A typical daily load curve generation method, system, equipment and medium

Abstract

The present invention discloses a typical daily load curve generation method, system, equipment and medium, and relates to the technical field of power system load analysis. The method comprises: obtaining and analyzing the annual historical load curve; based on the annual historical load curve, using the characteristic load neighborhood and Hermite interpolation method to calculate and generate the typical daily historical load curve of four seasons; based on the typical daily historical load curve of four seasons, generating the typical daily benchmark load curve of four seasons; based on the typical daily benchmark load curve of four seasons, using the characteristic load neighborhood and Hermite interpolation method to calculate and generate the typical daily forecast load curve of four seasons. The present invention generates a more realistic and complete typical daily benchmark load curve based on the historical load curve, and proposes a typical daily forecast load curve generation method, which can simultaneously present key indicators such as the maximum value of the midday peak, the maximum value of the evening peak, and the maximum peak-to-valley difference rate, while ensuring the rationality of the curve shape.

Description

Technical Field

[0001] The present invention relates to the technical field of power system load analysis, and in particular to a typical daily load curve generation method, system, equipment and medium. Background Art

[0002] In the field of power system load analysis, the typical daily load curve is an effective summary of the annual load curve. It can intuitively display the load characteristics and changing trends in the historical and forecast periods, and has been widely used in practice. In recent years, under the guidance of the new time-of-use electricity price, with demand-side response, virtual power plants, and user spontaneous response as the main influencing methods, key indicators such as the maximum and ratio of the midday and evening peaks of power load, and the maximum peak-to-valley difference rate are undergoing drastic changes, which puts higher requirements on the typical daily load curve.

[0003] At present, the generation methods of typical daily load curves are mainly based on clustering algorithms or normal distribution algorithms. These algorithms can effectively retain the overall characteristics of the samples, but they also lose some individual characteristics. There is a phenomenon that the load curve obtained is not completely consistent with the true value, especially the part of concern in practice, such as the actual occurrence value of the peak value in the afternoon and evening and its adjacent time periods; this greatly limits their application. Therefore, there is an urgent need for a typical daily load curve generation method that can simultaneously present key load characteristics such as the maximum value of the peak in the afternoon, the maximum value of the peak in the evening, and the maximum peak-to-valley difference rate, and try to match the actual data, while the curve shape is not distorted. Summary of the invention

[0004] The present invention provides a typical daily load curve generation method, system, equipment and medium, which are used to solve the defects of the existing typical daily load curve generation method based on clustering algorithm or normal distribution algorithm.

[0005] On the one hand, the present invention provides a method for generating a typical daily load curve, the method comprising the following steps: acquiring and analyzing an annual historical load curve; based on the annual historical load curve, using a characteristic load neighborhood and a Hermite interpolation method to calculate and generate a typical daily historical load curve for four seasons; based on the typical daily historical load curve for four seasons, generating a typical daily benchmark load curve for four seasons; based on the typical daily benchmark load curve for four seasons, using a characteristic load neighborhood and a Hermite interpolation method to calculate and generate a typical daily forecast load curve for four seasons.

[0006] In one implementation of the present invention, the annual historical load curve is expressed as follows:

[0007] ;

[0008] Where t represents the hour of the day, d represents the day of the year, and y represents the year to which the load data belongs.

[0009] In one implementation of the present invention, after obtaining and analyzing the annual historical load curve, the method further includes:

[0010] The maximum day of the daily midday peak in each season is determined based on the following formula:

[0011] ;

[0012] Among them, s is the season, It represents the maximum day of the midday peak in the season of year y. represents the set of days d in season s, depending on the definition of year and season; The maximum load at noon on day d in year y is expressed as:

[0013] ;

[0014] in, It represents the set of daily peak hours, which can be determined comprehensively according to the local load variation law;

[0015] Determine the day of the daily evening peak maximum for each season, expressed as:

[0016] ,

[0017] in, , It represents the set of peak hours in the evening, which can be determined based on factors such as the local sunset time;

[0018] Based on the following formula, the maximum peak-to-valley difference rate day of each season is determined, expressed as:

[0019] ;

[0020] in, ;

[0021] ;

[0022] .

[0023] In one implementation of the present invention, the obtaining and analyzing of the annual historical load curve specifically includes:

[0024] Determine the maximum value of the noon peak and its neighborhood of the historical load curve of a typical day in any season, as shown in the following formula:

[0025] ;

[0026] in, represents the load at time t of the typical daily load curve in season s of year y, The time set representing the neighborhood of the maximum value of the midday peak is determined by expert experience based on load characteristics;

[0027] Determine the maximum value of the evening peak of the typical daily historical load curve of the season and its neighborhood, as shown in the following formula: ;

[0028] in, The time set representing the neighborhood of the late peak maximum value is determined by expert experience based on load characteristics;

[0029] The daily minimum load and its neighborhood of the typical daily historical load curve of the season are determined based on the following formula:

[0030] ;

[0031] in, is the correction coefficient, which is used to correct the minimum load and its neighboring load on the day with the maximum peak-to-valley difference rate of the seasonal day, so as to ensure that the maximum peak-to-valley difference rate of the generated seasonal typical daily load curve is consistent with the actual data. Given by: ,in, Indicates the time when the minimum load occurs on the day with the maximum peak-to-valley difference rate in season s The load, i.e. the minimum load, It represents the daily maximum peak-to-valley difference rate in season s of year y, and is given by the following formula:

[0032]

[0033] The time set representing the neighborhood of the daily minimum is determined by expert experience based on load characteristics.

[0034] In an implementation of the present invention, generating a typical daily historical load curve for four seasons specifically includes:

[0035] Based on the Hermite interpolation function, the load value between the minimum load neighborhood and the midday peak neighborhood is determined;

[0036] Based on the Hermite interpolation function, the load value between the midday peak neighborhood and the evening peak neighborhood is determined;

[0037] Generate typical daily historical load curves for four seasons.

[0038] In an implementation of the present invention, determining the load value between the minimum load neighborhood and the midday peak neighborhood specifically includes:

[0039] The slope of the typical daily load curve at the end of the minimum load neighborhood is determined based on the following formula: ,

[0040]

[0041] in, express s The load value corresponding to the end time of the minimum load neighborhood of the typical daily load curve of the season, Indicates the load value corresponding to the previous moment;

[0042] use , , They represent the starting time, corresponding load value and slope of the midday peak load neighborhood of the typical daily load curve in season s. The slope is expressed by The difference between the load value at the next moment and the load value at the next moment is determined as follows:

[0043] ;

[0044] Determine the Hermite interpolation function between the minimum load neighborhood and the midday peak neighborhood, as follows:

[0045]

[0046] in,

[0047]

[0048]

[0049]

[0050]

[0051]

[0052] For a certain time t between the minimum load neighborhood and the noon peak neighborhood, substitute t into the formula to obtain the load value at time t.

[0053] In one implementation of the present invention, the generation of the typical daily load forecast curve for four seasons is specifically as follows:

[0054] Determine the midday peak maximum value and its neighborhood, evening peak maximum value and its neighborhood, and minimum value and its neighborhood of the typical daily forecast load curve of any season;

[0055] Determine the load value between the minimum load area and the noon peak neighborhood, and the load value between the noon peak neighborhood and the evening peak neighborhood of the typical daily forecast load curve of any season;

[0056] Generate a typical daily forecast load curve for the season.

[0057] The present invention also provides a typical daily load curve generation system, the system comprising: an annual historical load curve analysis module, used to obtain and analyze the annual historical load curve; a four-season typical daily historical load curve generation module, used to calculate and generate the four-season typical daily historical load curve based on the annual historical load curve using the characteristic load neighborhood and Hermite interpolation method; a four-season typical daily benchmark load curve generation module, used to generate the four-season typical daily benchmark load curve based on the four-season typical daily historical load curve; a four-season typical daily predicted load curve generation module, used to calculate and generate the four-season typical daily predicted load curve based on the four-season typical daily benchmark load curve using the characteristic load neighborhood and Hermite interpolation method.

[0058] The present invention also provides a typical daily load curve generating device, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can complete the aforementioned typical daily load curve generating method.

[0059] The present invention also provides a non-volatile computer storage medium for generating a typical daily load curve, which stores computer executable instructions. The computer executable instructions are executed by a processor to implement the aforementioned method for generating a typical daily load curve.

[0060] The present invention provides a typical daily load curve generation method, system, device and medium, which have the following beneficial effects:

[0061] (1) A method for generating a typical daily historical load curve based on characteristic load neighborhood and Hermite interpolation is proposed. The generated historical typical daily load curve effectively retains the authenticity of the load data at key moments such as the maximum value of the midday peak, the maximum value of the evening peak, and the maximum peak-to-valley difference rate, as well as the load data at adjacent moments, while ensuring the rationality of the curve shape;

[0062] (2) Based on the historical typical daily load curve, a more realistic and complete typical daily benchmark load curve is generated, and a typical daily forecast load curve generation method based on characteristic load neighborhood and Hermite interpolation is proposed, which can simultaneously present key indicators such as the maximum value of the midday peak, the maximum value of the evening peak, and the maximum peak-to-valley difference rate, while ensuring the rationality of the curve shape. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0064] Figure 1 A flow chart of a typical daily load curve generation method provided by an embodiment of the present invention;

[0065] Figure 2 A composition diagram of a typical daily load curve generation system provided by an embodiment of the present invention;

[0066] Figure 3 A schematic diagram of a typical daily load curve generating device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0068] The embodiment of the present invention provides a typical daily load curve generation method, system, device and medium. The technical solution proposed in the embodiment of the present invention is described in detail below with reference to the accompanying drawings.

[0069] Figure 1 A flow chart of a typical daily load curve generation method provided by an embodiment of the present invention. Figure 1 As shown, the method mainly includes the following steps:

[0070] Step 101: Obtain and analyze annual historical load curves.

[0071] Step 102: Based on the annual historical load curve, the characteristic load neighborhood and Hermite interpolation method are used to calculate and generate the typical daily historical load curves of four seasons.

[0072] Step 103: Generate a typical day benchmark load curve for four seasons based on the typical day historical load curve for four seasons.

[0073] Step 104: Based on the four-season typical day benchmark load curve, a characteristic load neighborhood and Hermite interpolation method are used to calculate and generate a four-season typical day forecast load curve.

[0074] In the embodiment of the present invention, first, an annual load history curve is obtained, which is expressed as:

[0075]

[0076] Where t represents the hour of the day, d represents the day of the year, and y represents the year to which the load data belongs, for example, 2023. If year y is a leap year, then .

[0077] Then, determine the maximum day of the daily midday peak in each season, expressed as:

[0078]

[0079] in, , It represents the maximum day of the midday peak in the season of year y. The set of days d in season s depends on the definition of year and season. For example, for 2023, if spring is defined as March, April, and May, summer is defined as June, July, and August, autumn is defined as September and October, and winter is defined as January, February, November, and December, then:

[0080]

[0081]

[0082]

[0083]

[0084] in, The maximum load at noon on day d in year y is expressed as:

[0085]

[0086] in, It represents the set of daily midday peak times, which can be determined comprehensively according to the local load variation law. For example, the daily midday peak is defined as from 9:00 to 16:00, and the maximum value of the midday peak generally occurs at noon.

[0087] Next, determine the day of the evening peak maximum for each season, expressed as:

[0088]

[0089] in, ,in, It represents the set of evening peak times, which can be determined based on factors such as the local sunset time. For example, the evening peak is defined as from 17:00 to 24:00, and the maximum value of the evening peak generally occurs within a few hours after nightfall.

[0090] For a receiving province in the east, combined with the local sunrise and sunset times and load growth patterns, it is recommended that the midday peak time and evening peak time be set as shown in Table 1 below:

[0091] Table 1 Suggested schedules for the afternoon and evening peak times in a certain eastern coastal province by month

[0092]

[0093] Finally, the maximum peak-to-valley difference rate day of each season is determined, expressed as:

[0094]

[0095] in

[0096]

[0097] .

[0098] In the embodiment of the present invention, in step 102, for a certain season, the maximum value of the noon peak and its neighborhood, the maximum value of the evening peak and its neighborhood, and the minimum value and its neighborhood of the typical daily historical load curve of the season are determined.

[0099] First, determine the maximum noon peak value and its neighborhood of the typical daily historical load curve of the season. The maximum noon peak value and its neighborhood of the typical daily load curve of the historical year y season are taken from the load value corresponding to the maximum noon peak value of the historical year y season:

[0100]

[0101] in, represents the load at time t of the typical daily load curve in season s of year y, The time set representing the neighborhood of the maximum load at noon peak is determined by expert experience based on load characteristics. For example, it is set to 1 hour before and 3 hours after the maximum load at noon peak:

[0102]

[0103] in, Indicates the time when the maximum load at noon peak occurs.

[0104] Then, determine the maximum evening peak value and its neighborhood of the typical daily historical load curve of the season. The maximum evening peak value and its neighborhood of the typical daily load curve of the historical year y season are taken from the load value corresponding to the day of the maximum evening peak value of the historical year y season:

[0105]

[0106] in, The time set representing the neighborhood of the evening peak maximum value is determined by expert experience according to the load characteristics, for example, it is set to 1 hour before and 2 hours after the occurrence of the evening peak maximum load. In addition, the present invention adds the period from the end of the evening peak maximum load neighborhood to midnight to the evening peak load neighborhood and performs the same treatment to achieve the purpose of simplifying the calculation steps:

[0107]

[0108] Finally, determine the daily minimum load and its neighborhood of the typical daily historical load curve of the season. The daily minimum value and its neighborhood of the typical daily load curve of the season will be calculated based on three factors, one is the daily maximum peak-to-valley difference rate of the day with the maximum peak-to-valley difference rate of the season, the other is the daily minimum load and its neighborhood load of the day with the maximum peak-to-valley difference rate of the season, and the last one is the daily maximum load of the typical daily load curve of the season determined in the previous article. The calculation formula is:

[0109]

[0110] in, It is the correction coefficient, which is used to correct the minimum load and its neighboring load on the day with the maximum peak-to-valley difference rate of the season, so as to ensure that the maximum peak-to-valley difference rate of the generated typical daily load curve of the season is consistent with the true value. Given by:

[0111]

[0112] in, represents the maximum value of the typical daily load curve in season s, taking the maximum value of the midday peak maximum value and the evening peak maximum value determined above, Indicates the time when the maximum peak-to-valley difference rate of the season and the minimum load of the day occur The load, i.e. the minimum load, It represents the daily maximum peak-to-valley difference rate in season s of year y, and is given by the following formula:

[0113]

[0114] in, The time set representing the daily minimum neighborhood is determined by expert experience based on load characteristics, for example, 1 hour before and after the daily minimum load occurs. In addition, the present invention adds the time from early morning to the beginning of the minimum neighborhood to the minimum load neighborhood and performs the same treatment to achieve the purpose of simplifying the calculation steps: .

[0115] In the embodiment of the present invention, in step 102, for a certain season, other parts of the typical day historical load curve of the season are determined to generate a typical day historical load curve. Specifically, the following steps are performed: first, the load value between the minimum load neighborhood and the daily peak neighborhood is determined. , , They represent the end time, corresponding load value and slope of the minimum load neighborhood of the typical daily load curve in season s. The slope is expressed by and the difference between the load value at the previous moment:

[0116]

[0117] use , , They represent the starting time, corresponding load value and slope of the midday peak load neighborhood of the typical daily load curve in season s. The slope is expressed by And the difference of the load value at the next moment is determined:

[0118]

[0119] Determine the Hermite interpolation function between the minimum load neighborhood and the midday peak neighborhood:

[0120]

[0121] in:

[0122]

[0123]

[0124]

[0125]

[0126] in:

[0127]

[0128] For a certain time t between the minimum load neighborhood and the noon peak neighborhood, substitute t into the formula to obtain the load value at time t.

[0129] Then, a similar method is used to determine the load value between the midday peak neighborhood and the evening peak neighborhood. , , They represent the end time of the midday peak load neighborhood of the typical daily load curve in season s, the corresponding load value and its slope, respectively. , , They respectively represent the starting time, corresponding load value and slope of the evening peak load neighborhood of the typical daily load curve in season s.

[0130] The Hermite interpolation function between the midday peak neighborhood and the evening peak neighborhood is expressed as:

[0131]

[0132] For a certain time t between the noon peak neighborhood and the evening peak neighborhood, substitute t into the formula to obtain the load value at time t.

[0133] In this way, the characteristic daily historical load curve of season s in year y is generated. .

[0134] In the embodiment of the present invention, determining the benchmark load curve and the predicted load curve of a typical day in four seasons specifically includes: first, determining the benchmark load curve of a typical day in four seasons. The method for generating the benchmark load curve can adopt an existing mature method, such as directly adopting the typical load curve of the four seasons in the most recent year, or the average load curve of the most recent years, or the weighted load curve of the most recent years, or other appropriate methods, selected according to specific circumstances. The benchmark load curve of a typical day in four seasons is expressed as:

[0135]

[0136] The superscript base represents the reference curve value.

[0137] Then, the maximum value of the daily midday peak, the maximum value of the daily evening peak, and the minimum daily load in the forecast year y season s are determined. The predicted values ​​of the maximum value of the daily midday peak, the predicted values ​​of the maximum value of the daily evening peak, and the predicted values ​​of the daily minimum daily load in the forecast year y season s are expressed as , , In practice, the minimum load is not predicted directly, but the maximum peak-to-valley difference is predicted. , the predicted value of the daily minimum load and the predicted value of the daily maximum peak-to-valley difference rate have the following relationship:

[0138]

[0139] in, .

[0140] Next, determine the maximum value of the daily midday peak and its neighboring load value, the maximum value of the daily evening peak and its neighboring load value, and the minimum value of the daily peak and its neighboring load value of the seasonal characteristic daily load curve in the y forecast year s:

[0141]

[0142]

[0143]

[0144] in, , , They respectively represent the daily midday peak maximum, evening peak maximum, and daily minimum value of the s season benchmark load curve.

[0145] Finally, determine the load values ​​between the characteristic load neighborhoods of the typical daily load curve in the s season of the forecast year y. The Hermite interpolation function between the minimum load neighborhood and the noon peak neighborhood is:

[0146]

[0147] in, , , , , , They respectively represent the end time, corresponding load value and slope of the minimum load neighborhood of the typical daily load curve in season s of forecast year y, and the start time, corresponding load value and slope of the maximum load neighborhood of the midday peak.

[0148] The Hermite interpolation function between the midday peak neighborhood and the evening peak neighborhood is:

[0149]

[0150] in, , , , , , They respectively represent the end time, corresponding load value and slope of the midday peak maximum load neighborhood of the typical daily load curve in season s of forecast year y, and the start time, corresponding load value and slope of the evening peak maximum load neighborhood.

[0151] In this way, the typical daily forecast load curve for season s in year y is generated. .

[0152] It should be noted that although the above description is based on typical days of four seasons as an example, in actual applications, the same method can be used to generate historical and predicted load curves for other typical days such as monthly typical days in combination with specific needs. At the same time, the definitions of seasonal range, daily midday peak and evening peak time range, characteristic load neighborhood range, etc. in the above text should also be set according to specific circumstances.

[0153] The above is a typical daily load curve generation method provided by an embodiment of the present invention. Based on the same inventive concept, an embodiment of the present invention also provides a typical daily load curve generation system. Figure 2 A typical daily load curve generation system composition diagram provided by an embodiment of the present invention is as follows: Figure 2As shown, the system mainly includes: an annual historical load curve analysis module 201, which is used to obtain and analyze the annual historical load curve; a four-season typical day historical load curve generation module 202, which is used to calculate and generate the four-season typical day historical load curve based on the annual historical load curve by using the characteristic load neighborhood and Hermite interpolation method; a four-season typical day benchmark load curve generation module 203, which is used to generate the four-season typical day benchmark load curve based on the four-season typical day historical load curve; a four-season typical day predicted load curve generation module 204, which is used to calculate and generate the four-season typical day predicted load curve based on the four-season typical day benchmark load curve by using the characteristic load neighborhood and Hermite interpolation method.

[0154] The above is a typical daily load curve generation system provided by an embodiment of the present invention. Based on the same inventive concept, an embodiment of the present invention also provides a typical daily load curve generation device. Figure 3 A schematic diagram of a typical daily load curve generating device provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, the device mainly includes: at least one processor 301; and a memory 302 that is communicatively connected to the at least one processor; wherein the memory 302 stores instructions that can be executed by the at least one processor 301, and the instructions are executed by the at least one processor 301 so that the at least one processor 301 can complete the aforementioned typical daily load curve generation method.

[0155] In addition, an embodiment of the present invention further provides a non-volatile computer storage medium for generating a typical daily load curve, which stores computer executable instructions. The computer executable instructions are executed by a processor for the aforementioned typical daily load curve generating method.

[0156] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0157] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0158] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0159] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0160] The various embodiments of the present invention are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0161] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0162] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims

1. A typical daily load curve generation method, characterized in that: The method comprises the following steps: Obtaining and analyzing the annual historical load curve; the obtaining and analyzing the annual historical load curve specifically includes: Determine the maximum value of the noon peak and its neighborhood of the historical load curve of a typical day in any season, as shown in the following formula: ； in, It represents the load at time t of the typical daily load curve in season s of year y, The time set representing the neighborhood of the maximum value of the midday peak is determined by expert experience based on load characteristics; Determine the maximum value of the evening peak of the typical daily historical load curve of the season and its neighborhood, as shown in the following formula: ; in, The time set representing the neighborhood of the late peak maximum value is determined by expert experience based on load characteristics; The daily minimum load and its neighborhood of the typical daily historical load curve of the season are determined based on the following formula: ； in, is the correction coefficient, which is used to correct the minimum load and its neighboring load on the day with the maximum peak-to-valley difference rate of the seasonal day, so as to ensure that the maximum peak-to-valley difference rate of the generated seasonal typical daily load curve is consistent with the actual data. Given by: ,in, It represents the maximum value of the typical daily load curve in season s, taking the maximum value of the midday peak and the evening peak. Indicates the time when the minimum load occurs on the day with the maximum peak-to-valley difference rate in the s season of year y The load, i.e. the minimum load, It represents the daily maximum peak-to-valley difference rate in season s of year y, and is given by the following formula: The time set representing the neighborhood of the daily minimum load is determined by expert experience based on load characteristics; Based on the annual historical load curve, a typical daily historical load curve of four seasons is calculated and generated by using characteristic load neighborhood and Hermite interpolation method; the generating of the typical daily historical load curve of four seasons specifically includes: Based on the Hermite interpolation function, the load value between the minimum load neighborhood and the midday peak neighborhood is determined; Based on the Hermite interpolation function, the load value between the midday peak neighborhood and the evening peak neighborhood is determined; Generate typical daily historical load curves for four seasons; Based on the four-season typical day historical load curve, generate a four-season typical day benchmark load curve; Based on the typical daily benchmark load curve of four seasons, a typical daily forecast load curve of four seasons is calculated and generated by using characteristic load neighborhood and Hermite interpolation method; The method further comprises: The maximum day of the daily midday peak in each season is determined based on the following formula: ； Among them, s is the season, It represents the maximum day of the midday peak in the season of year y. represents the set of days d in season s, depending on the definition of year and season; The maximum load at noon on day d in year y is expressed as: ； in, It represents the set of daily peak hours, which can be determined comprehensively according to the local load variation law; Determine the day of the daily evening peak maximum for each season, expressed as: ， in, , It represents the collection of peak hours in the evening, which can be determined according to the local sunset time; Based on the following formula, the maximum peak-to-valley difference rate day of each season is determined, expressed as: ； in, ; ； ； The generation of the typical daily forecast load curve for four seasons is specifically as follows: Determine the midday peak maximum value and its neighborhood, evening peak maximum value and its neighborhood, and minimum value and its neighborhood of the typical daily forecast load curve of any season; Determine the load value between the minimum load area and the noon peak neighborhood, and the load value between the noon peak neighborhood and the evening peak neighborhood of the typical daily forecast load curve of any season; Generate a typical daily forecast load curve for the season.

2. A typical daily load curve generation method according to claim 1, characterized in that: The annual historical load curve is expressed as follows: ； Where t represents the hour of the day, d represents the day of the year, and y represents the year to which the load data belongs.

3. A typical daily load curve generation method according to claim 1, characterized in that: The step of determining the load value between the minimum load neighborhood and the midday peak neighborhood specifically includes: The slope of the typical daily load curve at the end of the minimum load neighborhood is determined based on the following formula: , in, express s The load value corresponding to the end time of the minimum load neighborhood of the typical daily load curve of the season, Indicates the load value corresponding to the previous moment; use , , They represent the starting time, corresponding load value and slope of the midday peak load neighborhood of the typical daily load curve in season s. The slope is expressed by The difference between the load value at the next moment and the load value at the next moment is determined as follows: ； Determine the Hermite interpolation function between the minimum load neighborhood and the midday peak neighborhood, as follows: in, For a certain time t between the minimum load neighborhood and the noon peak neighborhood, substitute t into the formula to obtain the load value at time t.

4. A typical daily load curve generation system, using the typical daily load curve generation method according to claim 1, characterized in that: The system comprises: Annual historical load curve analysis module, used to obtain and analyze annual historical load curves; A module for generating a typical daily historical load curve for four seasons, which is used to calculate and generate a typical daily historical load curve for four seasons based on the annual historical load curve by using a characteristic load neighborhood and a Hermite interpolation method; A four-season typical day benchmark load curve generation module, used for generating a four-season typical day benchmark load curve based on the four-season typical day historical load curve; The four-season typical day forecast load curve generation module is used to calculate and generate the four-season typical day forecast load curve based on the four-season typical day benchmark load curve by using the characteristic load neighborhood and Hermite interpolation method.

5. A typical daily load curve generating device, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can complete the typical daily load curve generation method described in any one of claims 1-3.

6. A non-volatile computer storage medium for generating a typical daily load curve, storing computer executable instructions, characterized in that: The computer executable instructions are executed by a processor to implement a typical daily load curve generating method as described in any one of claims 1 to 3.

Images