Power distribution network multi-year planning layer iterative updating method and device based on GIS (Geographic Information System)

Abstract

The invention discloses a GIS-based power distribution network multi-year planning layer iterative updating method and device, and relates to the technical field of planning layer updating. According to the GIS-based power distribution network multi-year planning layer iterative updating method, a GIS initial planning layer is established by acquiring multi-source power distribution network data, operation state data is acquired by combining a power distribution network digital twin model, an area needing to be adjusted is determined through risk assessment, and the layer is updated, so that real-time linkage of the planning layer and a power grid operation state is realized; the method can dynamically optimize a planning scheme based on data driving, improves the accuracy, adaptability and risk response capability of power distribution network planning, guarantees that a planning layer continuously meets the actual demands of a power grid, provides powerful support for the efficient operation and scientific planning of the power distribution network, and improves the reliability of power distribution network planning. The problems that in existing power distribution network planning, due to data isolation and lack of a dynamic updating mechanism, planning and actual operation are disjointed, and power grid state changes and hidden risks cannot be responded in time can be solved.

Description

Technical Field

[0001] This invention relates to the field of planning layer updating technology, specifically to a method and apparatus for iterative updating of multi-year planning layers for power distribution networks based on GIS. Background Technology

[0002] Current GIS-based multi-year distribution network planning layer iterative update technology primarily utilizes multi-source data fusion to integrate historical load data, geographic information, equipment ledgers, and other data. It employs spatiotemporal data analysis models and algorithms to achieve dynamic simulation and prediction of the distribution network planning layer. Simultaneously, it combines version management mechanisms and collaborative editing technology to ensure the traceability of planning data at different stages and the efficiency of multi-person collaboration. Furthermore, it leverages a visual interactive interface to allow planners to intuitively compare and analyze planning schemes from different years, ultimately forming a precise, dynamic, and collaborative distribution network planning layer update system.

[0003] However, existing power distribution network planning suffers from problems such as data isolation, lack of dynamic update mechanisms leading to a disconnect between planning and actual operation, and an inability to respond promptly to changes in power grid status and potential risks. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and apparatus for iterative updating of multi-year planning layers for power distribution networks based on GIS. This solves the problems in existing power distribution network planning caused by isolated data and lack of dynamic update mechanisms, resulting in a disconnect between planning and actual operation, and an inability to respond promptly to changes in power grid status and potential risks.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for iterative updating of a multi-year planning layer for a distribution network based on GIS, comprising the following steps: acquiring multi-source distribution network data, establishing an initial GIS planning layer based on the multi-source distribution network data; acquiring a digital twin model of the distribution network, acquiring distribution network operation status data based on the digital twin model of the distribution network; conducting a risk assessment based on the distribution network operation status data to determine the areas of the distribution network that need adjustment; determining the adjustment scheme for the areas of the distribution network that need adjustment, and updating the initial GIS planning layer based on the adjustment scheme.

[0006] Furthermore, an initial GIS planning layer is established based on multi-source distribution network data, including the following steps:

[0007] The data format of multi-source distribution network data is converted to adapt to the GIS system. This multi-source data includes distribution network operation data, geographic information data of the distribution network planning area, regional development planning and land use planning data, and power grid equipment ledger data. The converted multi-source distribution network data is integrated into the GIS database to construct a basic data layer for distribution network planning. Load forecasting is performed on the distribution network to obtain the forecast results, which are then compared and evaluated with the current carrying capacity of the distribution network to determine if there is a planning need. If not, the basic data layer for distribution network planning is output as the initial planning layer in the GIS. If a need exists, network topology analysis is performed to identify weak areas in the distribution network. Based on these weak areas, planning adjustment schemes are determined, and these schemes are plotted in the GIS system, outputting the initial planning layer in the GIS.

[0008] Furthermore, load forecasting is performed on the distribution network to obtain the load forecast results, including the following steps: collecting historical load data, including active power, reactive power, and apparent power; simultaneously collecting data on influencing factors corresponding to the historical load data, including natural factors, social factors, and economic factors; normalizing the historical load data and influencing factor data, and constructing a multiple linear regression model:

[0009] y = β0 + β1*x1 + β2*x2 + ... + β n *x n +ò;

[0010] Where y is the predicted value, x1, x2, ..., x n Let β0, β1, β2, ..., β be the variables of each influencing factor. n All are regression coefficients, and ò is the error term;

[0011] Normalized historical load data and influencing factor data are divided into training and testing sets. The training set is used to train the multiple linear regression model. The regression coefficients are continuously adjusted using the least squares optimization algorithm to minimize the error between the predicted values ​​and the actual load values ​​of the multiple linear regression model, thus determining the optimal regression coefficients and obtaining the trained load forecasting model. Actual influencing factor data is obtained and input into the trained load forecasting model to obtain load forecasting results, including predicted active power, predicted reactive power, and predicted apparent power. If any item in the load forecasting results is greater than the current distribution network's carrying capacity, then there is a planning demand; if none of the items in the load forecasting results are greater than the current distribution network's carrying capacity, then there is no planning demand.

[0012] Further, network topology analysis is conducted to identify weak areas in the distribution network, including the following steps: Based on the network analysis function of the GIS system, the topology of the distribution network is constructed using distribution network equipment and lines as nodes and connecting lines;

[0013] Based on the established topology, the connection relationships between lines are analyzed to identify the power transmission paths and flow directions of the entire distribution network.

[0014] By comparing the real-time current of a line with its rated current, lines whose real-time current exceeds the rated current are identified and marked as overloaded lines. Based on the real-time collected voltage data, areas where the voltage data is lower than the standard voltage are identified and marked as low-voltage areas. Distribution network equipment and lines whose fault occurrence frequency exceeds a set threshold are identified and marked as high-frequency fault areas. Overloaded lines, low-voltage areas, and high-frequency fault areas are marked in the basic data layer of the distribution network planning to determine the weak areas of the distribution network.

[0015] Furthermore, determining the planning adjustment scheme based on the weak areas of the distribution network includes the following steps: obtaining multiple candidate planning schemes designed for the weak areas of the distribution network; performing multiple performance analyses on the multiple candidate planning schemes to determine the comprehensive evaluation coefficient of each candidate planning scheme; and determining the candidate planning scheme corresponding to the largest comprehensive evaluation coefficient, which is denoted as the planning adjustment scheme.

[0016] Further, multiple performance analyses are conducted to determine the comprehensive evaluation coefficient of each candidate planning scheme, including the following steps: Based on the buffer analysis function of GIS, spatial adaptability analysis is performed on the new facilities in each candidate planning scheme: a buffer of a certain radius is set for each new facility, and the proportion of sensitive areas within the buffer is viewed to obtain the total sensitive area proportion Mg of each candidate planning scheme; Based on the network analysis function of GIS, the distribution network topology structure after the implementation of each candidate planning scheme is simulated, the number of connection paths between power supply points and load points under different candidate planning schemes is calculated, and the proportion of single power supply is determined; Based on the attribute statistical analysis function of GIS, the expected cost of each candidate planning scheme is calculated, and the ratio of the expected cost to the budgeted cost is calculated to obtain the cost ratio Cg; Network topology analysis is performed on each candidate planning scheme to determine the weak area ratio Bg of the number of weak areas to the allowable number of weak areas for each candidate planning scheme; Based on the total sensitive area proportion, the proportion of single power supply, the cost ratio, and the weak area ratio, the comprehensive evaluation coefficient Zpx is determined.

[0017]

[0018] Among them, α1, α2, α3 and α4 are all weighting factors.

[0019] Furthermore, risk assessment is conducted based on distribution network operation status data to determine the areas requiring adjustment of the distribution network. This includes the following steps: dividing the distribution network into regions based on the power grid structure to obtain each distribution region; acquiring the distribution network operation status data of each distribution region and inputting the distribution network operation status data of each distribution region into a trained risk assessment model to output the risk assessment level, wherein the trained risk assessment model is based on a decision tree model based on machine learning; and recording the distribution regions with risk assessment levels greater than a set level threshold as the areas requiring adjustment of the distribution network.

[0020] Further, determining the adjustment scheme for the distribution network area that needs adjustment includes the following steps: obtaining multiple candidate adjustment schemes stored in the database; simulating and predicting the load forecast results after the implementation of each candidate adjustment scheme; performing a difference analysis between the load forecast results and the set grid carrying capacity to obtain the difference results, and determining the adjustment scheme for the distribution network area that needs adjustment, wherein the difference results include active power difference YG, reactive power difference WG, and apparent power difference SZ.

[0021] Furthermore, a difference analysis is performed between the load forecast results and the set grid carrying capacity to determine the adjustment scheme for the distribution network area that needs adjustment. This includes the following steps: determining whether the active power difference, reactive power difference, and apparent power difference are all greater than 0; if not, the corresponding candidate adjustment scheme is deleted; if so, the corresponding candidate adjustment scheme is retained. At the same time, the difference coefficient CZ is calculated based on the active power difference, reactive power difference, and apparent power difference: CZ=λ1*YG+λ2*WG+λ3*SZ; where λ1, λ2, and λ3 are all weighting factors; the candidate adjustment scheme corresponding to the largest difference coefficient is recorded as the adjustment scheme for the distribution network area that needs adjustment.

[0022] The GIS-based multi-year planning layer iterative update device for power distribution networks includes an initial layer acquisition module, a data acquisition module, an adjustment area determination module, and a layer update module. Specifically: the initial layer acquisition module acquires multi-source power distribution network data and establishes an initial GIS planning layer based on this data; the data acquisition module acquires a digital twin model of the power distribution network and obtains operational status data based on this model; the adjustment area determination module performs risk assessments based on the operational status data to determine areas requiring adjustment; and the layer update module determines adjustment schemes for these areas and updates the initial GIS planning layer based on these schemes.

[0023] The present invention has the following beneficial effects:

[0024] This GIS-based method for iteratively updating multi-year planning layers for power distribution networks establishes an initial GIS planning layer by acquiring multi-source power distribution network data. It then combines this with operational status data obtained from a digital twin model of the power distribution network. Risk assessment identifies areas requiring adjustment and updates the layer accordingly. This achieves real-time linkage between the planning layer and the power grid's operational status. It enables data-driven dynamic optimization of planning schemes, improving the accuracy, adaptability, and risk response capabilities of power distribution network planning. This ensures the planning layer continuously aligns with the actual needs of the power grid, providing strong support for efficient operation and scientific planning of the power distribution network. It addresses the problems in existing power distribution network planning caused by isolated data and a lack of dynamic update mechanisms, leading to a disconnect between planning and actual operation, and an inability to respond promptly to changes in power grid status and potential risks.

[0025] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0026] Figure 1 This is a flowchart of the GIS-based multi-year planning layer iterative update method for power distribution networks according to the present invention.

[0027] Figure 2 This is a flowchart of the GIS-based multi-year planning layer iterative update device for power distribution networks according to the present invention. Detailed Implementation

[0028] Please see Figure 1 The present invention provides a technical solution: a method for iterative updating of multi-year planning layers for power distribution networks based on GIS, comprising the following steps: acquiring multi-source power distribution network data, and establishing an initial GIS planning layer based on the multi-source power distribution network data;

[0029] The data from multiple distribution networks is converted to a suitable format for GIS systems (such as ESRI's shapefile format). This data includes distribution network operation data (such as voltage, current, and power), geographic information data of the distribution network planning area (such as topography, roads, and buildings), regional development planning and land use planning data, and power grid equipment ledger data (information on the model, parameters, and installation location of equipment such as transformers, lines, and switches). The converted multi-source distribution network data is then integrated into a GIS database to construct a basic data layer for distribution network planning, including:

[0030] Geographic base map layer: Overlays topographic, road, and building vector data as a spatial reference for planning;

[0031] Equipment Status Layer: Marks the actual location and parameters of equipment such as transformers, lines, and switches;

[0032] Load distribution layer: A heat map of the current load density is generated by interpolating historical operating data;

[0033] Planning constraint layer: Marking areas where construction is prohibited, such as nature reserves and municipal pipeline corridors.

[0034] Load forecasting is performed on the distribution network to obtain the load forecast results. The load forecast results are then compared and evaluated with the current carrying capacity of the distribution network to determine whether there is a planning requirement for the distribution network. If not, the basic data layer for distribution network planning is output as the initial planning layer of the GIS. If it exists, network topology analysis is performed to identify weak areas of the distribution network. Based on the weak areas of the distribution network, a planning adjustment scheme is determined, and the planning adjustment scheme is drawn into the GIS system, outputting the initial planning layer of the GIS.

[0035] Load forecasting for the distribution network involves the following steps: collecting historical load data, including active power, reactive power, and apparent power; simultaneously collecting data on influencing factors corresponding to the historical load data, including natural factors (meteorological data such as temperature and humidity in the region), social factors (holiday information, population size and growth trends), and economic factors (economic development indicators such as GDP growth rate and industrial output); and normalizing the historical load data and influencing factor data to construct a multiple linear regression model.

[0036] y = β0 + β1*x1 + β2*x2 + ... + β n *x n +ò;

[0037] Where y is the predicted value, x1, x2, ..., x n Let β0, β1, β2, ..., β be the variables of each influencing factor. n All are regression coefficients, and ò is the error term;

[0038] Normalized historical load data and influencing factor data are divided into training and testing sets. The training set is used to train the multiple linear regression model. The regression coefficients are continuously adjusted using the least squares optimization algorithm to minimize the error between the predicted values ​​and the actual load values ​​of the multiple linear regression model, thus determining the optimal regression coefficients and obtaining the trained load forecasting model. Actual influencing factor data is obtained and input into the trained load forecasting model to obtain load forecasting results, including predicted active power, predicted reactive power, and predicted apparent power. If any item in the load forecasting results is greater than the current distribution network's carrying capacity, then there is a planning demand; if none of the items in the load forecasting results are greater than the current distribution network's carrying capacity, then there is no planning demand.

[0039] By collecting historical load data and influencing factor data, a multiple linear regression model is constructed for load forecasting, enabling advance knowledge of future load conditions. If the load forecast exceeds the current distribution network's carrying capacity, advance planning can be implemented to avoid problems such as insufficient power supply and equipment overload caused by load growth. This solves the problem of insufficient estimation of future load growth in traditional planning, which leads to planning lagging behind actual demand.

[0040] By comparing the load forecast results with the current distribution network carrying capacity, if all forecast load items are not greater than the carrying capacity, it means that the existing distribution network can meet the demand, and no planning adjustment is needed. This avoids unnecessary investment and solves the problem of over-planning that may occur in traditional planning, which leads to resource waste.

[0041] Network topology analysis is conducted to identify weak areas in the distribution network. This includes the following steps: Based on the network analysis functions of a GIS system, the distribution network topology is constructed using distribution network equipment and lines as nodes and connections. During this construction process, connection rules between lines and equipment such as transformers, switches, and load points are set according to the actual connection relationships between devices to ensure that the topology accurately reflects the actual network layout. For example, the connection methods between transformers and incoming / outgoing lines, as well as the control relationships of switches on and off lines, are clearly defined.

[0042] Based on the established topology, the interconnections between lines are analyzed to trace the power transmission paths and directions of the entire distribution network. Starting from the power source, the direction of power flow is tracked along the lines to determine the role and status of each line in the power transmission process. Simultaneously, the interconnections between lines are examined to identify redundant lines or single-source power supply situations. This proactively identifies reliability weaknesses in the power grid structure, preventing the expansion of power outages due to insufficient line connections and addressing the difficulty of quantifying network redundancy using traditional methods.

[0043] By comparing the real-time current of a line with its rated current (e.g., a 10kV line with a real-time current of 300A and a rated current of 280A), lines whose real-time current exceeds the rated current are identified and recorded as overloaded lines. This allows for precise location of equipment capacity bottlenecks, preventing faults such as line insulation aging and transformer overheating caused by overload, and overcoming the lag in passively discovering overload problems in traditional inspections.

[0044] Based on real-time collected voltage data, areas where the voltage is lower than the standard voltage (e.g., a residential area with a voltage of only 190V, while the standard value is 220V±7%) are identified and marked as low-voltage areas. This helps to address voltage quality issues in advance, avoid damage to user equipment and complaints caused by long-term low voltage, and compensate for the shortcomings of traditional voltage monitoring, which is characterized by its dispersed nature and lack of spatial correlation analysis.

[0045] Identify distribution network equipment and lines that experience more faults than a set threshold and mark them as high-frequency fault areas (e.g., a switch that fails 4 times a year has a threshold of 2). Locate aging or defective equipment and prioritize the use of planned resources for equipment replacement in high-fault areas, thus solving the problem of resource waste caused by the "all-round" approach in traditional maintenance.

[0046] In the basic data layer of the distribution network planning, overloaded lines, low-voltage areas, and high-frequency fault areas are marked to identify weak areas in the distribution network. This provides a spatial reference for planning adjustment schemes, such as prioritizing line expansion in areas with dense overloaded lines, thus addressing the shortcomings of traditional text reports in visually representing the spatial distribution of problems.

[0047] Determining planning adjustment schemes based on weak areas of the distribution network includes the following steps: obtaining multiple candidate planning schemes designed for weak areas of the distribution network; designing multiple different schemes for weak areas (such as adding substations, upgrading lines, introducing distributed power sources, etc.) to avoid the limitations of a single scheme. For example, in weak mountainous areas, both line expansion and distributed photovoltaic access schemes are considered simultaneously to provide a basis for comparison in subsequent evaluations and solve the problem of insufficient optimization space caused by a single scheme in traditional planning.

[0048] Multiple performance analyses are performed on various candidate planning schemes to determine the comprehensive evaluation coefficient of each candidate planning scheme, including spatial adaptability analysis, network connectivity analysis, cost-benefit quantification analysis, and weak link improvement analysis; the candidate planning scheme corresponding to the largest comprehensive evaluation coefficient is determined and denoted as the planning adjustment scheme.

[0049] Multiple performance analyses are conducted to determine the comprehensive evaluation coefficients of each candidate planning scheme, including the following steps: Based on the buffer analysis function of GIS, spatial adaptability analysis is performed on the new facilities in each candidate planning scheme: a buffer of a certain radius is set for each new facility, and the proportion of sensitive areas within the buffer is viewed to obtain the total sensitive area proportion Mg of each candidate planning scheme; spatial conflicts of planning schemes are avoided in advance. For example, if the buffer of a candidate substation includes a school, the site selection or optimization scheme needs to be adjusted to solve the construction obstruction or environmental disputes caused by insufficient consideration of spatial constraints in traditional planning.

[0050] Based on the network analysis function of GIS, the distribution network topology after the implementation of each candidate planning scheme is simulated, the number of connection paths between power supply points and load points under different candidate planning schemes is calculated, and the proportion of single power supply is determined (Dg). The optimization effect of the scheme on the power grid structure is quantitatively evaluated, and multi-path power supply schemes are given priority to reduce the risk of power outages caused by single power supply failures, thus solving the problem of insufficient quantification of the effect of power supply reliability improvement in traditional planning.

[0051] Based on the attribute statistical analysis function of GIS, the estimated cost of each candidate planning scheme is calculated, and the ratio of the estimated cost to the budgeted cost is calculated to obtain the cost ratio Cg; this ensures that the planning scheme is within the budget and avoids overspending or waste of funds, such as eliminating schemes whose costs exceed the budget by 20%, thus solving the problem of lack of data support for cost control in traditional planning.

[0052] Network topology analysis is performed on each candidate planning scheme to determine the ratio Bg of the number of weak areas to the allowable number of weak areas in each candidate planning scheme; the degree of improvement of the scheme on the weak areas is quantified, and the scheme that can minimize overloaded lines and low voltage areas is given priority to solve the problem of vague evaluation of the improvement effect in traditional planning.

[0053] The comprehensive evaluation coefficient Zpx is determined based on the proportion of total sensitive areas, the proportion of single-power supply units, the cost ratio, and the proportion of vulnerable areas.

[0054]

[0055] Among them, α1, α2, α3 and α4 are all weighting factors.

[0056] By integrating multi-dimensional indicators into quantitative values, subjective judgments can be avoided. For example, a solution that is slightly more expensive but has significantly improved reliability may still be selected through weight allocation, thus solving the problem of lack of objective standards in multi-objective decision-making in traditional planning.

[0057] Obtain a digital twin model of the distribution network, and acquire distribution network operation status data based on the digital twin model; synchronize power grid equipment operation data (such as transformer oil temperature and line current) and geospatial information (such as line direction and equipment location) through the digital twin model of the distribution network to form a virtual model that interacts with the real power grid in real time, which solves the problem of lagging operation data and inability to reflect the power grid status in real time in traditional planning. For example, when a line trips due to lightning strike, the digital twin model can immediately locate the fault and update the status, providing real-time data support for risk assessment.

[0058] Risk assessment is conducted based on distribution network operation status data to determine the areas where distribution network adjustments are necessary.

[0059] Risk assessment based on distribution network operation status data determines areas requiring adjustment, including the following steps: First, the distribution network is divided into regions based on its structure (based on structural factors such as voltage level, substation distribution, and line connections). Each substation's power supply area is defined as a sub-region, clearly defining its supply range, avoiding overlaps and cross-regional power supply, facilitating power flow calculations, short-circuit current analysis, and improving fault location and isolation, thus enhancing the safety and stability of the power grid. Second, sub-regions are further divided according to voltage level and substation distribution (e.g., a 10kV power supply area centered on a 110kV substation is considered a separate region), ensuring no overlap in power supply ranges. This avoids the ambiguity of regional divisions in traditional assessments, which can lead to unclear responsibility. For example, if a region has low voltage, the fault location can be directly pinpointed to the corresponding substation's power supply area, improving fault location efficiency.

[0060] The system acquires the power distribution network operation status data of each distribution area and inputs the data into a trained risk assessment model to output the risk assessment level. The trained risk assessment model is based on a machine learning-based decision tree model. This eliminates the subjectivity and lag of manual assessment. For example, the decision tree model can output the results in real time, which is necessary for traditional manual inspections to complete the area assessment in 24 hours, thus solving the problem of untimely risk response.

[0061] Distribution areas with risk assessment levels exceeding a set threshold are designated as areas requiring adjustment. This avoids the resource waste of "comprehensive overhaul" in traditional planning, such as prioritizing renovations only in high-risk areas while maintaining the status quo in low-risk areas, thus addressing the problem of unreasonable resource allocation in planning.

[0062] Determine the adjustment plan for the area where the power distribution network needs to be adjusted, and update the initial planning layer of the GIS based on the adjustment plan.

[0063] Determining the adjustment plan for the distribution network area requiring adjustment includes the following steps: obtaining multiple candidate adjustment plans stored in the database (such as line expansion, adding transformers, installing reactive power compensation devices, etc.); simulating and predicting the load forecast results after the implementation of each candidate adjustment plan; performing a difference analysis between the load forecast results and the set grid carrying capacity to obtain the difference results, and determining the adjustment plan for the distribution network area requiring adjustment. The difference results include active power difference (YG), reactive power difference (WG), and apparent power difference (SZ). This process verifies the plan's ability to cope with load growth in advance, avoiding capacity gaps after actual implementation and solving the problem of the inability to quantify the effects of plans in advance in traditional planning.

[0064] The load forecast results are compared with the set grid carrying capacity to determine the adjustment scheme for the distribution network area that needs adjustment. This includes the following steps: Determining if the active power difference, reactive power difference, and apparent power difference are all greater than 0; if not, deleting the corresponding candidate adjustment scheme; if so, retaining the corresponding candidate adjustment scheme. Simultaneously, calculating the difference coefficient CZ based on the active power difference, reactive power difference, and apparent power difference: CZ = λ1*YG + λ2*WG + λ3*SZ; where λ1, λ2, and λ3 are weighting factors; the candidate adjustment scheme corresponding to the largest difference coefficient is recorded as the adjustment scheme for the distribution network area that needs adjustment. Multi-dimensional load indicators are integrated into quantitative values. For example, a scheme with a slightly lower active power difference but significant reactive power improvement may still be selected through weight allocation, solving the scheme imbalance problem caused by "single indicator priority" in traditional decision-making.

[0065] A GIS-based multi-year planning layer iterative update device for power distribution networks, such as Figure 2 As shown, the system includes an initial layer acquisition module, a data acquisition module, an adjustment area determination module, and a layer update module. Specifically: the initial layer acquisition module acquires multi-source distribution network data and establishes an initial GIS planning layer based on this data; the data acquisition module acquires a digital twin model of the distribution network and obtains distribution network operation status data based on this model; the adjustment area determination module performs risk assessments based on the distribution network operation status data to determine the areas requiring adjustment; and the layer update module determines adjustment schemes for the areas requiring adjustment and updates the initial GIS planning layer based on these schemes.

[0066] An electronic device includes: a processor; and a memory storing computer program instructions that, when executed by the processor, cause the processor to perform the GIS-based multi-year planning layer iterative update method for power distribution networks as described above.

[0067] A computer-readable storage medium for storing a program that, when executed by a processor, implements the GIS-based multi-year planning layer iterative update method for power distribution networks as described above.

[0068] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0069] This invention is described with reference to flowchart illustrations and / or block diagrams of systems, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0073] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A GIS-based method for iterative updating of multi-year planning layers in power distribution networks, characterized in that: Includes the following steps: Acquire multi-source power distribution network data and establish an initial GIS planning layer based on the multi-source power distribution network data; Obtain a digital twin model of the distribution network, and then obtain distribution network operation status data based on the digital twin model of the distribution network; Risk assessment is conducted based on distribution network operation status data to determine the areas where distribution network adjustments are necessary. Determine the adjustment plan for the area where the power distribution network needs to be adjusted, and update the initial planning layer of the GIS based on the adjustment plan.

2. The method for iterative updating of multi-year planning layers for power distribution networks based on GIS according to claim 1, characterized in that, Establishing an initial GIS planning layer based on multi-source power distribution network data includes the following steps: The data format of the multi-source distribution network data is converted to adapt to the GIS system. The multi-source distribution network data includes distribution network operation data, geographic information data of the distribution network planning area, regional development planning and land use planning data, and power grid equipment ledger data. The converted multi-source power distribution network data is integrated into the GIS database to construct a basic data layer for power distribution network planning. Load forecasting is performed on the distribution network to obtain the load forecast results. These results are then compared and evaluated with the current carrying capacity of the distribution network to determine whether there is a planning need for the distribution network. If it does not exist, the output distribution network planning basic data layer will be the GIS initial planning layer; If such areas exist, perform network topology analysis to identify weak points in the distribution network. Based on the weak areas of the power distribution network, a planning adjustment scheme is determined, and the planning adjustment scheme is drawn into the GIS system to output the initial planning layer of the GIS.

3. The method for iterative updating of multi-year planning layers for power distribution networks based on GIS according to claim 2, characterized in that, To perform load forecasting on the distribution network and obtain the load forecasting results, the following steps are included: Collect historical load data, including active power, reactive power, and apparent power; Simultaneously, data on influencing factors corresponding to historical load data are collected, including natural factors, social factors, and economic factors; Historical load data and influencing factor data were normalized, and a multiple linear regression model was constructed: Where y is the predicted value, x1, x2, ..., x n Let β0, β1, β2, ..., β be the variables of each influencing factor. n All are regression coefficients. This is the error term; The normalized historical load data and influencing factor data are divided into training set and test set. The training set is used to train the multiple linear regression model. The regression coefficients are continuously adjusted by the least squares optimization algorithm to minimize the error between the predicted value and the actual load value of the multiple linear regression model. The optimal regression coefficients are determined to obtain the trained load prediction model. Data on actual influencing factors are obtained and input into the trained load forecasting model to obtain load forecasting results, including predicted active power, predicted reactive power and predicted apparent power. If any of the load forecast results exceeds the current carrying capacity of the distribution network, then there is a planning need; If none of the items in the load forecast results are greater than the current distribution network's carrying capacity, then there is no planning demand.

4. The method for iterative updating of multi-year planning layers for power distribution networks based on GIS according to claim 2, characterized in that, Performing network topology analysis to identify weak points in the distribution network includes the following steps: Based on the network analysis function of the GIS system, the topology of the distribution network is constructed using distribution network equipment and lines as nodes and connecting lines. Based on the established topology, the connection relationships between lines are analyzed to identify the power transmission paths and flow directions of the entire distribution network. By comparing the real-time current of the line with the rated current of the line, the line whose real-time current exceeds the rated current is identified and recorded as an overload line. Based on the real-time collected voltage data, areas where the voltage data is lower than the standard voltage are identified and recorded as low voltage areas; Identify distribution network equipment and lines where the number of faults exceeds a set threshold and record them as high-frequency fault areas; In the basic data layer of the distribution network planning, overloaded lines, low-voltage areas, and high-frequency fault areas are marked to identify the weak areas of the distribution network.

5. The method for iterative updating of multi-year planning layers for power distribution networks based on GIS according to claim 2, characterized in that, Determining planning adjustment schemes based on weak areas of the power distribution network includes the following steps: Obtain multiple candidate planning schemes for weak areas of the power distribution network; Multiple performance analyses were performed on various candidate planning schemes to determine the comprehensive evaluation coefficient for each candidate planning scheme. The candidate planning scheme corresponding to the largest comprehensive evaluation coefficient is determined and denoted as the planning adjustment scheme.

6. The method for iterative updating of multi-year planning layers for power distribution networks based on GIS according to claim 5, characterized in that, Perform multiple performance analyses to determine the comprehensive evaluation coefficients for each candidate planning scheme, including the following steps: Based on the buffer analysis function of GIS, spatial adaptability analysis is performed on the new facilities in each candidate planning scheme: a buffer of a certain radius is set for each new facility, the proportion of sensitive areas within the buffer is viewed, and the total proportion of sensitive areas Mg of each candidate planning scheme is obtained. Based on the network analysis function of GIS, the distribution network topology after the implementation of each candidate planning scheme is simulated, the number of connection paths between power supply points and load points under different candidate planning schemes is calculated, and the proportion of single power supply Dg is determined. Based on the attribute statistical analysis function of GIS, the estimated cost of each candidate planning scheme is calculated, and the ratio of the estimated cost to the budgeted cost is calculated to obtain the cost ratio Cg. Network topology analysis is performed on each candidate planning scheme to determine the ratio Bg of the number of weak areas to the allowable number of weak areas for each candidate planning scheme. The comprehensive evaluation coefficient Zpx is determined based on the proportion of total sensitive areas, the proportion of single-power supply units, the cost ratio, and the proportion of weak areas. Among them, α1, α2, α3 and α4 are all weighting factors.

7. The method for iterative updating of multi-year planning layers for power distribution networks based on GIS according to claim 1, characterized in that, Risk assessment is conducted based on distribution network operation status data to determine areas where adjustments to the distribution network are necessary, including the following steps: Based on the power grid structure, the distribution network is divided into regions to obtain each distribution region; The system acquires the power distribution network operation status data of each distribution area and inputs the data into a trained risk assessment model to output the risk assessment level. The trained risk assessment model is based on a machine learning-based decision tree model. Distribution areas with risk assessment levels exceeding the set threshold are designated as areas requiring adjustment of the distribution network.

8. The method for iterative updating of multi-year planning layers for power distribution networks based on GIS according to claim 1, characterized in that, Determine the adjustment plan for the area requiring adjustment of the power distribution network, including the following steps: Retrieve multiple candidate adjustment schemes stored in the database; Simulate and predict the load forecast results after the implementation of each candidate adjustment scheme; The load forecast results are compared with the set grid carrying capacity to obtain the difference results. The adjustment scheme for the distribution network area that needs to be adjusted is determined. The difference results include active power difference YG, reactive power difference WG and apparent power difference SZ.

9. The method for iterative updating of multi-year planning layers for power distribution networks based on GIS according to claim 8, characterized in that, By performing a difference analysis between the load forecast results and the set grid carrying capacity, the adjustment plan for the distribution network area that needs adjustment is determined, including the following steps: Determine whether the active power difference, reactive power difference, and apparent power difference are all greater than 0: Otherwise, delete the corresponding candidate adjustment scheme; If so, the corresponding candidate adjustment scheme is retained, and the difference coefficient CZ is calculated based on the active power difference, reactive power difference, and apparent power difference: CZ = λ1*YG + λ2*WG + λ3*SZ; Wherein, λ1, λ2 and λ3 are all weighting factors; The candidate adjustment scheme corresponding to the largest difference coefficient is recorded as the adjustment scheme for the distribution network area that needs to be adjusted.

10. A GIS-based multi-year planning layer iterative update device for power distribution networks, applied to the GIS-based multi-year planning layer iterative update method for power distribution networks as described in any one of claims 1-9, characterized in that, It includes an initial layer acquisition module, a data acquisition module, an adjustment area determination module, and a layer update module, among which: The initial layer acquisition module is used to acquire multi-source power distribution network data and establish an initial GIS planning layer based on the multi-source power distribution network data; The data acquisition module is used to acquire the digital twin model of the distribution network and acquire the operating status data of the distribution network based on the digital twin model of the distribution network. The adjustment area determination module is used to conduct risk assessments based on distribution network operation status data and determine the areas of the distribution network that need to be adjusted. The layer update module is used to determine the adjustment plan for the power distribution network area that needs to be adjusted, and to update the initial GIS planning layer based on the adjustment plan.

Images