A power distribution network grid power supply mode construction method and device and a readable storage medium

Abstract

The application discloses a power distribution network grid power supply mode construction method and device and a readable storage medium. According to different power distribution network types, corresponding power distribution network grid evaluation models are established, grid evaluation features are extracted from the power distribution network grid to be constructed according to the power distribution network grid evaluation model, corresponding evaluation values and grid scenes are determined, a preset weight value construction model is used to determine the weight value corresponding to the grid evaluation features, the comprehensive evaluation result of the power distribution network grid to be constructed is determined based on the evaluation value and the weight value corresponding to the grid evaluation features, and finally, the power distribution network grid to be constructed is constructed in the power supply mode based on the grid scene and the comprehensive evaluation result. The power distribution network grid is constructed in the power supply mode by comprehensively considering the grid scene and the comprehensive evaluation result, better planning of the power distribution network can be realized, the method is applicable to different types of power systems, and is particularly applicable to new power systems.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and in particular to a method and device for constructing a power supply mode in a distribution network, and a readable storage medium. Background Art

[0002] As the photovoltaic industry advances, distributed power generation (DGs) are widely used. Distributed power sources offer effective peak-shaving capabilities and are relatively simple to operate. The large-scale integration of DGs has increased the complexity of distribution network structures, increased voltage levels, and presented a growing number of challenges. Furthermore, the differentiated access methods and capacities of DGs have varying impacts on distribution network characteristics, posing varying demands on power supply models. Therefore, addressing grid planning is a prerequisite for ensuring the safe and stable operation of the new power system. To reduce the complexity of distribution network planning under the new power system, grid-based planning has emerged.

[0003] The grid division system for the new power system has two requirements for division indicators: first, it must conform to the development characteristics of the new power system, and second, the indicators must be applicable to the distribution network grid. Traditional distribution network grid division methods mainly refer to the "Technical Guidelines for Distribution Network Planning and Design" (Q / GDW 10738-2020), in which the division of power supply areas only refers to load density. As the penetration rate of distributed generation in the new power system continues to increase, traditional distribution network grid division methods are gradually unable to adapt to distribution network planning under high distributed generation penetration rates. It is necessary to propose a new distribution network grid division method that takes into account the characteristics of the new power system. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, device and readable storage medium for constructing a distribution network grid power supply mode, which can be applied to different types of power systems, especially new power systems, to achieve better planning of the distribution network.

[0005] In order to solve the above technical problems, a technical solution adopted by the present invention is:

[0006] A method for constructing a power supply mode of a distribution network includes the following steps:

[0007] Determine the type of distribution network, and establish a corresponding distribution network grid evaluation model according to the distribution network type;

[0008] Extracting grid evaluation features from the distribution network grid of the power supply mode to be constructed according to the distribution network grid evaluation model;

[0009] Determining an evaluation value corresponding to the grid evaluation feature based on the distribution network grid evaluation model, and determining a grid scenario corresponding to the distribution network grid of the power supply mode to be constructed according to the evaluation value;

[0010] A model is constructed using preset weights to determine weights corresponding to the grid evaluation features;

[0011] Determining a comprehensive evaluation result of the distribution network grid of the power supply mode to be constructed according to the evaluation value and weight corresponding to the grid evaluation feature;

[0012] A power supply mode is constructed for the distribution network grid of the power supply mode to be constructed according to the grid scenario and the comprehensive evaluation result.

[0013] In order to solve the above technical problems, another technical solution adopted by the present invention is:

[0014] A distribution network grid power supply mode construction device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, each step of the above-mentioned distribution network grid power supply mode construction method is implemented.

[0015] In order to solve the above technical problems, another technical solution adopted by the present invention is:

[0016] A computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the various steps in the above-mentioned method for constructing a distribution network grid power supply mode.

[0017] The beneficial effects of the present invention are as follows: establishing corresponding distribution network grid evaluation models according to different distribution network types, extracting grid evaluation features from the distribution network grid of the power supply mode to be constructed according to the distribution network grid evaluation model, determining corresponding evaluation values ​​and grid scenarios, and using a preset weight construction model to determine weights corresponding to the grid evaluation features, determining comprehensive evaluation results of the distribution network grid of the power supply mode to be constructed based on the evaluation values ​​and weights corresponding to the grid evaluation features, and finally constructing the power supply mode of the distribution network grid of the power supply mode to be constructed based on the grid scenarios and comprehensive evaluation results; matching the corresponding distribution network grid evaluation model based on the distribution network type, determining the adapted grid evaluation features according to the different distribution network types, ensuring the integrity and accuracy of the distribution network grid evaluation, and dividing the grid scenarios based on the evaluation values ​​corresponding to the grid evaluation features, and constructing the power supply mode of the distribution network grid by comprehensively considering the grid scenarios and comprehensive evaluation results, which can achieve better planning of the distribution network and can be applicable to different types of power systems, especially new power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flow chart of the steps of a method for constructing a power supply mode of a distribution network according to an embodiment of the present invention;

[0019] Figure 2A schematic diagram of the structure of a distribution network grid evaluation model established in an embodiment of the present invention;

[0020] Figure 3 A schematic diagram of grid scene division in the balance dimension according to an embodiment of the present invention;

[0021] Figure 4 A schematic diagram of grid scene division in the flexibility dimension according to an embodiment of the present invention;

[0022] Figure 5 A schematic diagram of grid scene division in the dimension of resilience according to an embodiment of the present invention;

[0023] Figure 6 A flowchart of the steps for determining the indicator weights according to an embodiment of the present invention;

[0024] Figure 7 A schematic structural diagram of a device for constructing a power supply mode in a distribution network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To illustrate the technical content, achieved objectives and effects of the present invention in detail, the following description is given in conjunction with the embodiments and accompanying drawings.

[0026] The above-mentioned distribution network grid power supply mode construction method, device and readable storage medium of the present application can be applied to power planning of different types of distribution networks, especially to new power systems. The following is an explanation through specific implementation methods:

[0027] In an optional embodiment, if Figure 1 As shown, a method for constructing a distribution network grid power supply mode includes the following steps:

[0028] Determine the type of distribution network, and establish a corresponding distribution network grid evaluation model based on the distribution network type; for example, in new power systems, the key characteristic indicators that need to be considered are not only load density, but also distributed power sources, load initiative, and energy storage regulation capabilities have become important characteristic indicators of new power systems. At the same time, natural disasters and power electronic equipment disturbances are key factors affecting power supply reliability. In the evaluation of power supply grid indicators of new power systems with high reliability, disasters and disturbances should be considered. Therefore, the grid division can be considered from three aspects: balance level, flexibility level, and resilience level. A complete grid division system based on balance level, auxiliary flexibility level, and reference resilience level is formed to construct a distribution network grid evaluation model to guide the construction of target power supply modes for each grid;

[0029] Extracting grid evaluation features from the distribution network grid of the power supply mode to be constructed according to the distribution network grid evaluation model;

[0030] Determining an evaluation value corresponding to the grid evaluation feature based on the distribution network grid evaluation model, and determining a grid scenario corresponding to the distribution network grid of the power supply mode to be constructed according to the evaluation value;

[0031] A model is constructed using preset weights to determine weights corresponding to the grid evaluation features;

[0032] Determining a comprehensive evaluation result of the distribution network grid of the power supply mode to be constructed according to the evaluation value and weight corresponding to the grid evaluation feature;

[0033] A power supply mode is constructed for the distribution network grid of the power supply mode to be constructed according to the grid scenario and the comprehensive evaluation result.

[0034] In another optional embodiment, with a new type of power system, a Figure 2 The distribution network grid evaluation model shown;

[0035] Since the power grid under the new power system needs to consider the grid division and target power supply mode from the three aspects of balance, flexibility and resilience, the new power system grid characteristic evaluation index system should propose various evaluation indicators from the three aspects of balance, flexibility and resilience;

[0036] The entire evaluation index system is divided into three layers. The first layer is comprehensive characteristics, which are used to comprehensively evaluate the grid's demand for high reliability of power supply mode; the second layer is primary characteristics, which are used to express the grid's three-dimensional attributes of balance, flexibility, and resilience; the third layer is secondary characteristics, which are used to quantify the three-dimensional attributes separately, so that the entire index system can be combined with reality and intuitively reflect the values ​​of various grid indicators, as shown in Table 1.

[0037] Table 1

[0038]

[0039]

[0040] That is to say, the grid evaluation characteristics include one or more of load density, administrative level, regional level, distributed power supply penetration rate, distributed photovoltaic adjustability rate, distributed photovoltaic controllability rate, electric vehicle charging load penetration rate, load responsiveness rate, energy storage power penetration rate, energy storage power penetration rate, typhoon power outage frequency, pollution power outage frequency, icing power outage frequency, flood power outage frequency, harmonic power outage frequency, voltage flicker power outage frequency and power fluctuation power outage frequency. The specific grid evaluation characteristics included can be set according to the actual distribution network type.

[0041] In another optional implementation, a method for determining the characteristic value corresponding to each grid evaluation feature may be set. Table 2 shows an optional method for determining each grid evaluation feature.

[0042] Table 2

[0043]

[0044]

[0045] In another optional embodiment, the method further comprises the steps of:

[0046] Acquire a corresponding distribution network grid sample data set according to the grid evaluation feature, each distribution network grid sample data set includes a grid evaluation feature and its corresponding evaluation value;

[0047] Performing cluster analysis on the grid evaluation features and their corresponding evaluation values;

[0048] Determine the evaluation value ranges of multiple grid scenarios and their corresponding grid evaluation features according to the cluster analysis results;

[0049] Saving the mapping relationship between the grid scene and the evaluation value range of the corresponding grid evaluation feature;

[0050] Determining the grid scenario corresponding to the distribution network grid of the power supply mode to be constructed according to the evaluation value includes:

[0051] A grid scenario corresponding to the distribution network grid of the power supply mode to be constructed is determined according to the evaluation value and the mapping relationship.

[0052] In another optional embodiment, the performing cluster analysis on the grid evaluation features and their corresponding evaluation values ​​includes:

[0053] The grid evaluation feature includes a first grid evaluation feature and a second grid evaluation feature;

[0054] Performing cluster analysis on the first grid evaluation features and their corresponding first evaluation values ​​to obtain a plurality of grid coarse scenes;

[0055] Each network coarse scene in the plurality of grid coarse scenes is subdivided into a plurality of network fine scenes according to the second network evaluation feature and its corresponding second evaluation value.

[0056] The following is a detailed explanation using the new power system as an example:

[0057] (1) Balanced scenario

[0058] The grid's balance is graded and evaluated using a scale of A+ to E- based on economic and load development. First, grids are clustered into five scenarios (A, B, C, D, and E) based on net saturated load density. Each scenario is then further clustered into three categories based on distributed renewable energy density. Based on the clustering results, the upper and lower limits of the grid's net saturated load density and distributed renewable energy density are determined, thereby determining the scenario to which the grid belongs. The scenario classification is shown in Table 3.

[0059] Table 3

[0060]

[0061]

[0062] Among them, the upper and lower limits of the net saturated load density The inter-cluster distance of the system clustering results is calculated based on the Wald method (the sum of squared deviations method), and the upper and lower limits of the net load density are determined by the 90% of samples closest to the upper limit (the 5% with the furthest distance to the upper limit and the 5% with the furthest distance to the lower limit are removed to reduce the influence of extreme parameters and thus determine the upper and lower limits); the upper and lower limits of the distributed renewable energy density Similarly, the determination of the indicator values ​​in the flexibility scenario and the resilience scenario adopts the same method, and the final scenario division is as follows: Figure 3 shown.

[0063] (2) Flexibility scenarios

[0064] The scenarios are divided based on the flexibility index, and the system clustering method is used to form a typical scenario classification.

[0065] Typical scenarios for grid division using diverse power attributes are shown in Table 4:

[0066] Table 4

[0067] feature Highly scalable grid Low-Scheduling Grid Unscheduled Grid Distributed photovoltaic adjustable rate <![CDATA[(a2,a3)]]> <![CDATA[(a1,a2)]]> <![CDATA[(0,a1)]]> Distributed photovoltaic controllability <![CDATA[(b2,b3)]]> <![CDATA[(b1,b2)]]> <![CDATA[(0,b1)]]>

[0068] Typical scenarios for grid division using multiple load attributes are shown in Table 5:

[0069] Table 5

[0070] feature Highly responsive grid Low-response grid Non-responsive grid Electric vehicle load penetration rate <![CDATA[(c2,c3)]]> <![CDATA[(c1,c2)]]> <![CDATA[(0,c1)]]> Load responsiveness <![CDATA[(d2,d3)]]> <![CDATA[(d1,d2)]]> <![CDATA[(0,d1)]]>

[0071] Typical scenarios for multi-terminal energy storage attribute division grids are shown in Table 6:

[0072] Table 6

[0073] feature Emphasize section grid Weakly regulated grid Unregulated grid Energy storage power penetration rate <![CDATA[(e2,e3)]]> <![CDATA[(e1,e2)]]> <![CDATA[(0,e1)]]> Energy storage power penetration rate <![CDATA[(f2,f3)]]> <![CDATA[(f1,f2)]]> <![CDATA[(0,f1)]]>

[0074] The final scene division is as follows Figure 4 shown.

[0075] (3) Resilience Scenario

[0076] Based on the resilience index, the scenarios are divided and the typical scenario classification is formed using the system clustering method. The typical scenarios of the disaster prevention attribute division grid are shown in Table 7:

[0077] Table 7

[0078] feature High Disaster Resistance Grid Medium Disaster Resilience Grid Lower Disaster Resilience Grid Typhoon power outage frequency (times / year) <![CDATA[(g2,g3)]]> <![CDATA[(g1,g2)]]> <![CDATA[(0,g1)]]> Frequency of power outages caused by lightning (times / year) <![CDATA[(h2,h3)]]> <![CDATA[(h1,h2)]]> <![CDATA[(0,h1)]]> Frequency of power outages due to pollution (times / year) <![CDATA[(i2,i3)]]> <![CDATA[(i1,i2)]]> <![CDATA[(0,i1)]]> Frequency of power outages due to icing (times / year) <![CDATA[(j2,j3)]]> <![CDATA[(j1,j2)]]> <![CDATA[(0,j1)]]> Frequency of power outages due to floods (times / year) <![CDATA[(k2,k3)]]> <![CDATA[(k1,k2)]]> <![CDATA[(0,k1)]]>

[0079] Typical scenarios for grid division based on anti-interference properties are shown in Table 8:

[0080] Table 8

[0081] feature Grids with high anti-disturbance requirements Medium disturbance resistance demand grid More resistant to disturbances demand grid Harmonic power outage frequency (times / year) <![CDATA[(l2,l3)]]> <![CDATA[(l1,l2)]]> <![CDATA[(0,l1)]]> Voltage flicker power outage frequency (times / year) <![CDATA[(m2,m3)]]> <![CDATA[(m1,m2)]]> <![CDATA[(0,m1)]]> Power fluctuation outage frequency (times / year) <![CDATA[(n2,n3)]]> <![CDATA[(n1,n2)]]> <![CDATA[(0,n1)]]>

[0082] The final scene division is as follows Figure 5 shown.

[0083] In another optional embodiment, as Figure 6 As shown, the method of using a preset weight to construct a model to determine the weight corresponding to the grid evaluation feature includes:

[0084] The sampling analytic hierarchy process determines the first weight corresponding to the grid evaluation feature, namely the subjective weight: A = [a1, a2, a3, ..., a n ] T (a total of n grid evaluation features);

[0085] The sampling principal component analysis method determines the second weight corresponding to the grid evaluation feature, that is, the objective weight: B = [b1, b2, b3, ..., b n ] T ;

[0086] Determine a weight deviation between the first weight and the second weight:

[0087] C=BA=[c1,c2,c3,…,c n ] T ;

[0088] Determining whether the first weight and the second weight are consistent based on the weight deviation; if so, determining the geometric mean of the first weight and the second weight as the weight corresponding to the grid evaluation feature; otherwise, determining the weight fluctuation and the weight fluctuation value based on the weight deviation, and determining the weight corresponding to the grid evaluation feature based on the geometric mean of the first weight and the second weight, the weight fluctuation and the weight fluctuation value;

[0089] The determining, based on the weight deviation, whether the first weight value and the second weight value are consistent includes:

[0090] Determine the consistency index k according to the weight deviation: k = |C|;

[0091] like Then the first weight and the second weight are consistent, otherwise, the first weight and the second weight are inconsistent, where α is a consistency standard parameter and n is the number of grid evaluation features.

[0092] in, The smaller the k value, the better the consistency of subjective and objective weights. The larger the k value, the more inconsistent the subjective and objective weights. Calculate the subjective and objective weight consistency index k and set the consistency standard α, α∈[0,1];

[0093] Determining the weight corresponding to the grid evaluation feature according to the geometric mean of the first weight and the second weight, the weight fluctuation, and the weight fluctuation value includes:

[0094]

[0095] When d i ≥1, the weight corresponding to the grid evaluation feature is [w i -e i ,w i +e i ], when d i <1, the weight corresponding to the grid evaluation feature is w i ;

[0096] Among them, w i represents the geometric mean of the first and second weights, a i represents the first weight corresponding to the i-th grid evaluation feature, b i represents the second weight corresponding to the i-th grid evaluation feature, c i Represents the weight deviation between the first weight and the second weight corresponding to the i-th grid evaluation feature.

[0097] In another optional embodiment, the weights are further standardized. Specifically, when the subjective and objective weights are substantially consistent, the comprehensive weights of the indicators are standardized as follows:

[0098]

[0099] In the case of inconsistency between subjective and objective weights, the upper and lower limits of the weights of the inconsistent indicators are standardized as follows:

[0100]

[0101] When the subjective and objective weights are inconsistent, when calculating the comprehensive evaluation, the comprehensive weight is first obtained by weighted summation as w iThe index comprehensive score reference value x at the time of , and then calculate the index comprehensive score fluctuation value x corresponding to the upper and lower limits of the inconsistent index weights respectively min and x max , proposed comprehensive score fluctuation range [x min ,x max ], providing further reference value for the target power supply scenario type and power supply mode.

[0102] In this embodiment, compared with the existing evaluation index weighting technology, which usually performs comprehensive weighting based on consistent subjective and objective weights (that is, by solving the weight coefficient, the weight coefficient is adjusted to achieve consistency between the subjective and objective weights) to obtain an accurate weight value, such methods usually lose the subjective weight characteristics and cannot represent the objective weight characteristics, often resulting in the effect of taking both into account but neither representation is significant. This embodiment believes that when the subjective and objective are inconsistent, it is not appropriate to adopt an accurate weight value expression. It is recommended to express the weight characteristics with a range value. The accurate weight value of the subjective and objective comprehensive considerations is only a reference value, and its upper and lower limit range values ​​provide additional reference standards for the final decision, expand the range of reasonable choices, and avoid the unreasonable situation where a single weight causes certain indicators to have excessive tendencies, providing diversified decision-making ideas for power grid planning and construction, thereby achieving better power grid planning.

[0103] The following is described by specific examples:

[0104] Taking a certain grid as an example, based on the power grid data of a certain region, a sample library of grid indicators for the region is established. By applying the above-mentioned analytic hierarchy process and principal component analysis method, the weights of the evaluation indicators of the new power system grid characteristics are obtained as shown in Table 9 (taking α = 0.2):

[0105] Table 9

[0106]

[0107]

[0108] Through system clustering, the scene division parameters are shown in Table 10-12:

[0109] Table 10

[0110]

[0111] Table 11

[0112]

[0113]

[0114] Table 12

[0115] feature High Disaster Resistance Grid Medium Disaster Resilience Grid Lower Disaster Resilience Grid Typhoon power outage frequency (times / year) ＞3.5 1.5～3.5 0～1.5 Frequency of power outages caused by lightning (times / year) ＞4.9 0.5～4.9 0～0.5 Frequency of power outages due to pollution (times / year) ＞2.1 0.3～2.1 0～0.3 Frequency of power outages due to icing (times / year) ＞0.5 0.1～0.5 0～0.1 Frequency of power outages due to floods (times / year) ＞0.5 0.1～0.5 0～0.1 feature Grids with high anti-disturbance requirements Medium disturbance resistance demand grid More resistant to disturbances demand grid Harmonic power outage frequency (times / year) ＞1 0.1～1 0～0.1 Voltage flicker power outage frequency (times / year) ＞1 0.1～1 0～0.1 Power fluctuation outage frequency (times / year) ＞1 0.1～1 0～0.1

[0116] The grid indicator parameters and corresponding evaluation values ​​are shown in Table 13:

[0117] Table 13

[0118]

[0119]

[0120] Combining the scenario classification standards of balance, flexibility, and resilience in a certain region, the scenario to which a certain grid belongs and its comprehensive evaluation are shown in Table 14:

[0121] Table 14

[0122]

[0123] The higher the comprehensive grid grade evaluation score, the higher the grid's demand for grid construction intensity; the upper and lower limits of the comprehensive grid grade evaluation can be used as error references, and the scenarios and evaluation indicators can guide the construction of grid power supply modes under new power systems.

[0124] In another optional embodiment, as Figure 7 As shown, a distribution network grid power supply mode construction device includes a memory, a processor and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, each step of a distribution network grid power supply mode construction method described in any one of the above embodiments is implemented.

[0125] In another optional embodiment, a computer-readable storage medium stores computer program instructions thereon, and when the computer program instructions are executed by a processor, the steps of the method for constructing a distribution network grid power supply mode described in any of the above embodiments are implemented.

[0126] In summary, the present invention provides a method, device and readable storage medium for constructing a distribution network grid power supply mode, which establishes corresponding distribution network grid evaluation models according to different distribution network types, extracts grid evaluation features from the distribution network grid of the power supply mode to be constructed according to the distribution network grid evaluation model, determines the corresponding evaluation values ​​and grid scenarios, and adopts a weight construction model that considers the consistency of subjective and objective weights to determine the weights corresponding to the grid evaluation features, and determines the comprehensive evaluation results of the distribution network grid of the power supply mode to be constructed based on the evaluation values ​​and weights corresponding to the grid evaluation features. Finally, based on the grid scenarios and comprehensive evaluation results, the power supply mode of the distribution network grid to be constructed is constructed; based on the distribution network type matching corresponding distribution network grid evaluation model, it is possible to determine the adapted grid evaluation features according to different distribution network types, thereby ensuring the integrity and accuracy of the distribution network grid evaluation, and at the same time, the grid scenarios are divided based on the evaluation values ​​corresponding to the grid evaluation features, and the power supply mode of the distribution network grid is constructed by comprehensively considering the grid scenarios and comprehensive evaluation results, which can achieve better planning of the distribution network and can be applicable to different types of power systems, especially new power systems.

[0127] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's description and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for constructing a power supply mode of a distribution network, characterized in that: Including steps: Determine the type of distribution network, and establish a corresponding distribution network grid evaluation model according to the distribution network type; Extracting grid evaluation features from the distribution network grid of the power supply mode to be constructed according to the distribution network grid evaluation model; Determining an evaluation value corresponding to the grid evaluation feature based on the distribution network grid evaluation model, and determining a grid scenario corresponding to the distribution network grid of the power supply mode to be constructed according to the evaluation value; A model is constructed using preset weights to determine weights corresponding to the grid evaluation features; Determining a comprehensive evaluation result of the distribution network grid of the power supply mode to be constructed according to the evaluation value and weight corresponding to the grid evaluation feature; Constructing a power supply mode for the distribution network grid to be constructed according to the grid scenario and the comprehensive evaluation result; The grid evaluation characteristics include one or more of load density, administrative level, regional level, distributed power supply penetration rate, distributed photovoltaic adjustability rate, distributed photovoltaic controllability rate, electric vehicle charging load penetration rate, load response rate, energy storage power penetration rate, energy storage power penetration rate, typhoon power outage frequency, pollution power outage frequency, icing power outage frequency, flood power outage frequency, harmonic power outage frequency, voltage flicker power outage frequency, and power fluctuation power outage frequency; Also includes the steps: Acquire a corresponding distribution network grid sample data set according to the grid evaluation feature, each distribution network grid sample data set includes a grid evaluation feature and its corresponding evaluation value; Performing cluster analysis on the grid evaluation features and their corresponding evaluation values; Determine the evaluation value ranges of multiple grid scenarios and their corresponding grid evaluation features according to the cluster analysis results; Saving the mapping relationship between the grid scene and the evaluation value range of the corresponding grid evaluation feature; Determining the grid scenario corresponding to the distribution network grid of the power supply mode to be constructed according to the evaluation value includes: Determine a grid scenario corresponding to the distribution network grid of the power supply mode to be constructed according to the evaluation value and the mapping relationship; The method of using a preset weight value to construct a model to determine the weight value corresponding to the grid evaluation feature includes: Determining a first weight corresponding to the grid evaluation feature using a hierarchical analysis method; Using principal component analysis to determine the second weight corresponding to the grid evaluation feature; determining a weight deviation between the first weight and the second weight; According to the weight deviation, determine whether the first weight and the second weight are consistent. If so, determine the geometric mean of the first weight and the second weight as the weight corresponding to the grid evaluation feature. Otherwise, determine the weight fluctuation and the weight fluctuation value according to the weight deviation, and determine the weight corresponding to the grid evaluation feature according to the geometric mean of the first weight and the second weight, the weight fluctuation and the weight fluctuation value.

2. A method for constructing a power supply mode of a distribution network according to claim 1, characterized in that: The cluster analysis of the grid evaluation features and their corresponding evaluation values ​​includes: The grid evaluation feature includes a first grid evaluation feature and a second grid evaluation feature; Performing cluster analysis on the first grid evaluation features and their corresponding first evaluation values ​​to obtain a plurality of grid coarse scenes; Each network coarse scene in the plurality of grid coarse scenes is subdivided into a plurality of network fine scenes according to the second grid evaluation feature and its corresponding second evaluation value.

3. A method for constructing a power supply mode of a distribution network according to claim 1, characterized in that: The determining, based on the weight deviation, whether the first weight value and the second weight value are consistent includes: Determine the consistency index based on the weight deviation ; like , then the first weight and the second weight are consistent, otherwise, the first weight and the second weight are inconsistent, wherein, is the consistency standard parameter, The number of features to evaluate for the mesh.

4. A method for constructing a power supply mode of a distribution network according to claim 3, characterized in that: Determining the weight corresponding to the grid evaluation feature according to the geometric mean of the first weight and the second weight, the weight fluctuation, and the weight fluctuation value includes: when When the weight corresponding to the grid evaluation feature is ,when When the weight corresponding to the grid evaluation feature is ; in, represents the geometric mean of the first weight and the second weight, represents the first weight corresponding to the i-th grid evaluation feature, represents the second weight corresponding to the i-th grid evaluation feature, Represents the weight deviation between the first weight and the second weight corresponding to the i-th grid evaluation feature.

5. A device for constructing a power supply mode of a distribution network, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, each step of the method for constructing a distribution network grid power supply mode according to any one of claims 1 to 4 is implemented.

6. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the steps of the method for constructing a distribution network grid power supply mode according to any one of claims 1 to 4 are implemented.

Images