Power load control quantity distribution optimization method and device, power load management system

Abstract

The present application relates to a method and device for optimizing the distribution of electric load control quantities, and an electric load management system, wherein the method for optimizing the distribution of electric load control quantities includes: determining the control response completion capability of each load user through a pre-constructed polynomial regression model; and allocating electric load control quantities to each load user based on the control response completion capability of each load user. Information such as the load user's electricity consumption characteristics and load type is used as one of the variables of the polynomial regression model, and electric load control quantities can be allocated to various fields and various types of load users. In this way, the electric load control quantities of various load users can be comprehensively coordinated, avoiding the problem of uneven distribution of electric load control quantities between load users in different fields or of different types. In summary, the present invention solves the problem that the existing electric load control quantity allocation method cannot comprehensively coordinate the allocation of various types of electric load control quantities.

Description

Technical Field

[0001] The present application relates to the field of power control, and in particular to a method and device for optimizing the distribution of power load control quantity, and a power load management system. Background Art

[0002] In the current power system, there are many types of power loads, covering multiple fields such as industry, commerce, and residences. Their electricity consumption characteristics and needs vary, which makes load regulation also diverse. The existing power load regulation allocation method has low versatility and cannot match different types of power loads at the same time. Different load regulation allocation calculation methods are required for different types of power loads, making the operation of the power load management system more complicated. At the same time, different load regulation allocation calculation methods are independent of each other, which may lead to uneven distribution of different types of power load regulation, resulting in excessive concentration of power load regulation in a certain field.

[0003] Therefore, there is a need for an optimization method for allocating power load control quantities that can comprehensively coordinate and allocate various types of power load control quantities. Summary of the Invention

[0004] The present invention provides a method and device for optimizing the distribution of electric load control quantities, and an electric load management system to solve the problem that the existing electric load control quantity distribution method cannot comprehensively coordinate and distribute various types of electric load control quantities.

[0005] In a first aspect, the present invention provides a method for optimizing the distribution of power load control quantity, comprising:

[0006] The control response completion capability of each load user is determined by a pre-built polynomial regression model, which is:

[0007] Y=β1X4+β2X5+β3X6+β4X1X2X3+β5X7X8X9X 10

[0008] Among them, Y represents the control response completion capability, β1, β2, β3, β4 and β5 represent the first coefficient, the second coefficient, the third coefficient, the fourth coefficient and the fifth coefficient respectively, X1, X2 and X3 represent the power consumption nature, load type and control mode of the load user respectively, X4, X5 and X6 represent the maximum controllable load, control participation rate and control completion degree of the load user respectively, X7, X8, X9 and X1 represent the load user's maximum controllable load, control participation rate and control completion degree respectively, 10 They represent holiday status, weather, temperature and control time period respectively;

[0009] The power load regulation amount is allocated to each of the load users according to the regulation response completion capability of each of the load users.

[0010] In a second aspect, the present invention provides a device for optimizing the distribution of power load control quantity, comprising:

[0011] The control completion calculation module is used to determine the control response completion capability of each load user through a pre-built polynomial regression model. The polynomial regression model is:

[0012] Y=β1X4+β2X5+β3X6+β4X1X2X3+β5X7X8X9X 10

[0013] Among them, Y represents the control response completion capability, β1, β2, β3, β4 and β5 represent the first coefficient, the second coefficient, the third coefficient, the fourth coefficient and the fifth coefficient respectively, X1, X2 and X3 represent the power consumption nature, load type and control mode of the load user respectively, X4, X5 and X6 represent the historical maximum controllable load, historical control participation rate and historical control completion degree of the load user respectively, X7, X8, X9 and X1 represent the load user's historical maximum controllable load, historical control participation rate and historical control completion degree respectively, 10 They represent holiday status, weather, temperature and control time period respectively;

[0014] The load distribution module is used to distribute the power load regulation amount to each of the load users according to the regulation response completion capability of each of the load users.

[0015] In a third aspect, the present invention provides a load control platform, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the power load control quantity distribution optimization method described in the first aspect.

[0016] In a fourth aspect, the present invention provides an electric load management system, comprising the load regulation platform described in the third aspect, wherein the load regulation platform is deployed on the master station side of the electric load management system.

[0017] In a fifth aspect, the present invention provides a method for managing power load, comprising:

[0018] The power load control quantity allocation optimization method described in the first aspect is used to allocate power load control quantity to each load user.

[0019] Compared with related technologies, the present invention mainly calculates the load user's control response completion capability through a polynomial regression model, and uses information such as the load user's electricity consumption characteristics and load type as one of the variables of the polynomial regression model. Thus, the power load control quantity allocation optimization method can jointly allocate power load control quantities to various fields and various types of load users, rather than only allocating power load control quantities to a certain field or a certain type of load user. In this way, the power load control quantities of various load users can be comprehensively coordinated, avoiding the problem of uneven distribution of power load control quantities between different fields or different types of load users. In summary, the present invention solves the problem that the existing power load control quantity allocation method cannot comprehensively coordinate the allocation of various types of power load control quantities.

[0020] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a flow chart of a method for optimizing distribution of power load control quantity provided in some embodiments of the present invention;

[0022] Figure 2 It is a flow chart of a method for optimizing distribution of power load control quantity provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0024] Unless otherwise defined, the technical terms or scientific terms involved in this application should have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "an", "a", "the", "these" and the like in this application do not indicate quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Generally, the character " / " indicates that the related objects are in an "or" relationship. The terms "first," "second," "third," etc. used in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0025] In an embodiment of the present invention, a method for optimizing the distribution of power load control quantity is provided. Figure 1 is a flow chart of a method for optimizing the distribution of power load control quantity provided in some embodiments of the present invention, such as Figure 1 As shown, the process includes the following steps:

[0026] Step S110: Determine the control response completion capability of each load user through a pre-built polynomial regression model. The polynomial regression model is:

[0027] Y=β1X4+β2X5+β3X6+β4X1X2X3+β5X7X8X9X 10

[0028] Among them, Y represents the control response completion capability, β1, β2, β3, β4 and β5 represent the first coefficient, the second coefficient, the third coefficient, the fourth coefficient and the fifth coefficient respectively, X1, X2 and X3 represent the power consumption nature, load type and control mode of the load user respectively, X4, X5 and X6 represent the historical maximum controllable load, historical control participation rate and historical control completion degree of the load user respectively, X7, X8, X9 and X1 represent the load user's historical maximum controllable load, historical control participation rate and historical control completion degree respectively, 10 They represent holiday status, weather, temperature and control time period respectively.

[0029] Before determining the load user's control response completion capability, it is also necessary to obtain the load user's basic information, historical load control record information, and current time and environmental factor information.

[0030] Basic information about load users includes their electricity usage, load type, and control method. The usage is categorized into three types: industrial, commercial, and residential. Load types are primarily differentiated by the intended use of the electricity, such as lighting, industrial production, electric vehicle charging, and air conditioning. Control methods are categorized into hard control and soft control.

[0031] The historical load control record information of load users includes the number of demand control times, the number of participation control times, the total load control demand, the load control completion amount, etc. Through these data, the control participation rate and control completion degree can be calculated. The control participation rate is the ratio of the number of participation control times to the number of demand control times, and the control completion degree is the ratio of the load control completion amount to the total load control demand.

[0032] The current time and environmental factors include the holiday status, weather, temperature, and control time period of the control day. The holiday status refers to whether it is a holiday, the weather can be sunny, cloudy, or rainy, and the temperature refers to whether it is within a certain temperature range.

[0033] After obtaining various information about a load user, the control response completion capability of the load user can be determined through a polynomial regression model.

[0034] The first, second, third, fourth, and fifth coefficients are obtained by fitting historical data using the least squares method. This is done by fitting each user's historical control response capabilities, corresponding basic information, historical load control records, and current time and environmental factors. Because this data is continuously updated, the first, second, third, fourth, and fifth coefficients can be updated in real time based on each user's latest control response capabilities and corresponding information.

[0035] It should be noted that the above information is usually categorical features. In order to facilitate calculation, it needs to be converted into numerical features. Therefore, before this step, it is necessary to preprocess the basic information of load users, historical load control records, and current time and environmental factors. Data preprocessing mainly includes:

[0036] Use label encoding to convert categorical features into numerical features; missing values ​​can be handled by filling (such as mean, median, and mode filling), deletion, or interpolation (such as linear interpolation and multiple interpolation); for numerical features with large dimensional differences, normalization (scaling the features to between 0 and 1) is performed.

[0037] Step S120: Allocate the power load regulation amount to each load user according to the regulation response completion capability of each load user.

[0038] In the above technical solution, the load user's control response completion capability is mainly calculated through a polynomial regression model, and information such as the load user's electricity consumption characteristics and load type is used as one of the variables of the polynomial regression model. Then, the power load control quantity allocation optimization method can jointly allocate power load control quantities to various fields and various types of load users, rather than only allocating power load control quantities to a certain field or a certain type of load user. In this way, the power load control quantities of various load users can be fully coordinated to avoid the problem of uneven distribution of power load control quantities between different fields or different types of load users. In summary, the present invention solves the problem that the existing power load control quantity allocation method cannot comprehensively coordinate the allocation of various types of power load control quantities.

[0039] In some embodiments, step S120 includes:

[0040] Step S121: Calculate the first power load regulation amount of each load user according to the regulation response completion capability of each load user. The calculation formula is as follows:

[0041]

[0042] Among them, P Y Represents the first power load control quantity, P Yk represents the first power load control quantity of the kth load user, P A represents the total demand for power load regulation, Y k and Y i They represent the control response completion capabilities of the kth and ith load users respectively, and n represents the total number of load users.

[0043] Step S122: Calculate the actual controllable load of each load user. The calculation formula is as follows:

[0044] P dk =P rk -P mink

[0045] Among them, P d 、P r and P min They represent the actual controllable load, real-time load and minimum operating load respectively, P dk 、P rk and P mink They represent the actual controllable load, real-time load and minimum operating load of the kth load user respectively.

[0046] Step S123: Calculate the second power load control amount of each load user according to the actual controllable load amount of each load user. The calculation formula is as follows:

[0047]

[0048] Among them, P w Represents the second power load control quantity, P wk represents the second power load control quantity of the kth load user, P di Represents the actual adjustable load of the i-th load user.

[0049] Step S124: determining the final power load regulation amount of each load user according to the first power load regulation amount and the second power load regulation amount of each load user. The formula for determining the final power load regulation amount of each load user is as follows:

[0050]

[0051] Among them, P f Indicates the final power load control amount, P fk Represents the final power load regulation amount of the k-th load user.

[0052] 1. When the first power load control amount of the load user is greater than the actual controllable load amount, that is, The final power load control amount of the load user is the actual controllable load amount. This ensures that the load control amount allocated to the user is within the user's controllable range and the rationality of task allocation.

[0053] 2. When the first power load control amount of the load user is less than the actual controllable load amount and greater than half of the actual controllable load amount, that is, The final power load control amount of the load user is half of the sum of the first power load control amount and the second power load control amount.

[0054] 3. When the first power load control amount of the load user is less than the actual controllable load amount, that is, The final power load control amount of the load user is the second power load control amount P w When the user's control response completion capability is low, the waste of user-controllable load resources is reduced.

[0055] As follows, the power load control quantity allocation optimization method in the present invention is illustrated by a specific embodiment.

[0056] Reference Figure 2 In a specific overall embodiment, the power load control quantity allocation optimization method includes:

[0057] S11, obtain load user information based on the electricity consumption information collection system, obtain time and environmental data based on any weather website, and obtain user historical load control record data based on the new power load management system.

[0058] The multi-dimensional data of the five participating users in this implementation case are shown in the following table:

[0059] Table 1 Multi-dimensional data table

[0060]

[0061]

[0062] S12: Preprocess the multi-dimensional data features of the above users.

[0063] (1) Based on the participation and influence of different data ranges in each single data item on load regulation, the categorical features are defined differently using label coding, as shown in the following table:

[0064] Table 2 Feature encoding rules

[0065]

[0066]

[0067] (2) For numerical features with large dimensional differences, normalization (scaling the features to between 0 and 1) is performed.

[0068] Calculate user regulation participation rate and regulation completion rate.

[0069]

[0070] The user historical load regulation data in this embodiment is processed, and the processed data is as follows:

[0071] Table 3 Historical load control record processing results

[0072]

[0073] (3) Define the relationship between the variable terms of each eigenvalue of the function:

[0074] Table 4 Relationship between variable items and data items

[0075]

[0076]

[0077] First-order: maximum controllable load X4 (the user's maximum controllable load directly affects the rationality of load distribution and the user's completion ability. It has a different effect from other data items and is not affected by other data items. Therefore, it serves as an independent first-order item in the polynomial), control participation rate X5 (the user's control participation rate directly affects the user's load control response and completion. It has a different effect from other data items and is not affected by other data items. Therefore, it serves as an independent first-order item in the polynomial), and control completion degree X6 (the user's historical control completion degree serves as a reference and direct judgment condition for the user's load control completion status. It has a different effect from other data items and is not affected by other items. Therefore, it serves as an independent first-order item in the polynomial).

[0078] Third order: X1, X2 and X3 (the various data items in the user's basic information jointly affect the load regulation capacity and response capacity basis, and therefore together constitute the third-order terms of the polynomial).

[0079] Level 4: X7, X8, X9 and X 10 (The various data items in the time and environmental factors jointly affect the user's ability to control the execution of the task each time, and therefore together constitute the fourth-order term of the polynomial).

[0080] The programming library scikit-learn uses the least squares method to automatically complete the fitting of the function order coefficients.

[0081] The polynomial regression model for outputting the user's control response completion ability is:

[0082] Y=0.001836X4+0.0171X5+0.0203X6+0.00133X1X2X3+

[0083] 0.00128X7X8X9X 10

[0084] The control response completion capability of each user is calculated through the polynomial regression model, as shown in the following table:

[0085] Table 5 Control response completion capability of each user

[0086]

[0087] S21: The total demand for this regulation is 860 kW. Based on the participating users' response and completion capabilities, the following formula is used to make a preliminary distribution of the regulated load.

[0088]

[0089] Table 6 User Control Response Completion Capacity Load Distribution of Each User (First Power Load Control Amount)

[0090]

[0091] S22, calculate the actual adjustable load P of the participating users d .

[0092] P dk =P rk -P mink

[0093] Table 7 Load data of each user

[0094]

[0095]

[0096] S23, performing secondary distribution of the regulated load according to the regulated load amounts of the participating users.

[0097]

[0098] Table 8 Distribution of Controllable Load Amounts for Each User (Second Power Load Control Amount)

[0099]

[0100] S24, make the final load control amount allocation for the user based on the two allocation results. Compare the load allocated by the user's control response completion capability with the user's controllable load amount:

[0101]

[0102] Table 9 Load of each user

[0103]

[0104] In summary, the load control and allocation optimization method for power demand management provided by this invention accurately describes the relationship between load and various factors by constructing a polynomial function. As user control tasks are completed, the nonlinear regression model is automatically iteratively optimized. This allows for more accurate analysis of user control response capabilities based on load user information, time and environmental factors, and historical load control records. By comparing the relationship between user controllable loads, the rationality of control allocation is optimized, continuously improving the completion of control tasks while ensuring that basic user electricity consumption is not affected.

[0105] In an embodiment of the present invention, a device for optimizing the distribution of power load control quantity is also provided. The device is used to implement the above-mentioned embodiments and preferred embodiments, and the details that have been described will not be repeated. The terms "module", "unit", "sub-unit", etc. used below can be a combination of software and / or hardware that implements the predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, implementation by hardware, or a combination of software and hardware, is also possible and conceivable.

[0106] The power load control quantity distribution optimization device includes:

[0107] The control completion calculation module is used to determine the control response completion capability of each load user through a pre-built polynomial regression model. The polynomial regression model is:

[0108] Y=β1X4+β2X5+β3X6+β4X1X2X3+β5X7X8X9X 10

[0109] Among them, Y represents the control response completion capability, β1, β2, β3, β4 and β5 represent the first coefficient, the second coefficient, the third coefficient, the fourth coefficient and the fifth coefficient respectively, X1, X2 and X3 represent the power consumption nature, load type and control mode of the load user respectively, X4, X5 and X6 represent the historical maximum controllable load, historical control participation rate and historical control completion degree of the load user respectively, X7, X8, X9 and X1 represent the load user's historical maximum controllable load, historical control participation rate and historical control completion degree respectively, 10 They represent holiday status, weather, temperature and control time period respectively;

[0110] The load distribution module is used to distribute the power load regulation amount to each load user according to the regulation response completion capability of each load user.

[0111] In the above technical solution, the load user's control response completion capability is mainly calculated through a polynomial regression model, and information such as the load user's electricity consumption characteristics and load type is used as one of the variables of the polynomial regression model. Then, the power load control quantity allocation optimization method can jointly allocate power load control quantities to various fields and various types of load users, rather than only allocating power load control quantities to a certain field or a certain type of load user. In this way, the power load control quantities of various load users can be fully coordinated to avoid the problem of uneven distribution of power load control quantities between different fields or different types of load users. In summary, the present invention solves the problem that the existing power load control quantity allocation method cannot comprehensively coordinate the allocation of various types of power load control quantities.

[0112] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0113] In an embodiment of the present invention, a load regulation platform is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the power load regulation quantity distribution optimization method provided by the present invention.

[0114] An embodiment of the present invention further provides an electric load management system, comprising the load regulation platform provided by the present invention, wherein the load regulation platform is deployed at the master station side of the electric load management system.

[0115] An embodiment of the present invention further provides a method for managing power load, including:

[0116] The power load regulation quantity distribution optimization method provided by the present invention is used to distribute the power load regulation quantity to each load user.

[0117] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0118] Obviously, the accompanying drawings are merely examples or embodiments of the present application. A person skilled in the art can also apply the present application to other similar situations based on these drawings without inventive effort. Furthermore, it is understandable that, although the work involved in this development process may be complex and lengthy, certain design, manufacturing, or production changes based on the technical content disclosed in this application are merely routine technical means for a person skilled in the art and should not be considered to constitute a deficiency in the disclosure of the present application.

Claims

1. A method for optimizing the distribution of power load control quantity, characterized in that: include: The control response completion capability of each load user is determined by a pre-built polynomial regression model, which is: Y=β1X4+β2X5+β3X6+β4X1X2X3+β5X7X8X9X 10 Among them, Y represents the control response completion capability, β1, β2, β3, β4 and β5 represent the first coefficient, the second coefficient, the third coefficient, the fourth coefficient and the fifth coefficient respectively, X1, X2 and X3 represent the power consumption nature, load type and control mode of the load user respectively, X4, X5 and X6 represent the maximum controllable load, control participation rate and control completion degree of the load user respectively, X7, X8, X9 and X1 represent the load user's maximum controllable load, control participation rate and control completion degree respectively, 10 They represent holiday status, weather, temperature and control time period respectively; The first power load regulation amount of each load user is calculated according to the regulation response completion capability of each load user, and the calculation formula is as follows: Among them, P Yk represents the first power load control quantity of the kth load user, P A represents the total demand for power load regulation, Y k and Y i They represent the control response completion capabilities of the kth and ith load users respectively, and n represents the total number of load users; Calculate the actual controllable load of each load user using the following formula: P dk =P rk -P mink Among them, P dk 、P rk and P mink They represent the actual controllable load, real-time load and minimum operating load of the k-th load user respectively; The second power load control amount of each load user is calculated based on the actual controllable load amount of each load user, and the calculation formula is as follows: Among them, P wk represents the second power load control quantity of the kth load user, P di represents the actual adjustable load of the i-th load user; The final power load control amount of each load user is determined based on the first power load control amount and the second power load control amount of each load user. The final power load control amount of each load user is determined by the following formula: Among them, P fk Represents the final power load regulation amount of the k-th load user.

2. The power load control quantity allocation optimization method according to claim 1 is characterized in that: The first coefficient, the second coefficient, the third coefficient, the fourth coefficient and the fifth coefficient are obtained by fitting historical data using the least squares method.

3. The power load control quantity allocation optimization method according to claim 2 is characterized in that: Also includes: The first coefficient, the second coefficient, the third coefficient, the fourth coefficient, and the fifth coefficient are updated in real time.

4. The power load control quantity allocation optimization method according to claim 1, characterized in that: The nature of electricity consumption is divided into industrial, commercial and residential; The regulation participation rate is the ratio of the number of participation regulations to the number of demand regulations; The degree of control completion is the ratio of the load control completion amount to the total load control demand.

5. A power load control quantity distribution optimization device, characterized in that: include: The control completion calculation module is used to determine the control response completion capability of each load user through a pre-built polynomial regression model. The polynomial regression model is: Y=β1X4+β2X5+β3X6+β4X1X2X3+β5X7X8X9X 10 Among them, Y represents the control response completion capability, β1, β2, β3, β4 and β5 represent the first coefficient, the second coefficient, the third coefficient, the fourth coefficient and the fifth coefficient respectively, X1, X2 and X3 represent the power consumption nature, load type and control mode of the load user respectively, X4, X5 and X6 represent the historical maximum controllable load, historical control participation rate and historical control completion degree of the load user respectively, X7, X8, X9 and X1 represent the load user's historical maximum controllable load, historical control participation rate and historical control completion degree respectively, 10 They represent holiday status, weather, temperature and control time period respectively; The load distribution module is configured to calculate the first power load regulation amount of each load user according to the regulation response completion capability of each load user, and the calculation formula is as follows: Among them, P Yk represents the first power load control quantity of the kth load user, P A represents the total demand for power load regulation, Y k and Y i They represent the control response completion capabilities of the kth and ith load users respectively, and n represents the total number of load users; Furthermore, the load distribution module is further configured to calculate the actual controllable load of each load user, using the following formula: P dk =P rk -P mink Among them, P dk 、P rk and P mink They represent the actual controllable load, real-time load and minimum operating load of the k-th load user respectively; Furthermore, the load distribution module is further configured to calculate the second power load control amount of each load user according to the actual controllable load amount of each load user, and the calculation formula is as follows: Among them, P wk represents the second power load control quantity of the kth load user, P di represents the actual adjustable load of the i-th load user; Furthermore, the load distribution module is further configured to determine a final power load control amount for each load user based on the first power load control amount and the second power load control amount for each load user. The formula for determining the final power load control amount for each load user is as follows: Among them, P fk Represents the final power load regulation amount of the k-th load user.

6. A load control platform, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the power load control quantity distribution optimization method according to any one of claims 1 to 4.

7. A power load management system, characterized in that: It includes the load regulation platform described in claim 6, and the load regulation platform is deployed on the master station side of the power load management system.

8. A method for managing power load, characterized in that: include: The power load regulation quantity is distributed to each load user by using the power load regulation quantity distribution optimization method described in any one of claims 1-4.

Images