A power distribution method, apparatus, and equipment based on supply and demand.

Abstract

This application discloses a power distribution method, apparatus, and equipment based on supply and demand, comprising: acquiring load information of each load in the load side of the power consumption area and the load power consumption during a preset period; clustering each load according to the load power consumption and load information to obtain clustering results characterizing the power demand of the power consumption area during the preset period; making ultra-short-term predictions of the power demand of the power consumption area for future periods based on the clustering results to obtain prediction results; acquiring power generation data of different power generation units in the power generation side for each preset period within the preset period; determining the power supply interval representing the power generation of the power generation side within the preset period based on the power generation data; generating an optimal energy efficiency report and optimal transmission scheme information based on the prediction results and the power supply interval of the power generation; and adjusting the current power distribution situation based on the optimal energy efficiency report and optimal transmission scheme information. The power distribution method of this application realizes the balance between supply and demand in the system and improves the utilization of idle resources.

Description

Technical Field

[0001] This application relates to the field of power information technology, and more specifically, to a power distribution method, apparatus and equipment based on supply and demand. Background Technology

[0002] The core characteristic of the new power system is that new energy sources dominate and become the main energy form. The proportion of new energy in primary energy consumption is constantly increasing, accelerating the replacement of fossil fuels. In the future, my country's installed power capacity will maintain steady and rapid growth, showing a trend of "wind and solar leading, and multi-source coordination."

[0003] New power systems utilizing renewable energy sources have increased intermittency and volatility, significantly increasing the demand for flexible resources. However, existing power systems have weak regulation capabilities, often resulting in a large amount of idle flexible resources going unused. This leads to situations where some areas experience oversupply while others suffer from undersupply, preventing the system from achieving a balance between supply and demand. The utilization of idle resources is suboptimal, and system efficiency needs improvement. Summary of the Invention

[0004] In view of the above problems, this application is made to provide a power distribution method, apparatus, and equipment based on supply and demand, so as to achieve a balance between supply and demand in the system and improve the utilization of idle resources. The specific solution is as follows:

[0005] A power distribution method based on supply and demand includes:

[0006] Obtain load information for each load in the power consumption area and the power consumption of the load during a preset time period;

[0007] Based on the load power consumption and the load information, each load is clustered to obtain a clustering result that characterizes the power demand of the power consumption area within a preset time period;

[0008] Based on the clustering results, a short-term forecast of the electricity demand in the electricity consumption area is made for the future cycle, and the forecast results are obtained.

[0009] The power generation data of different power generation units in the power generation side are obtained for each preset time period within a preset period, wherein the preset period has the same period length as the future period.

[0010] Based on the power generation data for each preset time period within the preset period, a power supply interval representing the power generation on the power generation side within the preset period is determined.

[0011] Based on the prediction results and the power supply range representing the power generation on the power generation side within the preset period, an optimal energy efficiency report and optimal power transmission scheme information are generated.

[0012] Adjust the current power distribution situation based on the optimal energy efficiency report and the optimal power transmission scheme information.

[0013] Preferably, determining the power supply interval representing the power generation on the power generation side within the preset period based on the power generation data for each preset time period within the preset period includes:

[0014] Based on the power generation data for each preset time period within the preset period, the power generation interval for each preset time period within the preset period is determined.

[0015] According to a preset filtering strategy, the endpoint values ​​of the power generation interval in each preset time period within the preset period are filtered to determine the power supply interval representing the power generation on the power generation side within the preset period.

[0016] Preferably, determining the power generation interval for each preset time period within the preset period based on the power generation data for each preset time period within the preset period includes:

[0017] The power generation data for each preset time period within the preset period is screened for rationality to determine the power generation data for each preset time period within the preset period.

[0018] Determine the maximum and minimum values ​​of the power generation data for each preset time period within the preset cycle;

[0019] The maximum value and the minimum value are respectively used as the right endpoint and left endpoint of the power generation interval for each preset time period within the preset period, thus obtaining the power generation interval that corresponds one-to-one with each preset time period within the preset period.

[0020] Preferably, the step of filtering the endpoint values ​​of the power generation interval for each preset time period within the preset period according to a preset filtering strategy to determine the power supply interval representing the power generation on the power generation side within the preset period includes:

[0021] Outliers in the endpoint values ​​of the power generation intervals in each preset time period within the preset period are removed to obtain power generation intervals in at least one preset time period within the preset period after removing outliers.

[0022] If there is only one power generation interval, then the power generation interval shall be used as the power supply interval representing the power generation of the power generation side within the preset period.

[0023] If there are at least two power generation intervals, then the endpoint values ​​of the at least two power generation intervals that exceed the preset tolerance value are removed to obtain at least one preset time period within the preset period after removing the endpoint values ​​that exceed the preset tolerance value.

[0024] If there is only one power generation interval, then the power generation interval shall be used as the power supply interval representing the power generation of the power generation side within the preset period.

[0025] If there are at least two power generation intervals, then the endpoint values ​​that do not meet the reasonableness requirements among the endpoint values ​​of the at least two power generation intervals are removed to obtain at least one preset time period within the preset period after removing the endpoint values ​​that do not meet the reasonableness requirements.

[0026] The power generation interval within the preset period after removing endpoint values ​​that do not meet the rationality requirement is taken as the power supply interval representing the power generation on the power generation side within the preset period.

[0027] Preferably, before filtering the endpoint values ​​of the power generation interval for each preset time period within the preset period according to a preset filtering strategy, the method further includes:

[0028] Construct a box-and-whisker diagram of the endpoint values ​​of the power generation interval for each preset time period within the preset period. The box-and-whisker diagram is used to statistically analyze and display the dispersion of each endpoint value within the preset period during the process of filtering the endpoint values ​​of the power generation interval for each preset time period within the preset period.

[0029] Preferably, the step of obtaining load information of each load in the load side of the electricity consumption area and the load power consumption for a preset time period includes:

[0030] Obtain the electricity consumption information of each load in the load side of the electricity consumption area;

[0031] Based on the electricity consumption information of each load in the load side of the electricity consumption area, determine the load curve of each load in the load side of the electricity consumption area within a preset time period;

[0032] A non-intrusive load identification method is used to identify the load curves of each load, thereby obtaining the load information of each load on the load side of the power consumption area and the load power consumption for a preset time period.

[0033] Preferably, the load information includes:

[0034] The load information parameters in the load side of the power consumption area, the correlation between the line loss rate of various power sources and the total power consumption in the preset time period, the correlation between the line loss rate of the load and the total power consumption in the preset time period, the operating status of various power sources and loads in the preset time period, and the adjustable value of various power sources and loads in the preset time period.

[0035] The power consumption of the load includes:

[0036] The data on electricity consumption of various power sources and loads within the preset time period, and the active power of various power sources and loads within the preset time period.

[0037] Preferably, based on the load consumption and the load information, each load is clustered to obtain a clustering result characterizing the power demand of the power consumption area within a preset time period, including:

[0038] Multiple cluster centers are randomly generated, and each cluster center corresponds to a first cluster center value;

[0039] For each cluster center:

[0040] The loads whose electricity consumption is closest to the first cluster center value of the cluster center are clustered together to obtain the clustered load group;

[0041] Calculate the average power consumption of the loads in the clustered load group, and use the average value as the second cluster center value of the cluster center;

[0042] Determine whether the value of the first cluster center of the cluster center is the same as the value of the second cluster center of the cluster center. If so, the cluster load group of the cluster center is taken as the clustering result that characterizes the electricity demand of the electricity consumption area within the preset time period.

[0043] If not, replace the first cluster center value of the cluster center with the second cluster center value of the cluster center, and return to the step of clustering the loads corresponding to the loads whose electricity consumption is closest to the first cluster center value of the cluster center, until the first cluster center value of the cluster center is the same as the second cluster center value of the cluster center.

[0044] A power distribution device based on supply and demand, comprising:

[0045] The electricity consumption data acquisition unit is used to acquire the load information of each load in the load side of the electricity consumption area and the load electricity consumption during a preset period.

[0046] The data clustering unit is used to cluster each load according to the load power consumption and the load information to obtain a clustering result that characterizes the power demand of the power consumption area within a preset time period;

[0047] The data prediction unit is used to make ultra-short-term predictions of the electricity demand of the electricity consumption area for future periods based on the clustering results, and obtain prediction results.

[0048] A power generation data acquisition unit is used to acquire power generation data of different power generation units on the power generation side for each preset time period within a preset period, wherein the preset period has the same period length as the future period.

[0049] The interval determination unit is used to determine the power supply interval representing the power generation of the power generation side within the preset period based on the power generation data of each preset time period within the preset period.

[0050] An information generation unit is used to generate an optimal energy efficiency report and optimal power transmission scheme information based on the prediction results and the power supply interval representing the power generation of the power generation side within the preset period.

[0051] The power distribution adjustment unit is used to adjust the current power distribution status based on the optimal energy efficiency report and the optimal power transmission scheme information.

[0052] A power distribution device based on supply and demand relationships includes: a memory and a processor;

[0053] The memory is used to store programs;

[0054] The processor is used to execute the program to implement the various steps of the power distribution method based on supply and demand as described above.

[0055] By means of the above technical solution, the power distribution method based on supply and demand relationship of this application can first obtain the load information of each load in the load side of the power consumption area and the load power consumption of a preset period, cluster each load, perform ultra-short-term forecasting, and obtain the forecast result representing the power demand of the power consumption area in the future period; then obtain the power generation data of different power generation units in the power generation side in each preset period in the preset period, determine the power supply interval representing the power generation of the power generation side in the preset period, generate the optimal energy efficiency report and the optimal transmission scheme information according to the forecast result and the power supply interval, and then adjust the current power distribution situation according to the optimal energy efficiency report and the optimal transmission scheme information. Since the prediction results can reflect the electricity demand of the area within a preset period, and the power supply interval can reflect the power generation of different power generation units in the power generation side during each preset period within the preset period, the optimal energy efficiency report and optimal transmission scheme information generated based on the prediction results and the power supply interval within the preset period can accurately reflect the historical demand of the load side, the future demand forecast, and the power generation status of the power generation side. Power distribution based on the optimal energy efficiency report and optimal transmission scheme information can achieve a balance between supply and demand, realize information exchange between the supply and demand sides, improve the utilization of idle resources, and enhance system efficiency. Attached Figure Description

[0056] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0057] Figure 1A schematic flowchart illustrating a power distribution method based on supply and demand relationships, provided as an embodiment of this application;

[0058] Figure 2 A schematic diagram illustrating the process of determining the power supply range for power generation in an embodiment of this application;

[0059] Figure 3 This is a flowchart illustrating the process of determining power generation data provided in an embodiment of this application.

[0060] Figure 4 A schematic diagram of a power distribution device based on supply and demand relationship is provided for an embodiment of this application;

[0061] Figure 5 This is a schematic diagram of the structure of a power distribution method device based on supply and demand relationship, provided as an embodiment of this application. Detailed Implementation

[0062] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0063] New power systems utilizing renewable energy sources have increased intermittency and volatility, significantly increasing the demand for flexible resources. However, existing power systems have weak regulation capabilities, often resulting in a large amount of idle flexible resources going unused. This leads to situations where some areas experience oversupply while others suffer from undersupply, preventing the system from achieving a balance between supply and demand. The utilization of idle resources is suboptimal, and system efficiency needs improvement.

[0064] Therefore, in order to solve the above problems, this application provides a power distribution method, apparatus and equipment based on supply and demand relationship, so as to achieve a balance between supply and demand on both sides of the system and improve the utilization of idle resources.

[0065] The following section provides a detailed description of a power distribution method based on supply and demand, as described in this application. Please refer to [link / reference needed]. Figure 1 , Figure 1 This is a flowchart illustrating a power distribution method based on supply and demand provided in an embodiment of this application. The method may include the following steps:

[0066] Step S110: Obtain the load information of each load in the power consumption area and the load power consumption for a preset time period.

[0067] Specifically, the load can include various electrical appliances of residential users, charging piles, and other electrical load devices. Electrical appliances can include household refrigerators and air conditioners. The preset time period can be a time cycle within a certain duration, such as one day or one hour. Load information can include: load information parameters on the load side of the electricity consumption area, the correlation between the line loss rate of various power sources and the total electricity consumption within the preset time period, the correlation between the line loss rate of the load and the total electricity consumption within the preset time period, the operating status of various power sources and loads within the preset time period, and the adjustable value of various power sources and loads within the preset time period. Load electricity consumption can include: electricity consumption data of various power sources and loads within the preset time period, and the active power of various power sources and loads within the preset time period.

[0068] Step S120: Cluster each load according to the load power consumption and the load information to obtain a clustering result that characterizes the power demand of the power consumption area within a preset time period.

[0069] Specifically, since there are numerous loads on the load side within an electricity consumption area, individually calculating the electricity consumption and load information of each load would lead to increased time and economic costs. Therefore, clustering methods are used to classify and aggregate massive amounts of data based on similar characteristics. In some embodiments, the clustering method for clustering loads can be the K-means clustering algorithm, which can accurately cluster loads with similar electricity consumption characteristics. In other embodiments, the clustering method can also be other algorithms that achieve the same purpose.

[0070] Specifically, after clustering each load, multiple clustering results are obtained. In some embodiments, the number of clustering results is five: Cluster I, Cluster II, Cluster III, Cluster VI, and Cluster V. Cluster I represents loads with a very high degree of power shortage in the region, and Cluster I can send a feedback command indicating extreme power shortage; Cluster II represents loads with a relatively high degree of power shortage in the region, and Cluster II can send a feedback command indicating a moderate power shortage; Cluster III represents loads with a balanced supply and demand in the region, and Cluster III is not active at this time; Cluster VI represents loads with a relatively high degree of power supply in the region, and Cluster VI can send a feedback command indicating a large surplus of power; Cluster V represents loads with a very high degree of power supply in the region, and Cluster V can send a feedback command indicating a large surplus of power. Based on the feedback commands sent by the above clusters, the system can send operation commands to the power distribution center, thereby enabling the power distribution center to adjust the power distribution scheme.

[0071] Step S130: Based on the clustering results, perform ultra-short-term prediction of the electricity demand of the electricity consumption area for future cycles to obtain the prediction results.

[0072] Specifically, ultra-short-term forecasting is a prediction method that learns the linear and nonlinear characteristics of power load data over a certain short period of time through time series analysis. It plays an important role in ensuring the safe and stable operation of the power grid, optimizing energy management, improving the utilization rate of power generation equipment, and reducing operating costs. In this embodiment, ultra-short-term forecasting based on clustering results can obtain the electricity demand on the load side in different regions within the future period. This allows for adjustments to the power supply scheme for the load side in different regions in subsequent steps based on varying electricity demands.

[0073] Understandably, electricity consumption varies across different regions due to seasonality, environmental factors, and local policies. For example, some businesses in a region produce certain products in the summer but not in the winter; certain months are peak sales seasons with high production volumes, while other months are off-seasons with low production volumes; electricity consumption surges in summer and decreases in winter. Furthermore, users in areas without heating and with colder weather experience a significant increase in air conditioning consumption during winter. Because of these temporal variations in electricity consumption, ultra-short-term forecasts of future electricity demand are essential. These forecasts allow for anticipating future demand and adjusting power distribution plans accordingly.

[0074] This step, after performing ultra-short-term forecasts, can accurately predict distributed power output data, user energy consumption patterns, flexible load periods, weather information, and energy price information for the electricity consumption area in the future cycle.

[0075] Furthermore, the future period in this application can be a relatively long period of time, such as a week or a month.

[0076] Step S140: Obtain the power generation data of different power generation units in the power generation side for each preset period within a preset cycle.

[0077] The preset period and the future period have the same period length.

[0078] Specifically, the power generation side may include several power generation units.

[0079] Specifically, this application can make ultra-short-term predictions of the electricity demand of the electricity consumption area for future periods, and obtain the prediction results. At the same time, it can also obtain the power generation data of each preset period within a preset period of the same length as the future period, so as to match the power generation situation on the power generation side with the electricity demand on the load side within the same time period.

[0080] Step S150: Based on the power generation data of each preset time period within the preset period, determine the power supply interval representing the power generation of the power generation side within the preset period.

[0081] Specifically, the power generation amount of the power generation units in the power generation side is not a fixed value and will fluctuate due to various factors. Therefore, what can be determined in this step is the power supply interval of the power generation amount in the power generation side within the preset period.

[0082] For example, this application can obtain the power generation amount data of different power generation units in the power generation side every day within a week, and determine the most representative power supply interval within a week based on the power generation amount data of each day. This power supply interval can be the power supply interval of the power generation amount on a certain day within a week, or the power supply interval of the power generation amounts on certain days within a week, which is not limited herein.

[0083] Step S160: Generate an optimal energy efficiency report and the best power transmission plan information according to the prediction result and the power supply interval representing the power generation amount in the power generation side within the preset period.

[0084] Specifically, the optimal energy efficiency report can reflect the relationship between the supply and demand at both ends of the load side and the power generation side, as well as the relationship between the power supply distance and the power supply cost. For example, the regional power shortage is A, the power generation side B is far from the region, and the available power supply is B1, where B1 > A; the power generation side C is close to the region, and the available power supply is C1, where C1 < A. In this case, although the power generation side B is far from the region, an optimal energy efficiency report for supplying power from the power generation side B to the region is still generated. If the available power supplies of the power generation sides with different distances from the region all meet the requirements, then an optimal energy efficiency report can be generated based on considerations such as the shortest distance and the lowest cost.

[0085] Specifically, the system can adjust the power distribution plan based on the optimal energy efficiency report to generate the best power transmission plan information to determine the best power transmission plan.

[0086] Step S170: Adjust the current power distribution situation according to the optimal energy efficiency report and the best power transmission plan information.

[0087] Specifically, the system statistically analyzes the load information of each load in the load side of the power consumption area collected, the load power consumption of each load in the load side of the power consumption area during the preset time period, and the power generation amount data of each power generation unit in the power generation side during each preset time period within the preset period, generates an optimal energy efficiency report and the best power transmission plan, sends the best power transmission information and the optimal energy efficiency report to the power distribution center, and the power distribution center and the intelligent controller interact to adjust the power distribution plan, which can supply power to the shortage area or adjust the supply and demand balance between the areas with abundant power and the areas with shortage of power.

[0088] Furthermore, embodiments of this application can also store the load information of each load in the load side of the power consumption area, the load power consumption of each load in the load side of the power consumption area during a preset period, and the power generation data of each power generation unit in the power generation side within a preset period of a preset cycle, and generate a historical data query library so that all historical data can be called up during power distribution, maintenance or monitoring.

[0089] By means of the above technical solution, the power distribution method based on supply and demand relationship of this application can first obtain the load information of each load in the load side of the power consumption area and the load power consumption of a preset period, cluster each load, perform ultra-short-term forecasting, and obtain the forecast result representing the power demand of the power consumption area in the future period; then obtain the power generation data of different power generation units in the power generation side in each preset period in the preset period, determine the power supply interval representing the power generation of the power generation side in the preset period, generate the optimal energy efficiency report and the optimal transmission scheme information according to the forecast result and the power supply interval, and then adjust the current power distribution situation according to the optimal energy efficiency report and the optimal transmission scheme information. Since the prediction results can reflect the electricity demand of the area within a preset period, and the power supply interval can reflect the power generation of different power generation units in the power generation side during each preset period within the preset period, the optimal energy efficiency report and optimal transmission scheme information generated based on the prediction results and the power supply interval within the preset period can accurately reflect the historical demand of the load side, the future demand forecast, and the power generation status of the power generation side. Power distribution based on the optimal energy efficiency report and optimal transmission scheme information can achieve a balance between supply and demand, realize information exchange between the supply and demand sides, improve the utilization of idle resources, and enhance system efficiency.

[0090] In some embodiments of this application, the process of determining the power supply interval representing the power generation on the power generation side within the preset period based on the power generation data for each preset time period within the preset period is described, with reference to... Figure 2 The process may include:

[0091] Step S210: Based on the power generation data of each preset time period within the preset period, determine the power generation interval of each preset time period within the preset period.

[0092] Specifically, due to the intermittent and fluctuating nature of large-scale new energy power generation, and its susceptibility to weather conditions, different power generation units correspond to different power generation intervals within a preset time period. During the processing of massive amounts of data, some data will inevitably be inconsistent with the requirements. If left unprocessed, this inconsistency will affect the results, leading to discrepancies between the results and the actual situation. Therefore, this step processes the power generation data for each preset time period within the preset period to obtain the power generation interval for each preset time period within the preset period.

[0093] Step S220: Filter the endpoint values ​​of the power generation interval for each preset time period within the preset period according to a preset filtering strategy to determine the power supply interval representing the power generation on the power generation side within the preset period.

[0094] Specifically, analogous to the process of filtering water multiple times, in massive amounts of data, due to various objective reasons, such as unsuitable screening conditions, a single screening cannot remove all unreasonable data. Unfiltered unreasonable data will inevitably affect subsequent calculation results, leading to deviations from reality and errors. Therefore, in this step, after screening the endpoint values, a power supply interval representing the power generation on the power generation side within the preset period is determined.

[0095] Furthermore, this application can also obtain the total power generation of each power generation unit in the power generation side based on several power supply intervals, transmit the total power generation of several power generation units to the power distribution center, and the power distribution center supplies power to the power shortage area based on the distance from several power saturation areas to power shortage areas and the excess power generation, thereby realizing information exchange between power supply and demand sides and optimizing the power supply structure.

[0096] Specifically, in some embodiments of this application, before step S220, which filters the endpoint values ​​of the power generation interval for each preset time period within the preset period according to a preset filtering strategy, the method further includes:

[0097] Construct a box-and-whisker diagram of the endpoint values ​​of the power generation interval for each preset time period within the preset period. The box-and-whisker diagram is used to statistically analyze and display the dispersion of each endpoint value within the preset period during the process of filtering the endpoint values ​​of the power generation interval for each preset time period within the preset period.

[0098] Specifically, a box-and-whisker plot is a method of describing data using five statistical measures: minimum, upper quartile, median, lower quartile, and maximum. It can also roughly indicate whether the data has symmetry, the degree of dispersion of the distribution, etc., and is particularly suitable for comparing several samples. The box-and-whisker plot is a method used for statistical analysis and description of data in some embodiments of this application; in other embodiments, other methods that can achieve the same purpose may be used.

[0099] In some embodiments of this application, the process of determining the power generation interval for each preset time period within the preset period based on the power generation data for each preset time period within the preset period is described. (Refer to...) Figure 3 The process may include:

[0100] Step S310: Perform a rationality screening on the power generation data for each preset time period within the preset period, and determine the power generation data for each preset time period within the preset period.

[0101] Specifically, in some embodiments, taking the processing of data on day i as an example, the power generation data for each preset time period within the preset period is screened for reasonableness to determine the power generation data for each preset time period within the preset period, which may include the following steps:

[0102] Step S1: Calculate the sample mean m of the power generation data on day i. i and sample standard deviation σ i :

[0103]

[0104]

[0105] Where i = 1,...,n,n i Let data be the total amount of power generation data collected on day i. i,j This represents the j-th power generation data collected on day i.

[0106] Step S2: Determine the power generation data. i,j Does it satisfy the following formula:

[0107] |data i,j -m i |≤k*σ i

[0108] If the power generation data is data i,j If the formula is satisfied, then the data will be... i,j Retain, otherwise reduce power generation data. i,j Eliminate. Here, k is a constraint coefficient, the value of which is determined based on the actual situation.

[0109] Specifically, in this step, the data is filtered using the above-described conditional expressions. In some other embodiments, additional methods that can achieve the same purpose may also be used.

[0110] Step S3: Calculate the sample mean m and sample standard deviation σ of all power generation data retained in step S2 based on the following formula:

[0111]

[0112]

[0113] Among them, data' i,j For the j-th power generation data collected on the i-th day in step S2, n”i n” represents the number of all power generation data retained in step S2. i <n i .

[0114] Step S4: Determine data' i,j Does it satisfy the following condition:

[0115] |data' i,j -m|≤k*σ

[0116] If the data satisfies this condition, the data is retained; otherwise, the data is discarded. Here, k is a constraint coefficient, the value of which is determined based on the actual situation.

[0117] Specifically, in this step, the data is filtered using the above-described conditional expressions. In some other embodiments, additional methods that can achieve the same purpose may also be used.

[0118] Step S320: Determine the maximum and minimum values ​​of the power generation data for each preset time period within the preset cycle.

[0119] Step S330: Use the maximum value and the minimum value as the right endpoint and left endpoint of the power generation interval for each preset time period within the preset period, respectively, to obtain the power generation interval that corresponds one-to-one with each preset time period within the preset period.

[0120] Specifically, the power generation interval on day i is represented as:

[0121]

[0122] Where I represents the total number of data items retained in step S4 above on day i, and data” i,j c is the j-th power generation data collected on the i-th day retained in step S2. i and d i These are the left and right endpoints of the power generation section, respectively.

[0123] In some embodiments of this application, the process of filtering the endpoint values ​​of the power generation interval in each preset time period within the preset period according to a preset filtering strategy to determine the power supply interval representing the power generation on the power generation side within the preset period is described. This process may include:

[0124] Step S221: Remove outliers from the endpoint values ​​of the power generation intervals in each preset time period within the preset period to obtain at least one power generation interval within the preset period after removing outliers.

[0125] Specifically, in some embodiments of this application, box-and-whisker diagrams are used for statistical analysis and description of data. In other embodiments, other methods that achieve the same purpose may also be employed.

[0126] In this embodiment of the application, the endpoint value c of the power generation interval for each preset time period within the preset period is specified. i and d i Construct a box-and-whisker graph and determine the endpoint values ​​c. i and d i If the following formula is satisfied, the power generation intervals containing endpoint values ​​that do not satisfy the formula will be removed, resulting in power generation intervals within at least one preset time period in the preset period after removing outliers:

[0127] c i ∈[Q c (.25)-1.5IQR c Q c (.75)+1.5IQR c ]

[0128] d i ∈[Q d (.25)-1.5IQR d Q d (.75)+1.5IQR d ]

[0129] L i ∈[Q L (.25)-1.5IQR L Q L (.75)+1.5IQR L ]

[0130] Among them, L i =d i -c i Q(.25) is the lower four-digit fraction, indicating that one-quarter of all data values ​​are smaller than it; Q(.75) is the upper four-digit fraction, indicating that one-quarter of all data values ​​are larger than it; IQR is the interquartile range, representing the difference between the upper and lower four-digit fractions.

[0131] Specifically, in this step, the endpoint value after removing outliers is represented as c. i '、d i The power generation range after removing outliers is represented as [c']. i ,d' i ].

[0132] Specifically, in this step, the data is filtered using the above-described conditional expressions. In some other embodiments, additional methods that can achieve the same purpose may also be used.

[0133] Step S222: If there is one power generation interval, the power generation interval is used as the power supply interval representing the power generation of the power generation side within the preset period; if there are at least two power generation intervals, the endpoint values ​​of the endpoint values ​​of the at least two power generation intervals that exceed the preset tolerance value are removed to obtain at least one preset time period within the preset period after removing the endpoint values ​​that exceed the preset tolerance value.

[0134] Specifically, if only one power generation interval remains after removing outliers, the screening process is complete, and the remaining interval is used as the power supply interval representing the power generation on the power generation side within the preset period. If there are at least two power generation intervals, the following operations continue:

[0135] Determine the endpoint value c i 'and d i If the following formula is satisfied, the power generation intervals containing endpoint values ​​exceeding the preset tolerance value that do not satisfy the formula will be removed, resulting in power generation intervals within at least one preset time period in the preset period after removing those exceeding the preset tolerance value:

[0136] c' i ∈[m' c -kσ' c ,m' c +kσ' c ]

[0137] d' i ∈[m' d -kσ' d ,m' d +kσ' d ]

[0138] L' i ∈[m' L -kσ' L ,m' L +kσ' L ]

[0139] Among them, L' i =d' i -c' i ,m' c σ' is the sample mean of all left endpoint values ​​among the endpoint values ​​after outlier removal. c m' is the sample standard deviation of all left endpoint values ​​among the endpoint values ​​after outlier removal. d σ' is the sample mean of all right endpoint values ​​among the endpoint values ​​after outlier removal. d m' is the sample standard deviation of all right endpoint values ​​among the endpoint values ​​after outlier removal. L For all L' values ​​in the endpoint values ​​after removing outliersi The sample mean, σ' L For all L' values ​​in the endpoint values ​​after removing outliers i The sample standard deviation is given by k, which is a constraint coefficient. The value of k is determined according to the actual situation. In some embodiments, k is 2.

[0140] Specifically, in this step, the endpoint value after removing values ​​exceeding the preset tolerance value is denoted as c”. i ,d” i The power generation range after removing those exceeding the preset tolerance limit is represented as [c”]. i ,d” i ].

[0141] Specifically, in this step, the data is filtered using the above-described conditional expressions. In some other embodiments, additional methods that can achieve the same purpose may also be used.

[0142] Step S223: If there is one power generation interval, then the power generation interval is used as the power supply interval representing the power generation of the power generation side within the preset period; if there are at least two power generation intervals, then the endpoint values ​​of the at least two power generation intervals that do not meet the reasonableness requirements are removed to obtain at least one power generation interval within the preset period after removing the endpoint values ​​that do not meet the reasonableness requirements.

[0143] Specifically, if only one power generation interval remains after eliminating those exceeding the preset tolerance value, the screening process is complete, and the remaining power generation interval is used as the power supply interval representing the power generation volume of the power generation side within the preset period. If there are at least two power generation intervals, the following operations continue:

[0144] Calculate ξ * And determine ξ * Does m' satisfy? c ≤ξ * ≤m' d The power generation intervals containing endpoint values ​​that do not satisfy the formula are removed, resulting in power generation intervals within at least one preset time period of the preset period after removing those that do not meet the reasonableness requirement.

[0145]

[0146] Where, m' c σ' is the sample mean of all left endpoint values ​​among the endpoint values ​​after removing those exceeding a preset tolerance value. c 'm' is the sample standard deviation of all left endpoint values ​​among the endpoint values ​​that exceed the preset tolerance value. d σ” represents the sample mean of all right endpoint values ​​among the endpoint values ​​after outlier removal. dThis is the sample standard deviation of all right endpoint values ​​among the endpoint values ​​after outliers have been removed.

[0147] In this step, the power generation intervals that do not meet the rationality requirements are renumbered as 1, 2, ..., n', and represented as...

[0148] Specifically, in this step, the data is filtered using the above-described conditional expressions. In some other embodiments, additional methods that can achieve the same purpose may also be used.

[0149] Step S224: The power generation interval within the preset period after removing endpoint values ​​that do not meet the rationality requirement is taken as the power supply interval representing the power generation on the power generation side within the preset period.

[0150] Specifically, due to various real-world reasons, during the data acquisition and filtering process, there are situations where it is impossible to filter out all unreasonable data in a single pass. This application's embodiments, through the aforementioned steps, establish a multi-dimensional and multi-faceted filtering method to perform multiple filtering and processing operations on the data, ultimately obtaining effective and accurate data and ensuring the accuracy of the results.

[0151] In some embodiments of this application, the process of step S110 above, obtaining load information of each load in the load side of the power consumption area and the load power consumption of a preset time period is described in detail. This process may include:

[0152] Step S111: Obtain the power consumption information of each load in the power consumption area load side.

[0153] Specifically, sampling points are set up on the load side of the electricity consumption area to obtain the electricity consumption information of each load. These sampling points can be various load monitoring points, such as charging piles, residential users, and users converted from coal to electricity. During data collection, data can be sensed and transmitted via Ethernet TCP / IP communication protocol to devices such as area temperature sensors, brightness sensors, distributed energy monitoring terminals, energy storage system monitoring terminals, and multi-functional smart meters and smart sockets on each floor of the building. This data is used to collect power data from the area's distributed generation system and loads. During the data collection process, data such as area scene temperature and brightness environment can also be collected.

[0154] Step S112: Based on the electricity consumption information of each load in the load side of the power consumption area, determine the load curve of each load in the load side of the power consumption area within a preset time period.

[0155] Specifically, this step involves collecting analog data from each load on the load side of the electricity consumption area to obtain the operating parameters of each load and determine the load curve of each load. The analog data may include voltage, current, frequency, and phase angle, while the operating parameters may include active power, reactive power, and power consumption during different time periods.

[0156] Specifically, the load curve fitted based on the sampling points in this step can reflect the distribution of characteristic parameters of the load, such as load voltage, load current, load fundamental active power, and load fundamental reactive power.

[0157] Step S113: Use a non-intrusive load identification method to identify the load curves of each load, and obtain the load information of each load in the load side of the power consumption area and the load power consumption during the preset time period.

[0158] Specifically, in this step, a non-intrusive load identification method can be used to identify the load curve, obtaining the load information of each load in the power consumption area and the load consumption for a preset time period. The non-intrusive load identification method is a method of identifying electrical equipment and parameters through the characteristics (load imprint) of electrical loads. First, event detection is performed on the load curve. If a new event is detected (load start-up or state change, etc.), feature extraction is performed based on steady-state characteristics (such as active power, reactive power, voltage, current, etc.) and transient characteristics (such as active power transient waveform and reactive power transient waveform, etc.). Then, from the feature library of preset electrical equipment and the load characteristics extracted from the collected data, the components of the total load are identified, realizing the decomposition of load information, thereby obtaining the load information of each load in the power consumption area and the load consumption for a preset time period.

[0159] Specifically, the load information may include:

[0160] The load information parameters in the load side of the electricity consumption area, the correlation between the line loss rate of various power sources and the total electricity consumption within the preset time period, the correlation between the line loss rate of the load and the total electricity consumption within the preset time period, the operating status of various power sources and loads within the preset time period, and the adjustable value of various power sources and loads within the preset time period, etc.

[0161] The power consumption of the load may include:

[0162] The data includes the electricity consumption of various power sources and loads within the preset time period, and the active power of various power sources and loads within the preset time period.

[0163] In some embodiments of this application, the process of clustering each load according to the load power consumption and the load information to obtain clustering results characterizing the power demand of the power consumption area within a preset time period is described in detail. This process may include:

[0164] Step S121: Randomly generate multiple cluster centers, each cluster center corresponding to a first cluster center value.

[0165] Specifically, in some embodiments of this application, the K-means clustering algorithm can be used for clustering. K-means clustering is an unsupervised learning algorithm characterized by unlabeled variables in the training data, where the data is randomly divided into multiple classes. In the K-means algorithm, several cluster centers are randomly generated. Too many cluster centers can lead to overfitting, making it difficult to distinguish cluster features; too few cluster centers can lead to underfitting, making it impossible to accurately cluster based on features. In some embodiments of this application, the sum of squared errors is used to evaluate the model's prediction results.

[0166] Specifically, based on the actual situation of this application, there are 5 randomly generated cluster centers, namely cluster I, cluster II, cluster III, cluster VI, and cluster V, which respectively represent the region's high degree of power shortage, relatively high degree of power shortage, region's supply and demand balance, relatively high degree of power supply, and very high degree of power supply.

[0167] Step S122: For each cluster center: cluster the loads corresponding to the loads whose first cluster center values ​​are closest to the cluster center values ​​of that cluster center to obtain clustered load groups.

[0168] Specifically, in this step, considering the data with Euclidean distance, the sum of squared errors is used as the objective function for clustering. Each data point is assigned to its nearest cluster center based on the squared Euclidean distance to cluster the data.

[0169]

[0170] Among them, c i Let represent the value of the first cluster center for the i-th cluster center, x represent the load power consumption, dist represent the standard Euclidean distance, and k represent the total number of clusters. In this embodiment, k = 5. In the above formula, based on the standard Euclidean distance, the sum of squared errors between the load power consumption and the value of the first cluster center corresponding to each cluster center is calculated. If the sum of squared errors between the load power consumption and a certain value of the first cluster center is the smallest, it indicates that the distance between the load power consumption and the cluster center corresponding to this value of the first cluster center is the closest. The load cluster corresponding to this load power consumption and the cluster center corresponding to this value of the first cluster center are taken as the clustering result, and so on.

[0171] Step S123: Calculate the average value of the load power consumption in the clustered load group, and use the average value as the second cluster center value of the cluster center.

[0172] Specifically, the average power consumption of the loads in the clustered load groups is calculated using the following formula:

[0173]

[0174] Among them, S i Let |S| represent the clustering load group of the i-th cluster center. i | represents the number of cluster loads in the cluster load group of the i-th cluster center, x i This represents the load power consumption in the cluster load group of the i-th cluster center.

[0175] Step S124: Determine whether the value of the first cluster center of the cluster center is the same as the value of the second cluster center of the cluster center. If so, take the cluster load group of the cluster center as the cluster result that characterizes the power demand of the power consumption area within the preset time period.

[0176] If not, replace the first cluster center value of the cluster center with the second cluster center value of the cluster center, and return to the step of clustering the loads corresponding to the loads whose electricity consumption is closest to the first cluster center value of the cluster center, until the first cluster center value of the cluster center is the same as the second cluster center value of the cluster center.

[0177] Specifically, the K-means clustering algorithm used in this application embodiment calculates multiple times until the stopping condition is met, which can obtain relatively accurate clustering results.

[0178] The following describes a power distribution device based on supply and demand provided by an embodiment of this application. The power distribution device based on supply and demand described below can be referred to in correspondence with the power distribution method based on supply and demand described above.

[0179] See Figure 4 , Figure 4 This is a schematic diagram of a power distribution device structure based on supply and demand relationship disclosed in an embodiment of this application.

[0180] like Figure 4 As shown, the device may include:

[0181] The electricity data acquisition unit 11 is used to acquire the load information of each load in the load side of the electricity consumption area and the load power consumption during a preset period.

[0182] The data clustering unit 12 is used to cluster each load according to the load power consumption and the load information to obtain a clustering result that characterizes the power demand of the power consumption area within a preset time period.

[0183] The data prediction unit 13 is used to make a short-term prediction of the electricity demand of the electricity consumption area for the future cycle based on the clustering results, and obtain the prediction results.

[0184] The power generation data acquisition unit 14 is used to acquire the power generation data of different power generation units in the power generation side for each preset period within a preset cycle.

[0185] The preset period and the future period have the same period length.

[0186] The interval determination unit 15 is used to determine the power supply interval representing the power generation of the power generation side within the preset period based on the power generation data of each preset time period within the preset period.

[0187] The information generation unit 16 is used to generate an optimal energy efficiency report and optimal power transmission scheme information based on the prediction results and the power supply interval representing the power generation of the power generation side within the preset period.

[0188] The power distribution adjustment unit 17 is used to adjust the current power distribution status according to the optimal energy efficiency report and the optimal power transmission scheme information.

[0189] The power distribution device based on supply and demand provided in this application embodiment can be applied to a power distribution equipment based on supply and demand, such as a terminal: a computer, etc. Optionally, Figure 5 A hardware structure block diagram of a power distribution device based on supply and demand is shown, with reference to... Figure 5 A hardware structure for a power distribution device based on supply and demand may include: at least one processor 1, at least one communication interface 2, at least one memory 3, and at least one communication bus 4.

[0190] In this embodiment of the application, the number of processor 1, communication interface 2, memory 3, and communication bus 4 is at least one, and processor 1, communication interface 2, and memory 3 communicate with each other through communication bus 4;

[0191] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0192] Memory 3 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device;

[0193] The memory stores a program, which the processor can call. The program is used for:

[0194] Obtain load information for each load in the power consumption area and the power consumption of the load during a preset time period;

[0195] Based on the load power consumption and the load information, each load is clustered to obtain a clustering result that characterizes the power demand of the power consumption area within a preset time period;

[0196] Based on the clustering results, a short-term forecast of the electricity demand in the electricity consumption area is made for the future cycle, and the forecast results are obtained.

[0197] The power generation data of different power generation units in the power generation side are obtained for each preset time period within a preset period, wherein the preset period has the same period length as the future period.

[0198] Based on the power generation data for each preset time period within the preset period, a power supply interval representing the power generation on the power generation side within the preset period is determined.

[0199] Based on the prediction results and the power supply range representing the power generation on the power generation side within the preset period, an optimal energy efficiency report and optimal power transmission scheme information are generated.

[0200] Adjust the current power distribution situation based on the optimal energy efficiency report and the optimal power transmission scheme information.

[0201] Optionally, the refined and extended functions of the program can be found in the description above.

[0202] This application embodiment also provides a storage medium that can store a program suitable for execution by a processor, the program being used for:

[0203] Obtain load information for each load in the power consumption area and the power consumption of the load during a preset time period;

[0204] Based on the load power consumption and the load information, each load is clustered to obtain a clustering result that characterizes the power demand of the power consumption area within a preset time period;

[0205] Based on the clustering results, a short-term forecast of the electricity demand in the electricity consumption area is made for the future cycle, and the forecast results are obtained.

[0206] The power generation data of different power generation units in the power generation side are obtained for each preset time period within a preset period, wherein the preset period has the same period length as the future period.

[0207] Based on the power generation data for each preset time period within the preset period, a power supply interval representing the power generation on the power generation side within the preset period is determined.

[0208] Based on the prediction results and the power supply range representing the power generation on the power generation side within the preset period, an optimal energy efficiency report and optimal power transmission scheme information are generated.

[0209] Adjust the current power distribution situation based on the optimal energy efficiency report and the optimal power transmission scheme information.

[0210] Optionally, the refined and extended functions of the program can be found in the description above.

[0211] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0212] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0213] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A power distribution method based on supply and demand relationship, characterized by, The method comprises the following steps: obtaining load information of each load in a load side of a power consumption area and load power consumption in a preset period; clustering each load according to the load power consumption and the load information to obtain a clustering result representing a power demand degree of the power consumption area in the preset period; performing super-short-term prediction of power demand of the power consumption area in a future period according to the clustering result to obtain a prediction result; obtaining power generation data of different power generation units in each preset period in a preset period, wherein the preset period has the same length as the future period; determining a power supply interval representing power generation of the power generation side in the preset period according to the power generation data of each preset period in the preset period; generating an optimal energy efficiency report and optimal power transmission scheme information according to the prediction result and the power supply interval representing the power generation of the power generation side in the preset period; adjusting a current power distribution condition according to the optimal energy efficiency report and the optimal power transmission scheme information; clustering each load according to the load power consumption and the load information to obtain a clustering result representing a power demand degree of the power consumption area in the preset period, which comprises the following steps: randomly generating a plurality of clustering centers, each of which corresponds to a first clustering center value; for each clustering center: clustering the load corresponding to the load power consumption closest to the first clustering center value of the clustering center to obtain a clustered load group; calculating the average of the load power consumption in the clustered load group and taking the average as a second clustering center value of the clustering center; determining whether the first clustering center value of the clustering center is the same as the second clustering center value of the clustering center, if yes, taking the clustered load group of the clustering center as the clustering result representing the power demand degree of the power consumption area in the preset period; if no, replacing the first clustering center value of the clustering center with the second clustering center value of the clustering center, and returning to perform the step of clustering the load corresponding to the load power consumption closest to the first clustering center value of the clustering center until the first clustering center value of the clustering center is the same as the second clustering center value of the clustering center.

2. The method of claim 1, wherein, The step of determining a power supply interval representing power generation of the power generation side in the preset period according to the power generation data of each preset period in the preset period comprises the following steps: determining a power generation interval of each preset period in the preset period according to the power generation data of each preset period in the preset period; screening the end point value of the power generation interval of each preset period in the preset period according to a preset screening strategy to determine the power supply interval representing the power generation of the power generation side in the preset period.

3. The method of claim 2, wherein, The step of determining a power generation interval of each preset period in the preset period according to the power generation data of each preset period in the preset period comprises the following steps: reasonably screening the power generation data of each preset period in the preset period to determine the power generation data of each preset period in the preset period; determining the maximum value and the minimum value in the power generation data of each preset period in the preset period; The maximum value and the minimum value are respectively taken as right and left endpoints of a power generation interval of each preset time period in the preset period, to obtain a power generation interval corresponding to each preset time period in the preset period.

4. The method of claim 2, wherein, The endpoint values of the power generation interval of each preset time period in the preset period are screened according to a preset screening strategy, to determine a power supply interval representing power generation of the power generation side in the preset period, which comprises: abnormal values in the endpoint values of the power generation interval of each preset time period in the preset period are eliminated, to obtain the power generation interval of at least one preset time period in the preset period after elimination of abnormal values; if the power generation interval is one, the power generation interval is taken as the power supply interval representing power generation of the power generation side in the preset period; if the power generation interval is at least two, endpoint values exceeding a preset tolerance value among the endpoint values of the at least two power generation intervals are eliminated, to obtain the power generation interval of at least one preset time period in the preset period after elimination of endpoint values exceeding the preset tolerance value; if the power generation interval is one, the power generation interval is taken as the power supply interval representing power generation of the power generation side in the preset period; if the power generation interval is at least two, endpoint values not satisfying rationality among the endpoint values of the at least two power generation intervals are eliminated, to obtain the power generation interval of at least one preset time period in the preset period after elimination of endpoint values not satisfying rationality; the power generation interval of at least one preset time period in the preset period after elimination of endpoint values not satisfying rationality is taken as the power supply interval representing power generation of the power generation side in the preset period.

5. The method of claim 2, wherein, Before the endpoint values of the power generation interval of each preset time period in the preset period are screened according to a preset screening strategy, the method further comprises: a box-whisker plot about the endpoint values of the power generation interval of each preset time period in the preset period is constructed, the box-whisker plot is used to statistically and display dispersion of each endpoint value in the preset period in the process of screening the endpoint values of the power generation interval of each preset time period in the preset period.

6. The method of claim 1, wherein, The load information of each load in the power consumption area load side and the load power consumption of the preset time period are obtained, which comprises: obtaining power consumption information of each load in the power consumption area load side; determining load curves of each load in the power consumption area load side in the preset time period according to the power consumption information of each load in the power consumption area load side; using a non-intrusive load identification method to identify the load curves of each load, to obtain the load information of each load in the power consumption area load side and the load power consumption of the preset time period.

7. The method of claim 6, wherein, The load information comprises: load information parameters in the power consumption area load side, correlations of line loss rates of various power sources and total power consumption in the preset time period, correlations of line loss rates of loads and total power consumption in the preset time period, operating states of various power sources and loads in the preset time period, and adjustable values of various power sources and loads in the preset time period; the load power consumption comprises: The power consumption data of each type of power source and load in the preset period, and active power of each type of power source and load in the preset period.

8. A power distribution apparatus based on supply and demand relationship, characterized by, The method comprises the following steps: an electricity consumption data acquisition unit, configured to acquire load information of each load in a load side of an electricity consumption area and load electricity consumption in a preset period; a data clustering unit, configured to cluster each load according to the load electricity consumption and the load information, to obtain a clustering result representing an electricity demand degree of the electricity consumption area in the preset period; a data prediction unit, configured to perform super-short-term prediction of electricity demand of the electricity consumption area in a future period according to the clustering result, to obtain a prediction result; a power generation data acquisition unit, configured to acquire power generation data of different power generation units in the power generation side in each preset period in a preset period, wherein the preset period has the same length as the future period; an interval determination unit, configured to determine a power supply interval representing power generation of the power generation side in the preset period according to the power generation data of each preset period in the preset period; an information generation unit, configured to generate optimal energy efficiency report and optimal power transmission scheme information according to the prediction result and the power supply interval representing power generation of the power generation side in the preset period; a power distribution adjustment unit, configured to adjust current power distribution according to the optimal energy efficiency report and the optimal power transmission scheme information. The method comprises the following steps: randomly generating a plurality of clustering centers, each of which corresponds to a first clustering center value; for each clustering center: clustering the load corresponding to the load electricity consumption closest to the first clustering center value of the clustering center, to obtain a clustered load group; calculating the average of the load electricity consumption in the clustered load group, and taking the average as a second clustering center value of the clustering center; determining whether the first clustering center value of the clustering center is the same as the second clustering center value of the clustering center, if yes, taking the clustered load group of the clustering center as the clustering result representing the electricity demand degree of the electricity consumption area in the preset period; if not, replacing the first clustering center value of the clustering center with the second clustering center value of the clustering center, and returning to perform the step of clustering the load corresponding to the load electricity consumption closest to the first clustering center value of the clustering center, until the first clustering center value of the clustering center is the same as the second clustering center value of the clustering center.

9. A power distribution apparatus based on supply and demand relationship, characterized by, The method comprises the following steps: a memory and a processor; the memory is configured to store a program; the processor is configured to execute the program to implement each step of the power distribution method based on supply and demand relationship according to any one of claims 1-7.

Images