and economic efficiency as the basis for deployment. Then, deployment locations with unsatisfactory planning robustness coefficients and susceptible to the impact of external dynamic planning are marked as failure points. Deployment locations that conflict with the actual scenario and are difficult to implement stably are eliminated in advance before the scheme selection, avoiding the final scheme from being out of touch with actual needs. Finally, the power deficit is calculated based on the failure points, and transient stability simulation is carried out in conjunction with real-time power grid operating data. The final scheme is selected based on the power grid stability margin index, ensuring that the planning scheme not only meets internal electrical and economic requirements, but also adapts to external planning changes and guarantees long-term stable operation.

[0065] See Figure 2 This is a schematic diagram of a power supply layout planning device according to an embodiment of the present invention, comprising: The data acquisition module is used to acquire the architecture parameters, power characteristic parameters, real-time operating data, and predictive planning strategies of the power grid to be planned. The initial power deployment planning scheme generation module is used to generate several initial power deployment planning schemes based on the architecture parameters and the power characteristic parameters. The planning robustness coefficient calculation module is used to determine the average change frequency of the predicted planning strategy for each location in each initial power supply location planning scheme, and to verify and evaluate the planning robustness coefficient of the location based on the predicted planning strategy and the average change frequency. The total power deficit determination module is used to mark the locations where the planned robustness coefficient is less than the preset robustness threshold as failure points. Based on the initial power supply layout planning scheme, real-time operation data and architecture parameters, it calculates the power difference value of each failure point to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side. The sum of the power differences of each failure point is used as the total power deficit of the initial power supply layout planning scheme. The power grid stability margin index evaluation module is used to construct a power grid transient stability simulation model based on architecture parameters and real-time operating data, and to perform transient stability simulation on the power grid transient stability simulation model with the total power deficit as the disturbance condition, so as to obtain the power grid stability margin index of the initial power source layout planning scheme. The final power distribution planning scheme determination module is used to select the final power distribution planning scheme from the initial power distribution planning scheme based on the power grid stability margin index.

[0066] Preferably, the forecasting and planning strategy includes forecast accuracy, load distribution requirements, and power supply capacity information; The planning robustness coefficient calculation module is used to verify and evaluate the planning strategy and average change frequency to obtain the planning robustness coefficient of the site location, including: Based on the predictive planning strategy corresponding to the location of the power supply points, a conflict verification was performed with the initial power supply point planning scheme. The predictive planning strategy with no spatial overlap of the power supply points and no conflict in the construction sequence was selected as the first strategy. The correlation between the first strategy and the power distribution of the power grid to be planned is verified, and the first strategy that will cause the change value of regional power load to be greater than the preset change threshold after implementation is selected as the feasible planning strategy. The single-strategy impact value is obtained by calculating the dot product of the average change frequency and the prediction accuracy value corresponding to the feasible planning strategy. The strategy change value is obtained by weighting the single-strategy impact value and the number of feasible planning strategies based on the entropy weight method. Based on the power supply capacity information and the load distribution demand assessment, the distribution planning coefficient is obtained. The normalized difference between the distribution planning coefficient and the strategy change value is used as the planning robustness coefficient of the distribution location.

[0067] Preferably, the distribution planning coefficient is obtained based on the power supply capacity information and the load distribution demand assessment, including: By comparing the power supply capacity information of the deployment locations with the load deployment requirements corresponding to the feasible planning strategies, if the rated power supply capacity of the power supply capacity information meets the load deployment requirements, the preset value is used as the deployment planning coefficient. If the rated power supply capacity of the power supply capacity information does not meet the load distribution requirements, the grid topology location corresponding to the distribution location is obtained based on the architecture parameters. The power dispatch response speed and power dispatch capacity value are evaluated based on the grid topology location. The dispatch flexibility is calculated by weighting the power dispatch response speed and power dispatch capacity value. Based on the location of the power grid topology, determine whether power grid power flow scheduling can meet the load distribution requirements. If so, the site planning coefficient is determined based on the scheduling flexibility; where scheduling flexibility and site planning coefficient are positively correlated. If not, the number of additional deployment points is estimated based on the power gap corresponding to the load deployment demand, the number of additional spaces is estimated based on the area around the deployment point location where additional deployment points can be added, and the deployment planning coefficient is calculated based on the difference between the number of additional deployment points and the number of additional spaces, according to the scheduling flexibility.

[0068] This invention provides a power grid deployment planning device. A data acquisition module acquires the architecture parameters, power characteristic parameters, real-time operating data, and predictive planning strategies of the power grid to be planned. An initial deployment planning scheme generation module generates several initial power grid deployment planning schemes based on the architecture parameters and power characteristic parameters. A planning robustness coefficient calculation module determines the average change frequency of the predictive planning strategy for each deployment location in each initial power grid deployment planning scheme, and performs verification and evaluation based on the predictive planning strategy and the average change frequency to obtain the planning robustness coefficient of the deployment location. A total power deficit determination module marks locations where the planning robustness coefficient is less than a preset robustness threshold as failure points. Based on the initial power supply layout plan, real-time operating data, and architecture parameters, the power difference at each failure point is calculated to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side. The sum of the power differences at each failure point is taken as the total power deficit of the initial power supply layout plan. In the grid stability margin index evaluation module, a grid transient stability simulation model is constructed based on the architecture parameters and real-time operating data. The total power deficit is used as the disturbance condition to perform transient stability simulation on the grid transient stability simulation model, thereby obtaining the grid stability margin index of the initial power supply layout plan. Finally, in the final layout plan determination module, the final power supply layout plan is selected from the initial power supply layout plan based on the grid stability margin index.

[0069] By synchronously acquiring the predictive planning strategy of the power grid to be planned, and using it together with the architecture parameters, power characteristic parameters, and real-time operating data as the planning basis, external dynamic planning factors are placed on par with internal grid parameters. This addresses the shortcomings of existing technologies that ignore the impact of external planning from the data input level. For each deployment location, the predictive planning strategy and its average change frequency are used for verification and evaluation to obtain the planning robustness coefficient. This transforms the abstract impact of regional dynamic planning into a quantifiable evaluation indicator, moving beyond the reliance solely on electrical performance and economic efficiency as the basis for deployment decisions. Then, deployment locations with unsatisfactory planning robustness coefficients or those susceptible to external dynamic planning influences are marked as failure points. Before scheme selection, deployment locations that conflict with the actual scenario or are difficult to implement stably are eliminated in advance, preventing the final scheme from deviating from actual needs. Finally, power deficits are calculated based on failure points, and transient stability simulations are conducted using real-time grid operating data. The final scheme is selected based on the grid stability margin index, ensuring that the planning scheme not only meets internal electrical and economic requirements but also adapts to external planning changes and guarantees long-term stable operation.

[0070] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0071] Those skilled in the art will understand that, for convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0072] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a power distribution planning method as described in the above embodiments. The terminal device may be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The terminal device may include, but is not limited to, a processor and a memory.

[0073] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0074] The memory can be used to store the computer program. The processor implements various functions of the terminal device by running or executing the computer program stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device or other volatile solid-state storage device.

[0075] Another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform a power distribution planning method as described in the above embodiment.

[0076] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0077] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A power supply site planning method, characterized in that, include: Obtain the architecture parameters, power characteristic parameters, real-time operating data, and predictive planning strategies of the power grid to be planned; Several initial power supply placement planning schemes are generated based on the architecture parameters and the power characteristic parameters. For each location in the initial power supply layout plan, determine the average change frequency of the predictive planning strategy for the corresponding area. Based on the predictive planning strategy and the average change frequency, perform verification and evaluation to obtain the planning robustness coefficient of the location. Locations with a planned robustness coefficient less than a preset robustness threshold are marked as failure points. Based on the initial power supply layout planning scheme, real-time operation data, and architecture parameters, the power difference value of each failure point is calculated to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side. The sum of the power differences of each failure point is used as the total power deficit of the initial power supply layout planning scheme. A power grid transient stability simulation model is constructed based on the architecture parameters and real-time operating data. The transient stability simulation model is then subjected to transient stability simulation with the total power deficit as the disturbance condition to obtain the power grid stability margin index of the initial power source deployment planning scheme. The final power source deployment plan is obtained by selecting from the initial power source deployment plan based on the power grid stability margin index.

2. The power supply site planning method as described in claim 1, characterized in that, Forecasting and planning strategies include forecast accuracy, load distribution requirements, and power supply capacity information; Based on the predictive planning strategy and the average frequency of change, the robustness coefficient of the site selection is obtained through verification and evaluation, including: Based on the predictive planning strategy corresponding to the location of the power supply points, a conflict verification was performed with the initial power supply point planning scheme. The predictive planning strategy with no spatial overlap of the power supply points and no conflict in the construction sequence was selected as the first strategy. The correlation between the first strategy and the power distribution of the power grid to be planned is verified, and the first strategy that will cause the change value of regional power load to be greater than the preset change threshold after implementation is selected as the feasible planning strategy. The single-strategy impact value is obtained by calculating the dot product of the average change frequency and the prediction accuracy value corresponding to the feasible planning strategy. The strategy change value is obtained by weighting the single-strategy impact value and the number of feasible planning strategies based on the entropy weight method. Based on the power supply capacity information and the load distribution demand assessment, the distribution planning coefficient is obtained. The normalized difference between the distribution planning coefficient and the strategy change value is used as the planning robustness coefficient of the distribution location.

3. The power supply site planning method as described in claim 2, characterized in that, Based on the power supply capacity information and the load distribution demand assessment, the distribution planning coefficients are obtained, including: By comparing the power supply capacity information of the deployment locations with the load deployment requirements corresponding to the feasible planning strategies, if the rated power supply capacity of the power supply capacity information meets the load deployment requirements, the preset value is used as the deployment planning coefficient. If the rated power supply capacity of the power supply capacity information does not meet the load distribution requirements, the grid topology location corresponding to the distribution location is obtained based on the architecture parameters. The power dispatch response speed and power dispatch capacity value are evaluated based on the grid topology location. The dispatch flexibility is calculated by weighting the power dispatch response speed and power dispatch capacity value. Based on the location of the power grid topology, determine whether power grid power flow scheduling can meet the load distribution requirements. If so, the site planning coefficient is determined based on the scheduling flexibility; where scheduling flexibility and site planning coefficient are positively correlated. If not, the number of additional deployment points is estimated based on the power gap corresponding to the load deployment demand, the number of additional spaces is estimated based on the area around the deployment point location where additional deployment points can be added, and the deployment planning coefficient is calculated based on the difference between the number of additional deployment points and the number of additional spaces, according to the scheduling flexibility.

4. The power supply site planning method as described in claim 1, characterized in that, Based on the initial power supply deployment plan, real-time operational data, and architecture parameters, the power difference value used to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side is calculated for each failure point, including: From the initial power supply layout plan, extract the rated power that each failure point is pre-assigned to, as the expected power supply for the failure point; Based on real-time operating data, the rated capacity, real-time output, and total system reserve capacity of adjacent non-failure points are obtained. The maximum additional power of adjacent non-failure points is calculated based on the rated capacity and real-time output. The maximum transmission capacity of supplementary power is calculated based on the line topology, line impedance, and line power flow limitations in the architecture parameters. The sum of the system's total reserve capacity and the maximum additional power is taken as the total power increment that the grid side can provide. The minimum value between the total power increment and the maximum transmission capacity of the supplementary power is taken as the maximum dispatchable compensation power of the grid side corresponding to the failure point. The difference between the expected power supply and the maximum dispatchable compensation power on the grid side is taken as the power difference at the failure point; where the maximum dispatchable compensation power on the grid side is greater than or equal to the expected power supply, the power difference at the failure point is recorded as 0.

5. The power supply site planning method as described in claim 1, characterized in that, Using the total power deficit as a disturbance condition, transient stability simulations are performed on the power grid transient stability simulation model to obtain the power grid stability margin index of the initial power source deployment planning scheme, including: Power flow calculations are performed on the power grid transient stability simulation model based on real-time operating data to determine the initial steady-state operating points of the voltage, phase angle, generator output, and load power of each node in the power grid to be planned. The effectiveness of the power grid transient stability simulation model is verified based on the initial steady-state operating points and real-time operating data. After verifying the effectiveness of the power grid transient stability simulation model, transient stability simulation was performed using the total power deficit as a disturbance to obtain the dynamic change trajectory of generator power angle, bus voltage and system frequency during the simulation process; Based on the dynamic change trajectory, the calculated power angle stability margin, voltage stability margin, frequency stability margin, and critical cut-off time of the power grid to be planned are used as the power grid stability margin indicators corresponding to the initial power source layout planning scheme.

6. The power supply site planning method as described in claim 5, characterized in that, The final power source deployment plan is obtained by selecting from the initial power source deployment plan based on the grid stability margin index, including: The grid stability margin index corresponding to each initial power source layout planning scheme is quantitatively weighted to obtain the comprehensive stability score of each initial power source layout planning scheme; wherein, the weighting weight is preset based on the power supply reliability level requirements of the grid to be planned. Based on the comprehensive stability score, all initial power supply site planning schemes are ranked, and the initial power supply site planning scheme with the highest ranking is selected as the final power supply site planning scheme. If two or more initial power supply layout plans have the same overall stability score and both are the maximum value, the plan with the longest critical clearing time shall be selected as the final power supply layout plan; if the critical clearing times are the same, the plan with the fewest failure points shall be selected as the final power supply layout plan.

7. The power supply site planning method as described in claim 1, characterized in that, The architecture parameters include line topology, line impedance, and load distribution; the power supply characteristic parameters include power supply type, power supply output curve, and power supply deployment cost. Based on the architecture parameters and the power characteristic parameters, several initial power supply placement plans are generated, including: Based on the line topology, the line impedance, and the load distribution, the boundary constraints of the power grid to be planned are determined. With the goal of minimizing operating costs, and under boundary constraints, a multi-objective optimization algorithm is used to generate several power supply point combinations based on the line topology, line impedance, load distribution, power supply type, and power supply output curve. An initial power supply layout plan is generated based on each power supply layout combination; each initial power supply layout plan includes the layout locations.

8. A power supply layout planning device, characterized in that, include: The data acquisition module is used to acquire the architecture parameters, power characteristic parameters, real-time operating data, and predictive planning strategies of the power grid to be planned. The initial power deployment planning scheme generation module is used to generate several initial power deployment planning schemes based on the architecture parameters and the power characteristic parameters. The planning robustness coefficient calculation module is used to determine the average change frequency of the predicted planning strategy for each location in each initial power supply location planning scheme, and to verify and evaluate the planning robustness coefficient of the location based on the predicted planning strategy and the average change frequency. The total power deficit determination module is used to mark the locations where the planned robustness coefficient is less than the preset robustness threshold as failure points. Based on the initial power supply layout planning scheme, real-time operation data and architecture parameters, it calculates the power difference value of each failure point to characterize the difference between the expected power supply and the maximum dispatchable compensation power on the grid side. The sum of the power differences of each failure point is used as the total power deficit of the initial power supply layout planning scheme. The power grid stability margin index evaluation module is used to construct a power grid transient stability simulation model based on architecture parameters and real-time operating data, and to perform transient stability simulation on the power grid transient stability simulation model with the total power deficit as the disturbance condition, so as to obtain the power grid stability margin index of the initial power source layout planning scheme. The final power distribution planning scheme determination module is used to select the final power distribution planning scheme from the initial power distribution planning scheme based on the power grid stability margin index.

9. A terminal device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement a power distribution planning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform a power distribution planning method as described in any one of claims 1 to 7.

Images