Power failure power shortage evaluation method and related device

Abstract

The invention provides a power failure insufficient power supply quantity evaluation method and a related device, and the method comprises the steps: determining a plurality of adjustment coefficients based on a pre-trained coefficient determination model, the adjustment coefficients being used for dynamically adjusting the adjustment proportion of different time intervals, and the pre-trained coefficient determination model being determined based on historical user power consumption data; acquiring power consumption data and power failure data of a user, and determining power consumption parameters based on the power consumption data of the user; determining a plurality of power utilization characteristics based on the plurality of adjustment coefficients and the power utilization parameters, wherein the power utilization characteristics are used for representing power utilization conditions of the user in different time intervals; and determining the user power failure short power supply quantity based on the plurality of power utilization characteristics and the power failure data. Therefore, on the basis of the determined multiple adjustment coefficients, the power consumption characteristics of the power consumer in different time intervals are determined through the power consumption conditions in different time intervals, and the accuracy of determining the power failure and insufficient power supply quantity of the consumer in different seasons, dates and time periods is improved.

Description

Technical Field

[0001] This invention relates to the field of power technology, and in particular to a method and related apparatus for assessing power outage and power shortage. Background Technology

[0002] Accurately assessing the amount of power supply loss due to user outages is a crucial data foundation for measuring the reliability of the power supply system and formulating outage plans. However, methods that rely on user capacity and annual average load factor to calculate user power supply loss are inaccurate and do not meet current needs. Furthermore, the load factor used in calculating power supply loss is based on the previous year's specific conditions, resulting in significant errors. This leads to insufficient application of the average system equivalent outage time as an evaluation indicator, preventing it from playing its due role.

[0003] Currently, when power supply companies optimize power outage plans, they mainly reduce the impact on the number of households affected by power outages through comprehensive power outage measures such as event merging, without considering the amount of power shortage caused by power outages on different dates and at different times. Summary of the Invention

[0004] This application provides a method and related apparatus for assessing power outage supply shortages, which can accurately and scientifically determine the power outage supply shortages for users with different power loads in different time intervals.

[0005] In a first aspect, embodiments of this application provide a method for assessing power shortage during power outages, applied to a server in a power supply system, the method comprising:

[0006] Multiple adjustment coefficients are determined based on a pre-trained coefficient determination model. These adjustment coefficients are used to dynamically adjust the adjustment ratio in different time intervals. The pre-trained coefficient determination model is based on historical user electricity consumption data.

[0007] Acquire user electricity consumption data and power outage data, and determine electricity consumption parameters based on the user electricity consumption data;

[0008] Multiple electricity consumption characteristics are determined based on the multiple adjustment coefficients and the electricity consumption parameters. These electricity consumption characteristics are used to characterize the user's electricity consumption in different time intervals.

[0009] The power outage amount for the user is determined based on the multiple power consumption characteristics and the power outage data.

[0010] In one possible embodiment, the electricity consumption parameters include annual peak-valley difference rate parameters and annual average load parameters, and the step of determining the electricity consumption parameters based on the user's electricity consumption data includes:

[0011] Based on the user's electricity consumption data, determine the user's annual electricity consumption parameters and annual load parameters;

[0012] The annual average load parameter is determined based on the user's annual electricity consumption parameter and the first task model. The annual average load parameter is the energy consumed by each user per unit time in a year.

[0013] The annual peak-valley difference rate parameter is determined based on the annual load parameters and the first task model.

[0014] In one possible embodiment, the plurality of adjustment coefficients includes at least one of a first type of adjustment coefficient, a second type of adjustment coefficient, and a third type of adjustment coefficient; the time interval includes a seasonal range and / or a day type; the first type of adjustment coefficient corresponds to the seasonal range, and the second type of adjustment coefficient and / or the third type of adjustment coefficient corresponds to the day type; the plurality of electricity consumption characteristics includes at least one of a quarterly characteristic, a daily characteristic, and a time period characteristic;

[0015] The determination of multiple electricity consumption characteristics based on the multiple adjustment coefficients and the electricity consumption parameters includes:

[0016] The quarterly characteristics are determined based on the first type of adjustment coefficient and the annual average load parameter, wherein the first type of adjustment coefficient includes a first seasonal adjustment coefficient and a second seasonal adjustment coefficient.

[0017] The daily characteristics are determined based on the second type of adjustment coefficient and the quarterly characteristics, wherein the second type of adjustment coefficient includes a first type of daily average adjustment coefficient and a second type of daily average adjustment coefficient.

[0018] The time period characteristics are determined based on the third type of adjustment coefficient, the annual peak-to-valley difference rate parameter, and the daily characteristics. The third type of adjustment coefficient includes the first type of daily valley difference rate adjustment coefficient and the second type of daily valley difference rate adjustment coefficient.

[0019] In one possible embodiment, determining the quarterly characteristics based on the first type of adjustment coefficient and the annual average load parameter includes:

[0020] Input the first seasonal adjustment coefficient, the second seasonal adjustment coefficient, and the annual average load parameter into the second task model;

[0021] The seasonal characteristics are obtained by performing a first feature calculation on the second task model. The first feature calculation includes determining a first time characteristic based on the annual average load parameter, matching a first seasonal adjustment coefficient or a second seasonal adjustment coefficient based on the first time characteristic, and determining the seasonal characteristics based on at least one of the first seasonal adjustment coefficient or the second seasonal adjustment coefficient and the annual average load parameter.

[0022] In one possible embodiment, the first type of daily average adjustment coefficient and the first seasonal adjustment coefficient have a corresponding correlation, and the second type of daily average adjustment coefficient and the first seasonal adjustment coefficient have a corresponding correlation.

[0023] The determination of the daily characteristics based on the second type of adjustment coefficient and the quarterly characteristics includes:

[0024] The first type of daily average adjustment coefficient, the second type of daily average adjustment coefficient, and the seasonal characteristics are input into the third task model;

[0025] The daily characteristics are obtained by performing a second feature calculation on the third task model. The second feature calculation includes determining a second time characteristic based on the annual average load parameter, matching the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient based on the second time characteristic, and determining the daily characteristics based on at least one of the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient and the seasonal characteristics.

[0026] In one possible embodiment, the first type of daily valley difference rate adjustment coefficient and the first type of daily average adjustment coefficient have a corresponding correlation, and the second type of daily valley difference rate adjustment coefficient and the second type of daily average adjustment coefficient have a corresponding correlation.

[0027] The determination of the time period characteristics based on the third type of adjustment coefficient, the annual peak-to-valley difference rate parameter, and the daily characteristics includes:

[0028] The first type of daily valley difference rate adjustment coefficient, the second type of daily valley difference rate adjustment coefficient, the annual peak-valley difference rate parameter, and the daily characteristics are input into the fourth task model;

[0029] The time period characteristics are obtained by performing a third feature calculation on the fourth task model. The third feature calculation includes determining a third time characteristic based on the annual average load parameter, matching the first type of daily valley difference rate adjustment coefficient or the second type of daily valley difference rate adjustment coefficient based on the third time characteristic, determining a daily peak valley difference rate parameter based on at least one of the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient and the annual peak valley difference rate parameter, and determining the time period characteristics based on the daily peak valley difference parameter and the daily characteristics.

[0030] In one possible embodiment, the first seasonal adjustment factor is an adjustment factor within a first seasonal range, and the second seasonal adjustment factor is an adjustment factor within a second seasonal range, wherein the first seasonal adjustment factor includes 1.56 and the second seasonal adjustment factor includes 0.59;

[0031] The first type of daily average adjustment factor includes multiple first date adjustment factors within the first seasonal range, the multiple first date adjustment factors including 0.43, 0.88, and 1.65; the second type of daily average adjustment factor includes multiple second date adjustment factors within the second seasonal range, the multiple second date adjustment factors including 0.47, 0.85, and 1.62.

[0032] The first type of daily valley difference rate adjustment coefficient includes multiple first peak valley difference rate adjustment coefficients corresponding to the first date adjustment coefficient, and the multiple first peak valley difference rate adjustment coefficients include 0.93, 0.92, and 0.95; the multiple second date adjustment coefficients include multiple second peak valley difference rate adjustment coefficients corresponding to the second date adjustment coefficient, and the multiple second peak valley difference rate adjustment coefficients include 0.95, 0.96, and 0.97.

[0033] In one possible embodiment, the power outage data is used to characterize the user's power outage time information, the plurality of electricity consumption characteristics include the time period characteristics, and determining the user's power outage shortage based on the plurality of electricity consumption characteristics and the power outage data includes:

[0034] The peak and valley power outage duration is determined based on the power outage data and preset peak and valley time periods;

[0035] The power outage quantity is determined based on the peak and valley power outage duration and the time period characteristics.

[0036] Secondly, embodiments of this application provide a computer-readable storage medium storing a charging efficiency optimization program for a charging pile. The charging efficiency optimization program for the charging pile includes execution instructions. When a processor executes the execution instructions stored in the memory, the processor performs some or all of the steps described in the first aspect.

[0037] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and when the processor executes the one or more programs, the processor executes some or all of the instructions of the steps described in the first aspect of the embodiments of this application.

[0038] Fourthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program being operable to cause a computer to perform some or all of the steps described in the first aspect of embodiments of this application. The computer program product may be a software installation package.

[0039] By implementing the embodiments of this application, multiple adjustment coefficients are determined based on a pre-trained coefficient determination model. These adjustment coefficients are used to dynamically adjust the adjustment weight in different time intervals. The pre-trained coefficient determination model is based on historical user electricity consumption data. User electricity consumption data and power outage data are acquired, and electricity consumption parameters are determined based on the user electricity consumption data. Multiple electricity consumption characteristics are determined based on the multiple adjustment coefficients and the electricity consumption parameters. These electricity consumption characteristics are used to characterize the user's electricity consumption in different time intervals. The power outage supply is determined based on the multiple electricity consumption characteristics and the power outage data. In this way, based on the determined multiple adjustment coefficients, the electricity consumption characteristics of power users in different time intervals are determined through the electricity consumption in different time intervals, improving the accuracy of determining the power outage supply of users in different seasons, dates, and time periods. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the accompanying drawings used in the embodiments of the present invention or the background art will be described below.

[0041] Figure 1 This is a schematic diagram of the architecture of a power outage and power shortage assessment system provided in an embodiment of this application;

[0042] Figure 2 This is a flowchart illustrating a power outage and power shortage assessment method provided in an embodiment of this application;

[0043] Figure 3 This is a coefficient matching diagram of the first power outage power shortage assessment method provided in the embodiments of this application;

[0044] Figure 4 This is a schematic diagram of coefficient matching for the second power outage power shortage assessment method provided in the embodiments of this application;

[0045] Figure 5 This is a schematic diagram of the task model of a power outage and power shortage assessment method provided in an embodiment of this application;

[0046] Figure 6 This is a schematic diagram of the structure of a power outage and power shortage assessment device provided in an embodiment of this application;

[0047] Figure 7 This is a schematic diagram of another power outage and power shortage assessment device provided in an embodiment of this application;

[0048] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0049] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0050] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects and not to describe a particular order. Furthermore, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or electronic device that includes a series of steps or units is not limited to the listed steps or units, but in an alternative example includes steps or units not listed, or in an alternative example includes other steps or units inherent to these processes, methods, products, or electronic devices.

[0051] References to embodiments herein mean that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0052] Accurately assessing the amount of power supply loss due to user outages is a crucial data foundation for measuring the reliability of the power supply system and formulating outage plans. However, methods that rely on user capacity and annual average load factor to calculate user power supply loss are inaccurate and do not meet current needs. Furthermore, the load factor used in calculating power supply loss is based on the previous year's specific conditions, resulting in significant errors. This leads to insufficient application of the average system equivalent outage time as an evaluation indicator, preventing it from playing its due role.

[0053] Currently, when power supply companies optimize power outage plans, they mainly reduce the impact on the number of households affected by power outages through comprehensive power outage measures such as event merging, without considering the amount of power shortage caused by power outages on different dates and at different times.

[0054] To address the aforementioned issues, this application provides a method and related apparatus for assessing power outage and power supply shortages. Based on multiple predetermined adjustment coefficients, the method determines the electricity consumption characteristics of power users in different time intervals by analyzing electricity usage data from different time intervals, thereby improving the accuracy of determining power outage and power supply shortages for users in different seasons, dates, and time periods.

[0055] The power outage and power shortage assessment method provided in this application embodiment can be applied to, for example... Figure 1Please refer to the power outage and power shortage assessment system shown. Figure 1 , Figure 1 This is a schematic diagram of the architecture of a power outage and power shortage assessment system provided in an embodiment of this application. The power outage and power shortage assessment system 100 includes a data acquisition device 110 and a server 120. The data acquisition device 110 can communicate with the server 120 through a network. The data acquisition device 110 refers to statistical data, etc.

[0056] In this solution, the data acquisition device 110 is primarily responsible for collecting user electricity consumption data and transmitting information to the server 120. The server 120 is a remote computer used for processing large amounts of computational tasks and storing data. In this solution, the server 120 is equipped with a pre-trained coefficient determination model and a multi-task model of electricity consumption characteristics, used to determine multiple adjustment coefficients and perform multi-task analysis calculations of electricity consumption characteristics. The server 120 can also be used to collect data during model usage, such as historical user electricity consumption data, facilitating subsequent optimization of the pre-trained coefficient determination model and the multi-task model of electricity consumption characteristics.

[0057] Based on this, this application provides a method for assessing power outage and power shortage, which will be described in detail below with reference to the accompanying drawings.

[0058] Please see Figure 2 , Figure 2 This is a flowchart illustrating a power outage and power shortage assessment method provided in an embodiment of this application, as shown below. Figure 2 As shown, the method includes the following steps:

[0059] S210, multiple adjustment coefficients are determined based on a pre-trained coefficient determination model. The adjustment coefficients are used to dynamically adjust the adjustment ratio in different time intervals. The pre-trained coefficient determination model is determined based on historical user electricity consumption data.

[0060] Among them, multiple adjustment coefficients include the first type of adjustment coefficient, the second type of adjustment coefficient, and the third type of adjustment coefficient. The first type of adjustment coefficient includes the first seasonal adjustment coefficient and the second seasonal adjustment coefficient. The second type of adjustment coefficient includes the first type of daily average adjustment coefficient and the second type of daily average adjustment coefficient. The third type of adjustment coefficient includes the first type of daily valley difference rate adjustment coefficient and the second type of daily valley difference rate adjustment coefficient. The first-season adjustment factor is the adjustment factor within the first-season range, and the second-season adjustment factor is the adjustment factor within the second-season range. The first-season adjustment factor includes 1.56, and the second-season adjustment factor includes 0.59. The first-category daily average adjustment factor includes multiple first-date adjustment factors within the first-season range, including 0.43, 0.88, and 1.65. The second-category daily average adjustment factor includes multiple second-date adjustment factors within the second-season range, including 0.47, 0.85, and 1.62. The first-category daily trough rate adjustment factor includes multiple first-peak trough rate adjustment factors corresponding to the first-date adjustment factor, including 0.93, 0.92, and 0.95. The multiple second-date adjustment factors include multiple second-peak trough rate adjustment factors corresponding to the second-date adjustment factor, including 0.95, 0.96, and 0.97.

[0061] The first and second seasonal adjustment coefficients are used to measure the fluctuation characteristics of users' electricity consumption in different seasons.

[0062] Optionally, the methods for determining the first-season adjustment coefficient and the second-season adjustment coefficient can be as follows: The coefficient determination model filters out all data points for the first-season period (June-October) and all data points for the second-season period (January-May, November, December) from historical data. It then calculates the average of all hourly loads throughout the year, i.e., the annual average load; calculates the average of all hourly loads within all first-season periods; calculates the average of all hourly loads within all second-season periods; and obtains the first-season adjustment coefficient as (average of all hourly loads within the first-season period / annual average load) and the second-season adjustment coefficient as (average of all hourly loads within the second-season period / annual average load).

[0063] Optionally, the process for determining the first date adjustment factor and the second date adjustment factor can be as follows: The factor determination model filters out all dates that fall within the first or second season's timeframe and are holidays from historical data. The average daily electricity consumption (kWh) of all these holidays is calculated, and then divided by 24 to obtain the average hourly load for holidays within the first season's timeframe. The average daily electricity consumption equals the sum of electricity consumption at all sampling points on that day. The average hourly load for all dates within the first or second season's timeframe is then calculated, representing the average load for the first or second season's timeframe. The first date adjustment factor and the second date adjustment factor are obtained by dividing the average load for rest days, workdays, and holidays within the first or second season's timeframe by the average load for the first or second season's timeframe. For example, the calculation method for the first date adjustment factor includes: average load on holidays in the first season / average load in the first season, average load on rest days in the first season / average load in the first season, and average load on weekdays in the first season / average load in the first season; the calculation method for the second date adjustment factor includes: average load on holidays in the second season / average load in the second season, average load on rest days in the second season / average load in the second season, and average load on weekdays in the second season / average load in the second season.

[0064] Optionally, the method for determining the first peak-valley difference rate adjustment coefficient and the second peak-valley difference rate adjustment coefficient may include: the coefficient determination model obtains the annual peak-valley difference rate calculated based on historical data. Taking the calculation of the adjustment coefficient for holidays in the first seasonal range as an example: all dates of holidays in the first seasonal range in the historical data are screened out. For each screened day, its daily peak-valley difference rate is calculated. Daily peak-valley difference rate = (maximum load of the day - minimum load of the day) / maximum load of the day. The average of the daily peak-valley difference rates of all these holidays in the first seasonal range is calculated to obtain a first peak-valley difference rate adjustment coefficient. The calculation methods for the first seasonal range rest days, the first seasonal range work days, the second seasonal range holidays, the second seasonal range rest days, and the second seasonal range work days are similar and will not be repeated here.

[0065] Optionally, the above coefficient determination model can be an adjustment coefficient evaluation model based on coupling degree. The adjustment coefficient evaluation model based on coupling degree can include the following calculation logic:

[0066]

[0067] Where C is the adjustment coefficient, S 1,j Let S be the daily peak-to-valley difference at time j. 2,j Let be the peak-valley difference at time j.

[0068] It should be noted that the above method for determining the adjustment coefficient is only an example, and the specific calculation is not limited here.

[0069] S220: Obtain user electricity consumption data and power outage data, and determine electricity consumption parameters based on the user electricity consumption data.

[0070] The user electricity consumption data includes the user's electricity consumption, maximum load, and minimum load within the current statistical period. The statistical period includes a year, and the current statistical period can be a time period length calculated backwards from the current time point, or a time period length calculated backwards from a specified time point. For example, the user's electricity consumption, maximum load, and minimum load could be the user's annual electricity consumption, annual maximum load, and annual minimum load. In some cases, the statistical period can also be a quarter, month, day, etc., which is not limited here.

[0071] Among them, electricity consumption parameters are used to describe the two dimensions of the volume and volatility of a user's electricity consumption, and as a whole, they characterize the electricity load characteristics of a power user. For example, the valley difference rate parameter and the average load parameter within the statistical period. If the statistical period is an year, it can be the annual valley difference rate parameter, the annual valley difference rate parameter, etc.

[0072] The average load parameter mentioned above can be used to characterize the average load per hour within the statistical period. The peak-valley difference rate mentioned above is used to characterize the load fluctuation in the user's region within the statistical period. The larger the peak-valley difference rate, the greater the load fluctuation within the statistical period. The smaller the peak-valley difference rate, the smaller the load fluctuation within the statistical period.

[0073] In one possible embodiment, the electricity consumption parameters include an annual peak-valley difference rate parameter and an annual average load parameter. The step of determining the electricity consumption parameters based on the user's electricity consumption data includes: determining the user's annual electricity consumption parameter and annual load parameter based on the user's electricity consumption data; determining the annual average load parameter based on the user's annual electricity consumption parameter and a first task model, wherein the annual average load parameter is the energy consumed by each user per unit time during the year; and determining the annual peak-valley difference rate parameter based on the annual load parameter and the first task model.

[0074] Among them, the electricity consumption parameters are the annual peak-valley difference rate parameter and the annual average load parameter, that is, the statistical period is one year. The user electricity consumption data includes the user's annual electricity consumption, annual maximum load and annual minimum load.

[0075] The determination of electricity consumption parameters based on the user's electricity consumption data can be achieved through the following methods: Extracting standard data for a specified user in the current statistical period from the user's electricity consumption data. This user's electricity consumption data includes multiple elements such as data timestamp, electricity consumption, and active power, used for data extraction and alignment. Finding the meter readings at the beginning and end of the statistical period and calculating the difference to obtain the user's annual electricity consumption parameters; or, performing multiplication and accumulation operations based on the power value and time interval at each time point to obtain the user's annual electricity consumption parameters. Traversing the power sampling values ​​at all time points within the statistical period to determine the annual load parameters, collecting and extracting extreme values. These extreme values ​​include at least one of the maximum or minimum load. When the statistical period is annual, specifically, it can be at least one of the annual maximum or minimum load.

[0076] The first task model includes a first model formula and a second model formula. The first model formula divides the calculated electricity consumption by the total number of hours in the statistical period. The unit of electricity consumption is kWh. The annual average load parameter calculated by the first model formula of the first task model is an average description of the user's electricity consumption scale, that is, the energy consumed by each user per unit time in a year. The second model formula is used to calculate the difference between the calculated maximum load and minimum load and then calculate the ratio with the maximum load. The annual peak-valley difference rate parameter calculated by the second model formula of the first task model can reflect the fluctuation range and unevenness of the user's load throughout the year. The closer the value of the peak-valley difference rate parameter is to 1, the greater the peak-valley difference; the closer the value of the peak-valley difference rate parameter is to 0, the more stable the electricity consumption.

[0077] Specifically, the formula for the first model mentioned above includes: Annual average load parameter = User's annual electricity consumption parameter / T, where T is the number of hours included in the statistical period, preferably T = 8760.

[0078] Specifically, the formula for the second model mentioned above includes: Annual peak-valley difference rate parameter = (Annual maximum load - Annual minimum load) / Annual maximum load.

[0079] As can be seen, in this embodiment, by statistically analyzing the electricity consumption parameters and annual load parameters of users within the statistical period, the average hourly load and peak-valley difference rate within the statistical period can be determined, which can improve the accuracy and standardization of the subsequent power outage and power shortage determination process.

[0080] S230, based on the multiple adjustment coefficients and the power consumption parameters, multiple power consumption characteristics are determined, and the power consumption characteristics are used to characterize the power consumption of the user in the different time intervals.

[0081] Among them, electricity consumption refers to the characteristics of electricity consumption within different time intervals, such as quarters, months, weeks, days, etc. Electricity consumption includes, for example, load characteristics and peak-valley difference characteristics within different time intervals.

[0082] In one possible embodiment, the plurality of adjustment coefficients includes at least one of a first type of adjustment coefficient, a second type of adjustment coefficient, and a third type of adjustment coefficient; the time interval includes a seasonal range and / or a day type; the first type of adjustment coefficient corresponds to the seasonal range, and the second type of adjustment coefficient and / or the third type of adjustment coefficient corresponds to the day type; the plurality of electricity consumption characteristics includes at least one of a quarterly characteristic, a daily characteristic, and a time period characteristic; determining the plurality of electricity consumption characteristics based on the plurality of adjustment coefficients and the electricity consumption parameters includes: determining the quarterly characteristic based on the first type of adjustment coefficient and the annual average load parameter, wherein the first type of adjustment coefficient includes a first seasonal adjustment coefficient and a second seasonal adjustment coefficient; determining the daily characteristic based on the second type of adjustment coefficient and the quarterly characteristic, wherein the second type of adjustment coefficient includes a first type of daily average adjustment coefficient and a second type of daily average adjustment coefficient; and determining the time period characteristic based on the third type of adjustment coefficient, the annual peak-valley difference rate parameter, and the daily characteristic, wherein the third type of adjustment coefficient includes a first type of daily valley difference rate adjustment coefficient and a second type of daily valley difference rate adjustment coefficient.

[0083] The time interval includes a seasonal range and a day type. The seasonal range can be based on either seasons or months. For example, a seasonal range could be June-October, January-May, or November-December. The specific months can be adjusted according to actual conditions. The optimal division criteria can be determined based on simulation results from a simulation model. In this embodiment, June-October is preferred, as are January-May and November-December. The day type can be based on different types of dates. For example, day types can include rest days, holidays, and workdays. Holidays can include Spring Festival, Qingming Festival, Labor Day, Dragon Boat Festival, Mid-Autumn Festival, National Day, and New Year's Day. Rest days are those other than holidays, such as Saturdays and Sundays. Workdays are those other than holidays and rest days. For example, in some cases, it may also include some regional holidays, which are not limited here.

[0084] In some cases where the above date divisions overlap, such as holidays coinciding with Saturdays and Sundays, a priority coefficient or coupling coefficient can be pre-set. The priority coefficient defines the overlapping holiday / Sunday date as either a holiday or a rest day, and uses the adjustment coefficient of either holiday or rest day for subsequent calculations. The coupling coefficient can be used to couple the adjustment coefficients of rest days and holidays to obtain a new adjustment coefficient. For example, the coupling adjustment coefficient = (weight 1 × holiday coefficient) + (weight 2 × rest day coefficient). The weights 1 and 2 can be determined as follows: weight 1 = average load on overlapping days / average load on pure holidays, weight 2 = average load on overlapping days / average load on pure rest days. The sum of weights 1 and 2 equals 1. Weights 1 and 2 can also be assigned empirically; if the characteristics of holidays are considered to have a greater impact, they can be given a higher weight.

[0085] Among them, the quarterly characteristics are the electricity consumption characteristics of the aforementioned seasonal range, the daily characteristics are the electricity consumption characteristics of the aforementioned daily type, and the time period characteristics are the electricity consumption characteristics of different time periods within the daily type.

[0086] Specifically, the aforementioned first-season adjustment coefficient can correspond to one interval within the seasonal range, such as the first seasonal range, and the second-season adjustment coefficient can correspond to another interval within the seasonal range, such as the second seasonal range; the aforementioned first-type daily average adjustment coefficient corresponds to the first seasonal range, and the aforementioned second-type daily average adjustment coefficient corresponds to the second seasonal range. Specifically, the first-type daily average adjustment coefficient corresponds to holidays, rest days, and workdays within the first seasonal range, and the second-type daily average adjustment coefficient corresponds to holidays, rest days, and workdays within the second seasonal range; the aforementioned first-type daily valley difference rate adjustment coefficient can correspond to the first seasonal range, and the second-type daily valley difference rate adjustment coefficient can correspond to the second seasonal range, and the first-type daily valley difference rate adjustment coefficient and the second-type daily valley difference rate adjustment coefficient correspond to different time periods within different day types in the second seasonal range.

[0087] Specifically, the quarterly characteristics are determined by combining and processing the first type of adjustment coefficient and the annual average load parameter. Specifically, the quarterly characteristics are obtained by combining and processing the first and second seasonal adjustment coefficients with the annual average load parameters for different dates. These quarterly characteristics may include features corresponding to either the first or second seasonal range. The daily characteristics are determined by combining and processing the second type of adjustment coefficient and the quarterly characteristics. Specifically, the daily characteristics are obtained by matching the date characteristics of the quarterly characteristics with specific date types that match the quarterly characteristics. These specific date types include holidays, rest days, and workdays. The time-period characteristics are determined by combining and processing the third type of adjustment coefficient and the daily characteristics. Specifically, the time-period characteristics are obtained by matching the first and second types of daily valley difference rate adjustment coefficients with the daily characteristics and different time periods under specific dates that match the daily characteristics.

[0088] As can be seen, in this embodiment, the electricity consumption characteristics of power users in different time intervals are determined by the electricity consumption situation in different time intervals, thereby improving the accuracy of determining the power outage and power shortage of users in different seasons, dates and time periods.

[0089] In one possible embodiment, determining the quarterly characteristics based on the first type of adjustment coefficient and the annual average load parameter includes: inputting the first seasonal adjustment coefficient, the second seasonal adjustment coefficient, and the annual average load parameter into a second task model; obtaining the seasonal characteristics, wherein the seasonal characteristics are obtained by performing a first feature calculation on the second task model, the first feature calculation including determining a first time characteristic based on the annual average load parameter, matching the first seasonal adjustment coefficient or the second seasonal adjustment coefficient based on the first time characteristic, and determining the seasonal characteristics based on at least one of the first seasonal adjustment coefficient or the second seasonal adjustment coefficient and the annual average load parameter.

[0090] The second task model is a computational module containing processing logic. After inputting the first seasonal adjustment coefficient, the second seasonal adjustment coefficient, and the annual average load parameter, it determines the first time characteristic of the annual average load parameter. The first time characteristic refers to the seasonal range in which the annual average load parameter falls. For example, it could determine whether the annual average load parameter falls within the first or second seasonal range, and then match the corresponding seasonal adjustment coefficient based on the determined seasonal range. The matched seasonal adjustment coefficient is then used to calculate the corresponding seasonal characteristics of the annual average load parameter, which are then obtained for further calculations.

[0091] Specifically, the processing logic for the second task model is constructed. This model incorporates a calendar logic judgment module. Upon receiving the input date features, this module compares them with the seasonal rules defined above. After matching, a first time flag is output, which includes either `season-flag=1` or `season-flag=2`, representing the first and second seasons respectively. If `season-flag=1`, the first season adjustment coefficient is matched; if `season-flag=2`, the second season adjustment coefficient is matched. Based on the matched first or second season adjustment coefficient, the seasonal features are calculated using the annual average load parameter. The calculated seasonal features are returned as the result. This result can be directly displayed to the user or passed to the next calculation module for further calculation of daily features.

[0092] Preferably, the first seasonal adjustment factor is an adjustment factor within the first seasonal range, and the second seasonal adjustment factor is an adjustment factor within the second seasonal range. The first seasonal adjustment factor includes 1.56, and the second seasonal adjustment factor includes 0.59.

[0093] The seasonal characteristics determined based on at least one of the first or second seasonal adjustment coefficients and the annual average load parameter can be calculated using the following formula: Seasonal average load = Annual average load × Seasonal average load adjustment coefficient, whereby the seasonal average load is the seasonal characteristic.

[0094] For example, the first season is defined as June 1st 00:00 to October 31st, and the second season is defined as January 1st 00:00 to May 31st and November 1st 00:00 to December 31st. The adjustment factor for the first season is 1.56, and the adjustment factor for the second season is 0.59. The annual average load parameters are input into the second task model, and the first time characteristic of the annual average load parameters is extracted. The first time characteristic indicates that the annual average load parameter A is within the first season range, and the annual average load parameter B is within the second season range. Therefore, the annual average load parameter A is matched with the first season adjustment factor of 1.56, and the annual average load parameter B is matched with the second season adjustment factor of 0.59. Based on this, calculations are performed to obtain the seasonal average load as the seasonal characteristic: A × 1.56 and / or B × 0.59.

[0095] As can be seen, in this embodiment, the selection of coefficients is driven by date determination, which refines the macroscopic annual average load into a seasonal average load that better reflects seasonal changes, thereby improving the accuracy of determining the power outage and power shortage of users under different seasons, dates, and time periods.

[0096] In one possible embodiment, the first type of daily average adjustment coefficient and the first seasonal adjustment coefficient have a corresponding correlation, and the second type of daily average adjustment coefficient and the seasonal adjustment coefficient have a corresponding correlation; determining the daily characteristic based on the second type of adjustment coefficient and the seasonal characteristic includes: inputting the first type of daily average adjustment coefficient, the second type of daily average adjustment coefficient, and the seasonal characteristic into a third task model; obtaining the daily characteristic, wherein the daily characteristic is obtained by performing a second feature calculation on the third task model, the second feature calculation includes determining a second time characteristic based on the annual average load parameter, matching the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient based on the second time characteristic, and determining the daily characteristic based on at least one of the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient and the seasonal characteristic.

[0097] The first type of daily average adjustment coefficient is used for the first season and is based on the average load of the first season, further distinguishing between holidays, rest days and workdays. The second type of daily average adjustment coefficient is used for the second season and is based on the average load of the second season, with further refinement.

[0098] In this process, the first type of daily average adjustment coefficient, the second type of daily average adjustment coefficient, and the seasonal characteristic (i.e., the seasonal average load calculated in the previous step) are used as inputs to the third task model. The second time characteristic of the seasonal characteristic is determined. This second time characteristic refers to the date type range within which the seasonal characteristic falls. For example, it could be determining the date type range of the seasonal characteristic, such as rest days, holidays, and workdays. The corresponding daily average adjustment coefficient is then matched based on the determined date type range. The matched daily average adjustment coefficient is then used to calculate the corresponding daily characteristic, which is then used for the next calculation.

[0099] The first type of daily average adjustment coefficient includes daily average adjustment coefficients corresponding to different date characteristics. For example, it may include first daily average adjustment coefficient A, first daily average adjustment coefficient B, and first daily average adjustment coefficient C. The second type of daily average adjustment coefficient includes daily average adjustment coefficients corresponding to different date characteristics. For example, it may include second daily average adjustment coefficient D, second daily average adjustment coefficient E, and second daily average adjustment coefficient F.

[0100] Specifically, the third task model includes a computational module for processing logic, constructs the processing logic for the third task model, and has a built-in calendar logic judgment module. The third task model comprises a two-layer judgment workflow. The first layer reuses the seasonal type determined in the second task model to determine whether it belongs to the first or second season. Then, it enters the second layer, where the received date features are compared with the aforementioned defined date rules. After matching, a second time flag is output. The second time flag includes day-flag=1, day-flag=2, or day-flag=3, representing rest days, holidays, and workdays, respectively. Based on the determined second and first time flags, a daily average adjustment coefficient is matched.

[0101] Please refer to Figure 3 , Figure 3 A coefficient matching diagram for the first power outage power shortage assessment method provided in this application embodiment is shown below. Figure 3 As shown, if day-flag = 1 and season-flag = 1, it matches the average adjustment factor A for the first day; if day-flag = 2 and season-flag = 1, it matches the average adjustment factor B for the first day; if day-flag = 3 and season-flag = 1, it matches the average adjustment factor C for the first day; if day-flag = 1 and season-flag = 2, it matches the average adjustment factor D for the second day; if day-flag = 2 and season-flag = 2, it matches the average adjustment factor E for the second day; if day-flag = 3 and season-flag = 2, it matches the average adjustment factor F for the second day.

[0102] Specifically, the aforementioned first type of daily average adjustment coefficient includes multiple first date adjustment coefficients within the first seasonal range, wherein the multiple first date adjustment coefficients include 0.43, 0.88, and 1.65; the second type of daily average adjustment coefficient includes multiple second date adjustment coefficients within the second seasonal range, wherein the multiple second date adjustment coefficients include 0.47, 0.85, and 1.62; that is, the first daily average adjustment coefficient A is preferably 0.43, the first daily average adjustment coefficient B is preferably 0.88, the first daily average adjustment coefficient C is preferably 1.65, the second daily average adjustment coefficient D is preferably 0.47, the second daily average adjustment coefficient E is preferably 0.85, and the second daily average adjustment coefficient F is preferably 1.62.

[0103] After determining the daily average adjustment coefficient, the second-level workflow performs calculations based on the matched first-type or second-type daily average adjustment coefficient and the annual average load parameter. Specifically, the calculation process may include: Daily average load = Seasonal average load × Daily average load adjustment coefficient. The above-mentioned daily average load is the daily characteristic, and the daily average load adjustment coefficient is at least one of the matched first-day average adjustment coefficient A, first-day average adjustment coefficient B, first-day average adjustment coefficient C, second-day average adjustment coefficient D, second-day average adjustment coefficient E, and second-day average adjustment coefficient F.

[0104] As can be seen, in this embodiment, the seasonal load characteristics are refined to the daily load characteristics, and the user's electricity consumption characteristics are amplified step by step, so that the load forecasting and assessment can reflect the user's electricity consumption habits extremely accurately, and improve the accuracy of determining the power outage and power shortage of users in different seasons, dates and time periods.

[0105] In one possible embodiment, the first type of daily valley difference rate adjustment coefficient and the first type of daily average adjustment coefficient have a corresponding correlation, and the second type of daily valley difference rate adjustment coefficient and the second type of daily average adjustment coefficient have a corresponding correlation; determining the time period characteristics based on the third type of adjustment coefficient, the annual peak-valley difference rate parameter, and the daily characteristics includes: inputting the first type of daily valley difference rate adjustment coefficient, the second type of daily valley difference rate adjustment coefficient, the annual peak-valley difference rate parameter, and the daily characteristics into a fourth task model; obtaining the time period characteristics, wherein the time period characteristics are obtained by the fourth task model through third feature calculation, the third feature calculation includes determining a third time characteristic based on the annual average load parameter, matching the first type of daily valley difference rate adjustment coefficient or the second type of daily valley difference rate adjustment coefficient based on the third time characteristic, determining the daily peak-valley difference rate parameter based on at least one of the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient and the annual peak-valley difference rate parameter; and determining the time period characteristics based on the daily peak-valley difference parameter and the daily characteristics.

[0106] Among them, the first type of daily valley difference rate adjustment coefficient is a coefficient that further adjusts the peak-valley difference rate based on holidays, rest days and working days in the first season range, and the second type of daily valley difference rate adjustment coefficient is a coefficient that further adjusts the peak-valley difference rate based on holidays, rest days and working days in the second season range.

[0107] In this process, the first type of daily valley difference rate adjustment coefficient, the second type of daily valley difference rate adjustment coefficient, the annual peak-valley difference rate parameter, and the daily feature are used as inputs to the third task model to determine the third time characteristic of the daily feature. The third time characteristic refers to the date type range in which the daily feature falls, for example, rest days, holidays, and workdays. The corresponding daily valley difference rate adjustment coefficient is matched based on the determined date type range. Then, the matched daily valley difference rate adjustment coefficient is calculated in correspondence with the daily feature to determine the time period characteristic.

[0108] The first type of daily valley difference rate adjustment coefficient includes daily valley difference rate adjustment coefficients corresponding to different date characteristics. For example, it may include first day valley difference rate adjustment coefficient A, first day valley difference rate adjustment coefficient B, and first day valley difference rate adjustment coefficient C. The second type of daily average adjustment coefficient includes daily average adjustment coefficients corresponding to different date characteristics. For example, it may include second day valley difference rate adjustment coefficient D, second day valley difference rate adjustment coefficient E, and second day valley difference rate adjustment coefficient F.

[0109] Specifically, the fourth task model includes a computational module for processing logic, constructs the processing logic of the fourth task model, and has a built-in calendar logic judgment module. The fourth task model comprises a two-layer judgment workflow. The first layer reuses the day type determined in the second task model to determine whether it belongs to the first season's range or the second season's range (rest day, holiday, or workday). Then, it enters the second layer, where the received date features are compared with the aforementioned defined date rules. After matching, a third time flag is output. The third time flag includes day-flag=1, day-flag=2, or day-flag=3, representing rest day, holiday, and workday respectively. Based on the determined third and first time flags, a daily valley difference rate adjustment coefficient is matched.

[0110] Please refer to Figure 4 , Figure 4 A coefficient matching diagram for the second power outage and power shortage assessment method provided in this application embodiment is shown below. Figure 4As shown, if day-flag = 1 and season-flag = 1, it matches the first day's valley difference rate adjustment coefficient A; if day-flag = 2 and season-flag = 1, it matches the first day's valley difference rate adjustment coefficient B; if day-flag = 3 and season-flag = 1, it matches the first day's valley difference rate adjustment coefficient C; if day-flag = 1 and season-flag = 2, it matches the second day's valley difference rate adjustment coefficient D; if day-flag = 2 and season-flag = 2, it matches the second day's valley difference rate adjustment coefficient E; if day-flag = 3 and season-flag = 2, it matches the second day's valley difference rate adjustment coefficient F.

[0111] Specifically, the aforementioned first-type daily valley difference rate adjustment coefficient includes multiple first peak valley difference rate adjustment coefficients corresponding to the first date adjustment coefficient, wherein the multiple first peak valley difference rate adjustment coefficients include 0.93, 0.92, and 0.95; the multiple second-date adjustment coefficients include multiple second peak valley difference rate adjustment coefficients corresponding to the second date adjustment coefficient, wherein the multiple second peak valley difference rate adjustment coefficients include 0.95, 0.96, and 0.97. That is, the first-day valley difference rate adjustment coefficient A is preferably 0.93, the first-day valley difference rate adjustment coefficient B is preferably 0.92, the first-day valley difference rate adjustment coefficient C is preferably 0.95, the second-day valley difference rate adjustment coefficient D is preferably 0.95, the second-day valley difference rate adjustment coefficient E is preferably 0.96, and the second-day valley difference rate adjustment coefficient F is preferably 0.97.

[0112] After determining the daily valley difference rate adjustment coefficient, the second-layer workflow performs calculations based on the first or second type of daily valley difference rate adjustment coefficient and the annual peak-valley difference rate parameter. Specifically, the calculation process may include: Daily peak-valley difference rate = Annual peak-valley difference rate parameter * Daily valley difference rate adjustment coefficient, where the above-mentioned daily valley difference rate adjustment coefficient includes at least one of the following: First daily valley difference rate adjustment coefficient A, First daily valley difference rate adjustment coefficient B, First daily valley difference rate adjustment coefficient C, Second daily valley difference rate adjustment coefficient D, Second daily valley difference rate adjustment coefficient E, and Second daily valley difference rate adjustment coefficient F; Average load during peak hours = Daily characteristic * 2 / (2 - Daily peak-valley difference rate), Average load during off-peak hours = Average load during daily hours * 2 * (1 - Daily peak-valley difference rate) / (2 - Daily peak-valley difference rate), where the above-mentioned daily characteristic is the output result obtained in the third task model, i.e., the daily average load. The time period characteristic includes at least one of the above-mentioned daily peak-valley difference rate, average load during peak hours, and average load during off-peak hours.

[0113] As can be seen, in this embodiment, the daily load characteristics are refined to the peak-valley difference characteristics, and the user's electricity consumption characteristics are amplified step by step, so that the load forecasting and assessment can reflect the user's electricity consumption habits with extreme accuracy, and improve the accuracy of determining the power outage and power shortage of users in different seasons, dates and time periods.

[0114] S240, determine the amount of power supply shortage for the user based on the multiple power consumption characteristics and the power outage data.

[0115] Among them, multiple electricity consumption characteristics may include at least one of the above-mentioned quarterly characteristics, daily characteristics, and time-period characteristics. In some cases, the time-period characteristics are calculated based on the quarterly characteristics and daily characteristics. Multiple electricity consumption characteristics include at least the time-period characteristics.

[0116] The aforementioned power outage data includes outage time characteristics, which are used to assess the duration of power outages for users.

[0117] In one possible embodiment, the power outage data is used to characterize the user's power outage time information, the plurality of electricity consumption characteristics include the time period characteristics, and determining the user's power outage shortage based on the plurality of electricity consumption characteristics and the power outage data includes: determining the peak and valley power outage time length based on the power outage data and preset peak and valley time periods; and determining the power outage shortage based on the peak and valley power outage time length and the time period characteristics.

[0118] The process of determining the peak-valley power outage duration based on the power outage data and preset peak-valley time periods includes: extracting time features from the power outage data to determine power outage time features; evaluating the user's power outage duration based on the power outage time features; and determining the user's power outage duration by subtracting the power outage end time from the power outage start time, or by other methods, which are not limited here. Then, based on the peak-valley power outage duration and the preset peak-valley time periods, a first power outage duration during peak hours and a second power outage duration during off-peak hours are determined. The first power outage duration is the duration of the user's power outage during peak electricity consumption hours; the second power outage duration is the duration of the user's power outage during off-peak electricity consumption hours.

[0119] The preset peak and off-peak periods can be determined in advance based on the overall electricity consumption of the power grid system. For example, the peak period can be 8:00-18:00, and the off-peak period can be 0:00-7:00 and 19:00-23:00.

[0120] The power outage shortage based on the peak and valley power outage duration and the time period characteristics can be calculated using the following formula: User power outage shortage = Σ User peak period average load * Peak period power outage time + Σ User valley period average load * Valley period power outage time, where the user peak period average load and user valley period average load are included in the aforementioned time period characteristics.

[0121] As can be seen, in this embodiment, by distinguishing between peak and off-peak periods and calculating the power outage and power shortage in different time periods, the accuracy of determining the power outage and power shortage of users under different seasons, dates, and time periods is improved.

[0122] For an example, please refer to Figure 5 , Figure 5 This is a schematic diagram of the task model of a power outage and power shortage assessment method provided in an embodiment of this application, such as... Figure 5 As shown, several adjustment coefficients in multiple task models are first determined: First season adjustment coefficient = 1.56, Second season adjustment coefficient = 0.59, First day average adjustment coefficient A = 0.43, First day average adjustment coefficient B = 0.88, First day average adjustment coefficient C = 1.65, Second day average adjustment coefficient D = 0.47, Second day average adjustment coefficient E = 0.85, Second day average adjustment coefficient F = 1.62, First day trough difference rate adjustment coefficient A = 0.93, First day trough difference rate adjustment coefficient B = 0.92, First day trough difference rate adjustment coefficient C = 0.95, Second day trough difference rate adjustment coefficient D = 0.95, Second day trough difference rate adjustment coefficient E = 0.96, Second day trough difference rate adjustment coefficient F = 0.97. In the first task model, electricity consumption parameters are determined based on user electricity consumption data. These parameters include the annual peak-valley difference rate and the annual average load. These parameters, along with the first seasonal adjustment coefficient (1.56) and the second seasonal adjustment coefficient (0.59), are then input into the second task model. In the second task model, task calculations are performed based on these predetermined adjustment coefficients to obtain seasonal characteristics. These seasonal characteristics, along with the first day's average adjustment coefficients A (0.43), B (0.88), C (1.65), D (0.47), and E (0.8), are then used to calculate the seasonal characteristics. 5. The average adjustment coefficient F = 1.62 for the second day is input into the third task model. After the task calculation of the third task model, the daily characteristics are obtained. The daily characteristics, the first day's valley difference rate adjustment coefficients A = 0.93, B = 0.92, C = 0.95, D = 0.95, E = 0.96, and F = 0.97 are input into the fourth task model. After the task calculation of the fourth task model, the time period characteristics are determined. The time period characteristics include the daily peak-valley difference rate, the average load during peak hours, and the average load during off-peak hours. Based on the above time period characteristics, power outage data, and preset peak-valley periods, the power supply shortage due to power outages is determined.

[0123] As can be seen, in this embodiment, multiple adjustment coefficients are determined based on a pre-trained coefficient determination model. These adjustment coefficients are used to dynamically adjust the adjustment weight in different time intervals. The pre-trained coefficient determination model is based on historical user electricity consumption data. User electricity consumption data and power outage data are acquired, and electricity consumption parameters are determined based on the user electricity consumption data. Multiple electricity consumption characteristics are determined based on the multiple adjustment coefficients and the electricity consumption parameters. These electricity consumption characteristics are used to characterize the user's electricity consumption in different time intervals. The power outage supply is determined based on the multiple electricity consumption characteristics and the power outage data. Thus, based on the determined multiple adjustment coefficients, the electricity consumption characteristics of power users in different time intervals are determined through the electricity consumption in different time intervals, improving the accuracy of determining the power outage supply of users in different seasons, dates, and time periods.

[0124] Please see Figure 6 , Figure 6 This is a schematic diagram of a power outage and power shortage assessment device 600 provided in an embodiment of this application. The power outage and power shortage assessment device 600 includes: a coefficient determination module 610, a parameter determination module 620, a feature determination module 630, and a power consumption determination module 640, wherein:

[0125] The coefficient determination module 610 is used to determine multiple adjustment coefficients based on a pre-trained coefficient determination model. The adjustment coefficients are used to dynamically adjust the adjustment ratio in different time intervals. The pre-trained coefficient determination model is determined based on historical user electricity consumption data.

[0126] The parameter determination module 620 is used to acquire user electricity consumption data and power outage data, and determine electricity consumption parameters based on the user electricity consumption data;

[0127] The feature determination module 630 is used to determine multiple electricity consumption features based on the multiple adjustment coefficients and the electricity consumption parameters, wherein the electricity consumption features are used to characterize the user's electricity consumption in the different time intervals;

[0128] The power consumption determination module 640 is used to determine the amount of power supply missing for a user during a power outage based on the multiple power consumption characteristics and the power outage data.

[0129] In one possible embodiment, the parameter determination module 620, in determining the electricity consumption parameters, which include the annual peak-valley difference rate parameter and the annual average load parameter, specifically performs the following steps regarding determining the electricity consumption parameters based on the user's electricity consumption data: The electricity consumption parameters include the annual peak-valley difference rate parameter and the annual average load parameter; determining the electricity consumption parameters based on the user's electricity consumption data includes:

[0130] Based on the user's electricity consumption data, determine the user's annual electricity consumption parameters and annual load parameters;

[0131] The annual average load parameter is determined based on the user's annual electricity consumption parameter and the first task model. The annual average load parameter is the energy consumed by each user per unit time in a year.

[0132] The annual peak-valley difference rate parameter is determined based on the annual load parameters and the first task model.

[0133] In one possible embodiment, the plurality of adjustment coefficients includes at least one of a first type of adjustment coefficient, a second type of adjustment coefficient, and a third type of adjustment coefficient; the time interval includes a seasonal range and / or a daily type; the first type of adjustment coefficient corresponds to the seasonal range, and the second type of adjustment coefficient and / or the third type of adjustment coefficient corresponds to the daily type; the plurality of electricity consumption characteristics includes at least one of quarterly characteristics, daily characteristics, and time-period characteristics; the characteristic determination module 630, in determining the electricity consumption parameters based on the user's electricity consumption data, specifically uses the following methods to determine the electricity consumption parameters, including the annual peak-valley difference rate parameter and the annual average load parameter:

[0134] The quarterly characteristics are determined based on the first type of adjustment coefficient and the annual average load parameter, wherein the first type of adjustment coefficient includes a first seasonal adjustment coefficient and a second seasonal adjustment coefficient.

[0135] The daily characteristics are determined based on the second type of adjustment coefficient and the quarterly characteristics, wherein the second type of adjustment coefficient includes a first type of daily average adjustment coefficient and a second type of daily average adjustment coefficient.

[0136] The time period characteristics are determined based on the third type of adjustment coefficient, the annual peak-to-valley difference rate parameter, and the daily characteristics. The third type of adjustment coefficient includes the first type of daily valley difference rate adjustment coefficient and the second type of daily valley difference rate adjustment coefficient.

[0137] In one possible embodiment, the feature determination module 630, in determining the quarterly characteristics based on the first type of adjustment coefficient and the annual average load parameter, is specifically configured to:

[0138] Input the first seasonal adjustment coefficient, the second seasonal adjustment coefficient, and the annual average load parameter into the second task model;

[0139] The seasonal characteristics are obtained by performing a first feature calculation on the second task model. The first feature calculation includes determining a first time characteristic based on the annual average load parameter, matching a first seasonal adjustment coefficient or a second seasonal adjustment coefficient based on the first time characteristic, and determining the seasonal characteristics based on at least one of the first seasonal adjustment coefficient or the second seasonal adjustment coefficient and the annual average load parameter.

[0140] In one possible embodiment, the first type of daily average adjustment coefficient and the first seasonal adjustment coefficient have a corresponding correlation, and the second type of daily average adjustment coefficient and the first seasonal adjustment coefficient have a corresponding correlation; the feature determination module 630, in determining the daily feature based on the second type of adjustment coefficient and the seasonal feature, is specifically used for:

[0141] The first type of daily average adjustment coefficient, the second type of daily average adjustment coefficient, and the seasonal characteristics are input into the third task model;

[0142] The daily characteristics are obtained by performing a second feature calculation on the third task model. The second feature calculation includes determining a second time characteristic based on the annual average load parameter, matching the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient based on the second time characteristic, and determining the daily characteristics based on at least one of the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient and the seasonal characteristics.

[0143] In one possible embodiment, the first type of daily valley difference rate adjustment coefficient and the first type of daily average adjustment coefficient have a corresponding correlation, and the second type of daily valley difference rate adjustment coefficient and the second type of daily average adjustment coefficient have a corresponding correlation; the feature determination module 630, in determining the time period feature based on the third type of adjustment coefficient, the annual peak-valley difference rate parameter, and the daily feature, is specifically used for:

[0144] The first type of daily valley difference rate adjustment coefficient, the second type of daily valley difference rate adjustment coefficient, the annual peak-valley difference rate parameter, and the daily characteristics are input into the fourth task model;

[0145] The time period characteristics are obtained by performing a third feature calculation on the fourth task model. The third feature calculation includes determining a third time characteristic based on the annual average load parameter, matching the first type of daily valley difference rate adjustment coefficient or the second type of daily valley difference rate adjustment coefficient based on the third time characteristic, determining a daily peak valley difference rate parameter based on at least one of the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient and the annual peak valley difference rate parameter, and determining the time period characteristics based on the daily peak valley difference parameter and the daily characteristics.

[0146] In one possible embodiment, the first seasonal adjustment factor is an adjustment factor within a first seasonal range, and the second seasonal adjustment factor is an adjustment factor within a second seasonal range, wherein the first seasonal adjustment factor includes 1.56 and the second seasonal adjustment factor includes 0.59.

[0147] The first type of daily average adjustment factor includes multiple first date adjustment factors within the first seasonal range, the multiple first date adjustment factors including 0.43, 0.88, and 1.65; the second type of daily average adjustment factor includes multiple second date adjustment factors within the second seasonal range, the multiple second date adjustment factors including 0.47, 0.85, and 1.62.

[0148] The first type of daily valley difference rate adjustment coefficient includes multiple first peak valley difference rate adjustment coefficients corresponding to the first date adjustment coefficient, and the multiple first peak valley difference rate adjustment coefficients include 0.93, 0.92, and 0.95; the multiple second date adjustment coefficients include multiple second peak valley difference rate adjustment coefficients corresponding to the second date adjustment coefficient, and the multiple second peak valley difference rate adjustment coefficients include 0.95, 0.96, and 0.97.

[0149] In one possible embodiment, the power outage data is used to characterize the user's power outage time information, and the plurality of electricity consumption characteristics include the time period characteristics. The power consumption determination module 640, in determining the user's power outage supply based on the plurality of electricity consumption characteristics and the power outage data, is specifically used for:

[0150] The peak and valley power outage duration is determined based on the power outage data and preset peak and valley time periods;

[0151] The power outage quantity is determined based on the peak and valley power outage duration and the time period characteristics.

[0152] It is worth noting that the specific functional implementation of the power outage and power shortage assessment device 600 is described above. Figure 2 The description of the power outage and power shortage assessment method illustrates that, for example, the coefficient determination module 610 is used to implement the relevant content of execution S210, the parameter determination module 620 is used to implement the relevant content of execution S220, the feature determination module 630 is used to implement the relevant content of execution S230, and the power supply determination module 640 is used to implement the relevant content of execution S240. Each unit or module in the power outage and power shortage assessment device 600 can be individually or entirely merged into one or more other units or modules, or some of the units or modules can be further divided into multiple functionally smaller units or modules. This achieves the same operation without affecting the technical effect of the embodiments of the present invention. The above-mentioned units or modules are based on logical function division. In practical applications, the function of one unit (or module) is implemented by multiple units (or modules), or the function of multiple units (or modules) is implemented by one unit (or module).

[0153] As can be seen, the power outage and power shortage assessment device described in this application embodiment determines multiple adjustment coefficients based on a pre-trained coefficient determination model. These adjustment coefficients are used to dynamically adjust the adjustment weight for different time intervals. The pre-trained coefficient determination model is based on historical user electricity consumption data. The device acquires user electricity consumption data and power outage data, and determines electricity consumption parameters based on the user electricity consumption data. It then determines multiple electricity consumption characteristics based on the multiple adjustment coefficients and the electricity consumption parameters. These electricity consumption characteristics characterize the user's electricity consumption in different time intervals. Finally, it determines the user's power outage and power shortage based on the multiple electricity consumption characteristics and the power outage data. Thus, based on the determined multiple adjustment coefficients, the device determines the electricity consumption characteristics of power users in different time intervals by observing the electricity consumption in different time intervals, improving the accuracy of determining the user's power outage and power shortage under different seasons, dates, and time periods.

[0154] In the case of using integrated units, please refer to Figure 7 , Figure 7 This is a schematic diagram of another power outage and power shortage assessment device provided in an embodiment of this application, as shown below. Figure 7 As shown, the power outage and power shortage assessment device 600 includes a processing module 602 and a communication module 601. The processing module 602 controls and manages the operation of the power outage and power shortage assessment device 600, for example, executing the steps of the coefficient determination module 610, parameter determination module 620, feature determination module 630, and power consumption determination module 640, and / or performing other processes of the technology described herein. The communication module 601 is used for interaction between the power outage and power shortage assessment device 600 and other devices. Figure 7 As shown, the power outage and power shortage assessment device 600 may also include a storage module 603, which is used to store the program code and data of the power outage and power shortage assessment device 600.

[0155] The processing module 602 can be a processor or controller, such as a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication module 601 can be a transceiver, RF circuitry, or a communication interface, etc. The storage module 603 can be a memory.

[0156] All relevant content in the various scenarios involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here. The above-mentioned power outage and power shortage assessment device 600 can perform the above-mentioned... Figure 2 The method for assessing power outage and power supply shortage shown.

[0157] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 8 As shown, the electronic device 800 includes a processor 810, a memory 820, a communication interface 830, and one or more programs 821, which are stored in the memory 820 and configured to be executed by the processor 810.

[0158] The processor 810, memory 820, and communication interface 830 are interconnected and perform communication between them.

[0159] The memory 820 can be a volatile memory such as dynamic random access memory (DRAM) or a non-volatile memory such as a hard disk drive (HDD). The memory 820 stores a set of executable program code, and the processor 810 calls one or more programs 821 stored in the memory 820 to execute some or all of the steps of any power outage / supply shortage assessment method described in the above embodiments of the power outage / supply shortage assessment method.

[0160] Among them, electronic devices 800 may include smartphones (such as Android phones, iOS phones, Windows Phones, etc.), tablet computers, PDAs, dashcams, in-vehicle electronic devices, servers, laptops, mobile internet electronic devices (MIDs) or wearable electronic devices (such as smartwatches, Bluetooth headsets), etc. The above are just examples and not an exhaustive list, including but not limited to the above electronic devices.

[0161] As can be seen, the electronic device determines multiple adjustment coefficients based on a pre-trained coefficient determination model. These adjustment coefficients are used to dynamically adjust the adjustment weight in different time intervals. The pre-trained coefficient determination model is based on historical user electricity consumption data. User electricity consumption data and power outage data are acquired, and electricity consumption parameters are determined based on the user electricity consumption data. Multiple electricity consumption characteristics are determined based on the multiple adjustment coefficients and the electricity consumption parameters. These electricity consumption characteristics characterize the user's electricity consumption in different time intervals. Finally, the power outage supply is determined based on the multiple electricity consumption characteristics and the power outage data. Thus, based on the determined multiple adjustment coefficients, the electricity consumption characteristics of users in different time intervals are determined through the electricity consumption situation in different time intervals, improving the accuracy of determining the power outage supply for users in different seasons, dates, and time periods.

[0162] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0163] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0164] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0165] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0166] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0167] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0168] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0169] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer electronic device (which may be a personal computer, electronic device, or network electronic device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0170] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0171] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for assessing power supply shortage during power outages, characterized in that, The method, applied to a server in a power supply system, includes: Multiple adjustment coefficients are determined based on a pre-trained coefficient determination model. These adjustment coefficients are used to dynamically adjust the adjustment ratio in different time intervals. The pre-trained coefficient determination model is based on historical user electricity consumption data. Acquire user electricity consumption data and power outage data, and determine electricity consumption parameters based on the user electricity consumption data; Multiple electricity consumption characteristics are determined based on the multiple adjustment coefficients and the electricity consumption parameters. These electricity consumption characteristics are used to characterize the user's electricity consumption in different time intervals. The power outage amount for the user is determined based on the multiple power consumption characteristics and the power outage data.

2. The method according to claim 1, characterized in that, The electricity consumption parameters include annual peak-valley difference rate parameters and annual average load parameters. Determining the electricity consumption parameters based on the user's electricity consumption data includes: Based on the user's electricity consumption data, determine the user's annual electricity consumption parameters and annual load parameters; The annual average load parameter is determined based on the user's annual electricity consumption parameter and the first task model. The annual average load parameter is the energy consumed by each user per unit time in a year. The annual peak-valley difference rate parameter is determined based on the annual load parameters and the first task model.

3. The method according to claim 2, characterized in that, The plurality of adjustment coefficients include at least one of a first type of adjustment coefficient, a second type of adjustment coefficient, and a third type of adjustment coefficient; the time interval includes a seasonal range and / or a daily type; the first type of adjustment coefficient corresponds to the seasonal range, and the second type of adjustment coefficient and / or the third type of adjustment coefficient corresponds to the daily type; the plurality of electricity consumption characteristics include at least one of a quarterly characteristic, a daily characteristic, and a time period characteristic; The determination of multiple electricity consumption characteristics based on the multiple adjustment coefficients and the electricity consumption parameters includes: The quarterly characteristics are determined based on the first type of adjustment coefficient and the annual average load parameter, wherein the first type of adjustment coefficient includes a first seasonal adjustment coefficient and a second seasonal adjustment coefficient. The daily characteristics are determined based on the second type of adjustment coefficient and the quarterly characteristics, wherein the second type of adjustment coefficient includes a first type of daily average adjustment coefficient and a second type of daily average adjustment coefficient. The time period characteristics are determined based on the third type of adjustment coefficient, the annual peak-to-valley difference rate parameter, and the daily characteristics. The third type of adjustment coefficient includes the first type of daily valley difference rate adjustment coefficient and the second type of daily valley difference rate adjustment coefficient.

4. The method according to claim 3, characterized in that, The determination of the quarterly characteristics based on the first type of adjustment coefficient and the annual average load parameter includes: Input the first seasonal adjustment coefficient, the second seasonal adjustment coefficient, and the annual average load parameter into the second task model; The seasonal characteristics are obtained by performing a first feature calculation on the second task model. The first feature calculation includes determining a first time characteristic based on the annual average load parameter, matching a first seasonal adjustment coefficient or a second seasonal adjustment coefficient based on the first time characteristic, and determining the seasonal characteristics based on at least one of the first seasonal adjustment coefficient or the second seasonal adjustment coefficient and the annual average load parameter.

5. The method according to claim 3, characterized in that, The first type of daily average adjustment coefficient and the first seasonal adjustment coefficient have a corresponding correlation relationship, and the second type of daily average adjustment coefficient and the first seasonal adjustment coefficient have a corresponding correlation relationship. The determination of the daily characteristics based on the second type of adjustment coefficient and the quarterly characteristics includes: The first type of daily average adjustment coefficient, the second type of daily average adjustment coefficient, and the seasonal characteristics are input into the third task model; The daily characteristics are obtained by performing a second feature calculation on the third task model. The second feature calculation includes determining a second time characteristic based on the annual average load parameter, matching the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient based on the second time characteristic, and determining the daily characteristics based on at least one of the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient and the seasonal characteristics.

6. The method according to claim 3, characterized in that, The first type of daily valley difference rate adjustment coefficient and the first type of daily average adjustment coefficient have a corresponding correlation, and the second type of daily valley difference rate adjustment coefficient and the second type of daily average adjustment coefficient have a corresponding correlation. The determination of the time period characteristics based on the third type of adjustment coefficient, the annual peak-to-valley difference rate parameter, and the daily characteristics includes: The first type of daily valley difference rate adjustment coefficient, the second type of daily valley difference rate adjustment coefficient, the annual peak-valley difference rate parameter, and the daily characteristics are input into the fourth task model; The time period characteristics are obtained by performing a third feature calculation on the fourth task model. The third feature calculation includes determining a third time characteristic based on the annual average load parameter, matching the first type of daily valley difference rate adjustment coefficient or the second type of daily valley difference rate adjustment coefficient based on the third time characteristic, determining a daily peak valley difference rate parameter based on at least one of the first type of daily average adjustment coefficient or the second type of daily average adjustment coefficient and the annual peak valley difference rate parameter, and determining the time period characteristics based on the daily peak valley difference parameter and the daily characteristics.

7. The method according to any one of claims 4-6, characterized in that, The first seasonal adjustment factor is an adjustment factor within the first seasonal range, and the second seasonal adjustment factor is an adjustment factor within the second seasonal range. The first seasonal adjustment factor includes 1.56, and the second seasonal adjustment factor includes 0.

59. The first type of daily average adjustment factor includes multiple first date adjustment factors within the first seasonal range, the multiple first date adjustment factors including 0.43, 0.88, and 1.65; the second type of daily average adjustment factor includes multiple second date adjustment factors within the second seasonal range, the multiple second date adjustment factors including 0.47, 0.85, and 1.

62. The first type of daily valley difference rate adjustment coefficient includes multiple first peak valley difference rate adjustment coefficients corresponding to the first date adjustment coefficient, and the multiple first peak valley difference rate adjustment coefficients include 0.93, 0.92, and 0.95; the multiple second date adjustment coefficients include multiple second peak valley difference rate adjustment coefficients corresponding to the second date adjustment coefficient, and the multiple second peak valley difference rate adjustment coefficients include 0.95, 0.96, and 0.

97.

8. The method according to claim 3 or 6, characterized in that, The power outage data is used to characterize the user's power outage time information. The multiple electricity consumption characteristics include the time period characteristics. Determining the user's power outage power shortage based on the multiple electricity consumption characteristics and the power outage data includes: The peak and valley power outage duration is determined based on the power outage data and preset peak and valley time periods; The power outage quantity is determined based on the peak and valley power outage duration and the time period characteristics.

9. A computer-readable storage medium, characterized in that, The device stores a power outage and power shortage determination program, including execution instructions, which, when executed by the processor of the electronic device, perform the method as described in any one of claims 1 to 8.

10. An electronic device, characterized in that, It includes a processor, memory, a communication interface, and one or more programs, which are stored in the memory and configured to be executed by the processor; When the processor executes the one or more programs stored in the memory, the processor performs the method as described in any one of claims 1 to 8.

Images