A method, device and medium for regulating and optimizing user electrical load

Abstract

The present invention relates to a method, device and medium for regulating and optimizing user power consumption load, belonging to the technical field of power consumption load regulation, and includes the following steps: obtaining user power consumption load related data for a period to be regulated; using the user power consumption load related data as the input of a random forest algorithm to output the predicted value of the user power consumption load for the period to be regulated; obtaining the user's historical power consumption load, using the user's historical power consumption load and the predicted value of the user power consumption load for the period to be regulated as the input of the clustering algorithm K-means, and determining the power consumption mode of the predicted value of the user power consumption load according to the clustering result; obtaining the load regulation amount of the user power consumption load for the period to be regulated based on the power consumption mode; regulating the user power consumption load based on the load regulation amount; analyzing the reliability of the regulated user power consumption load and optimizing the load regulation amount, and regulating the user power consumption load based on the optimized load regulation amount. The present invention can effectively improve power consumption efficiency.

Description

Technical Field

[0001] The present invention relates to a method, device, and medium for regulating and optimizing user power consumption load, and belongs to the technical field of power consumption load regulation. Background Art

[0002] With the development of social economy and the continuous improvement of people's living standards, electricity plays a crucial role in various fields, and the regulation and optimization of power consumption load have become a key link in the stable operation and efficient management of the power system. The load regulation of traditional power systems mainly relies on adjustments on the power generation side, by increasing or decreasing the output power of generator sets to adapt to load changes. However, with the continuous expansion of the power market scale and the increasing complexity of the power consumption structure, such traditional load regulation methods have gradually revealed many defects and deficiencies.

[0003] The prior art, such as the Chinese patent application with the publication number CN116776040A, discloses a method, device, equipment, and medium for calculating load regulation potential, including the following steps: performing clustering processing on the preprocessed historical load of users to obtain the number of clusters c, cluster Ci, and the center μi of the i-th cluster; taking the cluster Ci as the daily load curve set of the i-th user power consumption pattern; calculating the regulation daily load baseline of the current user, and according to the regulation daily load baseline and the centers μi of each cluster Ci, calculating the membership degree of the regulation daily load baseline belonging to each cluster Ci, and obtaining the cluster to which the regulation daily load baseline of the current user belongs and the corresponding user power consumption pattern according to the membership degree; calculating the most likely regulation amount and the maximum adjustable amount according to the adjustable potential quantification calculation model under different power consumption pattern switches, the regulation daily load baseline, and the corresponding user power consumption pattern. However, after calculating the most likely regulation amount and the maximum adjustable amount, the above patent does not analyze and evaluate the reliability of the adjusted daily power consumption load of users. This means that in practical applications, there may be a risk that the adjusted load cannot meet the power supply reliability requirements, thus affecting the safe and stable operation of the power grid. And the above patent mainly determines the load regulation amount based on the clustering results and membership degrees. Although it can reflect the differences in user power consumption patterns to a certain extent, it does not consider some special situations or complex factors enough, which may lead to insufficient calculation accuracy of the regulation amount. Summary of the Invention

[0004] In order to solve the problems existing in the above prior art, the present invention proposes a method, device, and medium for regulating and optimizing user power consumption load.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, the present invention provides a method for regulating and optimizing user power consumption load, including the following steps:

[0007] Obtain the user's electricity load-related data for the period to be adjusted;

[0008] Use the user's electricity load-related data as the input of the random forest algorithm, and output the predicted value of the user's electricity load for the period to be adjusted;

[0009] Obtain the user's historical electricity load, use the user's historical electricity load and the predicted value of the user's electricity load for the period to be adjusted as the input of the K-means clustering algorithm, and determine the electricity consumption pattern of the predicted value of the user's electricity load according to the clustering result;

[0010] Obtain the load adjustment amount of the user's electricity load for the period to be adjusted based on the electricity consumption pattern;

[0011] Adjust the user's electricity load based on the load adjustment amount;

[0012] Analyze the reliability of the adjusted user's electricity load. If it is less than the lowest acceptable reliability threshold, optimize the load adjustment amount based on the reliability, and adjust the user's electricity load based on the optimized load adjustment amount.

[0013] Preferably, the user's electricity load-related data includes meteorological data, date type, and electricity consumption data;

[0014] The meteorological data includes temperature, humidity, and wind speed;

[0015] The date type includes weekdays and holidays;

[0016] The electricity consumption data includes current and voltage.

[0017] Preferably, using the user's electricity load-related data as the input of the random forest algorithm and outputting the predicted value of the user's electricity load for the period to be adjusted is expressed by the formula:

[0018] ;

[0019] In the formula, represents the predicted value of the user's electricity load for the period to be adjusted , represents the user's electricity load-related data for the period to be adjusted , represents the total number of decision trees represents the decision tree index represents the th decision tree.

[0020] Preferably, using the user's historical electricity load and the predicted value of the user's electricity load for the period to be adjusted as the input of the K-means clustering algorithm, and determining the electricity consumption pattern of the predicted value of the user's electricity load according to the clustering result, the specific steps are as follows:

[0021] Obtain the user's historical electricity load, and obtain the user's electricity consumption index based on the user's historical electricity load;

[0022] Normalize the user's electricity consumption index using the forward normalization method based on Min - Max scaling;

[0023] Pre - define the types of electricity consumption patterns, obtain the electricity consumption pattern of the user's historical electricity load, and obtain the index vector of the user's electricity consumption index based on the user's historical electricity load;

[0024] Among them, the types of electricity consumption patterns include double - peak pattern, single - peak pattern, and smooth pattern;

[0025] Take the index vector and the predicted value of the user's electricity load as the input of the K - means clustering algorithm to obtain the clustering result, and confirm the electricity consumption pattern of the predicted value of the user's electricity load according to the clustering result.

[0026] Preferably, based on the electricity consumption pattern, obtain the load adjustment amount of the user's electricity load in the period to be adjusted. The specific steps are as follows:

[0027] Construct a historical load curve based on the user's historical electricity load;

[0028] Obtain the load fluctuation range of the historical load curve, which is expressed by the formula:

[0029] ;

[0030] In the formula, represents the load fluctuation range of the historical load curve in the period to be adjusted , represents the maximum value of the historical load curve of the historical load curve in the period to be adjusted , represents the minimum value of the historical load curve of the historical load curve in the period to be adjusted ;

[0031] Determine the average electricity load corresponding to the electricity consumption pattern of the predicted value of the user's electricity load in the period to be adjusted , and based on the average electricity load obtain the deviation between the predicted value of the user's electricity load in the period to be adjusted and the average electricity load , which is expressed by the formula; ;

[0032] ;

[0033] In the formula, represents the deviation in the period to be adjusted User electricity load forecast value With the average electricity load Deviation;

[0034] Determine the time period to be adjusted based on the deviation and the load fluctuation range of the historical load curve Load adjustment range , expressed as:

[0035] ;

[0036] Where, Indicates that the adjustment period is pending The upper limit of the load adjustment range, represents the minimum function;

[0037] Based on the period to be adjusted Load adjustment range Get the time to be adjusted The load regulation capacity is expressed as follows:

[0038] ;

[0039] Where, Indicates that the adjustment period is pending The load regulation amount, Indicates adjustment gear position.

[0040] Preferably, the user's electricity load is adjusted based on the load adjustment amount, which is expressed as follows:

[0041] ;

[0042] Where, Indicates the period of adjustment after adjustment User electricity load.

[0043] Preferably, the method further includes a user power load adjustment method:

[0044] Shifting loads from high electricity price periods to low electricity price periods;

[0045] Reduce or increase the user's electricity load.

[0046] Preferably, the reliability of the adjusted user power load is analyzed, and if it is less than a minimum acceptable reliability threshold, the load adjustment amount is optimized based on the reliability, specifically in the following steps:

[0047] The reliability of the user's power load after adjustment is analyzed and expressed as follows:

[0048] ;

[0049] In the formula, represents the power consumption mode as the adjustment gear when the reliability of the user's power consumption load, represents the period to be adjusted the quantity of;

[0050] Optimize the load adjustment amount based on the reliability, and the specific steps are as follows:

[0051] Let the lowest acceptable threshold of reliability be ;

[0052] If , then perform upshift and downshift operations on the adjustment gear respectively, and calculate the reliability after the upshift or downshift operation of the adjustment gear ;

[0053] If the reliability after upshifting the adjustment gear is greater than the reliability before upshifting the adjustment gear , then the adjustment gear continues to upshift. If the reliability after downshifting the adjustment gear is greater than the reliability before downshifting the adjustment gear , then the adjustment gear continues to downshift; until the reliability is greater than or equal to the lowest acceptable threshold of reliability .

[0054] On the other hand, the present invention also provides an electronic device, on which a computer program is stored, and when the computer program is executed by a processor, it implements the user power consumption load adjustment and optimization method as described in any embodiment of the present invention.

[0055] On the other hand, the present invention also provides a computer-readable storage medium for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the user power consumption load adjustment and optimization method as described in any embodiment of the present invention.

[0056] The present invention has the following beneficial effects:

[0057] 1. By obtaining the user power consumption load-related data of the period to be adjusted, including multi-dimensional information such as meteorological data (temperature, humidity, wind speed), date type (weekday and holiday), and power consumption data (current and voltage), and inputting these data into the random forest algorithm, the present invention can more accurately predict the user power consumption load of the period to be adjusted.

[0058] 2. The present invention determines the user's electricity consumption pattern as a bimodal pattern, a unimodal pattern, or a smooth pattern by performing cluster analysis on the user's historical electricity load and the predicted value of the user's electricity load during the period to be adjusted. The load adjustment amount of the user's electricity load during the period to be adjusted is obtained according to different electricity consumption patterns, and this method can perform personalized adjustment according to the load characteristics of different users.

[0059] 3. After adjusting the user's electricity load based on the load adjustment amount, the present invention also analyzes the reliability of the adjusted user's electricity load. If the reliability is lower than the set minimum acceptance threshold, the adjustment gear will be adjusted through upshift and downshift operations until the reliability meets the requirements. This process can effectively avoid the risk that the adjusted load cannot meet the power supply reliability requirements and ensure the safe and stable operation of the power grid.

[0060] 4. The user's electricity load adjustment method of the present invention includes various methods such as transferring the load during high electricity price periods to low electricity price periods and reducing or increasing the user's electricity load. This provides flexible adjustment means for power system operators. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a flowchart of the implementation of the method of the present invention.

[0062] Figure 2 is a graph of the user's electricity load of the present invention.

[0063] Figure 3 is a graph of the upper limit of the load adjustment range of the present invention.

[0064] Figure 4 is a graph of the load adjustment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] 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 a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0066] It should be understood that the step numbers used in the text are only for convenient description and do not limit the execution order of the steps.

[0067] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless otherwise clearly specified in the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0068] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0069] The term "and / or" refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0070] Example 1:

[0071] See Figure 1 , this embodiment provides a method for regulating and optimizing user power consumption load, including the following steps:

[0072] Obtain user power consumption load-related data for the period to be regulated;

[0073] Use the user power consumption load-related data as the input of the random forest algorithm, and output the predicted value of the user power consumption load for the period to be regulated;

[0074] Obtain the user's historical power consumption load, use the user's historical power consumption load and the predicted value of the user's power consumption load for the period to be regulated as the input of the clustering algorithm K-means, and determine the power consumption pattern of the predicted value of the user's power consumption load according to the clustering result;

[0075] Obtain the load regulation amount of the user's power consumption load for the period to be regulated based on the power consumption pattern;

[0076] Regulate the user's power consumption load based on the load regulation amount;

[0077] Analyze the reliability of the regulated user power consumption load. If it is less than the lowest acceptable reliability threshold, optimize the load regulation amount based on the reliability, and regulate the user power consumption load based on the optimized load regulation amount.

[0078] Preferably, the user power consumption load-related data includes meteorological data, date type, and power consumption data;

[0079] The meteorological data includes temperature, humidity, and wind speed;

[0080] The date type includes weekdays and holidays;

[0081] The power consumption data includes current and voltage.

[0082] Preferably, using the user power consumption load-related data as the input of the random forest algorithm and outputting the predicted value of the user power consumption load for the period to be regulated is expressed by the formula:

[0083] ;

[0084] In the formula, represents the predicted value of the user's electricity load during the period to be adjusted, and represents the relevant data of the user's electricity load during the period to be adjusted, ; represents the total number of decision trees, represents the decision tree index, and represents the

[0085] Preferably, the user's historical electricity load and the predicted value of the user's electricity load during the period to be adjusted are used as the input of the K-means clustering algorithm, and the electricity consumption pattern of the predicted value of the user's electricity load is determined according to the clustering result. The specific steps are as follows:

[0086] Obtain the user's historical electricity load, including peak load, valley load, average load, and electricity consumption in different time dimensions;

[0087] Obtain the user's electricity consumption indicators based on the user's historical electricity load, including electricity load volatility, peak-valley difference rate, daily load rate, peak load rate, average load rate, valley period load rate, peak period duration, and load up and down ramp rate;

[0088] Normalize the user's electricity consumption indicators based on the forward normalization method of Min-Max scaling, which is expressed by the formula:

[0089] ;

[0090] In the formula, represents the normalized user's electricity consumption indicator, represents the user's electricity consumption indicator before normalization, represents the minimum value of the user's electricity consumption indicator, represents the maximum value of the user's electricity consumption indicator;

[0091] Pre-define the types of electricity consumption patterns, and obtain the electricity consumption patterns of the user's historical electricity load through the technical personnel's empirical analysis. Based on the user's historical electricity load, obtain the indicator vector of the user's electricity consumption indicators;

[0092] Among them, the types of electricity consumption patterns include double-peak pattern, single-peak pattern, and smooth pattern;

[0093] Use the indicator vector and the predicted value of the user's electricity load as the input of the K-means clustering algorithm to obtain the clustering result, and confirm the electricity consumption pattern of the predicted value of the user's electricity load according to the clustering result.

[0094] In one implementation, the power consumption pattern of the user's predicted power consumption load is confirmed according to the clustering result, specifically as follows:

[0095] Obtain the power consumption pattern corresponding to the index vector of the cluster to which the user's predicted power consumption load belongs;

[0096] Take the power consumption pattern with the largest quantity in the cluster as the power consumption pattern of the user's predicted power consumption load, that is, the power consumption pattern during the period to be adjusted.

[0097] Preferably, the load adjustment amount of the user's power consumption load during the period to be adjusted is obtained based on the power consumption pattern, and the specific steps are as follows:

[0098] Construct a historical load curve based on the user's historical power consumption load;

[0099] Obtain the load fluctuation range of the historical load curve, which is expressed by the formula:

[0100] ;

[0101] In the formula, represents the load fluctuation range of the historical load curve during the period to be adjusted , represents the maximum value of the historical load curve of the historical load curve during the period to be adjusted , represents the minimum value of the historical load curve of the historical load curve during the period to be adjusted ;

[0102] Determine the average power consumption load corresponding to the power consumption pattern of the user's predicted power consumption load during the period to be adjusted , and obtain the deviation between the user's predicted power consumption load during the period to be adjusted and the average power consumption load based on the average power consumption load ; In the formula,

[0103] ;

[0104] In the formula, represents the deviation between the user's predicted power consumption load during the period to be adjusted and the average power consumption load ;

[0105] Based on the deviation and the load fluctuation range of the historical load curve, determine the load adjustment range during the period to be adjusted , which is expressed by the formula:

[0106] ;

[0107] Where, Indicates that the adjustment period is pending The upper limit of the load adjustment range, represents the minimum function;

[0108] Based on the period to be adjusted Load adjustment range Calculated during the adjustment period The load regulation capacity is expressed as follows:

[0109] ;

[0110] Where, Indicates that the adjustment period is pending The load regulation amount, Indicates adjustment gear position.

[0111] Preferably, the user's electricity load is adjusted based on the load adjustment amount, which is expressed as follows:

[0112] ;

[0113] Where, Indicates the period of adjustment after adjustment User electricity load.

[0114] In at least one embodiment, the average power load in single peak mode is 195kw, the average power load in double peak mode is 230kw, and the average power load in smooth mode is 280kw. Including 10%, 20%, and 50%.

[0115] Preferably, the method further includes a user power load adjustment method:

[0116] Shifting loads from high electricity price periods to low electricity price periods;

[0117] Reduce or increase the user's electricity load.

[0118] Preferably, the reliability of the adjusted user power load is analyzed, and if it is less than a minimum acceptable reliability threshold, the load adjustment amount is optimized based on the reliability, specifically in the following steps:

[0119] The reliability of the user's power load after adjustment is analyzed and expressed as follows:

[0120] ;

[0121] Where, Indicates the power usage mode is Adjust the gear The reliability of the user's electricity load Indicates the number of time periods to be adjusted ;

[0122] Optimize the load adjustment amount based on the reliability. The specific steps are as follows:

[0123] Let the lowest acceptable reliability threshold be ;

[0124] If , then perform upshift and downshift operations on the adjustment gears respectively, and calculate the reliability after the upshift or downshift operation of the adjustment gear ;

[0125] If the reliability after upshifting the adjustment gear is greater than the reliability before upshifting the adjustment gear , then continue to upshift the adjustment gear . If the reliability after downshifting the adjustment gear is greater than the reliability before downshifting the adjustment gear , then continue to downshift the adjustment gear until the reliability is greater than or equal to the lowest acceptable reliability threshold .

[0126] Implementation scenario: Precise load control for aluminum profile processing enterprises

[0127] An aluminum profile processing enterprise has a daily power consumption of about 1700 kWh and belongs to a single-peak mode. The production peak period is from 07:00 to 17:00 on weekdays, and the load fluctuates between 150 - 350 kW. The main production equipment of this enterprise includes extrusion machines, anodizing lines, spraying lines, heat treatment furnaces, etc. Some of the equipment has a certain production flexibility and can adjust the load without affecting product quality and delivery time.

[0128] Implementation steps:

[0129] 1. Conduct a prediction of the user's electricity load for the time period to be adjusted: Obtain relevant data on the user's electricity load for the time period to be adjusted, and make a prediction based on the random forest algorithm. The prediction results are shown in Figure 2 .

[0130] 2. Classify the electricity consumption pattern: Obtain the user's electricity consumption indicators, and use the K-means clustering algorithm to classify the enterprise's load curve into a single-peak mode. The judgment criterion is that the load rises rapidly during working hours, remains high from 8:15 to 15:00, and gradually decreases in the afternoon.

[0131] 3. Analyze the adjustable capacity: Refer to Figure 3 , and based on the user's historical electricity load, obtain the upper limit of the load adjustment range at each moment 。

[0132] 4. Refer to Figure 4 and set the adjustment to 50% for adjustment, and obtain the reliability of the user's electricity load at this adjustment level to be 99.92%, which is greater than the minimum acceptable threshold of reliability of 99%. Therefore, adjust according to this level.

[0133] Example 2:

[0134] This example provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the user electricity load adjustment and optimization method as described in any embodiment of the present invention.

[0135] Example 3:

[0136] This example provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the user electricity load adjustment and optimization method as described in any embodiment of the present invention.

[0137] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent the situation where A exists alone, A and B exist simultaneously, or B exists alone. Where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0138] Those of ordinary skill in the art can realize that the various units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0139] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0140] In several embodiments provided by the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0141] The above are only the embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for regulating and optimizing user electrical load, characterized in that It includes the following steps: Obtain the user's electricity load-related data for the period to be adjusted; Take the user's electricity load-related data as the input of the random forest algorithm and output the predicted value of the user's electricity load for the period to be adjusted; Obtain the user's historical electricity load, take the user's historical electricity load and the predicted value of the user's electricity load for the period to be adjusted as the input of the K-means clustering algorithm, and determine the electricity consumption pattern of the predicted value of the user's electricity load according to the clustering result. The specific steps are as follows: Obtain the user's historical electricity load and obtain the user's electricity consumption index based on the user's historical electricity load; Normalize the user's electricity consumption index by the forward normalization method based on Min-Max scaling; Pre-define the types of electricity consumption patterns, obtain the electricity consumption patterns of the user's historical electricity load, and obtain the index vector of the user's electricity consumption index based on the user's historical electricity load; Among them, the types of electricity consumption patterns include bimodal pattern, unimodal pattern and smooth pattern; Take the index vector and the predicted value of the user's electricity load as the input of the K-means clustering algorithm to obtain the clustering result, and confirm the electricity consumption pattern of the predicted value of the user's electricity load according to the clustering result; Obtain the load adjustment amount of the user's electricity load for the period to be adjusted based on the electricity consumption pattern. The specific steps are as follows: Construct a historical load curve based on the user's historical electricity load; Obtain the load fluctuation range of the historical load curve, which is expressed by the formula: ； Wherein, represents the load fluctuation range of the historical load curve during the period to be adjusted , represents the maximum value of the historical load curve of the historical load curve during the period to be adjusted , represents the minimum value of the historical load curve of the historical load curve during the period to be adjusted . Determine the average power consumption load corresponding to the power consumption pattern of the predicted value of the user's power consumption load during the period to be adjusted Based on the average power consumption load Obtain the predicted value of the user's power consumption load during the period to be adjusted The deviation from the average power consumption load Is expressed by the formula: And the average power consumption load ​ ； In the formula, represents the predicted value of the user's electricity load during the period to be adjusted and the deviation from the average electricity load ; Determine the period to be adjusted based on the deviation and the load fluctuation range of the historical load curve for the load adjustment range , which is expressed by the formula: ； In the formula, represents the upper limit of the load adjustment range during the period to be adjusted , and represents the minimum value function. Based on the period to be adjusted Load adjustment range Obtain the load adjustment capacity during the period to be adjusted which is expressed by the formula as follows: ； In the formula, represents the load regulation amount during the period to be adjusted, represents the adjustment gear; Adjust the user's electricity load based on the load adjustment amount, which is expressed by the formula: ； In the formula, represents the adjusted user power load during the period to be adjusted ; Analyze the reliability of the adjusted user's electricity load. If it is less than the lowest acceptable threshold of reliability, optimize the load adjustment amount based on the reliability, and adjust the user's electricity load based on the optimized load adjustment amount.

2. The user power load regulation and optimization method according to claim 1, characterized in that The user's electricity load-related data includes meteorological data, date type and electricity consumption data; The meteorological data includes temperature, humidity and wind speed; The date type includes working days and holidays; The electricity consumption data includes current and voltage.

3. The user power load regulation and optimization method according to claim 1, characterized in that Taking the user's electricity load-related data as the input of the random forest algorithm and outputting the predicted value of the user's electricity load for the period to be adjusted is expressed by the formula: ； In the formula, represents the user's electricity load related data during the period to be adjusted , represents the total number of decision trees represents the decision tree index represents the th decision tree 4. The user power load regulation and optimization method according to claim 1, characterized in that The method also includes a method for adjusting the user's electricity load: Transfer the load during high electricity price periods to low electricity price periods; Cut or increase the user's electricity load.

5. The user power load regulation and optimization method according to claim 1, characterized in that Analyze the reliability of the adjusted user's electricity load. If it is less than the lowest acceptable threshold of reliability, optimize the load adjustment amount based on the reliability. The specific steps are as follows: Analyze the reliability of the adjusted user's electricity load, which is expressed by the formula: ； Wherein, indicates that the power consumption mode is when adjusting the gear the reliability of the user's power consumption load, indicates the number of time periods to be adjusted ; Optimize the load adjustment amount based on the reliability. The specific steps are as follows: Let the minimum acceptable reliability threshold be ; If , perform upshifting and downshifting operations on the adjustment gears respectively, and calculate the reliability after the upshifting or downshifting operation of the adjustment gear . If the adjustment gear The reliability after upshifting is greater than the adjustment gear The reliability before upshifting, then adjust the gear Continue to upshift. If the adjustment gear The reliability after downshifting is greater than the adjustment gear The reliability before downshifting, then adjust the gear Continue to downshift; until the reliability is greater than or equal to the lowest acceptable reliability threshold .

6. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the user's electricity load adjustment and optimization method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the user's electricity load adjustment and optimization method according to any one of claims 1 to 5.

Images