CN115455367A - Calculation method, system, device and storage medium of interruptible load - Google Patents

Abstract

An embodiment of the present invention provides a method, system, device, and storage medium for calculating an interruptible load, wherein the method includes: determining the target type of the target user's daily load curve based on a preset load classification model, and determining the target type based on the target user's daily load curve. The metering parameters in the load curve, the initial type parameters of the target user corresponding to the daily load curve of the target user are obtained, based on the user identification and initial type parameters of the target user, from the target preset type parameter distribution probability table corresponding to the target type , determine the target type parameter group and the type parameter distribution probability values corresponding to each type parameter in the target type parameter group, and calculate the interruptible load of the target user according to the target type parameter group and the distribution probability values of each type parameter. The invention realizes the accurate calculation of the interruptible load, thereby reducing the risk of wrong cut-off of load types with high requirements on power supply reliability, and improving the power supply reliability.

Description

Calculation method, system, device and storage medium of interruptible load

technical field

The present invention relates to the technical field of interruptible load management, in particular to a calculation method, system, equipment and storage medium of an interruptible load.

Background technique

Interruptible load refers to the part of the load that can be interrupted by the power consumer during peak hours or emergency situations. The power consumer and the power supplier realize the management of the interruptible load by signing the interruptible load contract. Existing interruptible load contracts are based on the total amount of load that users can interrupt.

However, with the development of the economy, the types of loads in the power system are gradually increasing. And different load types have different requirements for power supply reliability. If load shedding is carried out according to the contract established by the total amount of interruptible load, the risk of wrong shedding of load types with high requirements on power supply reliability will be increased, which will lead to a decrease in power supply reliability.

Contents of the invention

The purpose of the embodiments of the present invention is to provide a calculation method, system, device and storage medium for interruptible loads, so as to reduce the risk of wrong removal of load types that require high power supply reliability and improve power supply reliability. The specific technical scheme is as follows:

A method for calculating an interruptible load, the method comprising:

Determine the target type of the daily load curve of the target user based on the preset load classification model;

Obtaining an initial type parameter of the target user corresponding to the daily load curve of the target user based on the measurement parameters in the daily load curve of the target user;

Based on the user identification of the target user and the initial type parameters, from the target preset type parameter distribution probability table corresponding to the target type, determine the target type parameter group and corresponding to each type parameter in the target type parameter group respectively The type parameter distribution probability value of ;

The interruptible load of the target user is calculated according to the target type parameter group and the distribution probability value of each type parameter.

Optionally, the metering parameters are composed of total daily electricity consumption and daily maximum load, and the metering parameters corresponding to the daily load curve of the target user are obtained based on the metering parameters corresponding to the daily load curve of the target user. The initial type parameters of the target user, including:

By formula:

Obtaining the daily load rate LR of the target user, wherein the P is the total daily power consumption, and the EL _max is the daily maximum load;

By formula:

θ ₀ =1-LR

Obtaining the initial type parameter, wherein the θ ₀ is the initial type parameter.

Optionally, based on the user identifier of the target user and the initial type parameter, the target type parameter group and the target type parameter group are determined from the target type parameter distribution probability table corresponding to the target type. The type parameter distribution probability values corresponding to each type parameter in the parameter group, including:

Calculating the parameter difference between each reference type parameter in the target preset type parameter distribution probability table and the initial type parameter;

Determining the reference type parameter corresponding to the minimum value of each of the parameter differences as the target type parameter, and setting the type parameter distribution probability value corresponding to the target type parameter as a first value;

Determine the target adjacent type parameter of the target type parameter in the target preset type parameter distribution probability table, and set the type parameter distribution probability value corresponding to the target adjacent type parameter as a second value, wherein , the target adjacent type parameter is a reference type parameter whose value of the reference type parameter is greater than the target type parameter and adjacent to the target type parameter, the sum of the first value and the second value is 1;

The target type parameter set including the target type parameter and the target neighbor type parameter is obtained.

Optionally, the calculating the interruptible load of the target user according to the target type parameter group and the distribution probability value of each type parameter includes:

By formula:

obtain the interruptible load Xi (θ _j ) of the target user _i , wherein, the P _m is the preset peak-time unit electricity price parameter, the P ₀ is the preset sales unit electricity price parameter, and the λ is Preset power transmission unit cost parameters, the P _i (θ _j ) is the type parameter distribution probability value corresponding to the jth target type parameter θ _j of the target user i, and the θ _j+1 is the The target adjacent type parameter of the target type parameter θ _j , the K ₁ is the preset first power-off cost coefficient, the K ₂ is the preset second power-off cost coefficient, and the J is the target preset The total number of reference type parameters in the type parameter distribution probability table, the P _i (θ _n ) is the type parameter distribution probability value corresponding to the nth reference type parameter θ _n of the target user i.

Optionally, the training process of the preset load classification model includes:

Add the obtained first quantity of historical daily load curves to the sample data set;

randomly selecting a target historical daily load curve from the sample data set and determining it as the cluster center curve in the cluster center curve set;

Calculate the Euclidean distance between each of the historical daily load curves in the sample data set except the cluster center curve and the cluster center curve in the cluster center curve set;

Determine the historical daily load curve corresponding to the Euclidean distance with the smallest numerical value in each of the Euclidean distances as the cluster center curve in the cluster center curve set, and return to perform the respective calculations in the sample data set to divide all The step of the Euclidean distance between each of the historical daily load curves outside the cluster center curve and the cluster center curve in the cluster center curve set;

When the number of the cluster center curves in the cluster center curve set is equal to the number of preset classifications, the calculation is terminated to obtain the preset load classification model.

A computing system capable of interrupting loads, the computing system comprising:

A curve classification module, configured to determine the target type of the daily load curve of the target user based on a preset load classification model;

A parameter calculation module, configured to obtain the initial type parameter of the target user corresponding to the target user's daily load curve based on the metering parameters in the target user's daily load curve;

A data determination module, configured to determine the target type parameter group and the target type parameter group from the target preset type parameter distribution probability table corresponding to the target type based on the user identifier of the target user and the initial type parameter The type parameter distribution probability values corresponding to each type parameter in ;

The load calculation module is configured to calculate the interruptible load of the target user according to the target type parameter group and the distribution probability value of each type parameter.

Optionally, the parameter calculation module is set to:

By formula:

Obtaining the daily load rate LR of the target user, wherein the P is the total daily electricity consumption in the metering parameters, and the EL _max is the daily maximum load in the metering parameters;

By formula:

θ ₀ =1-LR

Obtaining the initial type parameter, wherein the θ ₀ is the initial type parameter.

Optionally, the data determination module is set to:

Calculating the parameter difference between each reference type parameter in the target preset type parameter distribution probability table and the initial type parameter;

Determining the reference type parameter corresponding to the minimum value of each of the parameter differences as the target type parameter, and setting the type parameter distribution probability value corresponding to the target type parameter as a first value;

Determine the target adjacent type parameter of the target type parameter in the target preset type parameter distribution probability table, and set the type parameter distribution probability value corresponding to the target adjacent type parameter as a second value, wherein , the target adjacent type parameter is a reference type parameter whose value of the reference type parameter is greater than the target type parameter and adjacent to the target type parameter, the sum of the first value and the second value is 1;

The target type parameter set including the target type parameter and the target neighbor type parameter is obtained.

Optionally, the load metering module is set to:

By formula:

obtain the interruptible load Xi (θ _j ) of the target user _i , wherein, the P _m is the preset peak-time unit electricity price parameter, the P ₀ is the preset sales unit electricity price parameter, and the λ is Preset power transmission unit cost parameters, the P _i (θ _j ) is the type parameter distribution probability value corresponding to the jth target type parameter θ _j of the target user i, and the θ _j+1 is the The target adjacent type parameter of the target type parameter θ _j , the K ₁ is the preset first power-off cost coefficient, the K ₂ is the preset second power-off cost coefficient, and the J is the target preset The total number of reference type parameters in the type parameter distribution probability table, the P _i (θ _n ) is the type parameter distribution probability value corresponding to the nth reference type parameter θ _n of the target user i.

Optionally, the calculation system of the interruptible load further includes:

The model training module is used to add the first quantity of historical daily load curves obtained to the sample data set;

randomly selecting a target historical daily load curve from the sample data set and determining it as the cluster center curve in the cluster center curve set;

Calculate the Euclidean distance between each of the historical daily load curves in the sample data set except the cluster center curve and the cluster center curve in the cluster center curve set;

Determine the historical daily load curve corresponding to the Euclidean distance with the smallest numerical value in each of the Euclidean distances as the cluster center curve in the cluster center curve set, and return to perform the respective calculations in the sample data set to divide all The step of the Euclidean distance between each of the historical daily load curves outside the cluster center curve and the cluster center curve in the cluster center curve set;

When the number of the cluster center curves in the cluster center curve set is equal to the number of preset classifications, the calculation is terminated to obtain the preset load classification model.

An interruptible load computing device, the computing device comprising:

processor;

memory for storing said processor-executable instructions;

Wherein the processor is configured to execute the instructions, so as to realize the calculation method of the interruptible load amount as described in any one of the above.

A computer-readable storage medium, when the instructions in the computer-readable storage medium are executed by a processor of a computing device with an interruptible load, the computing device can execute the interruptible How to calculate load.

An interruptible load calculation method, system, device, and storage medium provided by the embodiments of the present invention can classify daily load curves by using a preset load classification model, which can improve the determination accuracy of type parameters, thereby improving subsequent generation. Interruptible load accuracy. At the same time, based on the measurement parameters of the daily load curve, the initial type parameters that can characterize the target user type are determined. It avoids the reduction of calculation efficiency due to the huge amount of operation data and the reduction of calculation accuracy caused by the interference between data. Finally, the present invention can accurately calculate the interruptible load of each target user belonging to the same target type according to each target type parameter and type parameter distribution probability value in a target preset type parameter distribution probability table. It can be seen that the present invention realizes accurate calculation of interruptible loads, thereby reducing the risk of mis-cutting load types that require high power supply reliability, and improving power supply reliability.

Of course, implementing any product or method of the present invention does not necessarily need to achieve all the above-mentioned advantages at the same time.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

FIG. 1 is a flow chart of a calculation method for an interruptible load provided by an embodiment of the present invention;

Fig. 2 is a block diagram of an interruptible load computing system provided by an optional embodiment of the present invention;

Fig. 3 is a block diagram of a computing device capable of interrupting load provided by another optional embodiment of the present invention.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

An embodiment of the present invention provides a method for calculating an interruptible load, as shown in FIG. 1 , the method includes:

S101. Determine a target type of a target user's daily load curve based on a preset load classification model.

Wherein, the above-mentioned daily load curve (Load curve) is a curve used to characterize the change of various types of electric loads in the power system with time.

Optionally, in an optional embodiment of the present invention, in an actual application scenario, there may be multiple target types. For example: if the daily load curve shows a trend that the load is low during the day and the load decreases from high at night, it indicates that the target type corresponding to the daily load curve is a residential user. If the daily load curve shows a high load throughout the day, it indicates that the target type corresponding to the daily load curve is an industrial user. If the daily load curve shows that the load in the daytime is high and the load in the evening tends to decrease, it indicates that the target type corresponding to the daily load curve is a commercial user.

Optionally, in another optional embodiment of the present invention, the foregoing preset load classification model may be a model constructed based on a K-means clustering algorithm (k-means clustering algorithm, K-means). Since the daily load curve represents the usage of user load in different periods. And different types of user loads correspond to different type parameters. Therefore, the present invention can improve the determination accuracy of type parameters by using a preset load classification model to classify daily load curves. Thereby, the accuracy of subsequent generation of interruptible load is improved.

S102. Based on the measurement parameters in the target user's daily load curve, obtain the target user's initial type parameter corresponding to the target user's daily load curve.

Optionally, in an optional embodiment of the present invention, since the daily load curve includes a large amount of load data of the target user in a natural day. If the subsequent calculation of the interruptible load is carried out based on a large amount of load data, the calculation efficiency and calculation accuracy will be reduced. Therefore, the present invention determines the initial type parameters that can characterize the target user type based on the metering parameters of the daily load curve. It avoids the reduction of calculation efficiency due to the huge amount of operation data and the reduction of calculation accuracy caused by the interference between data.

S103. Based on the target user's user ID and initial type parameters, from the target preset type parameter distribution probability table corresponding to the target type, determine the target type parameter group and the type parameter distribution corresponding to each type parameter in the target type parameter group probability value.

Optionally, in an optional embodiment of the present invention, since the daily load curves of different users cannot be completely fitted, the initial type parameters for different target users with the same target type daily load curves will be different. At the same time, if the user temporarily increases the load or prolongs the power consumption time of the load, the daily load curve cannot reflect the real power consumption situation, and the initial type parameters will also change. Therefore, in order to facilitate the accurate calculation of the interruptible load of a large number of users with the same target type daily load curve, it is necessary to uniformly divide the initial type parameters of each target user, and to analyze the occurrence of multiple type parameters that may appear in the same user. The probability is determined.

Optionally, in another optional embodiment of the present invention, the above type parameter distribution probability value may be the initial type parameter determined based on the daily load curve of the target user, and the type parameter in the corresponding target preset type parameter distribution probability table match probability. The distribution probability value of this type parameter can be set after probabilistic statistics according to the historical daily load curve and the corresponding type parameters.

Optionally, in another optional embodiment of the present invention, the specific form of the target preset type parameter distribution probability table may be shown in Table 1 below.

Table 1

Wherein, the above-mentioned Table 1 records the type parameter distribution probability values of the preset types of the six users belonging to the same target type.

S104. Calculate the interruptible load of the target user according to the target type parameter group and the distribution probability value of each type of parameter.

Optionally, in an optional embodiment of the present invention, since the above target preset type parameter distribution probability table records all possible target type parameters of each target user belonging to the same target type, and the corresponding target type parameters The type parameter distribution probability of . Therefore, according to each target type parameter and type parameter distribution probability value in a target preset type parameter distribution probability table, accurate calculation of the interruptible load of each target user belonging to the same target type can be realized.

The present invention classifies daily load curves by using a preset load classification model, which can improve the determination accuracy of type parameters, thereby improving the accuracy of subsequent generation of interruptible loads. At the same time, based on the measurement parameters of the daily load curve, the initial type parameters that can characterize the target user type are determined. It avoids the reduction of calculation efficiency due to the huge amount of operation data and the reduction of calculation accuracy caused by the interference between data. Finally, the present invention can accurately calculate the interruptible load of each target user belonging to the same target type according to each target type parameter and type parameter distribution probability value in a target preset type parameter distribution probability table. It can be seen that the present invention realizes accurate calculation of interruptible loads, thereby reducing the risk of mis-cutting load types that require high power supply reliability, and improving power supply reliability.

Optionally, the metering parameters are composed of the total daily electricity consumption and the daily maximum load. Based on the metering parameters in the daily load curve of the target user, the initial type parameters of the target user corresponding to the daily load curve of the target user are obtained, including :

By formula:

Obtain the daily load rate LR of the target user, where P is the total daily electricity consumption, and EL _max is the daily maximum load;

By formula:

θ ₀ =1-LR

Obtain the initial type parameter, where θ ₀ is the initial type parameter.

Wherein, since the unit of the above-mentioned maximum daily load EL _max is kWh, the unit of the total daily power consumption is kW. In order to facilitate unified calculation, it needs to be multiplied by 24 hours to unify the unit.

Optionally, based on the target user's user ID and initial type parameters, determine the target type parameter group and the types corresponding to each type parameter in the target type parameter group from the target preset type parameter distribution probability table corresponding to the target type Parametric distribution probability values, including:

Calculate the parameter difference between each benchmark type parameter and the initial type parameter in the target preset type parameter distribution probability table;

The benchmark type parameter corresponding to the minimum value in each parameter difference is determined as the target type parameter, and the type parameter distribution probability value corresponding to the target type parameter is set as the first value;

Determine the target adjacent type parameter of the target type parameter in the target preset type parameter distribution probability table, and set the type parameter distribution probability value corresponding to the target adjacent type parameter as the second value, wherein the target adjacent type parameter is the benchmark The value of the type parameter is greater than the target type parameter, and the base type parameter adjacent to the target type parameter, the sum of the first value and the second value is 1;

Obtains an object type parameter group including an object type parameter and an object adjacent type parameter.

Optionally, calculate the interruptible load of the target user according to the target type parameter group and the distribution probability value of each type of parameter, including:

By formula:

Obtain the interruptible load X _i (θ _j ) of the target user i, where P _m is the preset peak hour unit electricity price parameter, P ₀ is the preset sales unit electricity price parameter, λ is the preset power transmission unit cost parameter, P _i (θ _j ) is the type parameter distribution probability value corresponding to the jth target type parameter θ _j of the target user i, θ _j+1 is the target adjacent type parameter of the target type parameter θ _j , K ₁ is the preset The first power outage cost coefficient, K ₂ is the preset second power outage cost coefficient, J is the total number of reference type parameters in the target preset type parameter distribution probability table, P _i (θ _n ) is the target user i The distribution probability value of the type parameter corresponding to the nth benchmark type parameter θ _n .

Optionally, the training process of the preset load classification model includes:

Add the obtained first quantity of historical daily load curves to the sample data set;

Randomly select a target historical daily load curve from the sample data set and determine it as the cluster center curve in the cluster center curve set;

Calculate the Euclidean distance between each historical daily load curve in the sample data set except the cluster center curve and the cluster center curve in the cluster center curve set;

Determine the historical daily load curve corresponding to the Euclidean distance with the smallest value in each Euclidean distance as the cluster center curve in the cluster center curve set, and return to execute the calculation of each historical day in the sample data set except the cluster center curve The steps of the Euclidean distance between the load curve and the cluster center curve in the cluster center curve set;

When the number of cluster center curves in the cluster center curve set is equal to the number of preset classifications, the calculation is terminated to obtain a preset load classification model.

Corresponding to the above method embodiments, the present invention also provides a calculation system for interruptible load, as shown in Figure 2, the calculation system includes:

A curve classification module 201, configured to determine the target type of the target user's daily load curve based on a preset load classification model;

The parameter calculation module 202 is used to obtain the initial type parameter of the target user corresponding to the target user's daily load curve based on the metering parameters in the target user's daily load curve;

The data determination module 203 is used to determine the target type parameter group and the respective type parameters in the target type parameter group from the target preset type parameter distribution probability table corresponding to the target type based on the target user's user identification and initial type parameters. The corresponding type parameter distribution probability value;

The load calculation module 204 is configured to calculate the interruptible load of the target user according to the target type parameter group and the distribution probability value of each type parameter.

Optionally, the above parameter calculation module 202 is set to:

By formula:

Obtain the daily load rate LR of the target user, where P is the total daily electricity consumption in the metering parameters, and EL _max is the daily maximum load in the metering parameters;

By formula:

θ ₀ =1-LR

Obtain the initial type parameter, where θ ₀ is the initial type parameter.

Optionally, the above data determination module 203 is set to:

Calculate the parameter difference between each benchmark type parameter and the initial type parameter in the target preset type parameter distribution probability table;

The benchmark type parameter corresponding to the minimum value in each parameter difference is determined as the target type parameter, and the type parameter distribution probability value corresponding to the target type parameter is set as the first value;

Determine the target adjacent type parameter of the target type parameter in the target preset type parameter distribution probability table, and set the type parameter distribution probability value corresponding to the target adjacent type parameter as the second value, wherein the target adjacent type parameter is the benchmark The value of the type parameter is greater than the target type parameter, and the base type parameter adjacent to the target type parameter, the sum of the first value and the second value is 1;

Obtains an object type parameter group including an object type parameter and an object adjacent type parameter.

Optionally, the above load calculation module 204 is set to:

By formula:

Obtain the interruptible load X _i (θ _j ) of the target user i, where P _m is the preset peak hour unit electricity price parameter, P ₀ is the preset sales unit electricity price parameter, λ is the preset power transmission unit cost parameter, P _i (θ _j ) is the type parameter distribution probability value corresponding to the jth target type parameter θ _j of the target user i, θ _j+1 is the target adjacent type parameter of the target type parameter θ _j , K ₁ is the preset The first power outage cost coefficient, K ₂ is the preset second power outage cost coefficient, J is the total number of reference type parameters in the target preset type parameter distribution probability table, P _i (θ _n ) is the target user i The distribution probability value of the type parameter corresponding to the nth benchmark type parameter θ _n .

Optionally, the above-mentioned calculation system for the interruptible load shown in Figure 2 also includes:

The model training module is used to add the first quantity of historical daily load curves obtained to the sample data set;

Randomly select a target historical daily load curve from the sample data set and determine it as the cluster center curve in the cluster center curve set;

Calculate the Euclidean distance between each historical daily load curve in the sample data set except the cluster center curve and the cluster center curve in the cluster center curve set;

Determine the historical daily load curve corresponding to the Euclidean distance with the smallest value in each Euclidean distance as the cluster center curve in the cluster center curve set, and return to execute the calculation of each historical day in the sample data set except the cluster center curve The steps of the Euclidean distance between the load curve and the cluster center curve in the cluster center curve set;

When the number of cluster center curves in the cluster center curve set is equal to the number of preset classifications, the calculation is terminated to obtain a preset load classification model.

An embodiment of the present invention also provides a computing device capable of interrupting load, as shown in FIG. 3 , the computing device includes:

Processor 301;

A memory 302 for storing instructions executable by the processor 301;

Wherein the processor 301 is configured to execute instructions, so as to implement any one of the methods for calculating the interruptible load amount as described above.

An embodiment of the present invention also provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by the processor of the computing device that can interrupt the load, the computing device can execute any of the above-mentioned Calculation method of interruption load.

In a typical configuration, a device includes one or more processors (CPUs), memory and a bus. A device may also include input/output interfaces, network interfaces, and the like.

Memory may include non-permanent memory in computer-readable media, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), and memory includes at least one memory chip. The memory is an example of a computer readable medium.

Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information. Information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridge, tape magnetic disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media excludes transitory computer-readable media, such as modulated data signals and carrier waves.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is a relationship between these entities or operations. any such actual relationship or order exists between them. It should also be noted that the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes Other elements not expressly listed, or elements inherent in the process, method, commodity, or apparatus are also included. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

Each embodiment in this specification is described in a related manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the related parts, please refer to the part of the description of the method embodiment.

The above are only examples of the present application, and are not intended to limit the present application. For those skilled in the art, various modifications and changes may occur in this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims (10)

1. A method of calculating an interruptible load amount, the method comprising:

determining a target type of a daily load curve of a target user based on a preset load classification model;

obtaining an initial type parameter of the target user corresponding to the daily load curve of the target user based on the metering parameter in the daily load curve of the target user;

determining a target type parameter group and type parameter distribution probability values respectively corresponding to various types of parameters in the target type parameter group from a target preset type parameter distribution probability table corresponding to a target type based on the user identification of the target user and the initial type parameters;

and calculating the interruptible load quantity of the target user according to the target type parameter group and the distribution probability value of each type parameter.

2. The method according to claim 1, wherein the metering parameters comprise total daily power consumption and maximum daily load, and the obtaining initial type parameters of the target user corresponding to the daily load curve of the target user based on the metering parameters in the daily load curve of the target user comprises:

by the formula:

obtaining the daily load rate LR of the target user, wherein P is the total daily power consumption, and EL is _max Is the daily maximum load;

by the formula:

θ ₀ ＝1-LR

obtaining the initial type parameter, wherein θ ₀ Is the initial type parameter.

3. The method of claim 2, wherein determining a target type parameter set and type parameter distribution probability values corresponding to respective types of parameters in the target type parameter set from a target preset type parameter distribution probability table corresponding to the target type based on the subscriber identity of the target subscriber and the initial type parameter comprises:

respectively calculating the parameter difference value of each reference type parameter and the initial type parameter in the target preset type parameter distribution probability table;

determining a reference type parameter corresponding to the minimum value in the parameter difference values as a target type parameter, and setting the type parameter distribution probability value corresponding to the target type parameter as a first numerical value;

determining a target adjacent type parameter of the target type parameter in the target preset type parameter distribution probability table, and setting the type parameter distribution probability value corresponding to the target adjacent type parameter as a second value, wherein the target adjacent type parameter is a reference type parameter of which the value is greater than that of the target type parameter and is adjacent to the target type parameter, and the sum of the first value and the second value is 1;

obtaining the target type parameter group including the target type parameter and the target neighbor type parameter.

4. The method of claim 3, wherein said calculating an interruptible load amount for the target user based on the target set of type parameters and each of the type parameter distribution probability values comprises:

by the formula:

determining an interruptible load X for the target user i _i (θ _j ) Wherein, said P _m Is a preset peak hour unit electricity price parameter, P ₀ Is a preset selling unit electricity price parameter, the lambda is a preset power transmission unit cost parameter, and the P is _i (θ _j ) Is the jth said target type parameter theta of said target user i _j Corresponding type parameter distribution probability value, theta _j+1 Is the target type parameter θ _j Target neighbor type parameter of (c), the K ₁ Is to preset a first outage cost coefficient, K ₂ Is a preset second outage cost coefficient, J is a total number of reference type parameters in the target preset type parameter distribution probability table, P is _i (θ _n ) Is the nth reference type parameter theta of the target user i _n And distributing probability values of the corresponding type parameters.

5. The method of claim 1, wherein the training process of the preset load classification model comprises:

adding the acquired first number of historical daily load curves to a sample data set;

randomly selecting a target historical daily load curve from the sample data set to determine as a clustering center curve in a clustering center curve set;

respectively calculating Euclidean distances between each historical daily load curve in the sample data set except the clustering center curve and the clustering center curve in the clustering center curve set;

determining a historical daily load curve corresponding to the Euclidean distance with the minimum value in each Euclidean distance as a clustering center curve in the clustering center curve set, and returning to execute the step of respectively calculating the Euclidean distances between each historical daily load curve except the clustering center curve in the sample data set and the clustering center curve in the clustering center curve set;

and when the number of the clustering center curves in the clustering center curve set is equal to the preset classification number, stopping the calculation to obtain the preset load classification model.

6. A computing system that can interrupt a load amount, the computing system comprising:

the curve classification module is used for determining a target type of a daily load curve of a target user based on a preset load classification model;

the parameter calculation module is used for solving initial type parameters of the target user corresponding to the daily load curve of the target user based on the metering parameters in the daily load curve of the target user;

a data determining module, configured to determine, based on the user identifier of the target user and the initial type parameter, a target type parameter group and type parameter distribution probability values respectively corresponding to various types of parameters in the target type parameter group from a target preset type parameter distribution probability table corresponding to the target type;

and the load quantity calculation module is used for calculating the interruptible load quantity of the target user according to the target type parameter group and the distribution probability value of each type parameter.

7. The computing system of claim 6, wherein the parameter calculation module is configured to:

by the formula:

obtaining the daily load rate LR of the target user, wherein P is the total daily power consumption in the metering parameters, and EL _max Is the daily maximum load in the metering parameter;

by the formula:

θ ₀ ＝1-LR

obtaining the initial type parameter, wherein the theta ₀ Is the initial type parameter.

8. The computing system of claim 7, wherein the data determination module is configured to:

respectively calculating the parameter difference between each reference type parameter and the initial type parameter in the target preset type parameter distribution probability table;

determining a reference type parameter corresponding to the minimum value in the parameter difference values as a target type parameter, and setting the type parameter distribution probability value corresponding to the target type parameter as a first numerical value;

determining a target adjacent type parameter of the target type parameter in the target preset type parameter distribution probability table, and setting the type parameter distribution probability value corresponding to the target adjacent type parameter as a second numerical value, wherein the target adjacent type parameter is a reference type parameter of which the numerical value of the reference type parameter is greater than that of the target type parameter and adjacent to the target type parameter, and the sum of the first numerical value and the second numerical value is 1;

obtaining the target type parameter set comprising the target type parameter and the target neighbor type parameter.

9. A computing device of interruptible load amounts, the computing device comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of calculating an interruptible load amount according to any one of claims 1-5.

10. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of a computing device of an interruptible load amount, enable the computing device to perform the method of computing an interruptible load amount according to any one of claims 1-5.

Images