Method and device for determining power consumption load level, electronic equipment and storage medium

Abstract

The application provides a power consumption load level determination method and device, electronic equipment and storage medium, relates to the technical field of big data, and the method comprises the following steps: acquiring power consumption data of a to-be-tested object; acquiring a first mean value and a first standard deviation of each power consumption in the power consumption data; determining each power consumption threshold value according to the first mean value, the first standard deviation and an initial setting coefficient corresponding to at least one power consumption threshold value; and determining a target power consumption load level of the to-be-tested object in a target period according to each power consumption threshold value and the power consumption in the target period. In summary, each power consumption threshold value is determined based on the statistical information of the power consumption data of the to-be-tested object in multiple periods, instead of being fixedly set, so that the accuracy and rationality of the target power consumption load level determination can be improved. Moreover, the power consumption of the to-be-tested object in at least one target period does not need to be forcibly divided into all power consumption load levels, so that the accuracy of the division result (i.e. the target power consumption load level) can be improved.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to a method, apparatus, electronic device and storage medium for determining power load levels. Background Technology

[0002] In the power industry, it is often necessary to classify the electricity load levels of enterprises. For example, the electricity load levels of enterprises are generally divided into the following five levels: production stoppage, low-level normal production, medium-level normal production, high-level normal production, and high-load production. By analyzing the changes in the electricity load level of an enterprise over a period of time, it can be determined whether the enterprise has stopped production, resumed production, or experienced production abnormalities, thereby enabling further supervision.

[0003] In related technologies, K-means clustering (e.g., 5-means) is used to determine the daily electricity load level of enterprises. However, since the value of K is difficult to determine, it is easy to classify similar points (i.e., daily electricity consumption) into different category levels, making it difficult to guarantee the accuracy of the determination of the enterprise's electricity load level. Furthermore, K-means clustering will forcibly divide the enterprise's electricity load level into K groups, resulting in low accuracy of the classification results.

[0004] For example, if a company's electricity consumption has been relatively stable over a long period of time, meaning that the company's electricity consumption has always been relatively stable, and the company's electricity load level is within the range of low-level normal production, medium-level normal production, or high-level normal production, then the K-means clustering algorithm will forcibly divide the company's electricity load level into two electricity load levels: shutdown and high-load production, resulting in a large difference between the classification result and the expected result. Summary of the Invention

[0005] The purpose of this application is to at least partially solve one of the aforementioned technical problems.

[0006] Therefore, this application proposes a method, apparatus, electronic device and storage medium for determining the power load level, so as to improve the accuracy and rationality of determining the power load level of the object under test.

[0007] The first aspect of this application proposes a method for determining the electricity load level, including:

[0008] Acquire the electricity consumption data of the object under test; wherein the electricity consumption data includes the electricity consumption for at least one time period;

[0009] Obtain at least one first mean and a first standard deviation of the said electricity consumption;

[0010] The at least one power consumption threshold is determined based on the first mean, the first standard deviation, and the initial setting coefficient corresponding to at least one power consumption threshold.

[0011] Based on the at least one power consumption threshold and the power consumption during the target period, the target power load level of the object under test is determined for the target period.

[0012] A second aspect of this application provides a device for determining electricity load levels, comprising:

[0013] The first acquisition module is used to acquire the electricity consumption data of the object under test; wherein, the electricity consumption data includes the electricity consumption for at least one time period;

[0014] The second acquisition module is used to acquire at least one first mean and a first standard deviation of the electricity consumption;

[0015] The first determining module is used to determine the at least one power consumption threshold value based on the first mean, the first standard deviation, and an initial setting coefficient corresponding to at least one power consumption threshold value.

[0016] The second determining module is used to determine the target power load level of the object under test in the target time period based on the at least one power consumption threshold value and the power consumption in the target time period.

[0017] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for determining the power load level as described in the first aspect.

[0018] The fourth aspect of this application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for determining the power load level as described in the first aspect.

[0019] A fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the method for determining the power load level described in the first aspect of this application.

[0020] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0021] By determining the electricity load level of the object under test based on at least one electricity consumption threshold, where the threshold is specifically determined based on statistical information of the object's electricity consumption data over multiple time periods rather than being fixed, the accuracy and reasonableness of the determination result can be improved. Furthermore, determining the electricity load level of the object under test based on statistical information of its electricity consumption data over multiple time periods allows for the classification of similar electricity consumption into the same load level, improving the accuracy of the classification results. Moreover, it avoids forcibly classifying the object's electricity consumption in at least one target time period into all load levels, thus improving the accuracy of the classification result (i.e., the target electricity load level).

[0022] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0023] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0024] Figure 1 A flowchart illustrating a method for determining electricity load levels provided in an embodiment of this application;

[0025] Figure 2 A flowchart illustrating another method for determining electricity load levels provided in this application embodiment;

[0026] Figure 3 A flowchart illustrating another method for determining electricity load levels provided in this application embodiment;

[0027] Figure 4 A flowchart illustrating another method for determining electricity load levels provided in this application embodiment;

[0028] Figure 5 A flowchart illustrating another method for determining electricity load levels provided in this application embodiment;

[0029] Figure 6 A flowchart illustrating another method for determining electricity load levels provided in this application embodiment;

[0030] Figure 7 A flowchart illustrating another method for determining electricity load levels provided in this application embodiment;

[0031] Figure 8 This is a schematic diagram illustrating the power consumption fluctuations within a set time window provided in an embodiment of this application.

[0032] Figure 9 This is a schematic diagram of a device for determining the power load level according to an embodiment of this application;

[0033] Figure 10 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0034] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0035] Currently, clustering algorithms (such as K-means clustering) can be used to cluster enterprise electricity consumption data to obtain the daily electricity load level of the enterprise. However, the K-means clustering algorithm has at least the following drawbacks:

[0036] Since the actual electricity consumption of enterprises may not fully cover the existing five levels, it is difficult to determine the specific value of K. If K-means clustering is forcibly performed according to K=5, the clustering result will definitely differ from the expected result, and it is easy to classify similar points (i.e., daily electricity consumption) into different level categories.

[0037] For example, if a company's electricity consumption has been relatively stable over a long period of time, meaning that the company's electricity consumption has always been relatively stable, and the company's electricity load level is within the range of low-level normal production, medium-level normal production, or high-level normal production, then if K is forcibly set to 5, the K-means clustering algorithm will forcibly divide the situation into shutdown and high-load production, resulting in a large difference between the clustering results and the expected results.

[0038] To address at least one of the aforementioned problems, embodiments of this application propose a method, apparatus, and electronic device for determining electricity load levels.

[0039] The following is combined Figure 1 This application provides a detailed explanation of the method for determining the electricity load level.

[0040] Figure 1 This is a flowchart illustrating a method for determining the power load level provided in an embodiment of this application.

[0041] The method for determining the power load level in this application embodiment can be executed by the power load level determination device provided in this application embodiment. The power load level determination device in this application can be applied to an electronic device to perform the function of determining the power load level. Alternatively, the power load level determination device can be configured in an application of the electronic device so that the application can perform the function of determining the power load level.

[0042] The electronic device can be any device with computing capabilities, and the device or the application within the device can perform the function of determining the power load level. The device with computing capabilities can be, for example, a personal computer, a mobile terminal, or a server. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, or other hardware device with various operating systems, touchscreens, and / or displays.

[0043] like Figure 1 As shown, the method for determining the electricity load level includes the following steps:

[0044] Step S101: Obtain the power consumption data of the object under test; wherein the power consumption data includes the power consumption for at least one time period.

[0045] In the embodiments of this application, the object to be measured refers to the object whose electricity load level is to be measured or determined. For example, the object to be measured can be an enterprise.

[0046] In this embodiment of the application, there is no limitation on the duration of the time period. For example, the duration of the time period can be half a day, 1 day, 2 days, 3 days, etc.

[0047] In this embodiment of the application, the power consumption of the object under test can be monitored to obtain the power consumption data of the object under test. The power consumption data may include the power consumption for at least one time period. For example, taking a time period of 1 day as an example, the power consumption data may include the daily power consumption for at least one day.

[0048] Step S102: Obtain at least one first mean and first standard deviation of electricity consumption.

[0049] In the embodiments of this application, at least one first mean of electricity consumption can be calculated, and at least one first standard deviation of electricity consumption can also be calculated.

[0050] Step S103: Determine at least one power consumption threshold value based on the first mean, the first standard deviation, and the initial setting coefficient corresponding to at least one power consumption threshold value.

[0051] In this embodiment of the application, the number of power consumption threshold values ​​is related to the number of preset power consumption load levels. For example, the number of power consumption threshold values ​​= the number of power consumption load levels - 1.

[0052] For example, when there are two power load levels, such as low-level production and high-level production, the number of power load thresholds can be one. When there are more than two power load levels, such as five power load levels, such as shutdown, low-level normal production, medium-level normal production, high-level normal production, and high-load production, the number of power load thresholds can be four.

[0053] In the embodiments of this application, at least one power consumption threshold is used to determine the corresponding power consumption range of multiple power load levels.

[0054] In this embodiment of the application, the initial setting coefficient corresponding to each power consumption threshold is a pre-set coefficient or threshold.

[0055] In this embodiment of the application, at least one power consumption threshold can be determined based on the first mean, the first standard deviation, and the initial setting coefficient corresponding to at least one power consumption threshold.

[0056] As an example, the determination of any power consumption threshold can be done as follows: the intermediate coefficient can be determined by multiplying the initial set coefficient corresponding to the power consumption threshold value with the first standard deviation, and the power consumption threshold value can be determined by the sum of the intermediate coefficient and the first mean. For example, the sum of the intermediate coefficient and the first mean can be used as the power consumption threshold value.

[0057] Step S104: Determine the target power load level of the object under test in the target time period based on at least one power consumption threshold and the power consumption in the target time period.

[0058] The target time period can be any one of the at least one time period in step S101, or it can be any time period before at least one time period in step S101, or it can be any time period after at least one time period in step S101. This application does not impose any restrictions on this.

[0059] The number of target time periods can be one or more, and this application embodiment does not limit this.

[0060] In this embodiment of the application, the electricity consumption during the target time period can be obtained, and the target electricity load level of the object under test during the target time period can be determined based on at least one electricity consumption threshold value and the electricity consumption during the target time period.

[0061] As one possible implementation method, the target electricity load level can be determined as follows: the electricity range corresponding to multiple electricity load levels can be determined based on at least one electricity threshold value, and the target electricity load level can be determined from the multiple electricity load levels based on the electricity consumption during the target period and the electricity range corresponding to the multiple electricity load levels; wherein the electricity consumption during the target period is within the electricity range corresponding to the target electricity load level.

[0062] The method for determining the electricity load level in this application embodiment involves acquiring the electricity consumption data of the object under test, and obtaining the first mean and first standard deviation of each electricity consumption in the electricity consumption data; determining at least one electricity consumption threshold value based on the first mean, the first standard deviation, and an initial setting coefficient corresponding to at least one electricity consumption threshold value; and determining the target electricity load level of the object under test in the target time period based on the at least one electricity consumption threshold value and the electricity consumption in the target time period. In summary, the at least one electricity consumption threshold value is specifically determined based on statistical information of the electricity consumption data of the object under test in multiple time periods, rather than being fixed. Determining the target electricity load level of the object under test in the target time period based on the determined electricity consumption threshold value can improve the accuracy and rationality of the determination result. Furthermore, determining the target electricity load level of the object under test in the target time period based on statistical information of the electricity consumption data of the object under test in multiple time periods can classify similar electricity consumption into the same electricity load level, improving the accuracy of the classification result. Furthermore, it eliminates the need to forcibly classify the electricity consumption of the object under test into all electricity load levels during at least one target time period, thereby improving the accuracy of the classification results (i.e., the target electricity load level).

[0063] In one possible implementation of this application, when there are multiple target time periods, the resumption status of the test object can be determined based on the target electricity load level of the test object in multiple target time periods. The following is in conjunction with... Figure 2 The above process will be explained in detail.

[0064] Figure 2 This is a flowchart illustrating another method for determining the power load level provided in an embodiment of this application.

[0065] like Figure 2 As shown, in Figure 1 Based on the illustrated embodiment, after step S104, the method for determining the electricity load level may further include the following steps:

[0066] Step S201: Encode the target electricity load level for multiple target time periods to obtain the encoded value of the target electricity load level for each target time period, wherein the multiple target time periods are located within at least two set time windows.

[0067] In this embodiment of the application, the window length of the set time window is not limited. For example, the window length of the set time window can be determined according to the duration of holidays in multiple target time periods. For example, when the multiple target time periods include May 1st Labor Day, the window length of the set time window can be 5 days. When the multiple target time periods include October 1st National Day, the window length of the set time window can be 7 days.

[0068] In the embodiments of this application, the window lengths of at least two set time windows can be the same or different, and this application does not impose any restrictions on this. For example, when the National Day holiday is included among multiple target time periods, the window length of the set time window including the National Day holiday (hereinafter referred to as time window 1) can be 7 days. The window length of the set time window adjacent to time window 1 (hereinafter referred to as time window 2) can be determined based on the duration of the working days before window 1, or the window length of time window 2 can be determined based on the duration of the working days after window 1.

[0069] In this embodiment of the application, the target electricity load level for multiple target time periods can be encoded based on the set encoding value corresponding to each electricity load level, so as to obtain the encoding value of the target electricity load level under each target time period.

[0070] For example, assuming there are N power load levels, where N is a positive integer, the setting code value corresponding to the lowest power load level can be 0, the setting code value corresponding to the second lowest power load level can be 1, ..., and the setting code value corresponding to the highest power load level can be N-1.

[0071] For example, assuming there are N power load levels, the setting code value corresponding to the lowest power load level can be 1, the setting code value corresponding to the next lowest power load level can be 2, ..., and the setting code value corresponding to the highest power load level can be N.

[0072] It should be noted that the values ​​of the set codes corresponding to the above-mentioned power load levels are only illustrative examples. In actual applications, the set codes corresponding to each power load level can also be other values. This application does not limit this. For example, the set code value corresponding to the lowest power load level can be 2, the set code value corresponding to the second lowest power load level can be 4, ..., the set code value corresponding to the highest power load level can be 2N, etc., which will not be listed here.

[0073] Step S202: Determine the production status of the object under test within the arbitrary set time window based on the encoding values ​​of each target time period within the arbitrary set time window.

[0074] In the embodiments of this application, the production status includes, but is not limited to, in-production status, shutdown status, and resumption status.

[0075] In this embodiment of the application, for any one of at least two set time windows, the production status of the object under test within the set time window can be determined based on the coding value of the target electricity load level under each target time period within the set time window.

[0076] Step S203: Determine the resumption status of the test object based on its production status within at least two set time windows.

[0077] In this embodiment of the application, the resumption status of the test object can be determined based on the production status of the test object within at least two set time windows.

[0078] In one possible implementation of this application embodiment, when there are two set time windows, it can be determined whether the production status of the first time window is in a shutdown state. If the production status of the first time window is in a shutdown state, it can be further determined whether the production status of the second time window is in a production state or a resumption state. If the production status of the second time window is in a production state or a resumption state, the resumption status of the object under test is determined to be a resumption of production. The first time window is located before the second time window.

[0079] If the production status in the first time window is in production or resumed, and / or the production status in the second time window is stopped, then the resumption status of the object under test is determined to be not a resumption of production.

[0080] In another possible implementation of this application embodiment, when the number of set time windows is three, it can be determined whether the production status of the third time window among the three set time windows is in production. If the production status of the third time window is in production, it is further determined whether the production status of the fourth time window among the three set time windows is in shutdown. If the production status of the fourth time window is in shutdown, it is further determined whether the production status of the fifth time window among the three set time windows is in resumption of work. If the production status of the fifth time window is in resumption of work, the resumption status of the object under test is determined to be resumption of production. Here, the fourth time window is after the third time window, and the fifth time window is after the fourth time window.

[0081] If the production status in the third time window is not in production, and / or the production status in the fourth time window is not in shutdown, and / or the production status in the fifth time window is not in resumption of production, then the resumption status of the object under test is determined to be not resumption of production.

[0082] In another possible implementation of this application embodiment, when the number of set time windows is at least four, it can be determined whether the production status of the sixth time window among the at least four set time windows is in production or in a resumed state. If the production status of the sixth time window is in production or in a resumed state, it can be determined whether the production status of at least one seventh time window is in a shutdown state. If the production status of at least one seventh time window is in a shutdown state, it can be determined that the resumption of work of the object under test is a resumption of production. The seventh time window is located before the sixth time window.

[0083] If the production status in the sixth time window is in a shutdown state, and / or the production status in the seventh time window is in a production state or a resumption state, then the resumption status of the object under test is determined to be not a resumption of production.

[0084] Therefore, it is possible to effectively determine the resumption status of the target object based on the specific production status within each set time window, thereby improving the effectiveness and accuracy of the determination of the resumption status.

[0085] The method for determining the power load level in this application embodiment can determine the resumption status of the test object based on the target power load level of the test object in multiple target time periods, so as to meet the actual application needs.

[0086] To clearly illustrate how step S202 in the above embodiments of this application determines the production status of the object under test within each set time window, this application also proposes a method for determining the power load level.

[0087] Figure 3 This is a flowchart illustrating another method for determining the power load level provided in an embodiment of this application.

[0088] like Figure 3 As shown, in Figure 1 Based on the illustrated embodiment, after step S104, the method for determining the electricity load level may further include the following steps:

[0089] Step S301: Encode the target electricity load level for multiple target time periods to obtain the encoded value of the target electricity load level for each target time period; wherein, the multiple target time periods are located within at least two set time windows.

[0090] The explanation of step S301 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0091] Step S302: Obtain statistical information of the encoded values ​​for each target time period within any set time window; wherein the statistical information includes at least one of the range, second mean, first encoded value, last encoded value, and median.

[0092] In the embodiments of this application, for any one of the at least two set time windows, the mean (referred to as the second mean) and range of the encoded values ​​under each target time period within the set time window can be calculated.

[0093] Furthermore, the first coded value, the last coded value, and the median of the coded values ​​for each target time period within the set time window can be obtained, and at least one of the range, the second mean, the first coded value, the last coded value, and the median can be used as statistical information of the coded values ​​for each target time period within the set time window.

[0094] Step S303: Based on statistical information, determine the power consumption fluctuation of the object under test within any set time window.

[0095] The fluctuations in electricity consumption include at least one of the following: fluctuation range, fluctuation location, and fluctuation trend.

[0096] In this embodiment of the application, the power consumption fluctuation of the object under test within the set time window can be determined based on statistical information.

[0097] In one possible implementation of this application embodiment, the method for determining electricity consumption fluctuations is, for example:

[0098] 1. Determine the fluctuation position based on the second mean.

[0099] As an example, when the second mean is within the first range, the fluctuation position is determined to be low; when the second mean is within the second range, the fluctuation position is determined to be middle; and when the second mean is within the third range, the fluctuation position is determined to be high.

[0100] The lower limit of the first value range is 0, and the upper limit of the first value range is the first target value. The first target value is determined based on the difference between the coding values ​​corresponding to the target electricity load levels of two adjacent levels. For example, when the difference between the coding values ​​corresponding to the target electricity load levels of two adjacent levels is 1 (e.g., the set coding value corresponding to the lowest electricity load level is 0, the set coding value corresponding to the next lowest electricity load level is 1, ..., and the set coding value corresponding to the highest electricity load level is N-1), the first target value can be 1.

[0101] Wherein, the lower limit of the second value range is the first target value, and the upper limit of the second value range is the second target value, wherein the second target value is a first set multiple of the first target value.

[0102] The lower limit of the third value range is the second target value, and the upper and lower limits of the third value range are the third target values. The third target value is a second set multiple of the first target value, and the second set multiple is greater than the first set multiple.

[0103] Wherein, the first set multiple and the second set multiple are both positive integers, and the first set multiple and the second set multiple are related to the number of power consumption threshold values. For example, when the number of power consumption threshold values ​​is 4, the first set multiple can be 3 and the second set multiple can be 4.

[0104] 2. Determine the fluctuation range based on the range.

[0105] As an example, when the range is zero, the fluctuation amplitude indicates that the power consumption fluctuation of the test object within any set time window is stable; when the range is the first target value, the fluctuation amplitude indicates that the power consumption fluctuation is slightly different; and when the range is greater than or equal to the fourth target value, the fluctuation amplitude indicates that the power consumption fluctuation is significantly different.

[0106] Among them, the value of the fourth target is greater than the value of the first target and less than the value of the second target. For example, when the difference between the coding values ​​corresponding to the target electricity load levels of two adjacent levels is 1, the value of the first target can be 1, the value of the second target can be 3, the value of the third target can be 4, and the value of the fourth target can be 2.

[0107] 3. Determine the fluctuation trend based on the first digit, the last digit, and the median.

[0108] In this embodiment of the disclosure, the fluctuation trend can be determined based on multiple factors among the first digit, the last digit, and the median.

[0109] As one possible approach, the fluctuation trend can be determined based on the first coded value, the last coded value, and the median value, even when the fluctuation amplitude indicates a small or large change.

[0110] As an example, when the target code value is less than the final target code value, the fluctuation trend can be determined to be upward.

[0111] As another example, when the first target code value is greater than the last target code value, the fluctuation trend can be determined to be downward.

[0112] As another example, when the median is less than both the first and last target code values, the fluctuation trend can be determined to be a decrease followed by an increase.

[0113] As another example, when the median is greater than both the first and last target code values, the fluctuation trend can be determined to be an initial increase followed by a decrease.

[0114] As another example, when the median is equal to the first target code value and the last target code value, the fluctuation trend can be determined to be fluctuation.

[0115] As another example, when the first target code value is greater than the median and the median is greater than the last target code value, the fluctuation trend can be determined to be a continuous decline.

[0116] As another example, when the first target code value is less than the median and the median is less than the last target code value, the fluctuation trend can be determined to be continuously rising.

[0117] 4. Determine the power consumption fluctuation of the object under test within any set time window based on at least one of the fluctuation amplitude, fluctuation location, and fluctuation trend.

[0118] In this embodiment of the disclosure, the power consumption fluctuation of the object under test within any set time window can be determined based on at least one of the fluctuation amplitude, fluctuation location, and fluctuation trend.

[0119] In one possible implementation of this application, when the fluctuation amplitude indicates a stable fluctuation and the fluctuation position is low, it can be determined that the power consumption fluctuation of the object under test within the set time window is a low-level stable fluctuation.

[0120] In one possible implementation of this application, when the fluctuation amplitude indicates a stable fluctuation and the fluctuation position is at the median, it can be determined that the power consumption fluctuation of the object under test within the set time window is a median stable fluctuation.

[0121] In one possible implementation of this application, when the fluctuation amplitude indicates a stable fluctuation and the fluctuation position is high, it can be determined that the power consumption fluctuation of the object under test within the set time window is a high-level stable fluctuation.

[0122] In one possible implementation of this application, when the fluctuation amplitude indication is a small change, the fluctuation position is low, and the fluctuation trend is upward, it can be determined that the power consumption fluctuation of the object under test within the set time window is a small increase from a low position.

[0123] In one possible implementation of this application, when the fluctuation amplitude indication is a small change, the fluctuation position is at the median, and the fluctuation trend is upward, it can be determined that the power consumption fluctuation of the object under test within the set time window is at the median with a slight increase.

[0124] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is high, and the fluctuation trend is upward, it can be determined that the power consumption fluctuation of the object under test within the set time window is a small increase from a high level.

[0125] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is low, and the fluctuation trend is downward, it can be determined that the power consumption fluctuation of the object under test within the set time window is a small decrease at a low level.

[0126] In one possible implementation of this application, when the fluctuation amplitude indicates a slight change, the fluctuation position is at the median, and the fluctuation trend is downward, it can be determined that the power consumption fluctuation of the object under test within the set time window is a slight decrease at the median.

[0127] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is high, and the fluctuation trend is downward, it can be determined that the power consumption fluctuation of the object under test within the set time window is high with a slight decrease.

[0128] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is low, and the fluctuation trend is first decreasing and then increasing, it can be determined that the power consumption fluctuation trend of the object under test within the set time window is low with a small decrease and then increasing.

[0129] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is at the median, and the fluctuation trend is first decreasing and then increasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is at the median with a small first decrease and then increase.

[0130] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is high, and the fluctuation trend is first decreasing and then increasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is high with a small decrease and then increasing.

[0131] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is low, and the fluctuation trend is first increasing and then decreasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is low with a small increase and then decrease.

[0132] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is at the median, and the fluctuation trend is first increasing and then decreasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is at the median with a small increase and then decrease.

[0133] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is high, and the fluctuation trend is first increasing and then decreasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is high with a small increase and then decrease.

[0134] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is low, and the fluctuation trend is fluctuation, it can be determined that the power consumption fluctuation of the object under test within the set time window is a low-level small fluctuation.

[0135] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is at the median, and the fluctuation trend is fluctuation, it can be determined that the power consumption fluctuation of the object under test within the set time window is a median small fluctuation.

[0136] In one possible implementation of this application, when the fluctuation amplitude indicates a small change, the fluctuation position is high, and the fluctuation trend is fluctuating, it can be determined that the power consumption fluctuation of the object under test within the set time window is a high-level small fluctuation.

[0137] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is low, and the fluctuation trend is continuously decreasing, it can be determined that the power consumption fluctuation of the test object within the set time window is a low-level, large-scale, and continuous decrease.

[0138] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is at the median, and the fluctuation trend is continuously decreasing, it can be determined that the power consumption fluctuation of the test object within the set time window is a significant and continuous decrease at the median.

[0139] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is high, and the fluctuation trend is continuously decreasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is a significant and continuous decrease from a high level.

[0140] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is low, and the fluctuation trend is continuously rising, it can be determined that the power consumption fluctuation of the test object within the set time window is a low-level, large-scale, and continuous increase.

[0141] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is at the median, and the fluctuation trend is continuously rising, it can be determined that the power consumption fluctuation of the object under test within the set time window is at the median level with a significant and continuous increase.

[0142] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is high, and the fluctuation trend is continuously rising, it can be determined that the power consumption fluctuation of the test object within the set time window is a significant and continuous increase at a high level.

[0143] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is low, and the fluctuation trend is first decreasing and then increasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is low, first decreasing and then increasing significantly.

[0144] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is at the median, and the fluctuation trend is first decreasing and then increasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is at the median, first decreasing and then increasing significantly.

[0145] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is high, and the fluctuation trend is first decreasing and then increasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is high, first decreasing and then increasing.

[0146] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is low, and the fluctuation trend is first increasing and then decreasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is low with a significant increase followed by a decrease.

[0147] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is at the median, and the fluctuation trend is first increasing and then decreasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is at the median level with a significant increase followed by a decrease.

[0148] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is high, and the fluctuation trend is first increasing and then decreasing, it can be determined that the power consumption fluctuation of the object under test within the set time window is high, with a significant increase followed by a decrease.

[0149] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is low, and the fluctuation trend is fluctuating, it can be determined that the power consumption fluctuation of the object under test within the set time window is a low-level large fluctuation.

[0150] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is at the median, and the fluctuation trend is fluctuating, it can be determined that the power consumption fluctuation of the object under test within the set time window is at the median level with significant fluctuation.

[0151] In one possible implementation of this application, when the fluctuation amplitude indicator changes significantly, the fluctuation position is high, and the fluctuation trend is fluctuating, it can be determined that the power consumption fluctuation of the object under test within the set time window is a high-level large fluctuation.

[0152] Step S304: Determine the production status of the object under test within any set time window based on the power consumption fluctuation.

[0153] In the embodiments of this application, the production status includes, but is not limited to, in-production status, shutdown status, and resumption status.

[0154] In this embodiment of the application, the production status of the test object within the set time window can be determined based on the power consumption fluctuation of the test object within the set time window.

[0155] For example, the electricity consumption fluctuations corresponding to each production state can be preset, that is, the correspondence between electricity consumption fluctuations and production states can be set. Thus, in this application, the above correspondence can be queried based on the electricity consumption fluctuations of the object under test within a set time window to determine the production state of the object under test within that set time window.

[0156] In one possible implementation of this application, the power consumption fluctuation situation corresponding to the production status may include at least one of the following: the median remains stable, the high level remains stable, the median rises slightly, the high level rises slightly, the median falls slightly, the high level falls slightly, the median rises sharply and continuously, the median falls sharply and continuously, the high level falls sharply and continuously, the median increases sharply and then decreases, the median decreases sharply and then increases, the median fluctuates slightly, the high level fluctuates slightly, the median increases slightly and then decreases, the high level increases slightly and then decreases, the median rises slightly and the high level rises slightly, the median decreases slightly and then increases, the high level decreases slightly and then increases, or the high level fluctuates sharply.

[0157] Among them, the low bit means that the average value of the encoded value under each target time period within the set time window is in the first value range; the middle bit means that the average value of the encoded value under each target time period within the set time window is in the second value range; and the high bit means that the average value of the encoded value under each target time period within the set time window is in the third value range.

[0158] In summary, by listing all the electricity consumption fluctuations corresponding to the production status, the accuracy and reliability of production status identification can be improved.

[0159] In another possible implementation of this application, the power consumption fluctuation corresponding to the shutdown state may include at least one of the following: low-level stable fluctuation, low-level slight decrease, mid-level slight decrease, low-level large and continuous decrease, mid-level large and continuous decrease, low-level large decrease followed by increase, mid-level large decrease followed by increase, low-level slight decrease followed by increase, mid-level slight decrease followed by increase, low-level slight increase followed by decrease, low-level slight increase, mid-level slight increase, low-level large and continuous increase, mid-level large and continuous increase, low-level large and continuous decrease, mid-level large and continuous decrease, low-level slight fluctuation, mid-level slight fluctuation, low-level slight decrease, mid-level slight decrease, low-level large fluctuation, or mid-level large fluctuation.

[0160] In summary, by listing all the power consumption fluctuations corresponding to the shutdown status, the accuracy and reliability of shutdown status identification can be improved.

[0161] In another possible implementation of this application, the power consumption fluctuation corresponding to the resumption of work status may include at least one of the following: stable fluctuation at the median level, stable fluctuation at the high level, slight increase at the median level, slight increase at the high level, significant and continuous increase at the low level, significant and continuous increase at the median level, significant and continuous increase at the high level, significant increase followed by decrease at the median level, significant increase followed by decrease at the high level, significant decrease followed by increase at the median level, significant decrease followed by increase at the high level, slight decrease followed by increase at the median level, slight fluctuation at the median level, significant and continuous decrease at the median level, slight decrease at the median level, or slight decrease at the high level.

[0162] In summary, by listing all the electricity consumption fluctuations corresponding to the resumption of work status, the accuracy and reliability of the resumption of work status identification can be improved.

[0163] Step S305: Determine the resumption status of the test object based on its production status within at least two set time windows.

[0164] For an explanation of step S305, please refer to the relevant description in any embodiment of this application.

[0165] The method for determining the power load level in this application embodiment can determine the power consumption fluctuation within a set time window based on the statistical information of the encoded values ​​of each target time period within the set time window, thereby improving the effectiveness and accuracy of determining the power consumption fluctuation.

[0166] To clearly explain how step S103 in the above embodiments of this application determines at least one power consumption threshold based on the first mean, the first standard deviation, and the initial setting coefficient corresponding to at least one power consumption threshold, this application also proposes a method for determining the power consumption load level.

[0167] Figure 4 This is a flowchart illustrating another method for determining the power load level provided in an embodiment of this application.

[0168] like Figure 4 As shown, in Figure 1 Based on the illustrated embodiment, step S102 may include the following steps:

[0169] Step S401: Obtain the initial mean and initial standard deviation of at least one electricity consumption.

[0170] In the embodiments disclosed herein, the mean of each electricity consumption (referred to as the initial mean in this application) can be calculated, and the standard deviation of each electricity consumption (referred to as the initial standard deviation in this application) can also be calculated.

[0171] Step S402: Determine the reference value range based on the third set multiple, the initial standard deviation, and the initial mean. In this embodiment, the third set multiple is a preset multiple or threshold; for example, the third set multiple can be 3.

[0172] In one possible implementation of this application, a reference value can be determined based on the product of a third predetermined multiple and the initial standard deviation, and a range of reference values ​​can be determined based on the initial mean and the reference value. For example, the upper limit of the reference value range can be: the initial mean + the reference value, and the lower limit of the reference value range can be: the initial mean - the reference value.

[0173] It should be noted that when the electricity consumption of the object under test is relatively stable or steady in each time period, the initial standard deviation is small. Calculating the electricity consumption threshold based on the small initial standard deviation may lead to inaccurate identification of the target electricity load level of the object under test in the target time period.

[0174] Therefore, in order to address the above problems, in one possible implementation of the present application embodiment, before step S402, a first reference value can be determined based on the product of the first set ratio and the initial mean, and it can be determined whether the initial standard deviation is greater than or equal to the first reference value. If the initial standard deviation is greater than or equal to the first reference value, step S402 can be executed.

[0175] The first set ratio is a pre-set ratio coefficient, for example, the first set ratio can be 10%.

[0176] If the initial standard deviation is less than the first reference value, the initial standard deviation can be updated based on the first reference value. For example, the first reference value can be assigned to the initial standard deviation.

[0177] Therefore, when the initial standard deviation is greater than or equal to the first reference value, it indicates that the electricity consumption of the test object in each time period is not in a stable or steady state. In this case, determining each electricity consumption threshold value based on the relatively large initial standard deviation can improve the distinguishability of each electricity consumption threshold value, thereby improving the accuracy of identifying the target electricity load level of the test object in the target time period. This avoids the situation where the electricity consumption threshold values ​​are not easily distinguished when calculated based on the relatively small initial standard deviation, resulting in inaccurate identification of the electricity load level. Conversely, when the initial standard deviation is less than the first reference value, increasing the initial standard deviation can improve the accuracy of identifying the target electricity load level of the test object in the target time period.

[0178] Step S403: Based on the reference value range, filter the electricity consumption for at least one time period to obtain the reserved electricity consumption within the reference value range.

[0179] In this embodiment of the application, the electricity consumption for at least one time period can be filtered according to the reference value range to filter out abnormal electricity consumption and retain normal electricity consumption, wherein the normal electricity consumption is within the reference value range.

[0180] Step S404: Determine the first mean based on the mean of each reserved electricity consumption, and determine the first standard deviation based on the standard deviation of each reserved electricity consumption.

[0181] In the embodiments of this application, the mean of each reserved electricity consumption (referred to as the first mean in this application) can be calculated, and the standard deviation of each reserved electricity consumption (referred to as the first standard deviation in this application) can also be calculated.

[0182] It should be noted that when the electricity consumption of each reserved power consumption is relatively stable or steady, the value of the first standard deviation is small. Calculating the threshold value of each power consumption based on the small value of the first standard deviation may make it difficult to distinguish between the different power consumption threshold values, resulting in inaccurate identification of the target power consumption load level of the object under test in the target time period.

[0183] Furthermore, if the difference between the highest and lowest values ​​of each reserved electricity consumption is large, resulting in a large first standard deviation, calculating the threshold value of each electricity consumption based on the larger first standard deviation may also lead to inaccurate identification of the target electricity consumption load level of the object under test in the target time period.

[0184] Therefore, in response to the above problems, in one possible implementation of this application embodiment, the specific calculation method for the first standard deviation in step S404 can be:

[0185] A second reference value is determined by multiplying the average of each reserved electricity consumption by a second set ratio. A third reference value can also be determined by multiplying the average of each reserved electricity consumption by a third set ratio; where the third set ratio is greater than the second set ratio, for example, the third set ratio could be 30% and the second set ratio could be 10%. Then, it can be determined whether the standard deviation of each reserved electricity consumption is greater than or equal to the second reference value and less than or equal to the third reference value. If the standard deviation of each reserved electricity consumption is greater than or equal to the third reference value and less than or equal to the fourth reference value, it indicates that the standard deviation of each reserved electricity consumption is appropriate. In this case, the standard deviation of each reserved electricity consumption can be used as the first standard deviation.

[0186] If the standard deviation of each reserved electricity consumption is less than the second reference value, it indicates that the standard deviation of each reserved electricity consumption is small. In this case, the first standard deviation can be determined based on the second reference value; for example, the second reference value can be used as the first standard deviation. Alternatively, if the standard deviation of each reserved electricity consumption is greater than the third reference value, it indicates that the standard deviation of each reserved electricity consumption is large. In this case, the first standard deviation can be determined based on the third reference value; for example, the third reference value can be used as the first standard deviation.

[0187] Therefore, if the standard deviation of each reserved electricity consumption is greater than or equal to the second reference value and less than or equal to the third reference value, it indicates that the standard deviation of each reserved electricity consumption is appropriate. In this case, determining the threshold value of each electricity consumption based on the relatively appropriate standard deviation can avoid situations where the threshold values ​​are not easily distinguishable or are too large, leading to inaccurate identification of the target electricity load level of the test object in the target time period. Conversely, if the standard deviation of each reserved electricity consumption is less than the second reference value, determining the threshold value of each electricity consumption based on the second reference value can improve the distinguishability of each threshold value, thereby improving the accuracy of subsequent identification. Alternatively, if the standard deviation of each reserved electricity consumption is greater than the third reference value, determining the threshold value of each electricity consumption based on the third reference value can improve the accuracy of identifying the target electricity load level of the test object in the target time period.

[0188] The method for determining the power load level in this application embodiment can screen abnormal power consumption among various power consumption levels, and then determine the threshold value of each power consumption level based on the standard deviation and mean of the retained non-abnormal power consumption levels, thereby improving the reliability and rationality of the determination of the power consumption threshold value.

[0189] To clearly illustrate how step S104 in the above embodiments of this application determines the target power load level of the object under test in the target time period based on at least one power consumption threshold and the power consumption in the target time period, this application also proposes a method for determining the power load level.

[0190] Figure 5 This is a flowchart illustrating another method for determining the power load level provided in an embodiment of this application.

[0191] like Figure 5 As shown, based on any of the above embodiments, step S104 may include the following steps:

[0192] Step S501: Determine the power consumption range corresponding to multiple power load levels based on at least one power consumption threshold.

[0193] In this embodiment of the application, the power consumption range corresponding to multiple power load levels can be determined based on at least one power consumption threshold value.

[0194] As an example, taking a scenario where there are two electricity load levels, such as low-level production and high-level production, and the number of electricity load thresholds can be one, with the threshold value marked as 'a', then:

[0195] a = mean1 + r * std1;

[0196] Where r is the initial coefficient corresponding to a. mean1 represents the first mean, and std1 represents the first standard deviation.

[0197] Then, the electricity consumption range corresponding to the lowest electricity consumption load level (i.e., low-level production) among the two electricity consumption load levels can be [0, a), and the electricity consumption range corresponding to the highest electricity consumption load level (i.e., high-level production) can be [a, +∞).

[0198] As another example, let's consider five electricity load levels: shutdown, low-level normal production, medium-level normal production, high-level normal production, and high-load production. We'll also use four electricity load thresholds, labeled a1, a2, a3, and a4. Assuming the initial setting coefficient for a1 is -1.2, for a2 it's -0.3, for a3 it's +0.5, and for a4 it's +1.5, then:

[0199] a1 = mean1 - 1.2 * std1;

[0200] a2 = mean1 - 0.3 * std1;

[0201] a3 = mean1 + 0.5 * std1;

[0202] a4 = mean1 + 1.5 * std1;

[0203] The electricity consumption range corresponding to the lowest electricity consumption load level (i.e., production stoppage) among the five electricity consumption load levels can be [0, a1), the electricity consumption range corresponding to the second lowest electricity consumption load level (i.e., low-level normal production) can be [a1, a2), and so on. The electricity consumption range corresponding to the middle level of normal production can be [a2, a3), the electricity consumption range corresponding to the high level of normal production can be [a3, a4), and the electricity consumption range corresponding to the high load production can be [a4, +∞).

[0204] Step S502: Based on the electricity consumption during the target period and the electricity consumption range corresponding to multiple electricity load levels, determine the target electricity load level from multiple electricity load levels; wherein, the electricity consumption during the target period is within the electricity consumption range corresponding to the target electricity load level.

[0205] In this embodiment of the application, a target power load level can be determined from multiple power load levels based on the power consumption during the target time period and the power consumption range corresponding to multiple power load levels; wherein, the power consumption during the target time period is within the power consumption range corresponding to the target power load level.

[0206] In other words, the electricity consumption during the target period can be compared with the corresponding electricity consumption range of multiple electricity load levels. If the electricity consumption during the target period falls within the corresponding electricity consumption range of a certain electricity load level, then that electricity load level can be used as the target electricity load level of the object under test during the target period.

[0207] The method for determining the power load level in this application embodiment determines the power consumption range corresponding to multiple power load levels based on each power consumption threshold value, and determines the target power load level of the object under test in the target time period based on the power consumption range of multiple power load levels, which can improve the effectiveness and rationality of the determination of the target power load level.

[0208] In any embodiment of this application, after determining each electricity consumption threshold, at least one of the electricity consumption thresholds can be modified to improve the accuracy of determining the target electricity load level of the object under test during the target time period. The following is in conjunction with... Figure 6 The above process will be explained in detail.

[0209] Figure 6 This is a flowchart illustrating another method for determining the power load level provided in an embodiment of this application.

[0210] like Figure 6 As shown, based on any of the above embodiments, after step S103, the method for determining the electricity load level may further include the following steps:

[0211] Step S601: Determine the initial power consumption range corresponding to multiple power consumption load levels based on at least one power consumption threshold value.

[0212] The explanation of step S601 can be found in the relevant description of step S501 in the above embodiments. The implementation principle is similar and will not be repeated here.

[0213] Step S602: For at least one of multiple power load levels, determine the target power consumption that is within the initial power consumption range of the at least one power load level.

[0214] In this embodiment of the disclosure, for at least one of a plurality of power load levels, a target power consumption within the initial power consumption range corresponding to the at least one power load level can be determined from each power consumption (or reserved power consumption).

[0215] Step S603: Adjust at least one power consumption threshold value according to the amount of target power consumption within the initial power consumption range of at least one power consumption load level.

[0216] In this embodiment of the disclosure, for any one of the above-mentioned at least one power load level, at least one power load threshold value can be adjusted according to the amount of target power consumption within the initial power consumption range of that power load level.

[0217] For example, the total amount of electricity consumed can be counted, and the percentage of the above amount to the total amount can be calculated. If the percentage exceeds the set percentage threshold, at least one electricity consumption threshold can be adjusted.

[0218] In one possible implementation of this application embodiment, the method for adjusting at least one power consumption threshold is, for example:

[0219] 1. For the highest-level first-level electricity load among multiple electricity load levels, determine the target electricity consumption within the initial electricity consumption range corresponding to the first-level electricity load from each electricity consumption (or each reserved electricity consumption).

[0220] In this embodiment of the application, for the first electricity load level, which is the highest among multiple electricity load levels (for example, taking the example in step S501, the first target electricity load level can be high-level production among two levels or high-load production among five levels), the target electricity consumption located within the initial electricity consumption range corresponding to the first electricity load level can be determined from each electricity consumption (or each reserved electricity consumption).

[0221] 2. Obtain the proportion of the target electricity consumption within the initial electricity consumption range corresponding to the first electricity consumption load level to the total electricity consumption of each category.

[0222] In this embodiment of the application, the number of target electricity consumption within the initial electricity consumption range corresponding to the first electricity load level can be counted, and the total number of each electricity consumption (or each reserved electricity consumption) can be counted, and the ratio of the above number to the total number can be calculated, that is, the ratio = number / total number.

[0223] 3. If the proportion is higher than the set proportion threshold, increase the first electricity consumption threshold among at least one electricity consumption threshold.

[0224] In this embodiment of the application, the percentage threshold is set to a preset percentage threshold, for example, the preset percentage threshold can be 10%.

[0225] In this embodiment of the application, the first power consumption threshold is used to determine the initial power consumption range corresponding to the first power consumption load level, and to determine the initial power consumption range corresponding to the level preceding the first power consumption load level.

[0226] It should be noted that the example uses five power load levels: shutdown, low-level normal production, medium-level normal production, high-level normal production, and high-load production. In actual application scenarios, the tested object (such as an enterprise) may experience a high proportion of shutdowns but not a high proportion of high-load production. That is, the number or frequency of the tested object's power consumption belonging to the highest power load level is not high, and the tested object may experience a low probability of high-load production. Based on this, in this embodiment, it can be determined whether the above proportion is higher than a set proportion threshold. If not, it indicates that the value of the first power consumption threshold is appropriate, and no processing is required. If yes, it indicates that the power consumption threshold value corresponding to the highest power load level (i.e., the first power consumption threshold value, such as a4 in step S501) is set too low. Therefore, in this application, at least one of the first power consumption threshold values ​​can be increased.

[0227] For example, the first power consumption threshold can be gradually increased by adjusting the value in relatively small increments until the proportion of the target power consumption within the power consumption range corresponding to the first power consumption load level in each power consumption (or each reserved power consumption) is less than or equal to the set proportion threshold.

[0228] The method for determining the electricity load level in this application embodiment can update the electricity load threshold when the value of a certain electricity threshold is unreasonable, so as to improve the accuracy of determining the target electricity load level of the target object in the target time period.

[0229] In any embodiment of this application, after determining each electricity consumption threshold, at least one of the electricity consumption thresholds can be modified to improve the accuracy of determining the target electricity load level of the object under test during the target time period. The following is in conjunction with... Figure 7 The above process will be explained in detail.

[0230] Figure 7 This is a flowchart illustrating another method for determining the power load level provided in an embodiment of this application.

[0231] like Figure 7 As shown, based on any of the above embodiments, after step S103, the method for determining the electricity load level may further include the following steps:

[0232] Step S701: Determine whether each power consumption threshold is less than the corresponding set value.

[0233] In this embodiment of the disclosure, each power consumption threshold can have a corresponding set value.

[0234] In this embodiment of the disclosure, it can be determined whether each power consumption threshold is less than the corresponding set value. If each power consumption threshold is not less than the corresponding set value, there is no need to adjust each power consumption threshold. However, if there is a power consumption threshold that is less than the corresponding set value, step S702 can be executed.

[0235] Step S702: If at least one power consumption threshold is less than the corresponding set value, adjust the initial setting coefficient corresponding to each power consumption threshold.

[0236] In this embodiment of the application, if at least one power consumption threshold is less than the corresponding set value, the initial setting coefficients corresponding to each power consumption threshold can be adjusted so that each power consumption threshold can be recalculated based on the adjusted initial setting coefficients, the first mean and the first standard deviation.

[0237] In one possible implementation of this disclosure, the adjustment method for the initial setting coefficient corresponding to each power consumption threshold is, for example:

[0238] 1. For the second power consumption threshold among at least one power consumption threshold, it can be determined whether the second power consumption threshold is less than the corresponding set value.

[0239] The second power consumption threshold can be preset to a relatively small value. For example, the second power consumption threshold can be set to 0.

[0240] It should be noted that for the second electricity consumption threshold among at least one electricity consumption threshold, the second electricity consumption threshold is used to determine the electricity consumption range corresponding to the lowest level of the second electricity consumption load level among multiple electricity consumption load levels, and to determine the electricity consumption range corresponding to the second lowest level of the electricity consumption load level (i.e., the next level after the second electricity consumption load level) among multiple electricity consumption load levels. For example, the second electricity consumption threshold can be a1 in step S501. When the second electricity consumption threshold is very small, it may result in the situation where the electricity consumption of the object under test during the target period is not classified as the second electricity consumption load level.

[0241] Therefore, in this embodiment of the application, in view of the above situation, it can be determined whether the second power consumption threshold is less than the corresponding set value. If it is, it indicates that the value of the second power consumption threshold is too small. At this time, the subsequent steps can be executed. If not, it indicates that the value of the second power consumption threshold is appropriate. Therefore, it is not necessary to update the second power consumption threshold.

[0242] 2. If the second power consumption threshold is less than the corresponding set value, the initial set coefficient corresponding to the second power consumption threshold is updated according to the first preset coefficient.

[0243] The first preset coefficient is a pre-set coefficient, for example, the first preset coefficient can be 0.2.

[0244] For example, if the second power consumption threshold is less than the corresponding set value, the first preset coefficient can be assigned to the initial set coefficient corresponding to the second power consumption threshold to obtain the updated initial set coefficient corresponding to the second power consumption threshold. Therefore, in this application, the second power consumption threshold can be updated based on the product of the updated initial set coefficient corresponding to the second power consumption threshold and the first average value. For example, the product of the updated initial set coefficient corresponding to the second power consumption threshold and the first average value can be used as the updated second power consumption threshold.

[0245] 3. Update the initial setting coefficient corresponding to the third power consumption threshold among at least one power consumption threshold values ​​according to the second preset coefficient.

[0246] The second preset coefficient is also a pre-set coefficient, and the second preset coefficient is greater than the first preset coefficient. For example, the second preset coefficient can be 0.65.

[0247] The third electricity consumption threshold is used to determine the electricity consumption range corresponding to the next level below the second electricity consumption load level (referred to as the third electricity consumption load level in this application), and to determine the electricity consumption range corresponding to the next level below the third electricity consumption load level. For example, the third electricity consumption threshold can be a2 in step S501.

[0248] In this embodiment of the application, the initial setting coefficient corresponding to the third power consumption threshold can also be updated according to the second preset coefficient. For example, the second preset coefficient can be assigned to the initial setting coefficient corresponding to the third power consumption threshold to obtain the updated initial setting coefficient corresponding to the third power consumption threshold.

[0249] Therefore, in this application, the third power consumption threshold can be updated based on the product of the updated initial setting coefficient corresponding to the third power consumption threshold and the first mean. For example, the product of the updated initial setting coefficient corresponding to the third power consumption threshold and the first mean can be used as the updated third power consumption threshold.

[0250] The method for determining the electricity load level in this application embodiment can update the electricity load threshold when the value of a certain electricity threshold is unreasonable, so as to improve the accuracy of determining the target electricity load level of the target object in the target time period.

[0251] In any embodiment of this application, the method for determining the power load level provided in any embodiment of this application is used to improve the problem of disordered clustering results caused by the fact that the coverage of actual power consumption data cannot completely cover all preset power load levels in traditional clustering algorithms.

[0252] In this application, from a statistical perspective, using the mean and variance to provide at least one electricity consumption threshold value is more reasonable for defining high and low electricity load levels. Specifically, the method provided in this application integrates the processing of outlier data, adjusting parameters based on the mean and variance and actual conditions. The final form is: inputting electricity consumption data of the same test object in sequence over a period of time, providing at least one electricity consumption threshold value to divide multiple electricity load levels. Taking five electricity load levels as an example: production stoppage, low-level normal production, medium-level normal production, high-level normal production, and high-load production, and with a first set ratio of 10%, a second set ratio of 30%, and a third set multiple of 3, the method provided in this application mainly includes the following steps:

[0253] 1. Calculate the mean (mean0) and standard deviation (std0) based on the input electricity consumption data (l0).

[0254] 2. If the standard deviation std0 is less than 10% of mean0, then std0 is calculated as 10% of mean0. The purpose of this step is to handle situations where the calculated standard deviation is too small when the electricity consumption data is extremely stable.

[0255] 3. In the electricity consumption data l0, identify values ​​outside the mean (mean0) plus or minus three times std0. These are considered outliers (i.e., abnormal electricity consumption) and can be discarded. The remaining electricity consumption is denoted as l1. Calculate the mean and standard deviation again using l1, denoted as mean1 and std1. The purpose of recalculating mean1 and std1 is to remove the influence of outliers on the statistical indicators.

[0256] 4. If the standard deviation std1 is less than 10% of mean1, then std1 is calculated as 10% of mean1 (this step is to handle the case where the calculated standard deviation is too small when the electricity consumption in l1 is extremely stable); if the standard deviation std1 is greater than 30% of mean1, then std1 is calculated as 30% of mean1 (this step is to handle the case where the calculated standard deviation is too large when the difference between the electricity consumption in l1 is large).

[0257] 5. Based on mean1, std1, and four initial set coefficients (which can be adjusted according to actual conditions), generate initial power consumption threshold values ​​a1, a2, a3, and a4. For example:

[0258] a1 = mean1 - 1.2 * std1;

[0259] a2 = mean1 - 0.3 * std1;

[0260] a3 = mean1 + 0.5 * std1;

[0261] a4 = mean1 + 1.5 * std1;

[0262] 6. If the proportion of electricity consumption at high production load is found to be higher than the set threshold (e.g., 10%), the value of a4 is continuously increased in small adjustment steps until the proportion of electricity consumption values ​​exceeding a4 in l1 is less than 10% of all data entries. This step aims to handle situations where a high proportion of production stoppages may occur in real-world applications, but a very high proportion of high production load is unlikely. If the identified proportion of high production load is too high, it indicates that the electricity consumption threshold for high production load is set too low.

[0263] 7. In some cases, if the calculated a1 value is less than the set value (e.g., 0), the classification that stops work will not occur. Therefore, the value of a1 needs to be increased. For example, if the a1 value is less than the set value, the a1 and a2 values ​​should be recalculated according to mean1.

[0264] a1 = 0.2 * mean1;

[0265] a2 = 0.65 * mean1;

[0266] 8. Based on the final a1, a2, a3, and a4, classify the electricity consumption in l0, for example:

[0267] Electricity consumption less than a1 falls under the category of: production stoppage;

[0268] Electricity consumption greater than or equal to a1 and less than a2 belongs to the category of: low-level normal production;

[0269] Electricity consumption greater than or equal to a2 and less than a3 belongs to the following category: median normal production;

[0270] Electricity consumption greater than or equal to a3 and less than a4 belongs to the category of: high-level normal production;

[0271] Electricity consumption greater than or equal to a4 falls under the category of high-load production.

[0272] 9. Use the classification results of each electricity consumption to determine whether enterprises should resume work and production after the holidays.

[0273] 9.1. The classification results determined in step 8 are encoded using numerical values. For example, taking the difference between the encoded values ​​corresponding to two adjacent electricity load levels as 1 as an example, then:

[0274] 0: Production halted;

[0275] 1: Normal production at a low level;

[0276] 2: Median production is normal;

[0277] 3: Normal production at a high level;

[0278] 4: High-load production;

[0279] 9.2 Defining the Time Window. The time window is determined based on the length of the holiday or target period. For example, for New Year's Day, Mid-Autumn Festival, Qingming Festival, and Dragon Boat Festival, the window length can be set to 3 days; for Labor Day, the window length can be set to 5 days; and for National Day and Spring Festival, the window length can be set to 7 days. (For example, when there are 3 time windows, the 3 time windows are: September 24th to September 30th, October 1st to October 7th, and October 8th to October 14th.)

[0280] 9.3 Calculate the key indicators of electricity consumption within each set time window. These indicators include the range r, the mean u, the coded value of the first day x_first, the coded value of the middle day x_mid, and the coded value of the last day x_last.

[0281] 9.4. Determine the electricity consumption fluctuations within each set time window according to the determination rules.

[0282] Define an enumeration of the electricity consumption fluctuations. The enumeration values combine the mean u (high, medium, low), the range r (stable fluctuation, small change, large change), and the fluctuation trend (stable, continuously increasing, continuously decreasing, decreasing first and then increasing, increasing first and then decreasing). Among them, when the range indicates stable fluctuation, the change in the fluctuation trend may not be further subdivided.

[0283] Among them, according to the range r within the set time window, judge the fluctuation amplitude of the electricity consumption within the set time window;

[0284] Among them, according to the mean u within the set time window, judge the fluctuation position of the electricity consumption within the set time window;

[0285] Among them, according to the magnitude relationship between the coding value x_first on the first day, the coding value x_mid on the middle day, and the coding value x_last on the last day within the set time window, judge the fluctuation trend of the electricity consumption within the set time window.

[0286] As an example, the electricity consumption fluctuations within the set time window can be as Figure 8 shown.

[0287] The specific judgment rules can be as follows:

[0288] 1) If the range r = 0, (the fluctuation amplitude is stable fluctuation);

[0289] if (if) 0 < u ≤ 1, Then (then) the electricity consumption fluctuation situation is low-level stable fluctuation;

[0290] if 1 < u ≤ 3, Then the electricity consumption fluctuation situation is medium-level stable fluctuation;

[0291] if 3 < u ≤ 4, Then the electricity consumption fluctuation situation is high-level stable fluctuation;

[0292] 2) If the range r = 1, (the fluctuation amplitude is small change);

[0293] 2-1) if x_first < x_last, Then the electricity consumption fluctuation situation is small increase;

[0294] if 0 < u ≤ 1, Then the electricity consumption fluctuation situation is low-level small increase;

[0295] if 1 < u ≤ 3, Then the electricity consumption fluctuation situation is medium-level small increase;

[0296] if 3 < u ≤ 4, Then the electricity consumption fluctuation situation is high-level small increase;

[0297] 2-2) If x_first > x_last, then the power consumption fluctuation situation is a slight decrease;

[0298] If 0 < u ≤ 1, then the power consumption fluctuation situation is a slight decrease at a low level;

[0299] If 1 < u ≤ 3, then the power consumption fluctuation situation is a slight decrease at a medium level;

[0300] If 3 < u ≤ 4, then the power consumption fluctuation situation is a slight decrease at a high level;

[0301] 2-3) If x_mid = min(x_first, x_mid, x_last) and x_first > x_mid and x_mid < x_last, then the power consumption fluctuation situation is a slight decrease first and then an increase;

[0302] If 0 < u ≤ 1, then the power consumption fluctuation situation is a slight decrease first and then an increase at a low level;

[0303] If 1 < u ≤ 3, then the power consumption fluctuation situation is a slight decrease first and then an increase at a medium level;

[0304] If 3 < u ≤ 4, then the power consumption fluctuation situation is a slight decrease first and then an increase at a high level;

[0305] 2-4) If x_mid = min(x_first, x_mid, x_last) and x_first < x_mid and x_mid > x_last, then the power consumption fluctuation situation is a slight increase first and then a decrease;

[0306] If 0 < u ≤ 1, then the power consumption fluctuation situation is a slight increase first and then a decrease at a low level;

[0307] If 1 < u ≤ 3, then the power consumption fluctuation situation is a slight increase first and then a decrease at a medium level;

[0308] If 3 < u ≤ 4, then the power consumption fluctuation situation is a slight increase first and then a decrease at a high level;

[0309] 2-5) If x_first = x_mid = x_last, then the power consumption fluctuation situation is a slight fluctuation;

[0310] If 0 < u ≤ 1, then the power consumption fluctuation situation is a slight fluctuation at a low level;

[0311] If 1 < u ≤ 3, then the power consumption fluctuation situation is a slight fluctuation at a medium level;

[0312] If 3 < u ≤ 4, then the power consumption fluctuation situation is a slight fluctuation at a high level;

[0313] 3) If the range r ≥ 2, (the fluctuation situation is a large change);

[0314] 3 - 1) If x_first > x_mid > x_last, Then the electricity consumption fluctuation situation is a large and continuous decrease;

[0315] If 0 < u ≤ 1, Then the electricity consumption fluctuation situation is a large and continuous decrease at a low level;

[0316] If 1 < u ≤ 3, Then the electricity consumption fluctuation situation is a large and continuous decrease at a medium level;

[0317] If 3 < u ≤ 4, Then the electricity consumption fluctuation situation is a large and continuous decrease at a high level;

[0318] 3 - 2) If x_first < x_mid < x_last, Then the electricity consumption fluctuation situation is a large and continuous increase;

[0319] If 0 < u ≤ 1, Then the electricity consumption fluctuation situation is a large and continuous increase at a low level;

[0320] If 1 < u ≤ 3, Then the electricity consumption fluctuation situation is a large and continuous increase at a medium level;

[0321] If 3 < u ≤ 4, Then the electricity consumption fluctuation situation is a large and continuous increase at a high level;

[0322] 3 - 3) If x_mid = min(x_first, x_mid, x_last) and x_first > x_mid and x_mid < x_last, Then the electricity consumption fluctuation situation is a large decrease first and then an increase;

[0323] If 0 < u ≤ 1, Then the electricity consumption fluctuation situation is a large decrease first and then an increase at a low level;

[0324] If 1 < u ≤ 3, Then the electricity consumption fluctuation situation is a large decrease first and then an increase at a medium level;

[0325] If 3 < u ≤ 4, Then the electricity consumption fluctuation situation is a large decrease first and then an increase at a high level;

[0326] 3 - 4) If x_mid = min(x_first, x_mid, x_last) and x_first < x_mid and x_mid > x_last, Then the electricity consumption fluctuation situation is a large increase first and then a decrease;

[0327] If 0 < u ≤ 1, Then the electricity consumption fluctuation situation is a large increase first and then a decrease at a low level;

[0328] If 1 < u ≤ 3, then the power consumption fluctuation is large at the middle level, first increasing and then decreasing;

[0329] If 3 < u ≤ 4, then the power consumption fluctuation is large at the high level, first increasing and then decreasing;

[0330] 3 - 5) If x_first = x_mid = x_last, then the power consumption fluctuation is large;

[0331] If 0 < u ≤ 1, then the power consumption fluctuation is large at the low level;

[0332] If 1 < u ≤ 3, then the power consumption fluctuation is large at the middle level;

[0333] If 3 < u ≤ 4, then the power consumption fluctuation is large at the high level.

[0334] 9.5. Determine whether the object to be measured resumes work and production according to the power consumption fluctuation.

[0335] For example, taking the number of set time windows as 3 for exemplary illustration, then according to the power consumption fluctuations of the first, middle, and last three time windows, the production status of the first, middle, and last three time windows can be determined, and according to the production status of the three set time windows, it is联动 determined whether the object to be measured resumes work and production.

[0336] For example, when the production status of the first time window (front) is in - production status, the production status of the second time window (middle) is shutdown status, and the production status of the third time window (back) is resume - work status, it can be determined that the object to be measured resumes work and production. Among them, the power consumption fluctuations corresponding to each production status can be as shown in Table 1.

[0337] Table 1 Power consumption fluctuations corresponding to production status

[0338]

[0339] In summary, compared with the traditional clustering algorithm, the method provided in this application removes the link of manually specifying to cluster into k classes. How many categories the final power consumption is divided into depends more on the statistical values of the power consumption data of the object to be measured, which is more reasonable.

[0340] Corresponding to the method for determining the power consumption load level provided in the above several embodiments, an embodiment of this application also provides a device for determining the power consumption load level. Since the device for determining the power consumption load level provided in the embodiment of this application corresponds to the method for determining the power consumption load level provided in the above several embodiments, the implementation manner of the method for determining the power consumption load level is also applicable to the device for determining the power consumption load level provided in this embodiment, and will not be described in detail in this embodiment.

[0341] Figure 9 This is a schematic diagram of a device for determining the power load level according to an embodiment of this application.

[0342] like Figure 9 As shown, the power load level determination device 900 may include: a first acquisition module 901, a second acquisition module 902, a first determination module 903, and a second determination module 904.

[0343] The first acquisition module 901 is used to acquire the electricity consumption data of the object under test; wherein the electricity consumption data includes the electricity consumption for at least one time period.

[0344] The second acquisition module 902 is used to acquire at least one first mean and first standard deviation of electricity consumption.

[0345] The first determining module 903 is used to determine at least one power consumption threshold value based on the first mean, the first standard deviation, and the initial setting coefficient corresponding to at least one power consumption threshold value.

[0346] The second determining module 904 is used to determine the target power load level of the object under test in the target time period based on at least one power consumption threshold and the power consumption in the target time period.

[0347] As one possible implementation of this application embodiment, the power load level determination device 900 may further include:

[0348] The encoding module is used to encode the target electricity load level for each target time period to obtain the encoded value of the target electricity load level for each target time period.

[0349] The third determination module is used to determine the production status of the object under test within any set time window based on the encoding value of each target time period within any set time window.

[0350] The fourth determination module is used to determine the resumption status of the test object based on its production status within at least two set time windows.

[0351] As one possible implementation of this application, the third determining module is specifically used for: obtaining statistical information on the encoded values ​​of each target time period within an arbitrary set time window; wherein the statistical information includes at least one of the range, second mean, first encoded value, last encoded value, and median; determining the power consumption fluctuation of the test object within the arbitrary set time window based on the statistical information; wherein the power consumption fluctuation includes at least one of the following: fluctuation amplitude, fluctuation position, and fluctuation trend; and determining the production status of the test object within the arbitrary set time window based on the power consumption fluctuation.

[0352] As one possible implementation of this application, the third determining module is specifically used for: determining the fluctuation amplitude based on the range; determining the fluctuation position based on the second mean; determining the fluctuation trend based on the first digit code value, the last digit code value, and the median value; and determining the power consumption fluctuation of the object under test within any set time window based on at least one of the fluctuation amplitude, fluctuation position, and fluctuation trend.

[0353] As one possible implementation of this application embodiment, the fourth determining module is specifically used for: when there are two set time windows, if the production status of the first time window is in a shutdown state and the production status of the second time window is in a production state or a resumption state, then the resumption status of the test object is determined to be a resumption of production; wherein the first time window is located before the second time window; when there are three set time windows, if the production status of the third time window is in a production state, the production status of the fourth time window is in a shutdown state, and the production status of the fifth time window is in a resumption state, then the resumption status of the test object is determined to be a resumption of production; wherein the fourth time window is located after the third time window, and the fifth time window is located after the fourth time window; when there are at least four set time windows, if the production status of the sixth time window is in a production state or a resumption state and the production status of at least one seventh time window is in a shutdown state, then the resumption status of the test object is determined to be a resumption of production; wherein the seventh time window is located before the sixth time window.

[0354] As one possible implementation of this application, the power consumption fluctuation situation corresponding to the production status includes at least one of the following: the median remains stable, the high level remains stable, the median rises slightly, the high level rises slightly, the median falls slightly, the high level falls slightly, the median rises sharply and continuously, the median falls sharply and continuously, the high level falls sharply and continuously, the median increases sharply and then decreases, the median decreases sharply and then increases, the median fluctuates slightly, the high level fluctuates slightly, the median increases slightly and then decreases, the high level increases slightly and then decreases, the median rises slightly and the high level rises slightly, the median decreases slightly and then increases, the high level decreases slightly and then increases, or the high level fluctuates sharply.

[0355] Among them, the low bit means that the average value of the encoded value under each target time period within the set time window is in the first value range; the middle bit means that the average value of the encoded value under each target time period within the set time window is in the second value range; and the high bit means that the average value of the encoded value under each target time period within the set time window is in the third value range.

[0356] The lower limit of the first value range is 0, the upper limit of the first value range is the first target value, the lower limit of the second value range is the first target value, the upper limit of the second value range is the second target value, the lower limit of the third value range is the second target value, and the upper and lower limits of the third value range are the third target values. The first target value is determined based on the difference between the coding values ​​corresponding to the target electricity load levels of two adjacent levels. The second target value is a first set multiple of the first target value, and the third target value is a second set multiple of the first target value. The second set multiple is greater than the first set multiple.

[0357] As one possible implementation of this application, the power consumption fluctuation situation corresponding to the shutdown state includes at least one of the following: low-level stable fluctuation, low-level slight decrease, mid-level slight decrease, low-level large and continuous decrease, mid-level large and continuous decrease, low-level large decrease followed by increase, mid-level large decrease followed by increase, low-level slight decrease followed by increase, mid-level slight decrease followed by increase, low-level slight increase followed by decrease, low-level slight increase, mid-level slight increase, low-level large and continuous increase, mid-level large and continuous increase, low-level large and continuous decrease, mid-level large and continuous decrease, low-level slight fluctuation, mid-level slight fluctuation, low-level slight decrease, mid-level slight decrease, low-level large fluctuation, or mid-level large fluctuation.

[0358] As one possible implementation of this application, the electricity consumption fluctuations corresponding to the resumption of work status include at least one of the following: stable fluctuation at the median level, stable fluctuation at the high level, slight increase at the median level, slight increase at the high level, significant and continuous increase at the low level, significant and continuous increase at the median level, significant and continuous increase at the high level, significant increase followed by decrease at the median level, significant increase followed by decrease at the high level, significant decrease followed by increase at the median level, significant decrease followed by increase at the high level, slight decrease followed by increase at the median level, slight fluctuation at the median level, significant and continuous decrease at the median level, slight decrease at the median level, or slight decrease at the high level.

[0359] As one possible implementation of this application embodiment, the second acquisition module 902 is specifically used for: acquiring at least one initial mean and initial standard deviation of electricity consumption; determining a reference value range based on a third set multiple, initial standard deviation, and initial mean; filtering electricity consumption for at least one time period based on the reference value range to obtain each reserved electricity consumption within the reference value range; determining a first mean based on the mean of each reserved electricity consumption, and determining a first standard deviation based on the standard deviation of each reserved electricity consumption.

[0360] As one possible implementation of this application, the second acquisition module 902 is further configured to: determine a first reference value based on the product of a first set ratio and an initial mean; determine whether the initial standard deviation is less than the first reference value; and update the initial standard deviation based on the first reference value if the initial standard deviation is less than the first reference value.

[0361] As one possible implementation of this application embodiment, the second acquisition module 902 is specifically used for: determining a second reference value based on the product of the average value of each reserved electricity consumption and a second set ratio; determining a third reference value based on the product of the average value of each reserved electricity consumption and a third set ratio; wherein the third set ratio is greater than the second set ratio; when the standard deviation of each reserved electricity consumption is greater than or equal to the second reference value and less than or equal to the third reference value, the standard deviation of each reserved electricity consumption is taken as the first standard deviation; when the standard deviation of each reserved electricity consumption is less than the second reference value, the first standard deviation is determined based on the second reference value; when the standard deviation of each reserved electricity consumption is greater than the third reference value, the first standard deviation is determined based on the third reference value.

[0362] As one possible implementation of this application embodiment, the power load level determination device 900 may further include:

[0363] The fifth determining module is used to determine the initial power consumption range corresponding to multiple power consumption load levels based on at least one power consumption threshold.

[0364] The sixth determining module is used to determine, for at least one of multiple power load levels, the target power consumption that is within the initial power consumption range of at least one power load level.

[0365] The first adjustment module is used to adjust at least one power consumption threshold value based on the amount of target power consumption within the initial power consumption range of at least one power consumption load level.

[0366] As one possible implementation of this application, the first adjustment module is specifically used for: counting the total amount of electricity consumption; obtaining the proportion of the target amount of electricity consumption within the initial electricity consumption range of the first electricity load level to the total amount; wherein, the first electricity load level is the highest electricity load level among multiple electricity load levels; when the proportion is higher than a set proportion threshold, increasing the first electricity threshold value among at least one electricity threshold value; wherein, the first electricity threshold value is used to determine the initial electricity consumption range corresponding to the first electricity load level.

[0367] As one possible implementation of this application embodiment, the power load level determination device 900 may further include:

[0368] The judgment module is used to determine whether each power consumption threshold is less than the corresponding set value.

[0369] The second adjustment module is used to adjust the initial setting coefficient corresponding to each power consumption threshold when at least one power consumption threshold is less than the corresponding set value.

[0370] As one possible implementation of this application embodiment, the second adjustment module is specifically used for: updating the initial setting coefficient corresponding to the second power consumption threshold value according to the first preset coefficient when the second power consumption threshold value among the multiple power consumption thresholds is less than the corresponding set value; wherein, the second power consumption threshold value is used to determine the power consumption range corresponding to the lowest level of the second power consumption load level among multiple power consumption load levels; and updating the initial setting coefficient corresponding to the third power consumption threshold value among at least one power consumption threshold value according to the second preset coefficient; wherein, the third power consumption threshold value is used to determine the power consumption range corresponding to the next level below the second power consumption load level.

[0371] As one possible implementation of this application, the second determining module 904 is specifically used for: determining the power consumption range corresponding to multiple power consumption load levels based on at least one power consumption threshold value; determining a target power consumption load level from multiple power consumption load levels based on the power consumption during the target time period and the power consumption range corresponding to the multiple power consumption load levels; wherein the power consumption during the target time period is within the power consumption range corresponding to the target power consumption load level.

[0372] The power load level determination device in this embodiment acquires the power consumption data of the object under test, and obtains the first mean and first standard deviation of each power consumption in the power consumption data; determines at least one power consumption threshold value based on the first mean, the first standard deviation, and an initial setting coefficient corresponding to at least one power consumption threshold value; and determines the target power load level of the object under test in the target time period based on the at least one power consumption threshold value and the power consumption in the target time period. In summary, the at least one power consumption threshold value is specifically determined based on statistical information of the power consumption data of the object under test in multiple time periods, rather than being fixed. Determining the target power load level of the object under test in the target time period based on the determined power consumption threshold value can improve the accuracy and rationality of the determination result. Furthermore, determining the target power load level of the object under test in the target time period based on statistical information of the power consumption data of the object under test in multiple time periods can classify similar power consumption into the same power load level, improving the accuracy of the classification result. Furthermore, it eliminates the need to forcibly classify the electricity consumption of the object under test into all electricity load levels during at least one target time period, thereby improving the accuracy of the classification results (i.e., the target electricity load level).

[0373] To achieve the above embodiments, this application also proposes an electronic device. Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes:

[0374] The memory 1001, the processor 1002, and the computer program stored on the memory 1001 and capable of running on the processor 1002.

[0375] When the processor 1002 executes the program, it implements the method for determining the power load level provided in any of the above embodiments.

[0376] Furthermore, electronic devices also include:

[0377] Communication interface 1003 is used for communication between memory 1001 and processor 1002.

[0378] The memory 1001 is used to store computer programs that can run on the processor 1002.

[0379] The memory 1001 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0380] The processor 1002 is used to implement the method for determining the power load level as described in any of the above embodiments when executing the program.

[0381] If the memory 1001, processor 1002, and communication interface 1003 are implemented independently, then the communication interface 1003, memory 1001, and processor 1002 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0382] Optionally, in a specific implementation, if the memory 1001, processor 1002, and communication interface 1003 are integrated on a single chip, then the memory 1001, processor 1002, and communication interface 1003 can communicate with each other through an internal interface.

[0383] The processor 1002 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0384] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method for determining the power load level as provided in any of the above embodiments.

[0385] To implement the above embodiments, this application also proposes a computer program product that, when executed by an instruction processor, implements the method for determining the power load level provided in any of the above embodiments.

[0386] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0387] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0388] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0389] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0390] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0391] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0392] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0393] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for determining the electricity load level, characterized in that, The method includes: Obtain the electricity consumption data of the object under test; wherein the electricity consumption data includes the electricity consumption for at least one time period; Obtain at least one first mean and a first standard deviation of the said electricity consumption; An intermediate coefficient is determined by multiplying the first standard deviation and the initial set coefficient corresponding to at least one power consumption threshold value; and the at least one power consumption threshold value is determined by the sum of the intermediate coefficient and the first mean value. Based on the at least one power consumption threshold and the power consumption during the target period, determine the target power consumption load level of the object under test during the target period; When there are multiple target time periods, and these multiple target time periods fall within at least two set time windows, the method further includes: The target electricity load level for each target time period is encoded to obtain the encoded value of the target electricity load level for each target time period; Statistical information of the encoded values ​​for each target time period within an arbitrary set time window is obtained, the statistical information including range, second mean, first encoded value, last encoded value, and median; the fluctuation amplitude is determined based on the range, the fluctuation position is determined based on the second mean, the fluctuation trend is determined based on the first encoded value, the last encoded value, and the median; the power consumption fluctuation of the test object within the arbitrary set time window is determined based on at least one of the fluctuation amplitude, the fluctuation position, and the fluctuation trend; the production status of the test object within the arbitrary set time window is determined based on the power consumption fluctuation; wherein, the power consumption fluctuation includes at least one of the following: fluctuation amplitude, fluctuation position, and / or fluctuation trend; The resumption status of the test object is determined based on its production status within at least two set time windows.

2. The method according to claim 1, characterized in that, The step of determining the resumption status of the test object based on its production status within the at least two set time windows includes: When there are two set time windows, if the production status of the first time window is a shutdown state and the production status of the second time window is a production state or a resumption state, then the resumption status of the object under test is determined to be a resumption of production; wherein, the first time window is located before the second time window; When there are three set time windows, if the production status of the third time window is in production, the production status of the fourth time window is in shutdown, and the production status of the fifth time window is in resumption, then the resumption status of the object under test is determined to be resumption of production; wherein, the fourth time window is after the third time window, and the fifth time window is after the fourth time window. When the number of set time windows is at least four, if the production status of the sixth time window among the at least four set time windows is in production or in a resumed state, and the production status of at least the seventh time window is in a shutdown state, then the resumption status of the object under test is determined to be a resumption of production; wherein, the seventh time window is located before the sixth time window.

3. The method according to claim 2, characterized in that, The electricity consumption fluctuations corresponding to the production status include at least one of the following: the median remains stable, the high level remains stable, the median rises slightly, the high level rises slightly, the median falls slightly, the high level falls slightly, the median rises sharply and continuously, the median falls sharply and continuously, the high level falls sharply and continuously, the median increases sharply and then decreases, the median decreases sharply and then increases, the median fluctuates slightly, the high level fluctuates slightly, the median increases slightly and then decreases, the high level increases slightly and then decreases, the median rises slightly and the high level rises slightly, the median decreases slightly and then increases, the high level decreases slightly and then increases, or the high level fluctuates sharply. Wherein, the low bit refers to the average value of the encoded values ​​under each target time period within the set time window being within a first value range; the middle bit refers to the average value of the encoded values ​​under each target time period within the set time window being within a second value range; and the high bit refers to the average value of the encoded values ​​under each target time period within the set time window being within a third value range. Wherein, the lower limit of the first value range is 0, the upper limit of the first value range is the first target value, the lower limit of the second value range is the first target value, the upper limit of the second value range is the second target value, the lower limit of the third value range is the second target value, and the upper and lower limits of the third value range are the third target values. The first target value is determined based on the difference between the coding values ​​corresponding to the target electricity load levels of two adjacent levels. The second target value is a first set multiple of the first target value, and the third target value is a second set multiple of the first target value. The second set multiple is greater than the first set multiple.

4. The method according to claim 2, characterized in that, The power consumption fluctuations corresponding to the shutdown status include at least one of the following: low-level stable fluctuations, low-level slight decreases, mid-level slight decreases, low-level significant and continuous decreases, mid-level significant and continuous decreases, low-level significant decreases followed by increases, mid-level significant decreases followed by increases, low-level slight decreases followed by increases, mid-level slight decreases followed by increases, low-level slight increases followed by decreases, low-level slight increases, mid-level slight increases, low-level significant and continuous increases, mid-level significant and continuous increases, low-level significant and continuous decreases, mid-level significant and continuous decreases, low-level slight fluctuations, mid-level slight fluctuations, low-level slight decreases, mid-level slight decreases, low-level significant fluctuations, or mid-level significant fluctuations.

5. The method according to claim 2, characterized in that, The electricity consumption fluctuations corresponding to the resumption of work status include at least one of the following: stable fluctuation at the median level, stable fluctuation at the high level, slight increase at the median level, slight increase at the high level, significant and continuous increase at the low level, significant and continuous increase at the median level, significant and continuous increase at the high level, significant increase followed by decrease at the median level, significant increase followed by decrease at the high level, significant decrease followed by increase at the median level, significant decrease followed by increase at the high level, slight decrease followed by increase at the median level, slight decrease followed by increase at the median level, slight fluctuation at the median level, significant and continuous decrease at the median level, slight decrease at the median level, or slight decrease at the high level.

6. The method according to any one of claims 1-4, characterized in that, Obtaining at least one first mean and first standard deviation of the electricity consumption includes: Obtain the initial mean and initial standard deviation of the at least one electricity consumption; The reference value range is determined based on the third set multiple, the initial standard deviation, and the initial mean; Based on the reference value range, the electricity consumption of the at least one time period is filtered to obtain each reserved electricity consumption within the reference value range; The first mean is determined based on the mean of each of the reserved electricity consumptions, and the first standard deviation is determined based on the standard deviation of each of the reserved electricity consumptions.

7. The method according to claim 6, characterized in that, Before determining the reference value range based on the third set multiple, the initial standard deviation, and the initial mean, the method further includes: The first reference value is determined based on the product of the first set ratio and the initial mean. Determine whether the initial standard deviation is less than the first reference value; If the initial standard deviation is less than the first reference value, the initial standard deviation is updated according to the first reference value.

8. The method according to claim 6, characterized in that, The step of determining the first standard deviation based on the standard deviation of each of the reserved electricity consumptions includes: The second reference value is determined by multiplying the average value of each of the reserved electricity consumptions by the second set ratio. A third reference value is determined by multiplying the average value of each of the reserved electricity consumptions by a third set ratio; wherein the third set ratio is greater than the second set ratio. If the standard deviation of each of the reserved electricity consumptions is greater than or equal to the second reference value and less than or equal to the third reference value, the standard deviation of each of the reserved electricity consumptions shall be taken as the first standard deviation. If the standard deviation of each of the reserved electricity consumption is less than the second reference value, the first standard deviation shall be determined according to the second reference value; If the standard deviation of each of the reserved electricity consumption is greater than the third reference value, the first standard deviation is determined based on the third reference value.

9. The method according to claim 1, characterized in that, After determining the at least one electricity consumption threshold based on the first mean, the first standard deviation, and an initial setting coefficient corresponding to at least one electricity consumption threshold, the method further includes: Based on the at least one power consumption threshold, determine the initial power consumption range corresponding to multiple power consumption load levels; For at least one of the plurality of power load levels, a target power consumption that falls within the initial power consumption range of the at least one power load level is determined from each of the power consumption levels; The at least one power consumption threshold is adjusted based on the amount of target power consumption within the initial power consumption range of the at least one power consumption load level.

10. The method according to claim 9, characterized in that, The step of adjusting the at least one power consumption threshold based on the amount of target power consumption within the initial power consumption range of the at least one power consumption load level includes: The total amount of electricity consumed is calculated. Obtain the ratio of the target electricity consumption within the initial electricity consumption range of the first electricity consumption load level to the total quantity; wherein, the first electricity consumption load level is the highest electricity consumption load level among the plurality of electricity consumption load levels; If the percentage is higher than a set percentage threshold, the first power consumption threshold among the at least one power consumption threshold is increased; wherein, the first power consumption threshold is used to determine the initial power consumption range corresponding to the first power consumption load level.

11. The method according to claim 1, characterized in that, After determining the at least one electricity consumption threshold based on the first mean, the first standard deviation, and an initial setting coefficient corresponding to at least one electricity consumption threshold, the method further includes: Determine whether each of the stated power consumption thresholds is less than the corresponding set value; If at least one of the power consumption thresholds is less than the corresponding set value, the initial setting coefficient corresponding to each of the power consumption thresholds is adjusted.

12. The method according to claim 11, characterized in that, The step of adjusting the initial setting coefficient corresponding to each of the power consumption thresholds when at least one of the power consumption thresholds is less than the corresponding set value includes: If the second power consumption threshold value among the various power consumption thresholds is less than the corresponding set value, the initial set coefficient corresponding to the second power consumption threshold value is updated according to the first preset coefficient; wherein, the second power consumption threshold value is used to determine the power consumption range corresponding to the lowest second power consumption load level among multiple power consumption load levels; Based on the second preset coefficient, the initial setting coefficient corresponding to the third power consumption threshold among the at least one power consumption threshold is updated; wherein, the third power consumption threshold is used to determine the power consumption range corresponding to the next level below the second power consumption load level.

13. The method according to claim 1 or 2, characterized in that, The step of determining the target electricity load level of the object under test in the target time period based on the at least one electricity consumption threshold and the electricity consumption in the target time period includes: Based on the at least one power consumption threshold, determine the power consumption range corresponding to multiple power load levels; Based on the electricity consumption during the target time period and the electricity consumption range corresponding to the multiple electricity load levels, the target electricity load level is determined from the multiple electricity load levels; The electricity consumption during the target time period is within the electricity consumption range corresponding to the target electricity load level.

14. A device for determining the electricity load level, characterized in that, The device includes: The first acquisition module is used to acquire the electricity consumption data of the object under test; wherein, the electricity consumption data includes the electricity consumption for at least one time period; The second acquisition module is used to acquire at least one first mean and a first standard deviation of the electricity consumption; The first determining module is used to determine an intermediate coefficient based on the product of the first standard deviation and an initial set coefficient corresponding to at least one power consumption threshold, and to determine the at least one power consumption threshold based on the sum of the intermediate coefficient and the first mean. The second determining module is used to determine the target power load level of the object under test in the target time period based on the at least one power consumption threshold value and the power consumption in the target time period; When there are multiple target time periods, and the multiple target time periods fall within at least two preset time windows, the device further includes: The encoding module is used to encode the target electricity load level for each target time period to obtain the encoded value of the target electricity load level for each target time period. The third determining module is used to acquire statistical information of the encoded values ​​for each target time period within an arbitrary set time window. The statistical information includes the range, the second mean, the first encoded value, the last encoded value, and the median. It determines the fluctuation amplitude based on the range, the fluctuation position based on the second mean, and the fluctuation trend based on the first encoded value, the last encoded value, and the median. Based on at least one of the fluctuation amplitude, the fluctuation position, and the fluctuation trend, it determines the power consumption fluctuation of the test object within the arbitrary set time window. Based on the power consumption fluctuation, it determines the production status of the test object within the arbitrary set time window. The power consumption fluctuation includes at least one of the following: fluctuation amplitude, fluctuation position, and / or fluctuation trend. The fourth determination module is used to determine the resumption status of the test object based on the production status of the test object within the at least two set time windows.

15. The apparatus according to claim 14, characterized in that, The fourth determining module is specifically used for: When there are two set time windows, if the production status of the first time window is a shutdown state and the production status of the second time window is a production state or a resumption state, then the resumption status of the object under test is determined to be a resumption of production; wherein, the first time window is located before the second time window; When there are three set time windows, if the production status of the third time window is in production, the production status of the fourth time window is in shutdown, and the production status of the fifth time window is in resumption, then the resumption status of the object under test is determined to be resumption of production; wherein, the fourth time window is after the third time window, and the fifth time window is after the fourth time window. When the number of set time windows is at least four, if the production status of the sixth time window among the at least four set time windows is in production or in a resumed state, and the production status of at least the seventh time window is in a shutdown state, then the resumption status of the object under test is determined to be a resumption of production; wherein, the seventh time window is located before the sixth time window.

16. The apparatus according to claim 15, characterized in that, The electricity consumption fluctuations corresponding to the production status include at least one of the following: the median remains stable, the high level remains stable, the median rises slightly, the high level rises slightly, the median falls slightly, the high level falls slightly, the median rises sharply and continuously, the median falls sharply and continuously, the high level falls sharply and continuously, the median increases sharply and then decreases, the median decreases sharply and then increases, the median fluctuates slightly, the high level fluctuates slightly, the median increases slightly and then decreases, the high level increases slightly and then decreases, the median rises slightly and the high level rises slightly, the median decreases slightly and then increases, the high level decreases slightly and then increases, or the high level fluctuates sharply. Wherein, the low bit refers to the average value of the encoded values ​​under each target time period within the set time window being within a first value range; the middle bit refers to the average value of the encoded values ​​under each target time period within the set time window being within a second value range; and the high bit refers to the average value of the encoded values ​​under each target time period within the set time window being within a third value range. Wherein, the lower limit of the first value range is 0, the upper limit of the first value range is the first target value, the lower limit of the second value range is the first target value, the upper limit of the second value range is the second target value, the lower limit of the third value range is the second target value, and the upper and lower limits of the third value range are the third target values. The first target value is determined based on the difference between the coding values ​​corresponding to the target electricity load levels of two adjacent levels. The second target value is a first set multiple of the first target value, and the third target value is a second set multiple of the first target value. The second set multiple is greater than the first set multiple.

17. The apparatus according to claim 15, characterized in that, The power consumption fluctuations corresponding to the shutdown status include at least one of the following: low-level stable fluctuations, low-level slight decreases, mid-level slight decreases, low-level significant and continuous decreases, mid-level significant and continuous decreases, low-level significant decreases followed by increases, mid-level significant decreases followed by increases, low-level slight decreases followed by increases, mid-level slight decreases followed by increases, low-level slight increases followed by decreases, low-level slight increases, mid-level slight increases, low-level significant and continuous increases, mid-level significant and continuous increases, low-level significant and continuous decreases, mid-level significant and continuous decreases, low-level slight fluctuations, mid-level slight fluctuations, low-level slight decreases, mid-level slight decreases, low-level significant fluctuations, or mid-level significant fluctuations.

18. The apparatus according to claim 15, characterized in that, The electricity consumption fluctuations corresponding to the resumption of work status include at least one of the following: stable fluctuation at the median level, stable fluctuation at the high level, slight increase at the median level, slight increase at the high level, significant and continuous increase at the low level, significant and continuous increase at the median level, significant and continuous increase at the high level, significant increase followed by decrease at the median level, significant increase followed by decrease at the high level, significant decrease followed by increase at the median level, significant decrease followed by increase at the high level, slight decrease followed by increase at the median level, slight decrease followed by increase at the median level, slight fluctuation at the median level, significant and continuous decrease at the median level, slight decrease at the median level, or slight decrease at the high level.

19. The apparatus according to claim 14 or 15, characterized in that, The second acquisition module is specifically used for: Obtain the initial mean and initial standard deviation of the at least one electricity consumption; The reference value range is determined based on the third set multiple, the initial standard deviation, and the initial mean; Based on the reference value range, the electricity consumption of the at least one time period is filtered to obtain each reserved electricity consumption within the reference value range; The first mean is determined based on the mean of each of the reserved electricity consumptions, and the first standard deviation is determined based on the standard deviation of each of the reserved electricity consumptions.

20. The apparatus according to claim 19, characterized in that, The second acquisition module is further configured to: The first reference value is determined based on the product of the first set ratio and the initial mean. Determine whether the initial standard deviation is less than the first reference value; If the initial standard deviation is less than the first reference value, the initial standard deviation is updated according to the first reference value.

21. The apparatus according to claim 19, characterized in that, The second acquisition module is specifically used for: The second reference value is determined by multiplying the average value of each of the reserved electricity consumptions by the second set ratio. A third reference value is determined by multiplying the average value of each of the reserved electricity consumptions by a third set ratio; wherein the third set ratio is greater than the second set ratio. If the standard deviation of each of the reserved electricity consumptions is greater than or equal to the second reference value and less than or equal to the third reference value, the standard deviation of each of the reserved electricity consumptions shall be taken as the first standard deviation. If the standard deviation of each of the reserved electricity consumption is less than the second reference value, the first standard deviation shall be determined according to the second reference value; If the standard deviation of each of the reserved electricity consumption is greater than the third reference value, the first standard deviation is determined based on the third reference value.

22. The apparatus according to claim 14, characterized in that, The device further includes: The fifth determining module is used to determine the initial power consumption range corresponding to multiple power consumption load levels based on the at least one power consumption threshold value; The sixth determining module is used to determine, for at least one of the plurality of power load levels, a target power consumption that is within the initial power consumption range of the at least one power load level; The first adjustment module is used to adjust the at least one power consumption threshold value according to the amount of target power consumption within the initial power consumption range of the at least one power consumption load level.

23. The apparatus according to claim 22, characterized in that, The first adjustment module is specifically used for: The total amount of electricity consumed is calculated. Obtain the ratio of the target electricity consumption within the initial electricity consumption range of the first electricity consumption load level to the total quantity; wherein, the first electricity consumption load level is the highest electricity consumption load level among the plurality of electricity consumption load levels; If the percentage is higher than a set percentage threshold, the first power consumption threshold among the at least one power consumption threshold is increased; wherein, the first power consumption threshold is used to determine the initial power consumption range corresponding to the first power consumption load level.

24. The apparatus according to claim 14, characterized in that, The device further includes: The judgment module is used to determine whether each of the power consumption threshold values ​​is less than the corresponding set value; The second adjustment module is used to adjust the initial setting coefficient corresponding to each of the power consumption thresholds when at least one of the power consumption thresholds is less than the corresponding set value.

25. The apparatus according to claim 24, characterized in that, The second adjustment module is specifically used for: If the second power consumption threshold value among the various power consumption thresholds is less than the corresponding set value, the initial set coefficient corresponding to the second power consumption threshold value is updated according to the first preset coefficient; wherein, the second power consumption threshold value is used to determine the power consumption range corresponding to the lowest second power consumption load level among multiple power consumption load levels; Based on the second preset coefficient, the initial setting coefficient corresponding to the third power consumption threshold among the at least one power consumption threshold is updated; wherein, the third power consumption threshold is used to determine the power consumption range corresponding to the next level below the second power consumption load level.

26. The apparatus according to claim 14 or 15, characterized in that, The second determining module is specifically used for: Based on the at least one power consumption threshold, determine the power consumption range corresponding to multiple power load levels; Based on the electricity consumption during the target time period and the electricity consumption range corresponding to the multiple electricity load levels, the target electricity load level is determined from the multiple electricity load levels; The electricity consumption during the target time period is within the electricity consumption range corresponding to the target electricity load level.

27. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method for determining the power load level as described in any one of claims 1-13.

28. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the method for determining the power load level as described in any one of claims 1-13.

Images