Distribution network settlement quota method, equipment and device based on big data

Abstract

The present invention discloses a method, equipment and device for settlement quota of distribution network based on big data, which relates to the technical field of settlement quota of distribution network, and includes the following steps: real-time acquisition of distributed energy generation data, classification of different types of distributed energy generation data according to cluster analysis algorithm; analysis according to different classifications to obtain the generation characteristics of distribution network; construction of real-time dynamic model of distribution network, and judgment of abnormal state of distribution network; adjustment of abnormal state of distribution network, and acquisition of adjusted compensation quota; and obtaining the optimal settlement quota scheme based on particle swarm optimization algorithm according to the generation characteristics and compensation quota of distribution network. The present invention optimizes the settlement quota scheme by power generation characteristics, so as to solve the problem that the settlement quota method cannot adapt to the dynamic changes in distribution network due to the difference in power generation characteristics caused by the access of distributed energy.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network quota, and more specifically, to a distribution network settlement quota method, device and apparatus based on big data. Background Art

[0002] As an important link in the power industry, distribution network settlement is not only related to the economic benefits of engineering projects, but also directly affects the healthy and stable development of the power market. With the full promotion of market-oriented reform and the continuous deepening of power system reform, the background technology of distribution network settlement is also evolving continuously to meet the requirements of a more efficient and intelligent power supply system.

[0003] For example, the method for distribution network demand response trading settlement based on blockchain technology announced in the invention patent with the announcement number of CN108681950A includes the following steps: according to the selected multi-region flexible interconnected distribution network, input the basic parameter information of the multi-region flexible interconnected distribution network respectively; based on the provided basic parameter information, establish the power trading pricing strategies for each regional distribution network in the multi-region flexible interconnected distribution network respectively; according to the end-to-end power trading bid sets of each regional distribution network, consider the active power transmission balance constraint of the multi-terminal intelligent soft switch to form a set of feasible solutions, and make intelligent contract decisions based on the improved highest comprehensive bid principle; according to the intelligent contract decision results, adopt the principle of equal sharing of interests to conduct end-to-end power trading settlement for the multi-region flexible interconnected distribution network, and output the power trading settlement results, including: the settlement amount of each regional distribution network, the transmission power of the multi-terminal intelligent soft switch. The present invention realizes the real-time adjustment of the output of the multi-terminal intelligent soft switch and the efficient and flexible operation of the system.

[0004] For example, an incremental distribution network market-based trading settlement method announced in the invention patent with the announcement number of CN115545914A includes: settlement entities, settlement components, settlement methods and system support, and the settlement methods include: the settlement method between the distribution network enterprise and the provincial power grid enterprise includes that the distribution network enterprise can independently choose the comprehensive settlement electricity price or the classified settlement electricity price to settle the electricity bill with the provincial power grid enterprise according to the actual situation, and the settlement method between the distribution network enterprise and non-market-oriented power users: the distribution network enterprise takes the proxy power purchase price as a reference. This incremental distribution network market-based trading settlement method adopts the settlement method between the distribution network enterprise and the provincial power grid enterprise, the settlement method between the distribution network enterprise and non-market-oriented power users, the settlement method between the distribution network enterprise and power users directly trading with power generation enterprises, etc., to more intuitively clarify the settlement responsibilities of all parties in the distribution network market.

[0005] Among the above disclosed technical solutions, there are at least the following technical problems:

[0006] With the enhancement of environmental awareness and the development of energy technology, distributed energy such as solar photovoltaic power generation and small wind power generation are increasingly connected to the distribution network. The traditional settlement quota method based on the power supply of the power grid is to settle the fees according to the fixed unit price of electricity and the pre-set settlement rules. However, distributed energy has the characteristics of intermittent and strong volatility, and its power generation and power generation are significantly affected by natural conditions (such as light intensity, wind force) and other factors. At the same time, the electricity consumption behavior of users is becoming increasingly complex and diverse, and the peak and valley differences in electricity demand are obvious. This leads to the inability of traditional settlement quota methods to adapt to the dynamic changes in power supply and demand in the distribution network. In actual operation, it is impossible to accurately measure the reasonable benefits that the power generation party should obtain due to the differences in power generation characteristics in different time periods, and it is difficult to reflect the impact of user power consumption behavior on the stability of the power grid, and it is even more impossible to effectively motivate the power generation party and the user to jointly maintain the stable operation of the distribution network, making it difficult for the interests of all parties to be reflected fairly and impartially. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a distribution network settlement quota method, equipment and device based on big data, which optimizes the settlement quota scheme through power generation characteristics, so as to solve the problem that the settlement quota method cannot adapt to the dynamic changes in the distribution network due to the differences in power generation characteristics caused by the access of distributed energy.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A distribution network settlement quota method based on big data obtains distributed energy generation data in real time, classifies different types of distributed energy generation data based on a cluster analysis algorithm, and analyzes the classification results to obtain the generation characteristics of the distribution network; constructs a real-time dynamic model of the distribution network, determines the abnormal state of the distribution network, adjusts the abnormal state of the distribution network, and obtains the adjusted compensation quota; and obtains an optimized settlement quota scheme based on the particle swarm optimization algorithm according to the generation characteristics and compensation quota of the distribution network.

[0010] In a preferred embodiment, different types of distributed energy generation data are classified based on a cluster analysis algorithm, specifically: based on big data, distributed energy generation data points under different seasons and weather conditions are obtained; the initial feature type is determined according to the impact of different seasons and weather conditions on distributed energy generation; the initial feature type is used as the initial cluster center, and the distance between the distributed energy generation data point and the initial cluster center is calculated based on the Euclidean distance formula; each distributed energy generation data point is assigned to the initial cluster center with the nearest distance; for all distributed energy generation data points in each initial cluster center, the average value in the light intensity feature dimension is calculated, and the average value is set as the new cluster center; based on the K-means algorithm, the process of calculating the distance, assigning data points and updating the cluster center is repeated until the algorithm converges to obtain the clustering result.

[0011] In a preferred embodiment, the power generation characteristics of the distribution network are obtained by analyzing according to different classifications, specifically: a scatter plot is drawn according to the clustering results, the light intensity is set as the X-axis, the power generation is set as the Y-axis, and the initial feature type is different colors; the scatter plot is analyzed to obtain the power generation characteristics of the distribution network with different initial feature types.

[0012] In a preferred embodiment, a real-time dynamic model of a distribution network is constructed and the abnormal state of the distribution network is judged, specifically: line loss data and voltage deviation data are obtained in real time, and a real-time dynamic model of the distribution network is constructed based on a neural network algorithm; the output of the real-time dynamic model of the distribution network within a preset time period is obtained and integrated into a data set; the mean and standard deviation of the data set are obtained by statistical methods; based on 3 In principle, a data set with a mean value exceeding 3 times the standard deviation is considered an abnormal state of the distribution network.

[0013] In a preferred embodiment, the abnormal state of the distribution network is adjusted to obtain the adjusted compensation quota, specifically: the abnormal state of the distribution network is obtained, and the abnormal state types of the distribution network include voltage abnormality, power factor abnormality and line abnormality; the abnormal state type of the distribution network is adjusted based on the reactive compensation of the compensation equipment, and when the abnormal state returns to normal, the investment is stopped; the total amount of reactive compensation is calculated according to the actually invested reactive compensation capacity and the switching time; the equipment characteristic information and the reactive compensation information per unit capacity in the process of line abnormality adjustment are obtained, and the adjusted compensation quota is obtained based on the total amount of reactive compensation.

[0014] In a preferred embodiment, an optimized settlement quota scheme is obtained based on a particle swarm optimization algorithm according to the power generation characteristics and compensation quota of the distribution network, specifically: determining the first feature corresponding to different seasons and weather conditions according to the power generation characteristics, the first feature including power generation characteristics, material characteristics and manpower characteristics; combining the first feature with the compensation quota to establish an objective function based on minimizing the comprehensive cost of the distribution network, and determining the constraint conditions; setting the position of each particle as a settlement quota scheme based on the particle swarm optimization algorithm, and setting the speed of each particle as the first feature and the compensation quota; initializing the position, speed and individual optimal position of each particle, performing an iterative cycle, and updating the speed and position of each particle according to the speed update formula and the position update formula; for each updated particle position, calculating its fitness value, the fitness value is the calculation of the objective function; if the fitness value of the current position is better than the individual optimal position, then updating the individual optimal position; when the iteration reaches the maximum number of iterations, stopping the iteration, selecting the individual optimal position with the smallest fitness value among all particles as the global optimal position, and the global optimal position is the optimal settlement quota scheme.

[0015] In a preferred embodiment, the voltage deviation data is specifically acquired by the following method: collecting voltage data in real time according to a preset time interval to obtain a voltage data set; calculating the average of the voltage data set based on a statistical method to obtain an average voltage deviation; calculating the standard deviation of the voltage data set based on the average voltage deviation to quantify the discrete degree of the voltage deviation to obtain the voltage deviation data.

[0016] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0017] 1. By acquiring distributed energy generation data and distribution network status information in real time, combined with cluster analysis and neural network algorithms, it can accurately predict power generation characteristics and dynamically monitor distribution network anomalies, improve stability and regulation accuracy, provide efficient support for the formulation of settlement quota plans and distribution network anomaly regulation, and enhance the intelligence and precision of the power system.

[0018] 2. The particle swarm optimization algorithm is combined with power generation characteristics, material characteristics and human characteristics to effectively optimize the settlement quota plan of the distribution network, which can minimize the comprehensive cost under different seasons and weather conditions and improve the accuracy of decision-making and optimization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of a distribution network settlement quota method based on big data provided in an embodiment of the present application.

[0020] Figure 2 A schematic diagram of the structure of a distribution network settlement quota device based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0022] Embodiment 1, Figure 1 The schematic diagram of the structure of the distribution network settlement quota method based on big data provided in the embodiment of the present application includes the following steps:

[0023] S1, real-time acquisition of distributed energy generation data, classification of different types of distributed energy generation data based on cluster analysis algorithm, and analysis of the classification results to obtain the power generation characteristics of the distribution network.

[0024] In this example, a large number of high-precision smart sensors with real-time communication capabilities are deployed at key nodes of the distribution network, including the output end of distributed energy generation equipment, the user's power access point, and the power transmission line of the power grid. These sensors can accurately collect various types of data at the millisecond level. The power generation is obtained in real time through power sensors and power metering devices installed on the power generation equipment.

[0025] After obtaining distributed energy generation data and user electricity consumption data in real time, the data is cleaned and preprocessed. The abnormal data caused by sensor failure or communication interference is removed through the outlier detection algorithm, and the missing data is reasonably supplemented by the data interpolation method. For different types of distributed energy generation data and user electricity consumption data, select the appropriate clustering analysis algorithm. Commonly used clustering algorithms include K-means algorithm, hierarchical clustering algorithm, DBSCAN algorithm, etc.

[0026] Different types of distributed energy generation data are classified according to the cluster analysis algorithm, specifically:

[0027] Obtain distributed energy generation data points under different seasons and weather conditions based on big data;

[0028] Determine the initial characteristic type according to the impact of different seasons and weather conditions on distributed energy generation, the initial characteristic type includes sunny summer, cloudy summer, sunny winter, cloudy winter;

[0029] The initial feature type is used as the initial cluster center, and the distance between the distributed energy generation data point and the initial cluster center is calculated based on the Euclidean distance formula;

[0030] Assign each distributed energy generation data point to the nearest initial cluster center;

[0031] For all distributed energy generation data points of each initial cluster center, calculate the average value of the light intensity feature dimension and set the average value as the new cluster center;

[0032] Based on the K-means algorithm, the process of calculating distance, assigning data points and updating cluster centers is repeated until the algorithm converges and the clustering result is obtained.

[0033] The specific calculation formula of the Euclidean distance formula is as follows:

[0034]

[0035] In the formula, is the coordinate vector of the distributed energy generation data point, is the coordinate vector of the cluster center, is the data dimension, where =1,2,3,..., R,R are integers.

[0036] The power generation characteristics of the distribution network are analyzed according to different classifications, specifically:

[0037] Draw a scatter plot based on the clustering results, set the light intensity as the X-axis, the power generation as the Y-axis, and the initial feature type as different colors;

[0038] The scatter plot is analyzed to obtain the power generation characteristics of different initial characteristic types of the distribution network;

[0039] For the initial characteristic type of sunny summer, the light intensity is high, the generated power generation is high, and the maintenance frequency of personnel becomes high;

[0040] For the initial characteristic types of cloudy summer and cloudy winter, the light intensity is low, the generated power generation is low, and the maintenance frequency of personnel becomes low;

[0041] For the initial characteristic type of sunny winter, the light intensity is medium, the power generation is moderate, and the frequency of personnel maintenance is moderate.

[0042] It should be noted that the analysis of the power generation characteristics of different clustering categories has the following advantages for the subsequent settlement quota plan formulation:

[0043] Enhanced accuracy: After a detailed understanding of the power generation characteristics of various power generation methods, it is possible to more accurately predict the power generation range. For example, by analyzing the historical data of wind power generation in a certain area and the characteristics of local wind resources, including wind direction, wind speed and other power generation characteristics, a more accurate power generation model can be established. When formulating a settlement quota plan, a reasonable quota standard can be determined based on this accurate model. For thermal power generation companies, considering the stability of their equipment operation and the predictability of fuel supply, a relatively fixed basic power generation quota can be formulated; for renewable energy power generation companies, combined with the characteristics of resource volatility, a dynamic quota adjustment mechanism linked to resource conditions is set up, so that the settlement quota plan can more accurately reflect the actual power generation situation.

[0044] Improve fairness: Different power generation categories have different power generation characteristics. For example, thermal power generation is relatively stable and can control power generation more accurately according to fuel supply conditions; hydropower generation is greatly affected by seasonal precipitation, and power generation varies significantly between the flood season and the dry season; wind power generation depends on wind resources and is intermittent and volatile. By analyzing the power generation characteristics of these different clustering categories, these differences can be taken into account when formulating the settlement quota plan.

[0045] In the settlement quota calculation, different electricity price strategies are formulated for categories with different power generation characteristics; in power dispatching, plans for power supply and demand balance are made in advance based on the power generation characteristics forecasts in different seasons and weather conditions.

[0046] S2, construct a real-time dynamic model of the distribution network, determine the abnormal state of the distribution network, adjust the abnormal state of the distribution network, and obtain the adjusted compensation quota.

[0047] In this example, building a real-time dynamic model of the distribution network can continuously monitor the operating status of the distribution network and track key parameters such as power flow, load changes, and equipment health in real time. When an abnormality occurs in the distribution network, the model can detect these abnormalities in real time and diagnose them. This can quickly identify problems at the early stage of a fault and provide early warnings, reducing power outage time and the impact of the fault. When a fault occurs in the distribution network, the real-time dynamic model can help quickly locate the fault area. The faulty line can be quickly determined. This allows operation and maintenance personnel to isolate and repair the fault in the shortest possible time, improving recovery efficiency. Building a real-time dynamic model of the distribution network can provide more efficient and accurate judgment and decision support before, during, and during the recovery process of a fault, thereby improving the operational safety and stability of the power grid.

[0048] Construct a real-time dynamic model of the distribution network and determine the abnormal state of the distribution network, specifically:

[0049] Acquire line loss data and voltage deviation data in real time, and build a real-time dynamic model of the distribution network based on the neural network algorithm;

[0050] Obtain the output of the real-time dynamic model of the distribution network within a preset time period and integrate it into a data set;

[0051] Use statistical methods to obtain the mean and standard deviation of the data set;

[0052] Based on 3 In principle, a data set with a mean value exceeding 3 times the standard deviation is considered an abnormal state of the distribution network.

[0053] Line loss data is used to evaluate the degree of line loss. It helps engineers analyze the operating efficiency of lines by reflecting the energy loss of power or signals during transmission. In the real-time dynamic model of the distribution network, line loss data plays a vital role, especially in judging and identifying abnormal conditions of the distribution network.

[0054] The specific method of obtaining line loss data is as follows:

[0055] Obtain the conductance, susceptance and voltage amplitude of the line;

[0056] The active power loss and reactive power loss of the line are calculated based on the power flow algorithm;

[0057] Line loss data is obtained by integrating active loss and reactive loss;

[0058] The specific calculation formula of the active power loss is as follows:

[0059]

[0060] The specific calculation formula of the reactive power loss is as follows:

[0061]

[0062] The specific calculation formula of the line loss data is as follows:

[0063]

[0064] In the formula, is the line loss data, For Line The reactive power loss, For Line Active power loss, For Line The conductivity, For Line The electrical susceptance, For Node The voltage amplitude, For Node The voltage amplitude, For Node , The voltage phase angle difference.

[0065] Voltage deviation data is used to quantify the degree of voltage deviation. That is, the difference between the actual voltage and the standard voltage in the power system. These data reflect the changes in voltage quality in the distribution network and are crucial to the stability of the power system and the operation of equipment. In the real-time dynamic model of the distribution network, voltage deviation data plays a vital role, especially when judging the abnormal state of the distribution network, it can provide strong support for detecting and locating problems.

[0066] The specific method of obtaining voltage deviation data is as follows:

[0067] Collect voltage data in real time according to a preset time interval to obtain a voltage data set;

[0068] The average voltage deviation is obtained by averaging the voltage data set based on a statistical method;

[0069] The standard deviation of the voltage data set is calculated based on the average voltage deviation to quantify the discreteness of the voltage deviation and obtain the voltage deviation data.

[0070] The specific calculation formula of the average voltage deviation is as follows:

[0071]

[0072] The standard deviation of the voltage data set is specifically calculated as follows:

[0073]

[0074] In the formula, is the voltage deviation data, For the Voltage data, is the standard voltage, is the average voltage deviation, and N is the total number of voltage data.

[0075] The real-time dynamic model of the distribution network, the specific calculation formula is as follows:

[0076]

[0077] In the formula, is the real-time dynamic model of the distribution network. is the line loss data, is the voltage deviation data, is the weight of line loss data, is the weight of the voltage deviation data.

[0078] It should be noted that the model is constructed through a neural network algorithm, and the weights of the line loss data and the voltage deviation data are obtained through a large amount of historical data through continuous adjustment and iterative training.

[0079] Adjust the abnormal state of the distribution network and obtain the adjusted compensation quota, specifically:

[0080] Acquire the abnormal state of the distribution network, the abnormal state types of the distribution network include voltage abnormality, power factor abnormality and line abnormality;

[0081] The abnormal voltage and power factor of the distribution network are regulated by inputting reactive power compensation based on the compensation equipment. When the abnormal state returns to normal, the input is stopped;

[0082] The total amount of reactive power compensation is calculated based on the actual reactive power compensation capacity and switching time;

[0083] The equipment characteristic information and reactive compensation information per unit capacity during the abnormal adjustment of the line are obtained, and the adjusted compensation quota is obtained based on the total amount of reactive compensation.

[0084] S3, based on the power generation characteristics and compensation quota of the distribution network, the optimized settlement quota scheme is obtained based on the particle swarm optimization algorithm, specifically:

[0085] Determining first characteristics corresponding to different seasons and weather conditions according to power generation characteristics, wherein the first characteristics include power generation characteristics, material characteristics, and human characteristics;

[0086] The first feature is combined with the compensation quota to establish an objective function based on minimizing the comprehensive cost of the distribution network and determine the constraint conditions;

[0087] Based on the particle swarm optimization algorithm, the position of each particle is set as a settlement quota scheme, and the speed of each particle is set as the first feature and the compensation quota;

[0088] Initialize the position, speed and individual optimal position of each particle, perform an iterative cycle, and update the speed and position of each particle according to the speed update formula and position update formula;

[0089] For each updated particle position, calculate its fitness value, which is the calculation of the objective function;

[0090] If the fitness value of the current position is better than the individual optimal position, the individual optimal position is updated. The fitness value of the current position is better than the individual optimal position, which can be understood as the fitness value of the current position is less than the individual optimal position.

[0091] When the iteration reaches the maximum number of iterations, the iteration is stopped, and the particle with the smallest fitness value is selected from the individual optimal positions of all particles as the global optimal position. The global optimal position is the optimal settlement quota plan.

[0092] The fitness value is specifically calculated as follows:

[0093]

[0094] In the formula, is the fitness value, For the power generation characteristics, is the material characteristic, For human characteristics, , , , They are the proportion of the settlement quota respectively.

[0095] The speed update formula, the specific calculation formula is as follows:

[0096]

[0097] The position update formula, the specific calculation formula is as follows:

[0098]

[0099] In the formula, For particles In the The speed at the iteration, W is the inertia weight, and is the learning factor, and for A random number uniformly distributed in the interval, For particles The individual optimal position of For particles In the The position at the iteration, is the global optimal position.

[0100] It should be noted that + + + =1 is the constraint condition.

[0101] Embodiment 2, Figure 2 The schematic diagram of the structure of the distribution network settlement quota device based on big data provided in the embodiment of the present application includes a clustering classification module, an abnormal state identification and compensation quota acquisition module, and a settlement quota scheme optimization module, and there are connections between the modules:

[0102] Clustering and classification module: used to obtain distributed energy generation data in real time, classify different types of distributed energy generation data based on clustering analysis algorithms, and analyze the classification results to obtain the power generation characteristics of the distribution network;

[0103] The abnormal state identification and compensation quota acquisition module is used to build a real-time dynamic model of the distribution network, determine the abnormal state of the distribution network, adjust the abnormal state of the distribution network, and obtain the adjusted compensation quota;

[0104] The settlement quota scheme optimization module is used to obtain an optimized settlement quota scheme based on the particle swarm optimization algorithm according to the power generation characteristics and compensation quota of the distribution network.

[0105] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0106] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0107] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0108] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0109] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0110] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A distribution network settlement quota method based on big data, characterized in that: The steps include: Obtain distributed energy generation data in real time, classify different types of distributed energy generation data based on cluster analysis algorithms, and analyze the classification results to obtain the generation characteristics of the distribution network; The cluster analysis algorithm is used to classify different types of distributed energy generation data, specifically: Obtain distributed energy generation data points under different seasons and weather conditions based on big data; Determine the initial characteristic type according to the impact of different seasons and weather conditions on distributed energy generation; Use the initial feature type as the initial cluster center; Assign each distributed energy generation data point to the nearest initial cluster center; For all distributed energy generation data points of each initial cluster center, calculate the average value of the light intensity feature dimension and set the average value as the new cluster center; Based on the algorithm, the process of calculating distance, assigning data points and updating cluster centers is repeated until the algorithm converges and the clustering result is obtained; Construct a real-time dynamic model of the distribution network, determine the abnormal state of the distribution network, adjust the abnormal state of the distribution network, and obtain the adjusted compensation quota; The settlement quota scheme is optimized based on the particle swarm optimization algorithm according to the power generation characteristics and compensation quota of the distribution network; The settlement quota scheme optimized based on the particle swarm optimization algorithm according to the power generation characteristics and compensation quota of the distribution network is specifically: Determining first characteristics corresponding to different seasons and weather conditions according to power generation characteristics, wherein the first characteristics include power generation characteristics, material characteristics, and human characteristics; The first feature is combined with the compensation quota to establish an objective function based on minimizing the comprehensive cost of the distribution network and determine the constraints.

2. The method for settling and quoting distribution network based on big data according to claim 1, characterized in that: The power generation characteristics of the distribution network are obtained by analyzing the classification results, specifically: Draw a scatter plot based on the clustering results, set the light intensity as the X-axis, the power generation as the Y-axis, and the initial feature type as different colors; The scatter plot is analyzed to obtain the power generation characteristics of different initial characteristic types of the distribution network.

3. The distribution network settlement quota method based on big data according to claim 1 is characterized in that: The construction of the real-time dynamic model of the distribution network and the determination of the abnormal state of the distribution network are specifically as follows: Acquire line loss data and voltage deviation data in real time, and build a real-time dynamic model of the distribution network based on the neural network algorithm; Obtain the output of the real-time dynamic model of the distribution network within a preset time period and integrate it into a data set; Use statistical methods to obtain the mean and standard deviation of the data set; Based on 3 In principle, a data set with a mean value exceeding 3 times the standard deviation is considered an abnormal state of the distribution network.

4. The distribution network settlement quota method based on big data according to claim 1 is characterized in that: The abnormal state of the distribution network is adjusted to obtain the adjusted compensation quota, specifically: Obtaining the abnormal state of the distribution network, the abnormal state types of the distribution network include voltage abnormality, power factor abnormality and line abnormality; Adjust the reactive power compensation of the compensation equipment based on the abnormal state type of the distribution network, and stop the input when the abnormal state returns to normal; The total amount of reactive power compensation is calculated based on the actual reactive power compensation capacity and switching time; The equipment characteristic information and reactive compensation information per unit capacity during the abnormal adjustment of the line are obtained, and the adjusted compensation quota is obtained based on the total amount of reactive compensation.

5. The distribution network settlement quota method based on big data according to claim 1 is characterized in that: The settlement quota scheme optimized based on the particle swarm optimization algorithm according to the power generation characteristics and compensation quota of the distribution network is specifically: Based on the particle swarm optimization algorithm, the position of each particle is set as a settlement quota scheme, and the speed of each particle is set as the first feature and the compensation quota; Initialize the position, speed and individual optimal position of each particle, perform an iterative cycle, and update the speed and position of each particle according to the speed update formula and position update formula; For each updated particle position, calculate its fitness value, where the fitness value is the calculation of the objective function; If the fitness value of the current position is better than the individual optimal position, the individual optimal position is updated; When the iteration reaches the maximum number of iterations, the iteration is stopped, and the particle with the smallest fitness value is selected from the individual optimal positions of all particles as the global optimal position. The global optimal position is the optimal settlement quota plan.

6. The distribution network settlement quota method based on big data according to claim 3 is characterized in that: The specific method for obtaining the voltage deviation data is as follows: Collect voltage data in real time according to a preset time interval to obtain a voltage data set; The average voltage deviation is obtained by averaging the voltage data set based on a statistical method; The standard deviation of the voltage data set is calculated based on the average voltage deviation to quantify the discreteness of the voltage deviation and obtain the voltage deviation data.

7. The method for settling quotas of distribution networks based on big data according to claim 6, characterized in that: The specific calculation formula of the average voltage deviation is as follows: The standard deviation of the voltage data set is specifically calculated as follows: In the formula, is the voltage deviation data, For the Voltage data, is the standard voltage, is the average voltage deviation, and N is the total number of voltage data.

8. A device using the distribution network settlement quota method based on big data as claimed in any one of claims 1 to 7, comprising a clustering classification module, an abnormal state identification and compensation quota acquisition module, and a settlement quota scheme optimization module, wherein the modules are connected: Clustering and classification module: used to obtain distributed energy generation data in real time, classify different types of distributed energy generation data based on clustering analysis algorithms, and analyze the classification results to obtain the power generation characteristics of the distribution network; The abnormal state identification and compensation quota acquisition module is used to build a real-time dynamic model of the distribution network, determine the abnormal state of the distribution network, adjust the abnormal state of the distribution network, and obtain the adjusted compensation quota; The settlement quota scheme optimization module is used to obtain an optimized settlement quota scheme based on the particle swarm optimization algorithm according to the power generation characteristics and compensation quota of the distribution network.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution network settlement quota method based on big data as described in any one of claims 1 to 7.

Images