Power distribution network planning method suitable for distributed new energy access

Abstract

The invention discloses a power distribution network planning method suitable for distributed new energy access, and relates to the technical field of power distribution networks. The method comprises the following steps: calculating a power distribution network subarea data feature weight through an entropy weight method; clustering data by using a KMEANS algorithm to generate a power distribution network subarea cluster, and calculating a weighted clustering center by combining a clustering center and a feature weight; and scoring the weighted clustering center by adopting a sorting method approximate to an ideal solution, and dividing functional labels of the power grid sub-regions. And calculating a channel transmission capability index and a stability index of the power distribution network sub-region, combining to obtain a channel comprehensive index, and classifying the channel comprehensive index as a main road or a redundant channel. Constructing a topological graph based on the function labels and channel categories, counting the number of sub-region main road connections and the number of redundant channel connections, calculating the energy storage index of the power distribution network sub-region by combining the function labels, and deploying central or edge energy storage units; and the adjustable load data and the energy storage unit are integrated, an energy storage load cooperation model is constructed, and dynamic power utilization planning of the power distribution network with new energy access is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution networks, and in particular to a distribution network planning method adapted for access of distributed new energy sources. Background Art

[0002] The rapid development of renewable energy, particularly the large-scale integration of distributed energy sources like photovoltaics and wind power, is posing new challenges to power system operation. Traditional distribution networks are typically planned based on assumptions about static loads and stability. However, the integration of renewable energy significantly increases the volatility and uncertainty of power loads, complicating grid scheduling and management. To ensure safe and reliable grid operation, distribution network planning and optimization require greater sophistication, particularly in the effective integration and scheduling of distributed energy resources, energy storage devices, and adjustable loads. This requires more advanced technologies and methods.

[0003] Currently, many existing technical solutions rely on simplified load forecasting and static analysis methods, based only on the statistical mean of historical data. This results in a lack of accurate quantitative description and real-time response mechanism for the dynamic changes in power load, and fails to effectively capture the dynamic fluctuation characteristics of new energy and make grid adjustments. Summary of the Invention

[0004] In view of the deficiencies of the existing technology, the present invention provides a distribution network planning method adapted to the access of distributed renewable energy, so as to solve the problems raised in the above background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a distribution network planning method adapted to the access of distributed new energy, comprising the following steps:

[0006] Step S1: Collect and preprocess the distribution network sub-area operation data to obtain the distribution network sub-area operation data set, calculate the entropy value of the distribution network sub-area operation data set using the entropy weight method, and obtain the feature weight of each feature column of the distribution network sub-area operation data set;

[0007] Step S2: clustering the distribution network sub-area operation data set using the KMEANS algorithm to obtain distribution network sub-area clusters; calculating weighted cluster centers by combining the cluster centers of the distribution network sub-area clusters and the feature weights of each feature column of the distribution network sub-area operation data set;

[0008] Step S3: Calculating scores for the weighted cluster centers using a ranking method that approximates an ideal solution to obtain a maximum approximation score for the weighted cluster centers; dividing the distribution network sub-areas into functional labels using the maximum approximation score to obtain functional labels for the distribution network sub-areas;

[0009] Step S4: collecting distribution network channel data, the distribution network channel data including: voltage level, feeder capacity, voltage sag probability and short-time frequency response capability; calculating a channel transmission capability index by combining the voltage level and feeder capacity; calculating a channel stability index by combining the channel transmission capability index and the channel stability index; calculating a channel comprehensive index by combining the channel comprehensive index to classify the channels in the distribution network through the data set to obtain channel categories, the channel categories being: main channels and redundant channels; constructing a distribution network channel topology map by using the functional labels of the distribution network sub-areas and the channel categories of the channels;

[0010] Step S5: Obtaining the number of main road connections and redundant channel connections in the distribution network sub-area based on the distribution network channel topology map; calculating an energy storage index for the distribution network sub-area by combining the functional label of the distribution network sub-area, the number of main road connections, and the number of redundant channel connections in the distribution network sub-area; and deploying energy storage units for the distribution network sub-area based on the energy storage index of the distribution network sub-area.

[0011] Step S6: Collect the adjustable load data of the distribution network sub-intervals, build an energy storage load coordination model based on the adjustable load data of the distribution network sub-intervals and the energy storage units, and realize the power consumption planning of the distribution network accessed by new energy through the energy storage load coordination model.

[0012] Preferably, the entropy value calculation of the distribution network operation data set by the entropy weight method to obtain the feature weight of each feature column of the distribution network operation data set includes the following specific steps:

[0013] The entropy value of the feature column in the distribution network sub-area operation data is calculated using the entropy weight method:

[0014]

[0015] in, is the entropy value of the jth feature of the distribution network sub-area operation data, n is the number of samples of the distribution network sub-area operation data, Refers to the proportion of the data of the i-th distribution network sub-area in the j-th feature column, j represents the index of the j-th feature, and i represents the data of the i-th distribution network sub-area;

[0016] Calculate the weight of each feature in the distribution network sub-area operation data:

[0017]

[0018] in, is the weight of the jth feature of the distribution network sub-area operation data, J is the total number of features of the distribution network sub-area operation data, is the entropy value of the jth feature of the distribution network sub-area operation data, and j represents the index of the jth feature.

[0019] Preferably, the step of calculating the weighted cluster center by combining the cluster center of the distribution network sub-area cluster and the feature weight of each feature column of the distribution network sub-area operation data set comprises the following steps:

[0020] By combining the cluster centers of the distribution network sub-area clusters and the feature weights, the weighted cluster centers are calculated:

[0021]

[0022] in, Represents the value of the k-th cluster center after weighting the j-th feature, represents the feature weight of the j-th feature, Indicates the first cluster in the distribution network sub-area cluster The value of the cluster center on the j-th feature, j represents the index of the j-th feature, and K represents the total number of cluster centers.

[0023] Preferably, the step of performing score calculation on the weighted cluster centers by a sorting method close to an ideal solution to obtain the maximum approximation score of the weighted cluster centers comprises the following steps:

[0024] For the distribution network sub-area with functional label L, its positive ideal solution is , the negative ideal solution is ;

[0025] For each distribution network sub-area cluster, calculate the distance between its weighted cluster center and the positive ideal solution of different functional labels of the distribution network sub-area:

[0026]

[0027] in, The distance between the kth distribution network sub-area cluster and the positive ideal solution of the Lth functional label, j represents the index of the jth feature, and J is the total number of features of the distribution network sub-area operation data. Represents the value of the k-th cluster center after weighting the j-th feature, represents the value of the positive ideal solution of the Lth functional label at the jth feature;

[0028] For each distribution network sub-area cluster, calculate the distance between its weighted cluster center and the negative ideal solution of different functional labels of the sub-area:

[0029]

[0030] in, The distance between the kth distribution network sub-area cluster and the negative ideal solution of the Lth functional label, j represents the index of the jth feature, and J is the total number of features of the distribution network sub-area operation data. Represents the value of the k-th cluster center after weighting the j-th feature, represents the value of the negative ideal solution of the Lth feature label at the jth feature;

[0031] For each distribution network sub-area cluster, the maximum approximation score of the distribution network sub-area cluster is calculated by the distance between its weighted cluster center and the positive ideal solution of different functional labels of the sub-area and the distance between the positive ideal solution:

[0032]

[0033] in, Indicates the The maximum similarity score of a cluster reflects its closeness to the ideal solution. The distance between the kth distribution network sub-area cluster and the positive ideal solution of the Lth functional label, The distance between the kth distribution network sub-area cluster and the negative ideal solution of the Lth functional label. max() is the maximum value function, which means taking the maximum similarity score between the kth distribution network sub-area cluster and the L functional labels. represents the similarity score between the kth distribution network sub-area cluster and the Lth functional label.

[0034] Preferably, the method of dividing the distribution network sub-areas into functional labels according to the maximum similarity score to obtain the functional labels of the distribution network sub-areas comprises the following specific steps:

[0035] For the kth distribution network sub-area cluster, by calculating the similarity scores between its weighted cluster center and different functional labels, when the similarity score between the kth distribution network sub-area cluster and the Lth functional label is the maximum, it is the maximum similarity score of the kth distribution network sub-area cluster, and the functional label of the kth distribution network sub-area cluster is .

[0036] Preferably, the step of calculating the channel transmission capability index by combining the voltage level and the feeder capacity comprises the following specific steps:

[0037] By combining the voltage level and feeder capacity, the channel transmission capacity index is calculated:

[0038]

[0039] in, is the channel transmission capability index, V is the voltage level, is the highest voltage of the channel, F is the feeder capacity, is the maximum feeder capacity of the channel.

[0040] Preferably, the calculation of the channel stability index by combining the voltage drop probability and the short-time frequency response capability comprises the following specific steps:

[0041] By combining the voltage drop probability and short-time frequency response capability, the channel stability index is calculated:

[0042]

[0043] in, is the channel stability index, D is the voltage drop probability, Q is the short-time frequency response capability, is the maximum voltage drop probability, It is the maximum value of short-time frequency response capability.

[0044] Preferably, the calculating of the channel comprehensive index by combining the channel transmission capability index and the channel stability index comprises the following specific steps:

[0045] By combining the channel transmission capacity index and the channel stability index, the channel comprehensive index is calculated:

[0046]

[0047] Among them, ZN is the channel comprehensive index, is the channel transmission capability index, is the channel stability index.

[0048] Preferably, the step of calculating the energy storage index of the distribution network sub-area by combining the functional label of the distribution network sub-area, the number of main road connections and the number of redundant channel connections of the distribution network sub-area comprises the following specific steps:

[0049] Based on the distribution network channel topology map, the energy storage index of the distribution network sub-area is calculated by combining the functional label of the distribution network sub-area, the number of main road connections and the number of redundant channel connections in the distribution network sub-area:

[0050]

[0051] in, represents the energy storage index of the ith distribution network sub-area, represents the number of main road connections in the ith distribution network sub-area, The functional label of the kth distribution network sub-area cluster to which the i-th distribution network sub-area belongs, represents the number of redundant channel connections in the ith distribution network sub-area, and is the weight coefficient, which is used to smooth the importance of the main road and redundant channel. a and b are linear indices, which are used to adjust the influence of the main road and redundant channel on the energy storage configuration.

[0052] Preferably, the construction of the energy storage load coordination model includes the following specific steps:

[0053] Construct an energy storage load coordination model. The objective function of the energy storage load coordination model is:

[0054]

[0055] in, is the objective function, To optimize the total number of time windows, n is the number of samples of the distribution network sub-area operation data, is the total number of adjustable loads, is the energy storage device i in time period The operating cost is related to the time-of-use electricity price. is the adjustable load m in the time period The power adjustment amount is positive, which increases the load, and negative, which reduces the load. is the adjustment compensation unit price of the adjustable load m;

[0056] Calculate the operating cost of energy storage equipment based on different types of energy storage units:

[0057]

[0058] in, is the energy storage device i in time period operating costs, represents the charging power of the i-th energy storage device in time period t, represents the discharge power of the i-th energy storage device in time period t, 、 represents the charging cost coefficient and discharging cost coefficient of the central energy storage system in time period t, (t), represents the charging cost coefficient and discharging cost coefficient of the edge energy storage unit in time period t;

[0059] The constraints of the energy storage load coordination model are: , , ,in, and Indicates the minimum state of charge and maximum state of charge allowed for the energy storage device. is the state of charge of the i-th energy storage device in time period t, indicating the proportion of the current storage capacity of the energy storage device to its rated capacity, usually ranging from 0 to 1. is the minimum power adjustment allowed for the mth type of adjustable load in time period t, is the maximum power adjustment allowed for the mth type of adjustable load in time period t, is the actual power adjustment of the mth type adjustable load in time period t;

[0060] Power Constraints: ,in, is the total output power of renewable energy in period t, that is, the sum of the real-time power generation of distributed renewable energy. is the discharge power of the i-th energy storage device in time period t, that is, the power released by the energy storage to the grid, is the rigid load power in time period t, is the reference power of the mth type adjustable load, is the power adjustment of the mth type adjustable load in time period t, is the charging power of the i-th energy storage device in time period t, i is the i-th energy storage device, n is the number of samples of distribution network sub-area operation data, m is the m-th type of adjustable load, and M is the total number of adjustable loads.

[0061] Beneficial effects

[0062] The present invention provides a distribution network planning method suitable for access to distributed renewable energy. It has the following beneficial effects:

[0063] (1) By combining the cluster centers of the distribution network sub-area clusters and the feature weights of each feature column in the operating data set, the distribution network sub-areas can be functionally divided more accurately. This method calculates the weights of features based on the degree of variation in the data itself, making planning decisions more objective and accurate. For example, the entropy weight method can automatically identify features that are closely related to renewable energy fluctuations, helping planners focus on key variables, thereby improving the rationality of energy storage configuration and scheduling strategies, and ensuring the efficiency and reliability of the distribution network in actual operation.

[0064] (2) Combining the channel transmission capacity index and the channel stability index, the channel comprehensive index is calculated to help comprehensively evaluate the transmission capacity and stability of the distribution network channel. This comprehensive index not only reflects the basic transmission capacity of the channel, but also takes into account the stability factors of voltage drop and frequency response capability, effectively improving the accuracy of channel classification. In distribution network planning, the use of the comprehensive index can help identify main roads and redundant channels, thereby optimizing the topology of the distribution network and ensuring the load balance and power transmission stability of the channel under different operating conditions.

[0065] (3) By combining the functional labels, the number of main road connections, and the number of redundant channel connections of the distribution network sub-area, the energy storage index of the distribution network sub-area is calculated, which can provide a scientific basis for the deployment of energy storage units. This method optimizes the configuration of the energy storage system by considering the connection characteristics and functional requirements of the sub-area, so that the energy storage equipment can better match the operating requirements of the distribution network. The energy storage index not only helps to identify the deployment methods of central energy storage systems and edge energy storage units, but also improves the flexibility of energy scheduling, enhances the risk resistance and emergency scheduling capabilities of the distribution network, and helps to achieve smooth operation and efficient utilization after the connection of new energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0067] Figure 1 This is a flow chart of the steps of a distribution network planning method adapted to the access of distributed new energy sources proposed by the present invention;

[0068] Figure 2 This is a hierarchical diagram of the steps of a distribution network planning method adapted to the access of distributed renewable energy, proposed by the present invention; DETAILED DESCRIPTION

[0069] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0070] See also Figure 1-2 The present invention provides a technical solution: a distribution network planning method suitable for access of distributed new energy.

[0071] Step S1: Collect distribution network operation data and perform preprocessing to obtain a distribution network operation data set. Calculate the entropy value of the distribution network operation data set using the entropy weight method to obtain the feature weight of each feature column of the distribution network operation data set.

[0072] Distribution network sub-area operational data is collected and preprocessed. Raw data is obtained from grid operation monitoring systems such as SCADA, smart meters, renewable energy power plants such as photovoltaic inverters and wind turbine controllers, and meteorological monitoring platforms. This data includes historical load curves with power values ​​recorded at 15-minute or hourly granularity, renewable energy output data such as real-time and forecasted photovoltaic / wind power generation, grid parameters such as feeder capacity, voltage level, and line impedance, voltage and current monitoring records, fault logs, and weather information such as sunlight intensity, wind speed, and temperature. After data acquisition, it is cleaned to address missing values, such as by linear interpolation or by removing invalid periods and outliers. Subsequently, the multi-source data is time-aligned and formatted to ensure consistent timestamps across all data points. Next, standardization is performed to normalize features of different dimensions, such as megawatt load and percentage voltage sag, to the same range (e.g., 0–1) to prevent dimensional differences from interfering with subsequent analysis. Finally, key features are extracted based on the research objectives: load peak-to-valley ratio, photovoltaic output fluctuation, and voltage stability coefficient. Redundant information is removed to obtain the distribution network sub-area operational dataset.

[0073] It should be noted that a distribution network sub-area refers to the smallest analysis unit in the distribution network with an independent data acquisition unit, for example: feeder power supply range: the area covered by a single feeder or a group of electrically connected feeders; electrical node group: a local power grid separated by switches or transformers; data acquisition node: the monitoring area covered by a smart meter or PMU synchronized phasor measurement device.

[0074] It should be noted that the sample data in the distribution network sub-area operation data set are the operation data of different energy storage stations, and the sample data in the distribution network sub-area operation data set does not contain repeated operation data of energy storage stations.

[0075] The entropy value of the distribution network sub-area operation data set is calculated using the entropy weight method to obtain the feature weights of the distribution network sub-area operation data set.

[0076] The entropy weighting method is a multi-attribute weighting method based on information entropy theory. It is used to objectively assess the importance of each feature in the decision-making process. This method quantifies the uncertainty of each feature by calculating its information entropy. Lower entropy values ​​indicate greater information content and a greater impact on the decision outcome, thus assigning a higher weight. The entropy weighting method can avoid subjective bias and is widely used in multi-attribute decision-making, feature selection, and model optimization.

[0077] The entropy value of the feature column in the distribution network sub-area operation data is calculated using the entropy weight method:

[0078]

[0079] in, is the entropy value of the jth feature of the distribution network sub-area operation data, n is the number of samples of the distribution network sub-area operation data, It refers to the proportion of the data of the i-th distribution network sub-area in the j-th feature column, where j represents the index of the j-th feature and i represents the data of the i-th distribution network sub-area.

[0080] Calculate the weight of each feature in the distribution network sub-area operation data:

[0081]

[0082] in, is the weight of the jth feature of the distribution network sub-area operation data, J is the total number of features of the distribution network sub-area operation data, is the entropy value of the jth feature of the distribution network sub-area operation data, and j represents the index of the jth feature.

[0083] It's important to note that in distribution network planning, using the entropy weighting method to calculate entropy values ​​for distribution network sub-area operational datasets to determine feature weights has significant implications and benefits in many ways. Distribution network sub-area operational data contains numerous features, such as load characteristics, renewable energy access, and line parameters, each of which has varying degrees of impact on planning. The entropy weighting method objectively determines the weights of these features, avoiding arbitrary subjectivity. Traditional methods may assign weights to certain features based on empirical experience, which may not accurately reflect actual conditions. The entropy weighting method, on the other hand, calculates weights based on the variability of the data itself. Features with greater variability carry more valuable information and are more critical to planning decisions, so the entropy weighting method assigns higher weights to these features. For example, in areas with high renewable energy penetration, the variability of renewable energy output fluctuations is high. The entropy weighting method emphasizes this feature, allowing planners to prioritize the impact of renewable energy fluctuations when formulating energy storage configuration and scheduling strategies, thereby improving the alignment between plans and actual operations.

[0084] Step S2: clustering the distribution network sub-area operation data set using the KMEANS algorithm to obtain distribution network sub-area clusters; and calculating weighted cluster centers by combining the cluster centers of the distribution network sub-area clusters and the feature weights of each feature column of the distribution network sub-area operation data set.

[0085] The specific steps of clustering the distribution network sub-area operation data set using the KMEANS algorithm are as follows:

[0086] The number of clusters is determined based on the characteristic dimensions of the preprocessed dataset (such as load peak-to-valley ratio, photovoltaic output fluctuation rate, voltage drop probability, etc.). The initial number of clusters can be selected using the elbow rule: the elbow rule plots the sum of squared distances of total samples corresponding to different numbers of clusters and selects the value at the inflection point as the optimal number of clusters. After the number of clusters is determined, the KMEANS algorithm model is trained on the standardized data. The cluster centers and sample assignments are iteratively updated until the change in the center point is less than a set threshold (such as 0.001) or the maximum number of iterations (such as 300) is reached. In each iteration, the Euclidean distance of each sample to each cluster center is calculated, and the sample is assigned to the cluster corresponding to the nearest center. The mean of the samples within the cluster is recalculated as the new center.

[0087] After clustering, the results need to be analyzed for validity. Use visualization tools (such as two-dimensional scatter plots or parallel coordinate plots after PCA dimensionality reduction) to verify the reasonableness of cluster distribution and examine whether the characteristics between clusters are significantly different. For example, calculate the standard deviation or coefficient of dispersion of the characteristics within each cluster to ensure that similar regions have similar characteristics. If the characteristics of samples within a cluster vary significantly (for example, the voltage drop probability changes from 5% to 25%), adjust the number of clusters or optimize the feature weights.

[0088] The distribution network sub-area operation data set is clustered using the KMEANS algorithm, and the number of clusters in the distribution network sub-area clusters is obtained as follows: , the cluster center of each cluster is:

[0089]

[0090] in, represents the kth cluster center, j represents the index of the jth feature, Indicates the first cluster in the distribution network sub-area cluster The value of the cluster center on the jth feature, K represents the total number of cluster centers.

[0091] By combining the cluster centers of the distribution network sub-area clusters and the feature weights, the weighted cluster centers are calculated:

[0092]

[0093] in, Represents the value of the k-th cluster center after weighting the j-th feature, represents the feature weight of the j-th feature, Indicates the first cluster in the distribution network sub-area cluster The value of the cluster center on the j-th feature, j represents the index of the j-th feature, and K represents the total number of cluster centers.

[0094] Step S3: Score the weighted cluster centers using a sorting method that approximates the ideal solution to obtain the maximum approximation score of the weighted cluster centers, and divide the distribution network sub-areas into functional labels using the maximum approximation score to obtain functional labels of the distribution network sub-areas.

[0095] In distribution network planning, the function labels of distribution network sub-areas are , divided into daytime load peak significant type, photovoltaic output mutation sensitive type and industrial-grade continuous load type, and the positive and negative ideal solutions of daytime load peak significant type, photovoltaic output mutation sensitive type and industrial-grade continuous load type are determined by a sorting method that approximates the ideal solution.

[0096] It should be noted that the photovoltaic output sudden change sensitivity type: This label is mainly defined by the output fluctuation sensitivity and the potential of new energy construction planning. The output fluctuation sensitivity measures the impact of new energy (such as photovoltaic) output sudden changes on the power grid. If the photovoltaic output of a certain area is greatly affected by weather changes (such as cloud cover causing a sudden drop in power), and the power grid structure in the area is more sensitive to such fluctuations (such as limited feeder capacity and insufficient voltage regulation capability), then its output fluctuation sensitivity is relatively high. At the same time, the potential for new energy construction planning reflects the scale of photovoltaic resources that can be developed in the region in the future. If a region has abundant light resources and a large number of photovoltaic installations are planned, even if the current output fluctuations are small, its potential fluctuation risks cannot be ignored. Therefore, the combination of these two labels can identify areas where energy storage or dynamic adjustment devices need to be configured to smooth out output fluctuations and ensure the stability of the power grid, such as rural areas or emerging energy development zones. The positive ideal solution of the photovoltaic output sudden change sensitivity type is =[neutral value of load curve shape, maximum output fluctuation sensitivity, neutral value of historical load peak-to-valley ratio, neutral value of load power factor, maximum new energy potential], negative ideal solution =[neutral value of load curve shape, minimum value of output fluctuation sensitivity, neutral value of historical load peak-to-valley ratio, neutral value of load power factor, minimum value of new energy potential]. The neutral value represents the average value of this feature, and the maximum value represents the maximum value of this feature. For example, the neutral value of load curve shape represents the average value of the load curve shapes of k cluster centers.

[0097] It should be noted that the core of the "Daytime Significant Load Peak" label is determined by the load curve shape and the historical load peak-to-valley ratio. The load curve shape reflects the temporal distribution of electricity consumption. If a region's load curve exhibits a significant peak during the day (e.g., from morning to evening) and a sharp drop at night, it indicates a daytime peak. The historical load peak-to-valley ratio further quantifies the intensity of the peak-to-valley difference. A high ratio indicates that the region's electricity consumption fluctuates significantly, with a significant peak-to-valley difference. For example, commercial or residential areas experience concentrated electricity consumption during the day and a sharp drop in demand at night. Both their load curve shape and peak-to-valley ratio meet the characteristics of this label. By combining these two labels, the system can identify areas that require priority in addressing daytime power supply pressures and deploying energy storage to smooth out peaks and fill valleys. In the positive ideal solution for the "Daytime Significant Load Peak" label, the load curve shape and the historical load peak-to-valley ratio are maximized, while other characteristics are neutral. In the negative ideal solution for the "Daytime Significant Load Peak" label, the load curve shape and the historical load peak-to-valley ratio are minimized, while other characteristics are neutral.

[0098] It should be noted that the key to the "Industrial Continuous Load" label lies in the synergistic effect of the load power factor and load curve shape. The load power factor reflects the energy efficiency of electrical equipment. Industrial loads (such as motors and inverters) typically have a high power factor (close to 1), indicating high energy conversion efficiency and low reactive power demand on the grid. Furthermore, the load curve in industrial areas is typically relatively stable, without significant peaks and valleys, as production processes must operate continuously (such as 24-hour production lines). Therefore, the combination of a high power factor and low load fluctuations is a typical characteristic of an industrial continuous load. These areas require high grid stability and require energy storage to cope with possible short-term disturbances, but do not require frequent adjustments. For example, in heavy industrial bases or chemical parks, the positive ideal solution for an industrial continuous load is to maximize the load power factor and load curve shape, while other characteristics are neutral. The positive ideal solution for an industrial continuous load is to minimize the load power factor and load curve shape, while other characteristics are neutral.

[0099] For the distribution network sub-area with functional label L, its positive ideal solution is , the negative ideal solution is .

[0100] For each distribution network sub-area cluster, calculate the distance between its weighted cluster center and the positive ideal solution of different functional labels of the distribution network sub-area:

[0101]

[0102] in, The distance between the kth distribution network sub-area cluster and the positive ideal solution of the Lth functional label, j represents the index of the jth feature, and J is the total number of features of the distribution network sub-area operation data. Represents the value of the k-th cluster center after weighting the j-th feature, represents the value of the positive ideal solution of the Lth feature label at the jth feature.

[0103] For each distribution network sub-area cluster, calculate the distance between its weighted cluster center and the negative ideal solution of different functional labels of the sub-area:

[0104]

[0105] in, The distance between the kth distribution network sub-area cluster and the negative ideal solution of the Lth functional label, j represents the index of the jth feature, and J is the total number of features of the distribution network sub-area operation data. Represents the value of the k-th cluster center after weighting the j-th feature, Represents the value of the negative ideal solution of the Lth feature label at the jth feature.

[0106] For each distribution network sub-area cluster, the maximum approximation score of the distribution network sub-area cluster is calculated by the distance between its weighted cluster center and the positive ideal solution and the negative ideal solution of different functional labels of the sub-area:

[0107]

[0108] in, Indicates the The maximum similarity score of a cluster reflects its closeness to the ideal solution. The distance between the kth distribution network sub-area cluster and the positive ideal solution of the Lth functional label, The distance between the kth distribution network sub-area cluster and the negative ideal solution of the Lth functional label. max() is the maximum value function, which means taking the maximum similarity score between the kth distribution network sub-area cluster and the L functional labels. represents the similarity score between the kth distribution network sub-area cluster and the Lth functional label.

[0109] For the kth distribution network sub-area cluster, by calculating the similarity scores between its weighted cluster center and different functional labels, when the similarity score between the kth distribution network sub-area cluster and the Lth functional label is the maximum, it is the maximum similarity score of the kth distribution network sub-area cluster, and the functional label of the kth distribution network sub-area cluster is .

[0110] Step S4: collecting distribution network channel data, the distribution network channel data including: voltage level, feeder capacity, voltage drop probability and short-time frequency response capability; calculating the channel transmission capability index by combining the voltage level and feeder capacity; calculating the channel stability index by combining the channel transmission capability index and the channel stability index; calculating the channel comprehensive index by combining the channel comprehensive index to classify the channels in the distribution network through the data set to obtain channel categories, the channel categories being: main channels and redundant channels; constructing a distribution network channel topology map by using the functional labels of the distribution network sub-areas and the channel categories of the channels.

[0111] Collect distribution network channel data, including voltage levels, feeder capacity, voltage drop probability, and short-term frequency impact capability of channels between distribution network sub-areas.

[0112] It should be noted that the voltage level indicates the voltage level of each channel (such as 10kV, 35kV), which directly affects the power transmission capacity and scope of application. Feeder capacity indicates the maximum transmission capacity of the channel (such as current carrying capacity, power limit), which is used to assess whether the load demand or the demand for new energy access is met. Voltage sag probability: The possibility of a voltage drop in the channel due to a fault or sudden load change, which needs to be combined with historical fault records or simulation data. Short-term frequency response capability: The adjustment speed and stability of the channel when the grid frequency fluctuates, which needs to be based on the dynamic response parameters of the equipment (such as inverters and energy storage).

[0113] It should be noted that the distribution network channel data refers to the channel data connecting different distribution network sub-areas, and does not include the channel data within the distribution network sub-area, for example: the data of the connection channel between distribution network sub-area A and distribution network sub-area B.

[0114] By combining the voltage level and feeder capacity, the channel transmission capacity index is calculated:

[0115]

[0116] in, is the channel transmission capability index, V is the voltage level, is the highest voltage of the channel, F is the feeder capacity, is the maximum feeder capacity of the channel.

[0117] The channel transmission capacity index is calculated by combining voltage level and feeder capacity. Voltage level represents the maximum voltage level a channel can carry for power transmission. Higher voltage level channels can carry greater power and are suitable for long-distance, high-load power transmission. Feeder capacity, on the other hand, reflects the channel's maximum transmission capacity under certain voltage conditions—the maximum current or power it can carry. Feeder capacity is closely related to current and determines the power load a channel can effectively carry without overload or failure. Combining these two factors provides a more comprehensive assessment of a channel's transmission capacity.

[0118] By combining the voltage drop probability and short-time frequency response capability, the channel stability index is calculated:

[0119]

[0120] in, is the channel stability index, D is the voltage drop probability, Q is the short-time frequency response capability, is the maximum voltage drop probability, It is the maximum value of short-time frequency response capability.

[0121] The channel stability index is calculated by combining voltage sag probability and short-term frequency response capability to assess the stability of distribution network channels under different operating conditions. The voltage sag probability reflects the frequency of voltage drops during channel operation. Voltage sags are typically caused by factors such as load fluctuations, equipment failures, or external interference. Frequent voltage sags can impact the normal operation of the distribution network and even cause power equipment failures. Therefore, the voltage sag probability is an important indicator for measuring the stability of distribution network channels. The short-term frequency response capability measures the channel's ability to respond to transient load changes or power system fluctuations. The frequency response capability reflects the distribution network channel's ability to quickly recover to a stable state when impacted by factors such as sudden load fluctuations or the integration of new energy sources. Combining these two factors, the calculated channel stability index comprehensively reflects the channel's stability under conditions such as voltage sags and load fluctuations. The voltage sag probability provides information about the potential risks of the channel in long-term operation, while the short-term frequency response capability reflects the channel's ability to recover from transient fluctuations.

[0122] By combining the channel transmission capacity index and the channel stability index, the channel comprehensive index is calculated:

[0123]

[0124] Among them, ZN is the channel comprehensive index, is the channel transmission capability index, is the channel stability index.

[0125] By combining the channel transmission capacity index and the channel stability index to calculate the channel comprehensive index, a comprehensive assessment is made of the distribution network channel's performance in terms of power transmission capacity and operational stability. The channel transmission capacity index primarily reflects the channel's maximum power transmission capacity at different voltage levels and feeder capacities, while the channel stability index reflects the channel's ability to respond to unstable factors such as voltage drops and frequency fluctuations during operation. Combining these two indices allows for a comprehensive assessment of the channel's overall performance from both a capacity and stability perspective, providing a more accurate basis for grid design and optimization. The calculation of the channel comprehensive index not only helps determine which channels are most suitable for carrying critical loads or integrating new energy, but also ensures that the grid maintains high reliability and stability during emergencies or load fluctuations, thereby improving the grid's overall operational efficiency and resilience.

[0126] Main roads: comprehensive index of passages With preset channel threshold For comparison, > , then it is a main road. Main roads are channels with high voltage levels, large feeder capacity, and low voltage drop probability, which are more suitable for carrying power transmission for critical loads or centralized access points of new energy.

[0127] Redundant channels: channel comprehensive index Less than the preset channel threshold Channels with lower scores are considered redundant channels, which are used for failover or load transfer to improve grid resilience. For example, in the event of a sudden change in PV output or equipment failure, rapid switching to a redundant channel can avoid the risk of a power outage.

[0128] A distribution network channel topology map is constructed using the distribution network sub-area function labels and channel categories.

[0129] It should be noted that in the distribution network channel topology map, nodes represent sub-areas: graphical nodes are labeled with their functional labels (e.g., color coded: red for daytime peak load, green for PV-sensitive load, blue for industrial load load). Edges represent channels: Directed edges are drawn based on the scoring results, with line width positively correlated with the score. Dashed lines represent redundant channels. Dynamic weight annotation: Key parameters are annotated next to the channels (e.g., "35kV, 5MW capacity, 2% voltage sag probability"). For example: Sub-area A (PV-sensitive load): connects two channels: Channel 1 (main channel, 35kV, 10MW capacity, score 0.85) and Channel 2 (redundant channel, 10kV, 3MW capacity, score 0.6). Sub-area B (industrial load): connects to Sub-area A via Channel 1 and has a redundant channel connecting to Sub-area C. Sub-area C (daytime peak load): connects to Sub-area B via a redundant channel. The resulting map: a thick solid line (high-scoring main channel) is drawn between Sub-areas A and B, labeled "35kV, 10MW." A thin dashed line (low-scoring redundant channel) is drawn between sub-areas B and C, labeled "10 kV, 3 MW, 5% drop probability." Sub-area A is labeled "PV-sensitive" and linked to the PV power plant icon.

[0130] Step S5: Based on the distribution network channel topology map, the number of main road connections and the number of redundant channel connections in the distribution network sub-area are obtained; by combining the functional label of the distribution network sub-area, the number of main road connections in the distribution network sub-area, and the number of redundant channel connections in the distribution network sub-area, an energy storage index of the distribution network sub-area is calculated; and based on the energy storage index of the distribution network sub-area, energy storage units are deployed for the distribution network sub-area.

[0131] According to the distribution network channel topology diagram, the number of main road connections and the number of redundant channel connections in the distribution network sub-area are obtained.

[0132] It should be noted that, based on the distribution network channel topology map, each node in the distribution network channel topology map represents a distribution network sub-area, and each edge in the distribution network channel topology map represents a connection channel of the distribution network sub-area. The distribution network channel topology map includes the functional label of each distribution network sub-area, the number of main road connections and the number of redundant channel connections in the distribution network sub-area.

[0133] Based on the distribution network channel topology map, the energy storage index of the distribution network sub-area is calculated by combining the functional label of the distribution network sub-area, the number of main road connections and the number of redundant channel connections in the distribution network sub-area:

[0134]

[0135] in, represents the energy storage index of the ith distribution network sub-area, represents the number of main road connections in the ith distribution network sub-area, The functional label of the kth distribution network sub-area cluster to which the i-th distribution network sub-area belongs, represents the number of redundant channel connections in the ith distribution network sub-area, and is the weight coefficient, which is used to smooth the importance of the main road and redundant channel. a and b are linear indices, which are used to adjust the influence of the main road and redundant channel on the energy storage configuration.

[0136] It should be noted that the functional labels of the distribution network sub-area clusters , defining numerical levels: the value of photovoltaic sensitive type (high fluctuation risk) is 3, the value of daytime peak type (medium fluctuation) is 2, and the value of industrial load type (low fluctuation) is 1.

[0137] The distribution network is divided into a central energy storage system and an edge energy storage unit by the distribution network sub-area energy storage index. If the energy storage index is greater than the preset threshold, the central energy storage system is deployed in the distribution network sub-area. If the energy storage index is less than the preset threshold, an edge energy storage unit is deployed in the distribution network sub-area.

[0138] Step S6: Collect the adjustable load data of the distribution network sub-intervals, build an energy storage load coordination model based on the adjustable load data of the distribution network sub-intervals and the energy storage units, and realize the power consumption planning of the distribution network accessed by new energy through the energy storage load coordination model.

[0139] To collect data on adjustable loads in distribution network sub-areas, it is necessary to identify the specific types of adjustable loads in the area (such as residential air conditioners, electric vehicle charging piles, industrial interruptible equipment, commercial lighting, etc.), and to collect statistics on their basic power consumption parameters, including rated power, typical power consumption period, number of devices, and distribution density.

[0140] Construct an energy storage load coordination model. The objective function of the energy storage load coordination model is:

[0141]

[0142] in, is the objective function, The total number of time periods in the optimization time window, is the total number of energy storage devices, M is the total number of adjustable loads, is the energy storage device i in time period operating costs, is the adjustable load m in the time period The power adjustment amount is positive, which increases the load, and negative, which reduces the load. The unit price of adjustment compensation for adjustable load m.

[0143] It should be noted that is the total number of periods in the optimized time window, is the time of the next T periods, The adjustment compensation unit price of the adjustable load m is set with different adjustment priorities and compensation coefficients according to the load type. For example, a high compensation unit price can be set for industrial interruptible equipment (because the adjustment affects production); a low compensation unit price can be set for residential air conditioners (because the adjustment flexibility is higher).

[0144] Calculate the operating cost of energy storage equipment based on different types of energy storage units:

[0145]

[0146] in, is the energy storage device i in time period operating costs, represents the charging power of the i-th energy storage device in time period t, represents the discharge power of the i-th energy storage device in time period t, 、 represents the charging cost coefficient and discharging cost coefficient of the central energy storage system in time period t, 、 Represents the charging cost coefficient and discharging cost coefficient of the edge energy storage unit in time period t.

[0147] The constraints of the energy storage load coordination model are: , ,in, and Indicates the minimum state of charge and maximum state of charge allowed for the energy storage device. is the state of charge of the i-th energy storage device in time period t, indicating the proportion of the current storage capacity of the energy storage device to its rated capacity, usually ranging from 0 to 1. is the minimum power adjustment allowed for the mth type of adjustable load in time period t, is the maximum power adjustment allowed for the mth type of adjustable load in time period t, is the actual power adjustment of the mth type of adjustable load in time period t.

[0148] Power Constraints: ,in, is the total output power of renewable energy in period t, is the discharge power of the i-th energy storage device in time period t, that is, the power released by the energy storage to the grid, is the rigid load power in time period t, is the reference power of the mth type adjustable load, is the power adjustment of the mth type adjustable load in time period t, is the charging power of the i-th energy storage device in time period t, i is the i-th energy storage device, n is the total number of energy storage devices, m is the m-th type of adjustable load, and M is the total number of adjustable loads.

[0149] The prediction data input of the energy storage load coordination model includes: the total output power of new energy, the benchmark power of rigid load and adjustable load, and the charging and discharging cost coefficient of the energy storage station.

[0150] It should be noted that the total output of renewable energy sources is predicted for a future period T by using real-time monitoring of renewable energy sources such as photovoltaic and wind power, as well as meteorological data. For example, this involves collecting meteorological data such as wind speed, light intensity, and temperature from a meteorological monitoring platform, as well as historical data on the total output of renewable energy sources. Machine learning models, such as support vector machine regression, are then used to predict the total output of renewable energy sources for the future period T. Furthermore, loads are divided into rigid loads and adjustable loads. Rigid loads include residential electricity consumption and infrastructure, while adjustable loads include air conditioners and electric vehicle charging stations. The charging cost coefficient represents the unit cost of purchasing electricity from the grid for charging during a specific period. It is typically directly derived from the time-of-use electricity price for that period (e.g., off-peak electricity price of 0.4 yuan / kWh). The discharging cost coefficient reflects the benefits or costs of supplying electricity to the grid during discharge. It is typically set as a negative value or a discounted value of the time-of-use electricity price (e.g., 80% of the peak electricity price of 1.2 yuan / kWh). For example, during peak hours, when high electricity prices correspond to high charging cost coefficients, the model prioritizes reducing charging and increasing discharging to reduce total costs. During off-peak hours, when low electricity prices correspond to low charging cost coefficients, the model tends to increase charging to reserve low-priced electricity. This design dynamically adjusts energy storage behavior through electricity price signals, responding to price fluctuations in the electricity market while optimizing the energy storage's charging and discharging strategies, ultimately minimizing total operating costs.

[0151] Optimization solution of energy storage load coordination model: Using rolling time domain optimization, at each time point Read the forecast data input of the energy storage load coordination model: the total output power of new energy, the benchmark power of rigid load and adjustable load, and the charging and discharging cost coefficient of the energy storage station. Use optimization tools such as Gurobi and CPLEX to solve the mixed integer linear programming problem while satisfying the constraints and power constraints of the energy storage load coordination model. Minimize the objective function of the energy storage load coordination model and ultimately output the decision variables for the future T period:

[0152]

[0153] in, is the decision variable for the future T period, represents the charging power of the i-th energy storage device in time period t, represents the discharge power of the i-th energy storage device in time period t, is the adjustable load m in the time period The power adjustment amount is , and T is the future T period.

[0154] It should be noted that the decision variables for the future T period provide a dynamically optimized operating strategy for the distribution network to address the uncertainty of renewable energy output and load demand, while achieving a balance between economy and safety. During periods of low electricity prices, the energy storage-load coordination model prioritizes charging energy storage devices to store low-priced electricity, guiding some adjustable loads (such as electric vehicles and water heaters) to increase their electricity consumption to absorb any excess renewable energy. During peak electricity price periods, the energy storage-load coordination model prioritizes discharging energy storage stations to provide high-priced electricity (equivalent to electricity sales revenue) and prioritizes the use of adjustable loads with low regulatory compensation units (such as residential air conditioning group control for gentle temperature increases) to reduce peak demand, while minimizing or avoiding the use of high-cost loads (such as industrial equipment outages that impact production). The energy storage-load coordination model compares the charging and discharging costs of central energy storage systems and edge storage units to optimize their deployment sequence and extent. For example, lower-cost edge storage units may be prioritized to smooth voltage fluctuations within a sub-area. If the total output of renewable energy is predicted to peak in the afternoon, the energy storage and load coordination model will schedule energy storage charging in advance when the midday electricity price is low, preparing to efficiently absorb the excess total output of energy in the afternoon and reduce peak power purchases. If the total output of renewable energy is predicted to dip in the evening, the energy storage and load coordination model will guide some adjustable loads (such as electric vehicles) to complete partial charging in advance when the total output of energy is sufficient and the electricity price is acceptable, avoiding concentrated high-power charging during the evening peak period, which will increase pressure on the grid.

[0155] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include," "comprise," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations. The phrase "includes an element defined by..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0156] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A distribution network planning method adapted to the access of distributed renewable energy, characterized by: The following steps are involved: Step S1: Collect and preprocess the distribution network sub-area operation data to obtain the distribution network sub-area operation data set, calculate the entropy value of the distribution network sub-area operation data set using the entropy weight method, and obtain the feature weight of each feature column of the distribution network sub-area operation data set; Step S2: clustering the distribution network sub-area operation data set using the KMEANS algorithm to obtain distribution network sub-area clusters; calculating weighted cluster centers by combining the cluster centers of the distribution network sub-area clusters and the feature weights of each feature column of the distribution network sub-area operation data set; Step S3: Calculating scores for the weighted cluster centers using a ranking method that approximates an ideal solution to obtain a maximum approximation score for the weighted cluster centers; dividing the distribution network sub-areas into functional labels using the maximum approximation score to obtain functional labels for the distribution network sub-areas; Step S4: collecting distribution network channel data, the distribution network channel data including: voltage level, feeder capacity, voltage sag probability and short-time frequency response capability; calculating a channel transmission capability index by combining the voltage level and feeder capacity; calculating a channel stability index by combining the channel transmission capability index and the channel stability index; calculating a channel comprehensive index by combining the channel comprehensive index to classify the channels in the distribution network through the data set to obtain channel categories, the channel categories being: main channels and redundant channels; constructing a distribution network channel topology map by using the functional labels of the distribution network sub-areas and the channel categories of the channels; Step S5: Obtaining the number of main road connections and redundant channel connections in the distribution network sub-area based on the distribution network channel topology map; calculating an energy storage index for the distribution network sub-area by combining the functional label of the distribution network sub-area, the number of main road connections, and the number of redundant channel connections in the distribution network sub-area; and deploying energy storage units for the distribution network sub-area based on the energy storage index of the distribution network sub-area. Step S6: Collect the adjustable load data of the distribution network sub-intervals, build an energy storage load coordination model based on the adjustable load data of the distribution network sub-intervals and the energy storage units, and realize the power consumption planning of the distribution network accessed by new energy through the energy storage load coordination model.

2. A distribution network planning method adapted to distributed renewable energy access according to claim 1, characterized in that: The entropy value of the distribution network operation data set is calculated by the entropy weight method to obtain the feature weight of each feature column of the distribution network operation data set, including the following specific steps: The entropy value of the feature column in the distribution network sub-area operation data is calculated using the entropy weight method: ； in, is the entropy value of the jth feature of the distribution network sub-area operation data, n is the number of samples of the distribution network sub-area operation data, Refers to the proportion of the data of the i-th distribution network sub-area in the j-th feature column, j represents the index of the j-th feature, and i represents the data of the i-th distribution network sub-area; Calculate the weight of each feature in the distribution network sub-area operation data: ； in, is the weight of the jth feature of the distribution network sub-area operation data, J is the total number of features of the distribution network sub-area operation data, is the entropy value of the jth feature of the distribution network sub-area operation data, and j represents the index of the jth feature.

3. A distribution network planning method adapted to distributed renewable energy access according to claim 2, characterized in that: The method of calculating a weighted cluster center by combining the cluster center of the distribution network sub-area cluster and the feature weight of each feature column of the distribution network sub-area operation data set comprises the following steps: By combining the cluster centers of the distribution network sub-area clusters and the feature weights, the weighted cluster centers are calculated: ； in, Represents the value of the k-th cluster center after weighting the j-th feature, represents the feature weight of the j-th feature, Indicates the first cluster in the distribution network sub-area cluster The value of the cluster center on the j-th feature, j represents the index of the j-th feature, and K represents the total number of cluster centers.

4. A distribution network planning method adapted to the access of distributed new energy according to claim 3, characterized in that: The method of performing score calculation on the weighted cluster centers by a sorting method close to an ideal solution to obtain the maximum approximation score of the weighted cluster centers comprises the following steps: For the distribution network sub-area with functional label L, its positive ideal solution is , the negative ideal solution is ; For each distribution network sub-area cluster, calculate the distance between its weighted cluster center and the positive ideal solution of different functional labels of the distribution network sub-area: ； in, The distance between the kth distribution network sub-area cluster and the positive ideal solution of the Lth functional label, j represents the index of the jth feature, and J is the total number of features of the distribution network sub-area operation data. Represents the value of the k-th cluster center after weighting the j-th feature, represents the value of the positive ideal solution of the Lth functional label at the jth feature; For each distribution network sub-area cluster, calculate the distance between its weighted cluster center and the negative ideal solution of different functional labels of the sub-area: ； in, The distance between the kth distribution network sub-area cluster and the negative ideal solution of the Lth functional label, j represents the index of the jth feature, and J is the total number of features of the distribution network sub-area operation data. Represents the value of the k-th cluster center after weighting the j-th feature, represents the value of the negative ideal solution of the Lth feature label at the jth feature; For each distribution network sub-area cluster, the maximum approximation score of the distribution network sub-area cluster is calculated by the distance between its weighted cluster center and the positive ideal solution of different functional labels of the sub-area and the distance between the positive ideal solution: ； in, Indicates the The maximum similarity score of a cluster reflects its closeness to the ideal solution. The distance between the kth distribution network sub-area cluster and the positive ideal solution of the Lth functional label, The distance between the kth distribution network sub-area cluster and the negative ideal solution of the Lth functional label. max() is the maximum value function, which means taking the maximum similarity score between the kth distribution network sub-area cluster and the L functional labels. is the similarity score between the kth distribution network sub-area cluster and the Lth functional label.

5. A distribution network planning method adapted to distributed renewable energy access according to claim 4, characterized in that: The method of dividing the distribution network sub-areas into functional labels according to the maximum approximation score to obtain the functional labels of the distribution network sub-areas includes the following specific steps: For the kth distribution network sub-area cluster, by calculating the similarity scores between its weighted cluster center and different functional labels, when the similarity score between the kth distribution network sub-area cluster and the Lth functional label is the maximum, it is the maximum similarity score of the kth distribution network sub-area cluster, and the functional label of the kth distribution network sub-area cluster is .

6. A distribution network planning method adapted to the access of distributed renewable energy according to claim 5, characterized in that: The method of calculating the channel transmission capacity index by combining the voltage level and the feeder capacity includes the following specific steps: By combining the voltage level and feeder capacity, the channel transmission capacity index is calculated: ； in, is the channel transmission capability index, V is the voltage level, is the highest voltage of the channel, F is the feeder capacity, is the maximum feeder capacity of the channel.

7. A distribution network planning method adapted to the access of distributed new energy according to claim 6, characterized in that: The method of calculating the channel stability index by combining the voltage drop probability and the short-time frequency response capability includes the following specific steps: By combining the voltage drop probability and short-time frequency response capability, the channel stability index is calculated: ； in, is the channel stability index, D is the voltage drop probability, Q is the short-time frequency response capability, is the maximum voltage drop probability, It is the maximum value of short-time frequency response capability.

8. A distribution network planning method adapted to distributed renewable energy access according to claim 7, characterized in that: The method of calculating the channel comprehensive index by combining the channel transmission capability index and the channel stability index comprises the following specific steps: By combining the channel transmission capacity index and the channel stability index, the channel comprehensive index is calculated: ； Among them, ZN is the channel comprehensive index, is the channel transmission capability index, is the channel stability index.

9. A distribution network planning method adapted to the access of distributed renewable energy according to claim 8, characterized in that: The method of calculating the energy storage index of the distribution network sub-area by combining the functional label of the distribution network sub-area, the number of main road connections and the number of redundant channel connections in the distribution network sub-area includes the following specific steps: Based on the distribution network channel topology map, the energy storage index of the distribution network sub-area is calculated by combining the functional label of the distribution network sub-area, the number of main road connections and the number of redundant channel connections in the distribution network sub-area: ； in, represents the energy storage index of the ith distribution network sub-area, represents the number of main road connections in the ith distribution network sub-area, The functional label of the kth distribution network sub-area cluster to which the i-th distribution network sub-area belongs, represents the number of redundant channel connections in the ith distribution network sub-area, and is the weight coefficient, which is used to smooth the importance of the main road and redundant channel. a and b are linear indices, which are used to adjust the influence of the main road and redundant channel on the energy storage configuration.

10. A distribution network planning method adapted to the access of distributed renewable energy according to claim 9, characterized in that: The construction of the energy storage load coordination model includes the following specific steps: Construct an energy storage load coordination model. The objective function of the energy storage load coordination model is: ； in, is the objective function, is the total number of time periods in the optimization time window, n is the number of samples of the distribution network sub-area operation data, M is the total number of adjustable loads, is the energy storage device i in time period The operating cost is related to the time-of-use electricity price. is the adjustable load m in the time period The power adjustment amount is positive, which increases the load, and negative, which reduces the load. is the adjustment compensation unit price of the adjustable load m; Calculate the operating cost of energy storage equipment based on different types of energy storage units: ； in, is the energy storage device i in time period operating costs, represents the charging power of the i-th energy storage device in time period t, represents the discharge power of the i-th energy storage device in time period t, 、 represents the charging cost coefficient and discharging cost coefficient of the central energy storage system in time period t, 、 represents the charging cost coefficient and discharging cost coefficient of the edge energy storage unit in time period t; The constraints of the energy storage load coordination model are: , , ,in, and Indicates the minimum state of charge and maximum state of charge allowed for the energy storage device. is the state of charge of the i-th energy storage device in time period t, indicating the proportion of the current storage capacity of the energy storage device to its rated capacity, ranging from 0 to 1. is the minimum power adjustment allowed for the mth type of adjustable load in time period t, is the maximum power adjustment allowed for the mth type of adjustable load in time period t, is the actual power adjustment of the mth type adjustable load in time period t; Power Constraints: ,in, is the total output power of renewable energy in period t, is the discharge power of the i-th energy storage device in time period t, that is, the power released by the energy storage to the grid, is the rigid load power in time period t, is the reference power of the mth type adjustable load, is the power adjustment of the mth type adjustable load in time period t, is the charging power of the i-th energy storage device in time period t, i is the i-th energy storage device, n is the number of samples of distribution network sub-area operation data, m is the m-th type of adjustable load, and M is the total number of adjustable loads.

Images