Transformer area load prediction method and system
By combining the current annual income list and natural load growth rate and other data, a multi-faceted calculation method is used to solve the problem of inaccurate load prediction in the station area, significantly improve the prediction accuracy, and realize accurate investment and power supply reliability. promote.
Patent Information
- Application Number
- CN202411241878.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-12-03
AI Technical Summary
The existing technology has inaccuracy in the load forecast of the station area, which has led to some station areas that cannot be overloaded being mistakenly included in the planning database and wasted resources. The station areas that are actually overloaded are not included in the planning, resulting in emergency measures and deviating from precise investment and The original intention of improving power supply reliability.
By using the current annual collection list as the data source, the current annual allocation maximum load P0 is determined, and based on the natural load growth rate α, the annual reporting capacity Si, the practical coefficient βi and the confidence coefficient δi, the formula is used to calculate the first The maximum annual distribution capacity P1 of each planned is combined with linear regression and data integration to improve the accuracy of load prediction.
It significantly improves the accuracy of load forecasting in the station area, achieves accurate investment, improves power supply reliability, and avoids resource waste and overload problems.
Smart Images

Figure CN119070296A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power load monitoring, and in particular to a method and system for predicting load in a distribution area. Background Art
[0002] At present, different methods are used to predict the load of substations. Some planners use the average growth rate method, but when determining the growth rate, the load of all substations in the town and street is calculated according to the values of each town and street calculated by the main network. This will cause problems, that is, the load forecast is not accurate enough, resulting in some substations that would not be overloaded being mistakenly included in the planning library and preliminary plans, wasting resources; while other substations that will actually be overloaded are not included in the planning library and preliminary plans. When peak loads occur, these substations will be seriously overloaded, and can only rely on emergency project establishment to solve the problem, deviating from the original intention of precise investment and improving power supply reliability.
[0003] Therefore, it is necessary to improve the existing technology. Summary of the invention
[0004] The present invention provides a method and system for predicting load in a substation area to solve the problems existing in the prior art.
[0005] To achieve the above object, the present invention provides the following technical solutions:
[0006] A method for predicting load in a substation area comprises the following steps:
[0007] Using the current annual revenue table as the data source, determine the current annual maximum load P0 of the distribution transformer;
[0008] Determine the natural growth rate of load α, and check and correct the natural growth rate of load α;
[0009] Determine the annual installed capacity Si planned by the user, and collect the low-voltage installed capacity based on the installed capacity Si;
[0010] Determine the utility coefficient βi of the user who applied for the installation; the user utility coefficient βi takes values according to different categories of the user who applied for the installation;
[0011] Determine the user confidence coefficient δi of the application; the user confidence coefficient δi takes values according to different application sources;
[0012] Based on the formula , calculate the maximum load P1 of the distribution transformer in the first planned year.
[0013] Optionally, the determining of the load natural growth rate α, and checking and correcting the load natural growth rate α, includes:
[0014] Determine the load natural growth rate α, and set the load natural growth rate α to be 1%-5%;
[0015] Verify based on district and county load forecast results;
[0016] Calculate the load of the first planned year through linear regression based on the load of the substation in the past five years;
[0017] Based on the first planned annual load, the natural load growth rate α is calculated.
[0018] Optionally, the determining of the planned annual installed capacity Si of the installed user, and collecting the low-voltage installed capacity based on the installed capacity Si, includes:
[0019] Through the pre-selected platform marketing management system business expansion, the installation work order is obtained by querying the conditions of low-voltage new installation and increase or decrease of capacity, and the work order information is limited.
[0020] Optionally, limiting the work order information includes:
[0021] The work order status is limited to archive and run; the time range of the work order is limited to the time period from the peak load in the current year to the peak load in the planned year; and the power supply unit of the work order is limited to the district bureau or town center.
[0022] Optionally, after limiting the work order information, the method further includes:
[0023] Integrate and match the various data already available at the town and street service center with the data in the specific survey form of the marketing department to filter out the potential user information that is not in the survey form;
[0024] Based on historical installation data and other relevant data, predict possible installation demand and obtain installation demand prediction results;
[0025] The application demand prediction result is used to provide clues for potential application users when collecting low-voltage application capacity based on the application capacity Si.
[0026] Optionally, the application user categories include residential, commercial, industrial, large industry and others, and the corresponding utility coefficient βi values are 0.35, 0.4, 0.7, 0.9 and 0.4 respectively.
[0027] Optionally, determining the confidence coefficient δi of the application user includes:
[0028] When the source of the application is an application work order, the confidence coefficient δi takes the value of 1;
[0029] When the application source is an application intention letter, the confidence coefficient δi is 0.7;
[0030] When the reporting source is potential electricity consumption capacity collected by other means, the confidence coefficient δi is 0.5.
[0031] Optionally, determining the load natural growth rate α includes:
[0032] Using the load of the substation in the past five years, linear regression is performed based on the forecast formula to calculate the load of the first planned year, and then the natural growth rate is calculated by predicting the load.
[0033] The present invention also provides a substation load prediction system, characterized in that it is used to implement the substation load prediction method as described in any one of the above items.
[0034] Compared with the prior art, the present invention has the following beneficial effects:
[0035] The invention provides a method and system for predicting load in a substation area, which significantly improves the accuracy of the prediction of load in the substation area through multi-faceted data collection and precise calculation.
[0036] The present invention has other features and advantages, which will be apparent from or will be described in detail in the accompanying drawings and the following detailed description incorporated herein, which together serve to explain the specific principles of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0038] Figure 1 This is a flow chart of a method for predicting load in a substation area provided in the first embodiment of the present invention;
[0039] Figure 2 It is a structural block diagram of a substation load prediction system provided in Embodiment 2 of the present invention.
[0040] Figure numerals: 10, data acquisition module; 20, data processing module; 30, calculation module; 40, result output module. DETAILED DESCRIPTION
[0041] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.
[0042] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.
[0043] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.
[0044] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.
[0045] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.
[0046] Without further limitations, in this application, the words "include", "comprises", "has" or other similar expressions used in the sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.
[0047] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.
[0048] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.
[0049] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms such as "install", "connect", "connect", "fix", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For technicians in the technical field to which the present application belongs, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.
[0050] Embodiment 1
[0051] Please refer to Figure 1 The embodiment of the present invention provides a method for predicting load in a substation, comprising the following steps:
[0052] S1. Using the current annual revenue table as the data source, determine the current annual maximum load P0 of the distribution transformer;
[0053] S2. Determine the natural growth rate of load α, and check and correct the natural growth rate of load α;
[0054] S3. Determine the capacity Si that the user plans to install in the year, and collect the low-voltage installation capacity based on the installed capacity Si;
[0055] S4, determining the utility coefficient βi of the user who applied for the installation; the user utility coefficient βi is determined according to different classifications of the user who applied for the installation;
[0056] S5, determining the user confidence coefficient δi of the application; the user confidence coefficient δi takes values according to different application sources;
[0057] S6, based on formula , calculate the maximum load P1 of the distribution transformer in the first planned year.
[0058] The parameters in the above formula are defined as follows:
[0059] P1: Maximum load of the distribution transformer in the first planned year under normal operation;
[0060] P0: Maximum load of the existing annual distribution transformer under normal operation;
[0061] α: natural growth rate of load, which is determined by the load base of the forecast area and the level of economic development, and is generally 1%-5%. The specific value can be verified based on the load forecast results of the district or county;
[0062] Si: the capacity reported by the i-th user in the planning year (i=1,2,…,N); the distribution transformer load forecast statistics the capacity reported by the low-voltage user (or potential power consumption capacity).
[0063] βi: Utility coefficient of the i-th registered user (i=1,2,…,N), classified into residential, commercial, industrial, large industry, and others, with values of 0.35, 0.4, 0.7, 0.9, and 0.4
[0064] δi: Confidence coefficient of the i-th user who applied for installation (i=1,2,…,N). According to the source of collection, it is divided into installation work order, installation intention letter, and potential power consumption capacity collected by other means, with values of 1, 0.7, and 0.5.
[0065] Each step is described in detail below.
[0066] In step S1, the current annual maximum load P0 of the distribution transformer is determined, including using the current annual collection table as a data source to obtain the current annual maximum load P0 of the distribution transformer, providing basic data for subsequent load forecasting. The current annual collection table is data obtained through actual measurement and statistics, has high reliability, and can be used as a starting point to estimate future load conditions.
[0067] In step S2, the natural load growth rate α is determined and checked and corrected, including:
[0068] Determine the natural growth rate of load α, and set it to 1%-5%. This value range is determined based on the general forecast area load base and economic development level. The natural growth rate of load reflects the natural growth trend of the load in the substation over time, and its value is affected by many factors, such as economic development, population growth, and increase in power equipment.
[0069] Verify the value of α according to the results of district and county load forecasts to ensure that it more accurately reflects the actual local situation. District and county load forecasts usually take into account a wider range of economic, social and electricity demand factors. By verifying the results of district and county load forecasts, the value of the natural growth rate of the load in the substation area can be made more reasonable.
[0070] Using the load of the substation in the past five years, linear regression is performed based on the forecast formula to calculate the load of the first planned year; the forecast formula is a mathematical formula for predicting future values, which can be used in various situations, including economic, stock, weather and other aspects. Linear regression is a regression analysis method in mathematical statistics to determine the quantitative relationship between variables. By performing linear regression on the load data of the substation in the past five years, the load of the first planned year can be predicted based on historical trends, providing a basis for calculating the natural growth rate of load.
[0071] Among them, linear regression is a statistical analysis method that uses regression analysis in mathematical statistics to determine the quantitative relationship between two or more variables that are interdependent. It is widely used. Its expression is: y=w′x+e, where e is the error that follows a normal distribution with a mean of 0.
[0072] Furthermore, based on the load of the first planned year, the natural growth rate of the load α is calculated, and α is corrected to make it more in line with the actual situation, so that the natural growth rate of the load can be continuously adjusted and optimized to improve the accuracy of load forecasting.
[0073] In step S3, the planned annual installed capacity Si of the registered user is determined, and the low-voltage installed capacity is collected based on the installed capacity Si, including: obtaining the installed work order by querying the conditions of low-voltage new installation and capacity increase and decrease through the pre-selected platform marketing management system business expansion, and limiting the work order information. Among them, the platform is used to provide detailed installation information, including user type, installed capacity, power supply area, etc., providing an important data source for load forecasting.
[0074] Furthermore, the work order information is limited, including: limiting the work order status to archive and run; limiting the time range of the work order to the time period from the peak load point in the current year to the peak load point in the planned year; and limiting the power supply unit of the work order to the district bureau or town center.
[0075] It is understandable that limiting the work order status to archived and running ensures that the obtained reported work orders have been actually executed or are being executed, thereby improving the reliability of the data. Only the actual or ongoing reports will have an impact on the load of the substation, so limiting the work order status can eliminate some uncertain factors.
[0076] Limiting the time range of the work order to the time period from the peak load in the current year to the peak load in the planned year makes the collected data more targeted and matches the time range of the load forecast. This ensures that the collected data is relevant to the forecasted time period and improves the accuracy of the load forecast.
[0077] Limit the power supply unit of the work order to the district bureau or town center to clarify the source range of the data. Limiting the power supply unit can make the data more centralized and clear, and facilitate analysis and processing.
[0078] Integrate and match the various data already available at the town and street service center with the data in the specific survey form of the marketing department to filter out the information of potential users who have registered but are not in the survey form. Through data integration and matching, data from different channels can be fully utilized to avoid missing potential load growth points. There may be differences between the data of the town and street service center and the data in the survey form of the marketing department. Through integration and matching, a more comprehensive understanding of the registration situation can be obtained.
[0079] It is understandable that based on historical application data and other relevant data, possible application demand is predicted to obtain application demand prediction results. This result can provide clues for potential application users when collecting low-voltage application capacity and improve the accuracy of load forecasting. Using historical application data and other relevant data for prediction, some potential application demand trends can be discovered, providing more comprehensive information for load forecasting.
[0080] In step S5, the classification of registered users includes residential, commercial, industrial, large industry and others. According to different user types, the practical coefficient βi takes values of 0.35, 0.4, 0.7, 0.9 and 0.4 respectively. Different types of users have different electricity consumption characteristics, and the practical coefficient reflects the proportional relationship between the actual electricity consumption of users and the registered capacity. For example, the electricity consumption of residential users is relatively stable, and the practical coefficient is low; while the electricity demand of industrial users may vary greatly with production conditions, and the practical coefficient is relatively high. By setting different practical coefficients for different types of users, the actual load situation can be reflected more accurately.
[0081] Furthermore, when determining the confidence coefficient δi of the application user:
[0082] When the source of the application is an application work order, the confidence coefficient δi takes the value of 1, because the application work order indicates that the application has been confirmed to be implemented and has a higher reliability. The application work order is applied for and approved by the user and has a clear implementation plan, so the confidence coefficient is higher.
[0083] When the source of the application is the application intention letter, the confidence coefficient δi is 0.7. The application intention letter has a certain degree of uncertainty compared to the application work order, so the value is slightly lower. The application intention letter is only the user's expression of intention and may not be implemented in the end, so the confidence coefficient is relatively low.
[0084] When the reported source is the potential power consumption capacity collected by other means, the confidence coefficient δi is 0.5. The potential power consumption capacity collected by other means has a large uncertainty, so the value is the lowest. The potential power consumption capacity collected by other means may be obtained through visits, surveys, etc., and its reliability is relatively low, so the confidence coefficient is also low.
[0085] When calculating the maximum load P1 of the distribution transformer in the first planned year based on the formula, the maximum load P1 of the distribution transformer in the first planned year is calculated under the normal operating mode. The above formula comprehensively considers multiple factors such as the current annual load, the natural growth rate of load, the reported capacity, the practical coefficient and the confidence coefficient, and can more accurately predict the maximum load of the substation in the first planned year. Among them, P0 is the current annual load, (1+α) represents the natural growth part of the load, and Σ(Si×βi×δi) represents the load contribution part of the reported users. By comprehensively considering these factors, the load of the substation can be predicted more comprehensively and the accuracy of the prediction can be improved.
[0086] Embodiment 2
[0087] Based on the above embodiments, the present invention further provides a load prediction system for a substation, which is used to implement the above load prediction method for a substation. The system includes a data acquisition module 10 , a data processing module 20 , a calculation module 30 and a result output module 40 .
[0088] The data collection module 10 is used to collect the required data from the current annual revenue table, platform marketing management system, marketing department survey form and other channels, including the current annual maximum load P0 of the distribution transformer, installation work order information, installation intention letter information, etc. The data collection module 10 needs to ensure the accuracy and completeness of the data to provide a reliable basis for subsequent analysis and processing.
[0089] The data processing module 20 is used to organize, filter and integrate the collected data, such as limiting the information of the work order, matching the data of the town service center with the data of the market department survey form, etc. The data processing module 20 needs to clean and process the data, remove noise and erroneous data, and improve the quality of the data. At the same time, it is also necessary to integrate and match data from different sources to make the data more unified and standardized.
[0090] The calculation module 30 is used to calculate the natural growth rate α of the load, determine the reported capacity Si, determine the values of the practical coefficient βi and the confidence coefficient δi, and calculate the maximum load P1 of the distribution transformer in the first planned year according to the formulas and steps in the above-mentioned load forecasting method of the substation. The calculation module 30 needs to accurately perform various calculation steps to ensure the accuracy and reliability of the calculation results. At the same time, the calculation efficiency and performance also need to be considered to meet the needs of practical applications.
[0091] The result output module 40 is used to output the calculated maximum load P1 of the first planned year distribution transformer and other related results to the power department for substation planning and investment decision-making. The result output module 40 needs to present the calculation results to the user in a clear and intuitive manner to facilitate the user's understanding and use. At the same time, it is also necessary to provide some analysis and suggestions to help users make more scientific and reasonable decisions.
[0092] The method and system for predicting load in an electric power substation of the present invention can improve the accuracy of load prediction in an electric power substation, achieve precise investment, enhance power supply reliability, and provide strong support for the stable operation and sustainable development of the electric power system.
[0093] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.
Claims
1. A method for predicting load in a substation, characterized in that: The following steps are involved: Using the current annual revenue table as the data source, determine the current annual maximum load P0 of the distribution transformer; Determine the natural growth rate of load α, and check and correct the natural growth rate of load α; Determine the annual installed capacity Si planned by the user, and collect the low-voltage installed capacity based on the installed capacity Si; Determine the utility coefficient βi of the registered user; The user utility coefficient βi takes values according to different classifications of registered users; Determine the confidence coefficient δi of the user who applied for the installation; The user confidence coefficient δi is taken according to different application sources; Based on the formula , calculate the maximum load P1 of the distribution transformer in the first planned year.
2. The method for predicting load in a substation according to claim 1, characterized in that: The determining of the load natural growth rate α, and checking and correcting the load natural growth rate α, includes: Determine the load natural growth rate α, and set the load natural growth rate α to be 1%-5%; Verify based on district and county load forecast results; Calculate the load of the first planned year through linear regression based on the load of the substation in the past five years; Based on the first planned annual load, the natural load growth rate α is calculated.
3. The method for predicting load in a substation according to claim 1, characterized in that: The determination of the annual planned installed capacity Si of the user who applied for installation, and the collection of the low-voltage installed capacity based on the installed capacity Si, include: Through the pre-selected platform marketing management system business expansion, the installation work order is obtained by querying the conditions of low-voltage new installation and increase or decrease of capacity, and the work order information is limited.
4. The method for predicting load in a substation according to claim 3, characterized in that: The limiting of the work order information includes: The work order status is limited to archive and run; the time range of the work order is limited to the time period from the peak load in the current year to the peak load in the planned year; and the power supply unit of the work order is limited to the district bureau or town center.
5. The method for predicting load in a substation according to claim 4, characterized in that: After limiting the work order information, the following steps are also included: Integrate and match the various data already available at the town and street service center with the data in the specific survey form of the marketing department to filter out the potential user information that is not in the survey form; Based on historical installation data and other relevant data, predict possible installation demand and obtain installation demand prediction results; The application demand prediction result is used to provide clues for potential application users when collecting low-voltage application capacity based on the application capacity Si.
6. The method for predicting load in a substation according to claim 1, characterized in that: The application user categories include residential, commercial, industrial, large industry and others, and the corresponding utility coefficient βi values are 0.35, 0.4, 0.7, 0.9 and 0.4 respectively.
7. The method for predicting load in a substation according to claim 1, characterized in that: The step of determining the confidence coefficient δi of the application user includes: When the source of the application is an application work order, the confidence coefficient δi takes the value of 1; When the application source is an application intention letter, the confidence coefficient δi is 0.7; When the reporting source is potential electricity consumption capacity collected by other means, the confidence coefficient δi is 0.
5.
8. The method for predicting load in a substation according to claim 1, characterized in that: The determining of the natural load growth rate α comprises: Using the load of the substation in the past five years, linear regression is performed based on the forecast formula to calculate the load of the first planned year, and then the natural growth rate is calculated by predicting the load.
9. A load forecasting system for a substation, characterized in that: Used to implement the substation load forecasting method as described in any one of claims 1 to 9.
