Classification method, device and storage medium based on customer load characteristics on the electricity consumption side

Abstract

The present invention relates to a classification method, device and storage medium based on the load characteristics of electricity-consuming customers, and is applied to the field of electricity market transaction technology. The method comprises: judging which analysis method is suitable for electricity customers based on the actual electricity consumption data of customers on the electricity sales side of the electricity market, using different analysis methods to finely classify electricity customers for customers with different electricity load characteristics, analyzing and classifying customers at the electricity load level, and helping electricity sales companies to better classify and manage users and conduct electricity transactions.

Description

Technical Field

[0001] The present invention relates to the technical field of power market transactions, and in particular to a classification method, device and storage medium based on load characteristics of electricity-consuming customers. Background Art

[0002] Due to the current classification management of electricity-using customers in the power industry, power sales companies can only classify and manage different customers based on industry and electricity customer contract type. They are unable to analyze the customer's load characteristics from a more microscopic perspective of customer load electricity. The lack of effective analysis and classification management leads to chaotic user management, unclear user types, and transaction decisions that are not tailored to individual users in actual transactions. It is impossible to make transaction judgments based on the user's electricity consumption characteristics and make scientific and efficient transaction decisions.

[0003] Simply put, existing technologies mainly rely on manual classification of customer types based on the type of contract signed by the customer, the industry to which the customer belongs, etc. The customer classification management method is relatively simple and cannot be more finely divided according to the customer's electricity usage characteristics. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a classification method, device and storage medium based on the load characteristics of customers on the electricity consumption side, so as to solve the problem in the existing technology that customer types are manually divided according to the type of contract signed by the customer, the industry to which the customer belongs, etc., the customer classification management method is relatively simple, and it is impossible to make more detailed divisions according to the customer's electricity consumption characteristics.

[0005] According to a first aspect of an embodiment of the present invention, a classification method based on load characteristics of electricity-consuming customers is provided, the method comprising:

[0006] Obtain the daily time-of-use electricity consumption of electricity users published by the trading center; obtain the daily peak, flat, and valley time periods published by the trading center; obtain the time-of-use average curve and typical decomposition curve published by the trading center; obtain the meteorological temperature curve of each city; obtain the T time periods published by the trading center and the electricity consumption of electricity users in each T time period;

[0007] According to the daily time-of-use electricity consumption of the electricity user and the four daily peak, peak, flat and valley periods, the electricity consumption of the electricity user during the four peak, peak, flat and valley periods within the target period is obtained. If the difference between the peak period electricity consumption and the valley period electricity consumption is greater than or equal to a preset peak-valley difference threshold, the peak-flat-valley classification method is used to classify the electricity user;

[0008] If the difference between peak-period electricity consumption and valley-period electricity consumption is less than a preset peak-valley difference threshold, the total time-of-use electricity consumption of the electricity user within the target period is obtained based on the daily time-of-use electricity consumption of the electricity user. A time-of-use electricity consumption curve is obtained based on the total time-of-use electricity consumption. The correlation between the time-of-use electricity consumption curve and the meteorological temperature curve of each city, or the time-period average curve and the typical decomposition curve is obtained. If any correlation exists that is greater than the preset correlation threshold, the electricity user is classified using the correlation analysis method;

[0009] If there is no correlation greater than the preset correlation threshold, it is determined whether the electricity consumption of the electricity user in each T time period includes the electricity consumption in the specified time period. If so, the electricity user is classified using the T-based electricity consumption characteristic analysis method;

[0010] If there is no electricity consumption in the specified time period, the cluster analysis method is used to classify electricity users.

[0011] Preferably,

[0012] The obtaining of the correlation between the time-of-use electricity consumption curve and the meteorological temperature curve of each city, or the time-period average curve and the typical decomposition curve, and if any correlation is greater than a preset correlation threshold, classifying the electricity users by using the correlation analysis method includes:

[0013] Obtaining the correlation between the time-of-use electricity consumption curve and the time-period average curve and the typical decomposition curve published by the trading center respectively; if any correlation is greater than a preset correlation threshold, classifying the electricity users by using the decomposition curve correlation analysis method;

[0014] If there is no correlation greater than the preset correlation threshold, the meteorological temperature curve of each city within the target period is obtained based on the meteorological temperature curve of each city, and the correlation between the time-sharing electricity consumption curve and the meteorological temperature curve of each city within the target period is obtained respectively. If there is any correlation greater than the preset correlation threshold, the temperature correlation analysis method is used to classify the electricity users.

[0015] Preferably,

[0016] The method of classifying electricity users by using the peak-flat-valley analysis method includes:

[0017] According to the daily time-of-use electricity consumption of the electricity user and the four time periods of daily peak, peak, flat and off-peak, the daily electricity consumption of the electricity user during the four time periods of daily peak, peak, flat and off-peak is obtained; the daily electricity consumption of the four time periods of daily peak, peak, flat and off-peak within the target period is added according to the same time period type to obtain the electricity consumption of the electricity user during the four time periods of daily peak, peak, flat and off-peak within the target period;

[0018] According to the electricity consumption of the electricity users in the four periods of peak, on-peak, flat and off-peak within the target period, the electricity users are divided into peak users, peak users, flat users or off-peak users according to the period with the largest proportion of electricity consumption.

[0019] Preferably,

[0020] The classification of electricity customers by using the decomposition curve correlation analysis method includes:

[0021] The Pearson correlation analysis method is adopted, with the electricity customer's time-of-use electricity consumption curve as the vertical coordinate and the time-period average curve or typical decomposition curve released by the trading center as the horizontal coordinate, to obtain the linear correlation value between the electricity customer and each curve, and the time-period average curve or typical decomposition curve corresponding to the maximum correlation value is used as the curve type of the electricity customer.

[0022] Preferably,

[0023] The method of classifying electricity users by using the temperature correlation analysis method includes:

[0024] The Pearson correlation analysis method is used, with the time-of-use electricity consumption curve of electricity users as the vertical axis and the meteorological temperature curve of each city within the target period as the horizontal axis. The linear correlation value between electricity users and each meteorological temperature curve is obtained, and electricity users are classified into the city with the greatest correlation.

[0025] Preferably,

[0026] The classification of electricity users by using the T-based electricity consumption characteristics analysis method includes:

[0027] Obtain the classification results of the peak, flat and valley analysis method for electricity users;

[0028] For all peak users, determine whether the designated time period type is included according to the daily time-of-use electricity consumption of each peak user. If not, they are peak regular users; if included, they are peak designated users;

[0029] For all peak users, determine whether the designated time period type is included according to the daily time-of-use electricity consumption of each peak user. If not, they are peak regular users; if included, they are peak designated users;

[0030] For all flat-segment users, determine whether the designated time period type is included based on the daily time-of-use electricity consumption of each flat-segment user. If not, they are flat-segment regular users; if included, they are flat-segment designated users.

[0031] For all off-peak users, determine whether the specified time period type is included based on the daily time-of-use electricity consumption of each off-peak user. If not, they are off-peak regular users; if included, they are off-peak designated users.

[0032] Preferably,

[0033] The cluster analysis method is used to classify electricity customers, including:

[0034] Obtain the total time-of-use electricity consumption of electricity users within the target period; and use the total time-of-use electricity consumption as a data set;

[0035] Determine the cluster K value and randomly select the initial centroid for each cluster in the data set;

[0036] Cluster the data set according to the minimum distance principle;

[0037] Use the updated sample mean of each cluster as the new centroid of each cluster;

[0038] The clustering process is repeated until the difference between the new centroid of each cluster and the previous centroid is less than the preset threshold or the preset number of iterations is reached, and the final centroid and K cluster divisions are obtained to divide electricity customers into different clusters.

[0039] According to a second aspect of an embodiment of the present invention, a classification device based on load characteristics of a power-consuming customer is provided, the device comprising:

[0040] Data acquisition module: used to obtain the daily time-of-use electricity consumption of electricity users published by the trading center, obtain the daily peak, flat and valley time periods published by the trading center, obtain the time-of-use average curve and typical decomposition curve published by the trading center, obtain the meteorological temperature curve of each city, obtain the T time periods published by the trading center and the electricity consumption of electricity users in each T time period;

[0041] Peak assessment and classification module: used to obtain the peak, peak, flat and valley power consumption of the electricity user within the target period according to the daily time-of-use power consumption of the electricity user and the four time periods of peak, peak, flat and valley. If the difference between the peak power consumption and the valley power consumption is greater than or equal to the preset peak-valley difference threshold, the peak-flat-valley analysis method is used to classify the electricity user;

[0042] Correlation classification module: used to obtain the total time-of-use electricity consumption of the electricity user within the target period based on the daily time-of-use electricity consumption of the electricity user, if the difference between the peak period electricity consumption and the valley period electricity consumption is less than a preset peak-valley difference threshold, obtain the time-of-use electricity consumption curve based on the total time-of-use electricity consumption, obtain the correlation between the time-of-use electricity consumption curve and the meteorological temperature curve of each city, or the time-of-use average curve and the typical decomposition curve, and if any correlation exists that is greater than the preset correlation threshold, classify the electricity user using the correlation analysis method;

[0043] T-based classification module: if there is no correlation greater than the preset correlation threshold, it is used to determine whether the electricity consumption of the electricity user in each T-based time period includes the electricity consumption in the specified time period. If so, the electricity user is classified using the T-based electricity consumption characteristic analysis method;

[0044] Cluster classification module: used to classify electricity users using cluster analysis method if there is no electricity consumption in the specified time period.

[0045] According to a third aspect of an embodiment of the present invention, a storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a host controller, each step in the above method is implemented.

[0046] The technical solutions provided by the embodiments of the present invention may have the following beneficial effects:

[0047] This application is based on the actual electricity consumption data of customers on the electricity sales side of the power market to determine which analysis method is suitable for electricity customers. Different analysis methods are used to fine-tune the classification of electricity customers for customers with different electricity load characteristics. Customers are analyzed and classified and managed from the electricity load level, helping electricity sales companies to better classify and manage users and conduct electricity transactions.

[0048] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0050] Figure 1 is a flow chart illustrating a classification method based on load characteristics of electricity-consuming customers according to an exemplary embodiment;

[0051] Figure 2 is a system schematic diagram of a classification device based on load characteristics of electricity-consuming customers according to another exemplary embodiment;

[0052] In the accompanying figure: 1-data acquisition module, 2-peak evaluation classification module, 3-correlation classification module, 4-T classification module, 5-cluster classification module. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0054] Example 1

[0055] Figure 1 is a flow chart of a classification method based on the load characteristics of electricity-consuming customers according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0056] S1: Obtain the daily time-of-use electricity consumption of electricity users published by the trading center, obtain the daily peak, flat, and valley time periods published by the trading center, obtain the time-of-use average curve and typical decomposition curve published by the trading center, obtain the meteorological temperature curve of each city, obtain the T time periods published by the trading center, and the electricity consumption of electricity users in each T time period;

[0057] S2, based on the daily time-of-use electricity consumption of the electricity user and the four daily peak, peak, flat and valley periods, obtain the electricity consumption of the electricity user during the four peak, peak, flat and valley periods within the target period; if the difference between the peak period electricity consumption and the valley period electricity consumption is greater than or equal to a preset peak-valley difference threshold, classify the electricity user using the peak-flat-valley classification analysis method;

[0058] S3. If the difference between the peak electricity consumption and the valley electricity consumption is less than a preset peak-valley difference threshold, the total time-of-use electricity consumption of the electricity user within the target period is obtained based on the daily time-of-use electricity consumption of the electricity user. A time-of-use electricity consumption curve is obtained based on the total time-of-use electricity consumption. The correlation between the time-of-use electricity consumption curve and the meteorological temperature curve of each city, or the time-of-use average curve and the typical decomposition curve is obtained. If any correlation is greater than the preset correlation threshold, the electricity user is classified using a correlation analysis method.

[0059] S4, if no correlation is greater than a preset correlation threshold, determining whether the electricity consumption of the electricity user in each sub-time period includes the electricity consumption in the specified time period; if so, classifying the electricity user using the sub-time period electricity consumption characteristic analysis method;

[0060] S5, if there is no electricity consumption in the specified time period, the electricity users are classified using cluster analysis method;

[0061] It is understood that data collection includes:

[0062] Customer time-of-use electricity consumption: Daily time-of-use electricity consumption of electricity users, this data is published by the trading center;

[0063] Peak and Off-peak periods: The Power Trading Center divides daily electricity consumption into four periods: Peak, Off-peak, and Off-peak. The types of periods are announced monthly by the Trading Center.

[0064] Decomposition curve: The medium- and long-term transaction volume of electricity in the power market is decomposed into monthly, daily, and hourly decomposition curves on the load side based on the decomposition curve function provided by the trading center. The decomposition curves are formed in two ways: time-based average curves and typical decomposition curves. These two types of decomposition curves are published by the trading center.

[0065] Temperature: The temperature of the province where the electricity sales company trades. Weather temperature is a key factor influencing electricity market transactions. Analyzing the correlation between customer load and temperature can help understand customer electricity usage habits. This data is generated independently by each participating entity.

[0066] Customer electricity consumption by T: Obtain the user's monthly meter point electricity consumption, which is displayed in time period types of T1, T2, T3, T4, T5, and T6. This data is published by the trading center. It is worth emphasizing that generally speaking, the time period types of T1, T2, T3, and T4 are regular time periods, which means that the 24 time periods of a day are divided into four regular types. The number of time periods in each type is subject to the results published by the trading center. Regular time periods do not overlap with each other. The time period types of T5 and T6 are specified time periods. For example, T5 can be the first 12 hours of a day, while T6 is the last 12 hours of a day. Obviously, T5 or T6 may overlap with the time period types of T1, T2, T3, and T4.

[0067] After a simple collation and preliminary classification of the customer electricity consumption data obtained, different analysis methods can be used to perform more detailed classification based on the results, including:

[0068] If the time-of-use electricity consumption of customers within a province has obvious peak and valley characteristics (for example, more electricity is consumed during peak hours and less during valley hours, that is, the peak-valley difference is greater than the preset peak-valley difference threshold), the peak-valley analysis method is used:

[0069] Allocate the customer's 24 / 7 electricity consumption into peak, average, and valley periods according to the power trading center's rules, calculate the total electricity consumption for each period, and then divide the electricity users into peak users, peak users, average users, and valley users according to the power sales company's own classification rules;

[0070] The specific implementation steps of the above algorithm are:

[0071] Step 1: Obtain the time-of-use electricity consumption of electricity users and the time points included in the peak, flat, and valley time periods of the month;

[0072] Step 2: Obtain the target customer's time-of-use electricity consumption within the date range and calculate the total by time point;

[0073] Step 3: Set classification rules. Generally speaking, the period with the highest electricity consumption among the four periods of peak, flat and valley is used as the classification result of electricity users, namely peak users, peak users, flat users and valley users.

[0074] If the electricity customer's time-of-use electricity consumption does not have obvious peak-valley characteristics, then it is determined whether there is a certain degree of correlation between the customer's time-of-use electricity consumption and the various decomposition curves published by the trading center. That is, the customer's total time-of-use electricity consumption within the target period is obtained based on the customer's daily time-of-use electricity consumption, and the time-of-use electricity consumption curve is obtained based on the total time-of-use electricity consumption. Then, the correlation between the time-of-use electricity consumption curve and the time-of-use average curve and the typical decomposition curve is obtained respectively. If any correlation exists that is greater than the preset correlation threshold, the decomposition curve correlation analysis method is used to classify the electricity customer.

[0075] Decomposition curve correlation analysis: Select the decomposition curve and fit the time-of-use electricity consumption within the target customer's date range to the decomposition curve. Use the Pearson correlation coefficient analysis method to group customers with high fit between time-of-use electricity consumption and the decomposition curve into the same group, thereby classifying and managing customers through the decomposition curve;

[0076] The specific implementation steps of the above algorithm are:

[0077] Step 1: Obtain the target decomposition curve within the customer's target date range;

[0078] Step 2: Obtain the target customer's time-of-use electricity consumption within the date range and sum it up at each time point to obtain the customer's total time-of-use electricity consumption within the target period. This is the total electricity consumption for 24 hours in a day within the target period, corresponding to 24 electricity consumption data. Connect the 24 electricity consumption data in chronological order to obtain the time-of-use electricity consumption curve.

[0079] Step 3: Use the Pearson correlation analysis method, with the customer as the vertical axis and the decomposition curve as the horizontal axis, to measure the linear correlation between the customer and each curve data. The value range is -1 to 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no linear correlation. Calculate the correlation value between the customer and the decomposition curve, and use the curve with the largest correlation as the customer's curve type.

[0080] If the correlation values ​​of the decomposition curves are all less than the preset correlation threshold, the meteorological temperature curves of each city within the target period are obtained based on the meteorological temperature curves of each city, and the correlations between the time-of-use electricity consumption curves and the meteorological temperature curves of each city within the target period are obtained respectively. If any correlation is greater than the preset correlation threshold, the temperature correlation analysis method is used to classify the electricity users;

[0081] Temperature correlation analysis: Select the target customer's time-of-use electricity consumption on the target date, select the temperature of each city in the province as a reference, and conduct a Pearson correlation analysis between the temperature of the target city in the province and the time-of-use electricity consumption. Analyze the relationship between customer load electricity and the temperature of each city, and classify them;

[0082] The specific implementation steps of the above algorithm are:

[0083] Step 1: Obtain the target customer's time-of-use electricity consumption curve within the date range;

[0084] Step 2: Select cities for temperature correlation analysis;

[0085] Step 3: Use the Pearson correlation analysis method, with customers as the vertical axis and the temperature of each city as the horizontal axis, to measure the linear correlation between customers and the temperature data of each city. The value range is -1 to 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no linear correlation. Customers are classified into the city with the greatest correlation.

[0086] If no correlation is greater than the preset correlation threshold, it is determined whether the electricity consumption of the electricity user in each T period includes the electricity consumption of the specified period (that is, the T5 period type or the T6 period type). If so, the electricity user is classified using the T-based electricity consumption characteristic analysis method;

[0087] Analysis method of electrical characteristics of T:

[0088] Step 1: First, combine the analysis method 1 to perform preliminary classification;

[0089] Step 2: Determine whether each type of electricity user (peak user, peak user, flat user, off-peak user) only includes electricity consumption during regular time periods (i.e., the electricity consumption of the electricity user in a day is concentrated in T1, T2, T3 or T4, and does not include electricity consumption during designated time periods. For example, if the electricity consumption of an electricity user is 8-12 in a day, concentrated in the T2 type time period, while the designated time period T5 is 13-18, and the designated time period T6 is 19-24, then the electricity consumption type of the electricity user does not include electricity consumption during designated time periods). The electricity user is a regular customer. If the electricity user's electricity consumption data includes the T5 or T6 time period, the electricity user is a designated user. Of course, for designated users, further subdivision can be performed, i.e., single designated time period users or multi-designated time period users.

[0090] If there is no obvious pattern in the electricity demand of most customers in a province, and it is difficult to classify them simply, kmeans cluster analysis can be used to classify electricity customers.

[0091] Select the customer's time-of-use electricity usage within the target date range, choose the number of clusters to divide the data into, and iteratively divide the data set into clusters represented by the closest cluster center points. Then, recalculate the cluster center point based on all points in each cluster (taking the average value). Repeat this process until the change in the cluster center point is minimal or the specified number of iterations is reached, and finally divide the customers into different clusters.

[0092] The specific implementation steps of the above algorithm are:

[0093] Step 1: Obtain the customer's time-of-use electricity consumption within the target date range;

[0094] Step 2: Determine the cluster k value;

[0095] Step 3: Randomly select initial centroids for K clusters in the dataset;

[0096] Step 4: Cluster the data set according to the minimum distance principle;

[0097] Step 5: Iteratively update the centroid using the sample means of the K clusters;

[0098] Step 6: Repeat steps 3 and 4 until the center of mass stabilizes and no longer changes;

[0099] Step 7: Output the final centroid and K cluster divisions.

[0100] Example 2:

[0101] Figure 2 1 is a system diagram illustrating a classification device based on load characteristics of electricity-consuming customers according to another exemplary embodiment, the device comprising:

[0102] Data acquisition module 1: used to obtain the daily time-of-use electricity consumption of electricity users published by the trading center, obtain the daily peak, flat and valley time periods published by the trading center, obtain the time-of-use average curve and typical decomposition curve published by the trading center, obtain the meteorological temperature curve of each city, obtain the T time periods published by the trading center and the electricity consumption of electricity users in each T time period;

[0103] Peak assessment and classification module 2: used to obtain the peak, peak, flat and valley power consumption of the electricity user within the target period according to the daily time-of-use power consumption of the electricity user and the four time periods of peak, peak, flat and valley. If the difference between the peak power consumption and the valley power consumption is greater than or equal to the preset peak-valley difference threshold, the peak-flat-valley analysis method is used to classify the electricity user;

[0104] Correlation classification module 3: for obtaining the customer's total time-of-use electricity consumption within the target period based on the customer's daily time-of-use electricity consumption if the difference between the peak-period electricity consumption and the valley-period electricity consumption is less than a preset peak-valley difference threshold, obtaining a time-of-use electricity consumption curve based on the total time-of-use electricity consumption, obtaining the correlation between the time-of-use electricity consumption curve and the meteorological temperature curve of each city, or the time-period average curve and the typical decomposition curve, and classifying the customer using a correlation analysis method if any correlation is greater than a preset correlation threshold;

[0105] T-by-T classification module 4: for determining whether the electricity consumption of the electricity user in each T-by-T time period includes the electricity consumption in the specified time period if no correlation is greater than a preset correlation threshold. If so, the electricity user is classified using the T-by-T electricity consumption characteristic analysis method;

[0106] Cluster classification module 5: used to classify electricity users by using cluster analysis method if there is no electricity consumption in the specified time period.

[0107] Example 3:

[0108] This embodiment provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a host controller, each step in the above method is implemented;

[0109] It is understandable that the storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0110] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0111] It should be noted that, in the description of the present invention, the terms "first," "second," etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, "a small number of sparsely distributed" means at least two.

[0112] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or less sparsely distributed executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0113] It should be understood that various components of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiment, a small number of sparsely distributed steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0114] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0115] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0116] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0117] Throughout this specification, references to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or a small number of sparsely distributed embodiments or examples.

[0118] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A classification method based on the load characteristics of electricity-consuming customers, characterized by: The method comprises: Obtain the daily time-of-use electricity consumption of electricity users published by the trading center; obtain the daily peak, flat, and valley time periods published by the trading center; obtain the time-of-use average curve and typical decomposition curve published by the trading center; obtain the meteorological temperature curve of each city; obtain the T time periods published by the trading center and the electricity consumption of electricity users in each T time period; According to the daily time-of-use electricity consumption of the electricity user and the four daily peak, peak, flat and valley periods, the electricity consumption of the electricity user during the four peak, peak, flat and valley periods within the target period is obtained. If the difference between the peak period electricity consumption and the valley period electricity consumption is greater than or equal to a preset peak-valley difference threshold, the peak-flat-valley classification method is used to classify the electricity user; If the difference between peak-period electricity consumption and valley-period electricity consumption is less than a preset peak-valley difference threshold, the total time-of-use electricity consumption of the electricity user within the target period is obtained based on the daily time-of-use electricity consumption of the electricity user. A time-of-use electricity consumption curve is obtained based on the total time-of-use electricity consumption. The correlation between the time-of-use electricity consumption curve and the meteorological temperature curve of each city, or the time-period average curve and the typical decomposition curve is obtained. If any correlation exists that is greater than the preset correlation threshold, the electricity user is classified using the correlation analysis method; If there is no correlation greater than the preset correlation threshold, it is determined whether the electricity consumption of the electricity user in each T time period includes the electricity consumption in the specified time period. If so, the electricity user is classified using the T-based electricity consumption characteristic analysis method; If there is no electricity consumption in the specified time period, the cluster analysis method is used to classify electricity users.

2. The method according to claim 1, characterized in that The obtaining of the correlation between the time-of-use electricity consumption curve and the meteorological temperature curve of each city, or the time-period average curve and the typical decomposition curve, and if any correlation is greater than a preset correlation threshold, classifying the electricity users by using the correlation analysis method includes: Obtaining the correlation between the time-of-use electricity consumption curve and the time-period average curve and the typical decomposition curve published by the trading center respectively; if any correlation is greater than a preset correlation threshold, classifying the electricity users by using the decomposition curve correlation analysis method; If there is no correlation greater than the preset correlation threshold, the meteorological temperature curve of each city within the target period is obtained based on the meteorological temperature curve of each city, and the correlation between the time-sharing electricity consumption curve and the meteorological temperature curve of each city within the target period is obtained respectively. If there is any correlation greater than the preset correlation threshold, the temperature correlation analysis method is used to classify the electricity users.

3. The method according to claim 2, characterized in that The method of classifying electricity users by using the peak-flat-valley analysis method includes: According to the daily time-of-use electricity consumption of the electricity user and the four time periods of daily peak, peak, flat and off-peak, the daily electricity consumption of the electricity user during the four time periods of daily peak, peak, flat and off-peak is obtained; the daily electricity consumption of the four time periods of daily peak, peak, flat and off-peak within the target period is added according to the same time period type to obtain the electricity consumption of the electricity user during the four time periods of daily peak, peak, flat and off-peak within the target period; According to the electricity consumption of the electricity users in the four periods of peak, on-peak, flat and off-peak within the target period, the electricity users are divided into peak users, peak users, flat users or off-peak users according to the period with the largest proportion of electricity consumption.

4. The method according to claim 2, characterized in that The classification of electricity customers by using the decomposition curve correlation analysis method includes: The Pearson correlation analysis method is adopted, with the electricity customer's time-of-use electricity consumption curve as the vertical coordinate and the time-period average curve or typical decomposition curve released by the trading center as the horizontal coordinate, to obtain the linear correlation value between the electricity customer and each curve, and the time-period average curve or typical decomposition curve corresponding to the maximum correlation value is used as the curve type of the electricity customer.

5. The method according to claim 2, characterized in that The method of classifying electricity users by using the temperature correlation analysis method includes: The Pearson correlation analysis method is used, with the time-of-use electricity consumption curve of electricity users as the vertical axis and the meteorological temperature curve of each city within the target period as the horizontal axis. The linear correlation value between electricity users and each meteorological temperature curve is obtained, and electricity users are classified into the city with the greatest correlation.

6. The method according to claim 5, characterized in that The classification of electricity users by using the T-based electricity consumption characteristics analysis method includes: Obtain the classification results of the peak, flat and valley analysis method for electricity users; For all peak users, determine whether the designated time period type is included according to the daily time-of-use electricity consumption of each peak user. If not, they are peak regular users; if included, they are peak designated users; For all peak users, determine whether the designated time period type is included according to the daily time-of-use electricity consumption of each peak user. If not, they are peak regular users; if included, they are peak designated users; For all flat-segment users, determine whether the designated time period type is included based on the daily time-of-use electricity consumption of each flat-segment user. If not, they are flat-segment regular users; if included, they are flat-segment designated users. For all off-peak users, determine whether the specified time period type is included based on the daily time-of-use electricity consumption of each off-peak user. If not, they are off-peak regular users; if included, they are off-peak designated users.

7. The method according to claim 6, characterized in that The cluster analysis method is used to classify electricity customers, including: Obtain the total time-of-use electricity consumption of electricity users within the target period; and use the total time-of-use electricity consumption as a data set; Determine the cluster K value and randomly select the initial centroid for each cluster in the data set; Cluster the data set according to the minimum distance principle; Use the updated sample mean of each cluster as the new centroid of each cluster; The clustering process is repeated until the difference between the new centroid of each cluster and the previous centroid is less than the preset threshold or the preset number of iterations is reached, and the final centroid and K cluster divisions are obtained to divide electricity customers into different clusters.

8. A classification device based on the load characteristics of electricity-consuming customers, characterized in that: The device comprises: Data acquisition module: used to obtain the daily time-of-use electricity consumption of electricity users published by the trading center, obtain the daily peak, flat and valley time periods published by the trading center, obtain the time-of-use average curve and typical decomposition curve published by the trading center, obtain the meteorological temperature curve of each city, obtain the T time periods published by the trading center and the electricity consumption of electricity users in each T time period; Peak assessment and classification module: used to obtain the peak, peak, flat and valley power consumption of the electricity user within the target period according to the daily time-of-use power consumption of the electricity user and the four time periods of peak, peak, flat and valley. If the difference between the peak power consumption and the valley power consumption is greater than or equal to the preset peak-valley difference threshold, the peak-flat-valley analysis method is used to classify the electricity user; Correlation classification module: used to obtain the total time-of-use electricity consumption of the electricity user within the target period based on the daily time-of-use electricity consumption of the electricity user, if the difference between the peak period electricity consumption and the valley period electricity consumption is less than a preset peak-valley difference threshold, obtain the time-of-use electricity consumption curve based on the total time-of-use electricity consumption, obtain the correlation between the time-of-use electricity consumption curve and the meteorological temperature curve of each city, or the time-of-use average curve and the typical decomposition curve, and if any correlation exists that is greater than the preset correlation threshold, classify the electricity user using the correlation analysis method; T-based classification module: if there is no correlation greater than the preset correlation threshold, it is used to determine whether the electricity consumption of the electricity user in each T-based time period includes the electricity consumption in the specified time period. If so, the electricity user is classified using the T-based electricity consumption characteristic analysis method; Cluster classification module: used to classify electricity users using cluster analysis method if there is no electricity consumption in the specified time period.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the main controller, each step of the classification method based on the load characteristics of the electricity-side customer is implemented as described in any one of claims 1 to 7.

Images