Emergency supply insurance method for power distribution area

Abstract

The invention relates to an emergency supply insurance method for a power distribution area, and the method comprises the following steps: obtaining the user file information of a target power distribution area, and dividing the supply insurance priority of each user according to the user file information; acquiring power supply and demand data in the disaster scene, analyzing a coupling relationship between the disaster scene and the power supply and demand data, and analyzing power balance conditions of the target power distribution area in different stages of the disaster; and designing a staged photovoltaic and energy storage cooperative control strategy according to a power balance condition analysis result, and supplying power to electric equipment of each user when a disaster occurs in combination with the guarantee supply priority of each user.

Description

Technical Field

[0001] The present invention relates to a method for emergency power supply guarantee in a distribution substation area, belonging to the technical field of emergency guarantee for distribution networks. Background Art

[0002] To cope with the challenges of disaster prevention and control, some places have implemented a power risk avoidance mechanism, that is, when extreme weather occurs, a preventive power outage plan is initiated for a certain area, which in turn affects the power supply reliability of important distribution station areas (DSAs) such as hospitals, schools, commercial areas, and industrial areas.

[0003] Regarding the problem of emergency power supply guarantee for DSAs in disaster-prone areas, it mainly includes three stages: emergency preparation, impact assessment, and emergency power supply guarantee. In the emergency preparation stage, the power supply company constructs a disaster power emergency supply guarantee system and formulates an emergency power supply guarantee plan for DSAs in advance to reduce the impact of disasters on the power supply of DSAs. In the impact assessment stage, the impact of disasters on the operation of DSAs is analyzed through quantitative indicators to provide a basis for formulating emergency power supply guarantee strategies for DSAs. In the emergency power supply guarantee stage, emergency power supply guarantee for DSAs in disaster scenarios is achieved through network reconfiguration, island operation control, and multi-energy collaborative optimization.

[0004] Existing methods for emergency power supply guarantee for DSAs are diverse. However, there is currently a lack of a systematic evaluation method for the guarantee objectives of different types of DSAs, making it difficult to accurately formulate differentiated power supply guarantee strategies; and for the complex coupling relationship among disaster occasionality, photovoltaic power randomness, and guarantee demand differences, an effective source-load-storage collaborative operation mechanism has not been established, seriously restricting the further improvement of the emergency power supply guarantee ability of DSAs. Summary of the Invention

[0005] To solve the problems existing in the above-mentioned prior art, the present invention proposes a method for emergency power supply guarantee in a distribution substation area. First, based on the classification of the importance of DSA loads, a quantitative analysis of the emergency power supply guarantee requirements for multiple types of DSAs under disasters is carried out to clarify the power supply guarantee priorities of different users; secondly, the complex coupling relationship between disaster scenarios and power supply and demand data is analyzed; finally, a phased DSA power balance analysis method is constructed to achieve accurate matching of supply and demand, and a phased photovoltaic and energy storage collaborative control strategy is designed to meet the diverse power supply guarantee requirements of DSAs.

[0006] The technical solution of the present invention is as follows: On the one hand, the present invention provides a method for emergency power supply guarantee in a distribution substation area, including the following steps: Obtain the user profile information of the target distribution substation area, and divide the power supply guarantee priorities of each user according to the user profile information; Obtain the power supply and demand data under the disaster scenario, analyze the coupling relationship between the disaster scenario and the power supply and demand data, and analyze the power balance situation of the target distribution substation area at different stages of the disaster; Design a phased collaborative control strategy for photovoltaic and energy storage according to the analysis results of the power balance situation, and supply power to the electrical equipment of each user when the disaster occurs, combined with the power supply guarantee priorities of each user.

[0007] As a preferred implementation manner, the step of dividing the power supply guarantee priorities of each user according to the user profile information includes: Extract multiple characteristic indicators reflecting the sensitivity of the user to power supply interruption through the user profile information; Assign weights to each characteristic indicator; Calculate the scoring value of the sensitivity of each user to power supply interruption according to the weighting results and the characteristic values of the characteristic indicators of each user extracted through the user profile information; Divide the power supply guarantee priorities according to the scoring values of the sensitivity of each user to power supply interruption.

[0008] As a preferred implementation manner, in the step of assigning weights to each characteristic indicator: Use the entropy weight method to assign weights to each characteristic indicator.

[0009] As a preferred implementation manner, the step of dividing the power supply guarantee priorities according to the scoring values of the sensitivity of each user to power supply interruption includes: Perform clustering according to the scoring values of the sensitivity of each user to power supply interruption; According to the clustering results, obtain the scoring values of the sensitivity of all users in each cluster to power supply interruption, and calculate the evaluation benchmark score for each cluster based on this; Sort according to the magnitudes of the evaluation benchmark scores of each cluster, determine the power supply guarantee priority of each cluster, and assign the corresponding power supply guarantee priority to all users in each cluster.

[0010] As a preferred implementation manner, the obtaining of the power supply and demand data under the disaster scenario includes: The power consumption load prediction data, photovoltaic power generation prediction data, and charge and discharge capacity of the energy storage system of the target distribution substation area under the disaster scenario are used as the power supply and demand data; Among them, the power consumption load prediction data and photovoltaic power generation prediction data are obtained through machine learning algorithms.

[0011] As a preferred implementation manner, the step of analyzing the coupling relationship between the disaster scenario and the power supply and demand data includes: Introduce the accidental variables of the inducing factors that induce the corresponding disaster scenario to occur; Extract the random variables of power supply resources and the differential variables of power supply demand from the power supply and demand data. Among them, the random variable of power supply resources is the random variable of photovoltaic power, and the differential variable of power supply demand is the differential variable of electricity load. Conduct coupling analysis, specifically as follows: Use the Copula function to calculate the three-variable joint distribution function among the contingency of inducing factors, the randomness of power supply resources, and the difference of power supply demand.

[0012] As a preferred implementation manner, the step of analyzing the power balance situation of the target distribution substation in different stages of the disaster is specifically as follows: Divide the entire disaster occurrence period into different stages; Solve the power balance problem of the target distribution substation in different stages through the dynamic programming method; among them, construct the first objective function of the dynamic programming method with the goal that the power provided by the power supply resources can meet the electricity demand to the greatest extent; the power supply resources include photovoltaic and energy storage systems; Solve the first objective function through dynamic recursion to obtain the optimal solution of the power provided by the power supply resources in different stages; Recursively derive through the optimal solution of the power provided by the stage power supply resources to obtain the power balance situation of the target distribution substation in each stage.

[0013] As a preferred implementation manner, the step of designing a phased photovoltaic and energy storage collaborative control strategy according to the power balance situation evaluation result and the power supply priority of each user is specifically as follows: Construct a second objective function with the goal of minimizing the power supply cost of the target distribution substation during the disaster under the constraint conditions of the power balance situation of the target distribution substation in each stage and the capacity of the photovoltaic and energy storage systems; Solve the second objective function to obtain the control strategies of the photovoltaic and energy storage systems in each stage.

[0014] On the other hand, the present invention also proposes an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the emergency power supply method for the distribution substation as described in any embodiment of the present invention.

[0015] On the other hand, the present invention also proposes a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the emergency power supply method for the distribution substation as described in any embodiment of the present invention.

[0016] The present invention proposes a phased DSA emergency power supply control method based on the coordination of photovoltaic energy storage. First, the power supply sensitivity of users is identified from multiple dimensions, and the classification of the importance of user power supply is completed. By predicting the electricity load and photovoltaic power generation power under disasters and combining the charge and discharge capabilities of the energy storage system, a power supply and demand coupling model under disaster scenarios is established, revealing the internal relationship between the accidental nature of disasters, the randomness of photovoltaic power output, and the differences in user power supply requirements. Based on the time scale, the DSA power balance is dynamically evaluated, the power balance in different stages is analyzed, and by optimizing the photovoltaic energy storage coordination control strategy, the optimal power supply for different levels of users is ensured with limited power supply resources. This method can effectively increase the DSA emergency power supply duration and reduce the DSA emergency power supply cost.

[0017] Additional aspects and advantages of the present invention will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the present invention. In addition, the various aspects and advantages of the present invention may be realized and obtained by the means of the method steps and combinations particularly pointed out in the appended claims. Brief Description of the Drawings

[0018] Figure 1 It is a schematic flowchart of the method of an embodiment of the present invention; Figure 2 It is a schematic flowchart of generating photovoltaic power generation data and electricity load data samples through the GAN network in an embodiment of the present invention. Detailed Embodiments

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0020] It should be understood that the step numbers used in the text are only for convenient description and do not limit the execution order of the steps.

[0021] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0022] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0023] The term "and / or" refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0024] See Figure 1 , this embodiment provides an emergency power supply method for a distribution substation area, specifically including the following steps: S100. Based on the marketing system and power consumption information collection system of the power supply company, obtain the user profile information of the target distribution substation area and the real-time measurement data such as current and voltage of the electric meter at 96 points per day. Combine the multi-dimensional factors in the user profile to identify the sensitive characteristics of the user's power supply, and complete the importance analysis of the user's power supply guarantee; then classify the user's power supply guarantee and divide the supply guarantee priority of the user to provide a basis for the power supply of DSA users during disasters.

[0025] S200. Obtain the power consumption load prediction data and photovoltaic power generation power prediction data of the target distribution substation area under disaster scenarios, and analyze the charge and discharge capacity of the energy storage system to obtain the power supply and demand data under disaster scenarios; among them, the power consumption load prediction data and photovoltaic power generation power prediction data are obtained through machine learning algorithms.

[0026] On this basis, analyze the coupling relationship between the disaster scenario and the power supply and demand data, and reveal the internal connection between the accidental nature of the disaster and the power supply and demand data.

[0027] S300. Analyze the power balance situation of the target distribution substation area at different stages of the disaster; design a phased photovoltaic and energy storage collaborative control strategy according to the analysis results of the power balance situation. Combine the supply guarantee priorities of each user, and during the disaster, use the phased photovoltaic and energy storage collaborative control strategy to supply power to the electrical equipment of each user; finally, evaluate the superiority of the implementation of the control strategy. If it is not optimal, readjust and divide the supply guarantee priorities of the users. The superiority of the implementation of the control strategy can be evaluated by efficiency, economy, effectiveness, adaptability, sustainability, etc.

[0028] In one embodiment, in step S100, the step of dividing the supply guarantee priorities of each user according to the user profile information includes: S101. Extract multiple characteristic indicators reflecting the sensitivity degree of the user to power supply interruption from the user profile information; among them, the user type, credit record, user, etc. are collected Archive information such as level and supply guarantee times provides user attribute data for the supply guarantee priority analysis of DSA users and supports multi-dimensional evaluation. The real-time data of voltage, active power, reactive power, current, etc. of the user's electricity meter collected at a frequency of 96 points per day provides accurate power load and operation status data for the DSA disaster emergency supply guarantee control strategy.

[0029] Specifically, the sensitivity of a user to power supply interruption refers to the severity of the impact of power supply interruption on multiple aspects within a DSA power supply area, reflecting the important position of the user in regional activities.

[0030] In this embodiment, the sensitivity of DSA users to power supply interruption includes 3 dimensions and 10 characteristic indicators, as shown in Table 1: Table 1 Index Table of the Sensitivity of DSA Users to Power Supply Interruption

[0031] S102. There are significant differences in the development levels of different regions, which leads to differences in the weights of the characteristic indicators of the sensitivity of DSA users to power supply interruption in different regions. Therefore, in order to accurately evaluate the sensitivity of DSA users to power supply interruption in each region, it is necessary to assign weights to each characteristic indicator according to the regional characteristics.

[0032] The methods of assigning weights can include: entropy weight method, principal component analysis method (PCA), factor analysis method, CRITIC method, grey relational analysis, etc.

[0033] S103. According to the weight assignment results and the eigenvalue of the characteristic indicators of each user extracted from the user archive information, calculate the scoring value of the sensitivity of each user to power supply interruption to determine the comprehensive scoring value of the sensitivity of each user to power supply interruption, and assign a quantitative score reflecting its sensitivity to power supply interruption to each user, so as to provide a decision-making basis for the analysis of the importance of supply guarantee. In the analysis of the importance of user supply guarantee, the score of the scoring value of the sensitivity of power supply interruption directly reflects the importance of the user. The higher the score, the higher the sensitivity of the user to power supply interruption and the greater its importance; conversely, users with lower scores have lower importance.

[0034] S104. Conduct supply guarantee priority division according to the scoring values of the sensitivity of each user to power supply interruption. The division methods can include: Division by score segments: The scoring values of the sensitivity of each user to power supply interruption can be divided into different score segments, such as high, medium, and low three levels, or more detailed levels. This method is simple and intuitive, easy to understand and operate.

[0035] Division by percentage: According to the distribution of the scoring values of the power supply interruption sensitivity of each user, the users are divided into a high-score group in the top X%, a medium-score group in the middle Y%, and the remaining low-score group. This method can more accurately reflect the differences between users.

[0036] Cluster analysis: Use a clustering algorithm (such as the K-means algorithm) to cluster the scoring values of the power supply interruption sensitivity of each user to form different groups of users sensitive to power supply interruption.

[0037] In one embodiment, for step S102, the entropy weight method is used to assign weights to the characteristic indicators. The entropy weight method (EWM) is a weight adjustment method based on information entropy. In EWM, the size of the information entropy is used to determine the weight size of the characteristic indicators. When the information entropy is larger, the dispersion degree of the corresponding characteristic indicator is smaller, and the weight of the corresponding characteristic indicator is also smaller; on the contrary, when the information entropy is smaller, the weight of the corresponding characteristic indicator is larger.

[0038] The specific steps of using the entropy weight method to assign weights to the characteristic indicators are as follows: Standardize the original data: ; Among them, is the original data, specifically representing the index value of the th sample on the th characteristic indicator, is the maximum value of the th characteristic indicator, is the minimum value of the th characteristic indicator; is the standardized data, specifically representing the standardized data of the th sample on the th characteristic indicator; Calculate the proportionality coefficient of each sample under each characteristic indicator: ; Among them, represents the proportionality coefficient of the th sample under the th characteristic indicator; Calculate the information entropy η of the e SL.η th characteristic indicator as: ; Among them, n SL is the number of characteristic indicators.

[0039] Calculate the information entropy redundancy of the η th feature index g SL.η is: ; Calculate the weight of the η th feature index w SL.η is: .

[0040] Based on the above embodiments, in step S103, the formula for calculating the scoring value of the power supply interruption sensitivity of each user b SL.η is specifically: ; wherein, is the index value of the η th feature index.

[0041] In one embodiment, in step S103, the steps for analyzing the importance of user power supply guarantee are specifically as follows: Assume that there are m SL users in the target distribution substation area. The features in Table 1 above are used to evaluate each user, and the index values of each feature are obtained. Then, the importance of user power supply guarantee in the target distribution substation area can be represented by the matrix D as: ; wherein, is the evaluation score of each index of the first user in DSA; is the evaluation score of each index of the m SL th user in DSA; The evaluation score of each index can be obtained by weighted calculation of the weight of the feature index calculated in step S102 above and the corresponding index value of the feature index.

[0042] In one embodiment, for step S104, clustering is used to divide the power supply guarantee priority. In this embodiment, the K-Medoids algorithm is specifically used for clustering. The K-Medoids algorithm is a clustering algorithm based on data partitioning and is an improved version of the K-Means algorithm, which can effectively solve the problem of being sensitive to outliers in K-Means clustering. The way of determining the center point of the K-Medoids algorithm is different from that of the K-Means algorithm. The K-Medoids algorithm takes the point with the minimum sum of distances between the center points of each category in the clustering and other points as the center to improve the ability to cluster abnormal data points. Therefore, the K-Medoids algorithm is used to classify user power supply in this embodiment; The cost function is used to evaluate the quality of user power supply classification. The optimal clustering partition and center points are solved by means of iterative repetition, and the clustering error of Euclidean distance is used to evaluate the quality of the clustering results of user power supply classification. The clustering error of the K-Medoids algorithm for user power supply δ SSE is: ; where x KE is a sample point in the user power supply clustering data space; k KE is the number of objects randomly selected from the user power supply clustering dataset; O KE.j is the j th clustering center.

[0043] The specific implementation process is as follows: A100. Randomly select k KE objects from the user power supply dataset as the initial representative objects for user power supply classification; A200. Calculate the Euclidean distance between the remaining user power supply objects and the representative objects, and divide them into the clusters of the nearest user power supply objects according to the distance; A300. Randomly select a non-representative object O rand ; A400. Use the non-representative object O rand to replace the j th clustering center O KE.j of the user power supply clustering; the cost function is calculated using the user power supply clustering error δ SSE ; A500. If the substitution cost value of the user power supply sample is negative, then use O rand to replace O KE.j , and form a new object set; A600. Repeat steps A200 - A500 until the total cost value does not change.

[0044] According to the clustering results, user classification is performed, and the average score evaluated by the sensitivity of power supply interruption of each type of user is used as the evaluation benchmark score. Specifically, the calculation formula of the evaluation benchmark score d KE is as follows: ; where mKE is the number of DSA users in this category after clustering using the K-Medoids algorithm; d pcs.j is the j evaluation score of the sensitivity of the DSA user's power supply interruption for the

[0045] th user, which can be specifically obtained through the formula for calculating the scoring value of the power supply interruption sensitivity of each user in step S103 of the above-mentioned embodiment.

[0046] Because the occurrence of disasters is relatively rare, the time for emergency power outage avoidance is less than normal, resulting in relatively limited available data samples of the electricity load and photovoltaic power generation in the DSA area under disaster scenarios. Therefore, in one embodiment, in step S200, the method for obtaining the electricity load prediction data and photovoltaic power generation prediction data through the machine learning algorithm is specifically as follows: Use the small-sample learning method to predict the electricity load and photovoltaic power generation in the DSA area, specifically as follows: Use a generative adversarial network (GAN) to transform or generate new data from the existing photovoltaic power generation and DSA electricity load, so as to expand the sample size of the power and load prediction model training set, thereby improving the prediction accuracy and generalization ability of the model for photovoltaic power generation and DSA electricity load.

[0047] Through the adversarial training of the generator and the discriminator, GAN can generate synthetic data that is highly similar to the real data distribution, and has the advantage of generating data close to the real data. Therefore, GAN is suitable for data augmentation of photovoltaic power generation and DSA electricity load data in small-sample scenarios.

[0048] In the process of GAN generating photovoltaic power generation and DSA electricity load data, the generator receives the random noise of photovoltaic power generation and DSA electricity load as input and converts it into data similar to the real data distribution of photovoltaic power generation and DSA electricity load; the discriminator receives the real data and the generated data and tries to distinguish between the two. Through continuous optimization, the generator gradually generates more realistic data, while the discriminator continuously improves its discrimination ability. In the task of generating photovoltaic power generation and DSA electricity load data, GAN generates high-quality synthetic data through adversarial training, effectively expanding the training sample set, thereby improving the performance of the prediction model. The specific process is as Figure 2 shown.

[0049] After obtaining sufficient sample data, the photovoltaic power generation and DSA power consumption loads are predicted. In the prediction of photovoltaic power generation, the input data are meteorological and PV module data. Among them, the meteorological data are solar irradiance, humidity, and temperature data, which are from the 1*1 square kilometer regional data of Numerical Weather Prediction (NWP); the PV module data are PV module conversion rate, PV module tilt angle, and PV combination loss, which are from the PV management system. In the prediction of DSA power consumption load, the input data include meteorological data, historical load data, and economic data. Among them, the meteorological data are the same as those in the prediction of photovoltaic power generation; the historical load data are from the power consumption information collection system, and the economic data are GDP data.

[0050] The prediction model uses the LSTM long short-term memory neural network, and the LSTM consists of an input gate, a forget gate, a memory cell, and an output gate. In this embodiment, the input gate is used to input the meteorological and PV module data for the prediction of photovoltaic power generation, and the meteorological data, historical load data, and economic data for the prediction of DSA power consumption load. The forget gate can selectively record the input data for the prediction of photovoltaic power generation and DSA power consumption load; the memory cell is used to store and update information in the LSTM. The output gate then outputs the prediction data for photovoltaic power generation and DSA power consumption load.

[0051] The predicted photovoltaic power generation data output by LSTM p PV.pred is: ; where tan is the hyperbolic tangent activation function used by the forget gate in the LSTM for the prediction of photovoltaic power generation and DSA power consumption load: γ is the activation function in the LSTM for the prediction of photovoltaic power generation and DSA power consumption load, γ and the Sigmoid function can be used; p PV.hist is the historical photovoltaic power generation data; p PV.FG is the photovoltaic power generation data that has passed through the forget gate of the LSTM network; β met is the meteorological data of NWP; β eff is the PV module data.

[0052] The predicted DSA power consumption load data output by LSTM p EL.pred is: ; where, pEL.hist Historical electricity load data for DSA; p EL.FG DSA electricity load data passing through the forgetting gate of the LSTM network; β eff GDP data for the area where DSA is located.

[0053] In one embodiment, in step S200, analyzing the charge-discharge capacity of the energy storage system specifically means analyzing energy storage losses, which refers to the power losses caused by physical and chemical factors during the charge-discharge process of the energy storage device. Energy storage losses will reduce the overall efficiency of DSA emergency power supply.

[0054] Energy storage losses p ES.loss Specifically: ; Among them, p ES.chg is the internal resistance loss caused by the energy storage system during the charge-discharge process; p ES.sdl is the loss caused by the self-reaction of the active substances inside the energy storage system; p ES.cv is the loss of AC-DC conversion of the energy storage system.

[0055] In one embodiment, in step S200, the steps of analyzing the coupling relationship between the disaster scenario and the power supply and demand data include: Introducing the accidental variable of the inducing factor that induces the corresponding disaster scenario to occur; Extracting the random variable of the power supply resources and the differential variable of the power supply demand from the power supply and demand data. Among them, the random variable of the power supply resources is the random variable of the photovoltaic power, and the differential variable of the power supply demand is the differential variable of the electricity load; Taking the mountain fire disaster scenario as an example, during the emergency power supply for mountain fire disasters, when the power supply company receives the wind warning information of level 7 or above issued by the local meteorological bureau, or monitors the wind of level 7 or above through the micro-meteorological device arranged on the transmission line, it will immediately start the emergency power outage and risk avoidance measures and resume power supply after the wind weakens. Therefore, the wind of level 7 or above is an inducing factor that induces the mountain fire disaster scenario to occur. By exploring the coupling between the accidentality of the wind of level 7 or above, the randomness of the photovoltaic power, and the difference of the electricity load, it can provide a basis for the emergency power supply strategy for the mountain fire disaster scenario, thereby improving the power supply capacity and reducing the power outage risk of important users under mountain fire disasters.

[0056] Copula function is a method to describe the correlation structure and dependence relationship of multiple random variables. Copula function associates the joint distribution function with the marginal distribution functions of other variables to analyze their correlation. Due to the occasionality of strong winds of level 7 and above, the randomness of photovoltaic power, and the inconsistent dimensions of security requirements, in this embodiment, Copula function is selected to perform coupling analysis on the occasionality of strong winds of level 7 and above, the randomness of photovoltaic power, and the security requirements, and calculate the three-variable joint distribution function among the three H corr It is: ; Among them, f wind ( p wind ) is the marginal distribution function of the occasionality variable of strong winds of level 7 and above; f PV ( p PV ) is the marginal distribution function of the randomness variable of photovoltaic power; f EL ( p EL ) is the marginal distribution function of the difference variable of electricity consumption load; σ is the trivariate Copula function, which connects the above three marginal distribution functions of the occasionality of strong winds of level 7 and above, the randomness of photovoltaic power, and the difference of electricity consumption load to form a trivariate joint distribution function.

[0057] In specific implementation, first, it is necessary to model the occasionality of strong winds of level 7 and above, the randomness of photovoltaic power, and the difference of electricity consumption load to obtain their respective marginal distribution functions f wind ( p wind ), f PV ( p PV ) and f EL ( p EL ). Subsequently, by selecting an appropriate trivariate Copula function σ , the three marginal distribution functions are connected to construct a three-variable joint distribution function H corr . This step can accurately describe the Copula function of the correlation and dependence relationship between variables to ensure the accuracy and reliability of the joint distribution function.

[0058] In one embodiment, in step S300, the step of analyzing the power balance of the target distribution substation area at different stages of the disaster specifically includes: S311. Divide the entire disaster occurrence period into different stages; according to the statistics of DSA disaster power outage and risk avoidance, the DSA disaster emergency power supply period usually lasts from several hours to several days. During this period, the continuity of power supply is directly related to the production and living guarantee of the region. Due to the influence of solar radiation on photovoltaic power generation and the influence of user behavior on user load, there are significant differences in different time periods. For example, the photovoltaic power generation power is relatively high when the solar radiation is strong during the day, and almost zero at night. The output power of the energy storage depends on its charge and discharge state, capacity limit, and scheduling strategy. The user load depends on the production and living habits of the users. Therefore, in order to more accurately respond to the dynamic changes in power supply and demand, it is necessary to divide the disaster emergency power supply period into multiple stages and conduct a detailed analysis of the power supply and demand balance in each stage. By evaluating the power balance between the DSA user demand and the power supply capabilities of photovoltaic and energy storage, targeted power scheduling strategies can be formulated, resource allocation can be optimized, and the stable operation of the power system during the DSA mountain fire disaster can be ensured.

[0059] S312. Solve the power balance problem of the target distribution substation area at different stages through the dynamic programming method; dynamic programming (DP) is an operations research method that can optimize multi-stage decision-making processes. DP decomposes the power balance problem of the target distribution substation area into several sub-problems, such as the photovoltaic control sub-problem, the energy storage control sub-problem, and the user electricity demand control sub-problem, and uses the DSA power balance solutions of the sub-problems to solve the DSA power balance solution of the entire stage.

[0060] Among them, a first objective function of the dynamic programming method is constructed with the goal of maximizing the power provided by the power supply resources to meet the electricity demand; the power supply resources include photovoltaic and energy storage systems; the first objective function z DP is: ; Among them, n T is the period of emergency power supply; p EL.pred.j is the DSA electricity load demand in the j th period, which is obtained from the electricity load prediction data obtained through step S200.

[0061] S313. Solve the first objective function through dynamic recursion to obtain the optimal solution of the power provided by the power supply resources at different stages, and obtain the power supply strategy of the optimal solution V DP.t is: ; Among them, p EL.pred.t is the DSA power load demand for the current period; V PV.ES.t+1 is the strategy for the maximum power provided by the photovoltaic and energy storage systems from the next period to the final emergency power supply moment.

[0062] S314. And by recursively obtaining the optimal solutions of the power provided by the power supply resources in each stage, the power balance situation of the target distribution substation area in each stage is obtained.

[0063] In one embodiment, in step S300, the step of designing the staged photovoltaic and energy storage collaborative control strategy according to the power balance situation evaluation result and the power supply priority of each user is specifically as follows: S321. Construct a second objective function with the goal of minimizing the power supply cost of the target distribution substation area during a disaster under the constraint conditions of the power balance situation, photovoltaic and energy storage system capacity in the target distribution substation area in each stage C tot : ; Among them, n op is the number of stages of DSA disaster emergency power supply; p ld.k , p pv.k , p es.k are respectively the DSA user load, photovoltaic power generation, and energy storage discharge power in the k th power supply stage; c ld.k , c pv.k , c es.k are respectively the cost functions of DSA users, photovoltaic power generation, and energy storage discharge in the k th power supply stage; p pv.l.k , p es.l.k are respectively the lower limits of photovoltaic power generation and energy storage discharge power in the k th power supply stage; p pv.h.k , p es.h.k are respectively the upper limits of photovoltaic power generation and ES discharge power in the k th power supply stage.

[0064] Among them, the composition of the photovoltaic power generation cost c pv is: ; Among them, c pv.inv is the unit investment cost per kilowatt-hour of power generation for PV construction; c pv.om is the operation and maintenance cost per kilowatt-hour of PV power generation.

[0065] Composition of energy storage discharge cost c es is: ; Among them, c es.cyc is the usage cost for the number of ES cycle life times; c es.chg is the internal resistance loss cost caused during the ES charge and discharge process; c es.sdl is the loss cost caused by the self-reaction of the active substances inside the ES; c es.cv is the power loss cost for the AC-DC conversion of the ES. C es.inv is the unit investment cost per kilowatt-hour of discharge for ES construction; Cost of DSA users c ld is composed of: ; Among them, c ld.elecp is the electricity price and electricity cost of DSA users.

[0066] S322. In each power supply guarantee stage, repeatedly solve the second objective function, and at the same time execute the above steps S312~S313, then the control strategy for the coordination of the photovoltaic and energy storage systems in each stage can be obtained ( V DP.t ).

[0067] This application also proposes an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the emergency power supply guarantee method for the distribution transformer area as described in any embodiment of the present invention.

[0068] This application also proposes a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the emergency power supply guarantee method for the distribution transformer area as described in any embodiment of the present invention.

[0069] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent the cases of A existing alone, A and B existing simultaneously, and B existing alone. Wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0070] Those of ordinary skill in the art can realize that the various units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0071] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0072] In several embodiments provided by the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (hereinafter referred to as ROM), random access memory (hereinafter referred to as RAM), magnetic disks, or optical discs that can store program codes.

[0073] The above are only the embodiments of the present invention, and thus do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for emergency power supply in a distribution substation area, characterized in that It includes the following steps: Obtain the user profile information of the target distribution substation area, and divide the power supply guarantee priorities of each user according to the user profile information; Obtain the power supply and demand data under the disaster scenario, analyze the coupling relationship between the disaster scenario and the power supply and demand data, and analyze the power balance situation of the target distribution substation area at different stages of the disaster; Design a phased collaborative control strategy for photovoltaic and energy storage according to the analysis results of the power balance situation, and supply power to the electrical equipment of each user when the disaster occurs in combination with the power supply guarantee priorities of each user.

2. The emergency power supply method for a distribution substation area according to claim 1, characterized in that, The step of dividing the power supply guarantee priorities of each user according to the user profile information includes: Extract multiple characteristic indicators reflecting the sensitivity of users to power supply interruption through the user profile information; Assign weights to each characteristic indicator; According to the weighting results and the characteristic values of the characteristic indicators of each user extracted through the user profile information, calculate the scoring values of the sensitivity of each user to power supply interruption; Divide the power supply guarantee priorities according to the scoring values of the sensitivity of each user to power supply interruption.

3. The emergency power supply method for a distribution substation area according to claim 2, characterized in that, In the step of assigning weights to each characteristic indicator: The entropy weight method is used to assign weights to each characteristic indicator.

4. A power distribution area emergency power supply method according to claim 2, characterized in that, The step of dividing the power supply guarantee priorities according to the scoring values of the sensitivity of each user to power supply interruption includes: Cluster according to the scoring values of the sensitivity of each user to power supply interruption; According to the clustering results, obtain the scoring values of the sensitivity of all users in each cluster to power supply interruption, and calculate the evaluation benchmark score for each cluster based on this; Sort according to the magnitudes of the evaluation benchmark scores of each cluster, determine the power supply guarantee priorities of each cluster, and assign the corresponding power supply guarantee priorities to all users in each cluster.

5. A method for emergency power supply in a distribution substation area according to claim 1, characterized in that, The obtaining of the power supply and demand data under the disaster scenario includes: The power consumption load prediction data, photovoltaic power generation prediction data, and charge and discharge capacity of the energy storage system of the target distribution substation area under the disaster scenario are used as the power supply and demand data; Among them, the power consumption load prediction data and photovoltaic power generation prediction data are obtained through machine learning algorithms.

6. A power distribution substation emergency power supply method according to claim 5, characterized in that The step of analyzing the coupling relationship between the disaster scenario and the power supply and demand data includes: Introduce the accidental variables of the inducing factors that induce the corresponding disaster scenario to occur; Extract the random variables of the power supply guarantee resources and the differential variables of the power supply guarantee demand from the power supply and demand data, where the random variables of the power supply guarantee resources are the random variables of photovoltaic power, and the differential variables of the power supply guarantee demand are the differential variables of the power consumption load; Conduct coupling analysis, specifically: Use the Copula function to calculate the three-variable joint distribution function between the accidentality of the inducing factors, the randomness of the power supply guarantee resources, and the difference of the power supply guarantee demand.

7. A power distribution substation emergency power supply method according to claim 1, characterized in that The step of analyzing the power balance situation of the target distribution substation area at different stages of the disaster is specifically: Divide the entire disaster occurrence period into different stages; Solve the power balance problem of the target distribution substation area at different stages through the dynamic programming method; among them, the first objective function of the dynamic programming method is constructed with the goal of maximizing the power provided by the power supply guarantee resources to meet the power consumption demand; the power supply guarantee resources include photovoltaic and energy storage systems; Dynamically recursively solve the first objective function to obtain the optimal solution of the power provided by the power supply guarantee resources at different stages; Recursively obtain the power balance of the target distribution transformer substation in each stage through the optimal solution of the power provided by the stage-by-stage supply resources.

8. A power distribution substation emergency power supply method according to claim 7, characterized in that, The steps of designing the staged photovoltaic and energy storage collaborative control strategy according to the analysis result of the power balance situation are specifically as follows: Construct a second objective function with the goal of minimizing the supply guarantee cost of the target distribution transformer substation during disasters under the constraints of the power balance situation of the target distribution transformer substation in each stage and the capacities of the photovoltaic and energy storage systems. Solve the second objective function to obtain the control strategies of the photovoltaic and energy storage systems in each stage.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the emergency power supply method for the distribution transformer substation according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the emergency power supply method for the distribution transformer substation according to any one of claims 1 to 8.

Images