Power load data adjusting method and device, equipment, medium and program product

Abstract

The invention relates to the technical field of data processing, and provides a power load data adjusting method and device, equipment, a medium and a program product, and the method comprises the steps: predicting the starting information of electric equipment in a first time period in the future based on a data set of the electric equipment; based on the starting information, determining a set temperature of the electric equipment in a second time period in the future; based on the historical power load data of the electric equipment, determining a power load base line of the electric equipment in a future first time period; selecting a power load base line of the electric equipment in a second time period in the future from the power load base lines of the electric equipment in the first time period in the future; and adjusting the power load data of the electric equipment based on the difference value between the power load base line of the electric equipment in the second time period in the future and the power load corresponding to the set temperature. According to the invention, the power demand of the user is fully considered in the process of estimating the adjustable load, and the power load data is adjusted on the basis of ensuring the user experience.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment, medium and program product for regulating power load data. Background Art

[0002] At present, more and more power-consuming equipment has electricity metering function, which can record and report the power load data during operation at any time, making it possible to regulate power-consuming equipment to meet the peak power shaving demand of the power grid.

[0003] Unlike the basically stable operating load of industrial and commercial machines, the power load of household appliances is not only affected by objective factors such as weather, but also by user behavior habits. The power load of traditional household appliances is adjusted directly based on the prediction results, but if it is forcibly adjusted during the time period when the user needs to use the device, it will have a serious negative impact on the user experience. Therefore, how to adjust the power load data while ensuring the user experience has become an urgent problem to be solved. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method for adjusting power load data, which fully considers the power demand of users in the process of estimating adjustable loads, thereby adjusting the power load data on the basis of ensuring the user experience.

[0005] The present invention also provides an electric load data regulating device, an electronic device, a non-transitory computer-readable storage medium and a computer program product.

[0006] A method for adjusting power load data according to an embodiment of a first aspect of the present invention includes: Based on a data set of an electric device, predicting the startup information of the electric device in a first time period in the future; the data set includes historical usage data of the electric device; Based on the startup information of the electric device in the first time period in the future, determining the set temperature of the electric device in the second time period in the future; the second time period is the time period for starting the electric device in the first time period; the set temperature is the temperature parameter set by the user when using the electric device; Determining a power load baseline of the power consumption equipment in the first future time period based on the historical power load data of the power consumption equipment; Selecting the power load baseline of the power consumption equipment in the second time period in the future from the power load baseline of the power consumption equipment in the first time period in the future; The power load data of the electric device is adjusted based on the difference between the power load baseline of the electric device in the second time period in the future and the power load corresponding to the set temperature.

[0007] According to an embodiment of the present invention, the set temperature includes a maximum set temperature and a minimum set temperature; and adjusting the power load data of the electric device based on the difference between the power load baseline of the electric device in the second time period in the future and the power load corresponding to the set temperature includes: Determine a first difference between the power load baseline of the electrical equipment in the second future time period and the power load corresponding to the maximum set temperature, and a second difference between the power load baseline of the electrical equipment in the second future time period and the power load corresponding to the minimum set temperature; When the first difference is 0, the second difference is used as a load adjustment value; When the second difference is 0, taking 0 as the load adjustment value; When the first difference is greater than 0 and the second difference is greater than 0, determining the load adjustment value based on the first difference and the second difference; Based on the load adjustment value, the power load data of the electrical equipment is adjusted.

[0008] According to an embodiment of the present invention, adjusting the power load data of the electrical equipment based on the load adjustment value includes: Determining the adjustment priority of the electrical equipment based on the load adjustment value and the weight of the electrical equipment; In the case where the load value to be adjusted is less than the load adjustment upper limit value, at least one target electrical equipment is selected based on the adjustment priority of the electrical equipment; the load adjustment upper limit value is the total load adjustment value in the first future time period; Based on the load adjustment value, the power load data of the target electrical equipment is adjusted.

[0009] According to an embodiment of the present invention, determining the power load baseline of the power consumption device in the first future time period based on the historical power load data of the power consumption device includes: In the case where the adjustment time of the power load data is a statutory working day, the power load baseline of the power-consuming equipment in the first time period in the future is determined based on the historical power load data of multiple historical statutory working days; the power load in the first time period of the historical statutory working days all conforms to the power load corresponding to the user's power consumption behavior habits; In the case where the adjustment time of the power load data is a non-statutory working day, the power load baseline of the electrical equipment in the first future time period is determined based on historical power load data of a plurality of consecutive historical non-statutory working days.

[0010] According to an embodiment of the present invention, predicting the startup information of the electric device in a first future time period based on the data set of the electric device includes: Extracting feature data from the historical usage data in the data set, and cross-combining different features on the feature data; Extracting effective information from the cross-combination features; the effective information is a feature or feature combination that is relevant to whether the electrical device is turned on; Based on the valid information, the startup information of the electric device in the first time period in the future is predicted.

[0011] According to an embodiment of the present invention, determining the set temperature of the electric device in the second time period in the future based on the startup information of the electric device in the first time period in the future includes: Determining the second time period based on the startup information of the electric device in the first time period in the future; Extracting characteristic data of the second time period from the data set; Based on the characteristic data of the second time period, a set temperature of the electrical equipment in the second time period in the future is determined.

[0012] The device for adjusting power load data according to the second aspect of the present invention includes: A prediction module, configured to predict, based on a data set of the electric device, the startup information of the electric device in a first future time period; the data set includes historical usage data of the electric device; A set temperature determination module is used to determine the set temperature of the electrical device in a second time period in the future based on the start-up information of the electrical device in the first time period in the future; the second time period is a time period for turning on the electrical device in the first time period; the set temperature is a temperature parameter set by the user when using the electrical device; A power load baseline determination module, configured to determine the power load baseline of the power consumption equipment in the first future time period based on the historical power load data of the power consumption equipment; A selection module, configured to select the power load baseline of the power consumption equipment in the second time period in the future from the power load baseline of the power consumption equipment in the first time period in the future; The adjustment module is used to adjust the power load data of the power device based on the difference between the power load baseline of the power device in the second time period in the future and the power load corresponding to the set temperature.

[0013] According to an embodiment of the third aspect of the present invention, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for regulating power load data as described above is implemented.

[0014] According to the non-transitory computer-readable storage medium of the fourth aspect of the present invention, a computer program is stored thereon, and when the computer program is executed by a processor, the method for adjusting the power load data as described in any one of the above is implemented.

[0015] A computer program product according to an embodiment of the fifth aspect of the present invention comprises a computer program, which, when executed by a processor, implements any of the above-mentioned methods for adjusting power load data.

[0016] The above one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: In the process of estimating adjustable load, the user's electricity demand is fully considered, so that the power load data can be adjusted on the basis of ensuring the user experience; It can effectively improve the success rate of C-end users participating in the virtual power plant peak-shaving task, and can effectively reduce the user interruption behavior during the execution of the virtual power plant peak-shaving task.

[0017] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of a method for adjusting power load data provided in an embodiment of the present invention.

[0020] Figure 2 It is a structural diagram of the DNN deep learning model provided by an embodiment of the present invention.

[0021] Figure 3It is a structural diagram of the MMOE multi-task model provided by an embodiment of the present invention.

[0022] Figure 4 It is a structural schematic diagram of the power load data regulating device provided in an embodiment of the present invention.

[0023] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0025] In the description of the embodiments of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0026] In the embodiments of the present invention, unless otherwise clearly specified and limited, the first feature being "above" or "below" the second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature being "above", "above" and "above" the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. The first feature being "below", "below" and "below" the second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0027] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0028] In related technologies, virtual power plants are a control technology based on dynamic power demand response, specifically an Internet of Things (IoT) technology that coordinates and controls distributed energy, controllable loads, and energy storage in a unified manner to respond to grid dispatch. At present, power demand response based on household appliances is still vacant. Residential power demand response has unique advantages, mainly including: (1) Residential smart appliances have a large-scale stock, and smart appliances can be monitored and controlled in the cloud, with considerable control potential; (2) Residential appliances are widely distributed and highly flexible, and can dynamically respond to power control needs in different provinces or regions; (3) Some categories of appliances have energy storage characteristics (such as electric water heaters), which can store energy during low power consumption, completely staggered from peak power consumption, and have strong control capabilities.

[0029] During the execution of the virtual power plant peak shaving task, users are usually required to keep the electrical appliances working in a low-power state for a period of time, or even turn them off for a period of time. However, it is difficult for many users to keep the electrical appliances working in a low-power state or turn them off for an hour. Users often restart the high-power function of the electrical appliances in the middle of the virtual power plant peak shaving task, thereby interrupting the peak shaving task. This will cause the actual adjustable load of electricity to be much lower than the estimated virtual power plant adjustable load in advance, resulting in the failure of the virtual power plant peak shaving task for the electrical appliance. In addition, if the device is forcibly adjusted during the time period when the user needs to use the device, it will have a serious negative impact on the user experience.

[0030] Based on the above problems, the present invention proposes a method for adjusting power load data. The method determines in advance whether the user has the need to use the product within the time period of responding to the virtual power plant control task. If so, the product power load is adjusted downward on the basis of ensuring the user experience as much as possible.

[0031] Figure 1 1 is a flow chart of a method for adjusting power load data provided by an embodiment of the present invention. Figure 1 The embodiment of the present invention provides a method for adjusting power load data, comprising: Step 101: predicting the startup information of the electric device in a first time period in the future based on a data set of the electric device.

[0032] It should be noted that the execution subject of the power load data adjustment method provided in the embodiment of the present invention can be a server, a computer device, such as a smart phone, a tablet computer, a laptop computer, a vehicle-mounted electronic device, a wearable device, etc.

[0033] Collect the historical usage data and historical weather data corresponding to each historical usage time period of the electrical equipment, and then build a data set of the electrical equipment based on the collected data. The historical usage time period can refer to different time periods within a day, such as 8:00-9:00, 10:00-11:00, 12:00-13:00; it can also refer to different time periods within a week, such as Monday, Tuesday, Wednesday, etc. The electrical equipment can be household equipment, such as electric water heaters, air conditioners, electric heaters, etc.

[0034] For example, integrate historical date data (including whether it is a weekend, holiday, etc.), historical weather data (including indoor and outdoor temperatures, etc.), and working status information of electrical equipment such as electric water heaters, air conditioners, and electric heaters. The working status information may include working mode, working gear, continuous working time, power load, and other information.

[0035] 1) Select n electrical appliances (including electric water heaters, air conditioners and electric heaters) in a province, collect the historical usage data reported by n electrical appliances in the past year, obtain the identification information of the electrical appliances (such as device ID), device type, city identification information of the city where the electrical appliances are located (such as city ID), data reporting date, and count the working mode, working gear size, hourly power load and indoor temperature of the electrical appliances every day and every hour based on the historical usage data. The processed data is as follows:

[0036] 2) Based on the historical weather data records, process the weather data of the area where the electrical equipment is located in the past year and generate the following data table:

[0037] 3) Arrange the historical date data of electrical equipment in the past year and generate the following data table:

[0038] Among them, the demand response day refers to the receipt of the power grid's peak-shaving demand on the corresponding date and the successful response. Because the electrical equipment on that day implemented peak-shaving regulation, the power load data needs to be distinguished from the power load data on normal working days or holidays.

[0039] 4) Perform data integration and feature generation on the data generated in steps 1) to 3) to generate the following data table:

[0040] Based on the historical usage data and historical weather data of the power-consuming equipment corresponding to each historical usage time period integrated in the above table, a data set of power-consuming equipment is constructed.

[0041] After constructing a data set of electrical equipment, the power-on information of the electrical equipment in the first time period in the future is predicted based on the data set. The first time period may refer to different time periods within a day, such as 8:00-9:00, 10:00-11:00, 12:00-13:00; it may also refer to different time periods within a week, such as Monday, Tuesday, Wednesday, etc. The power-on information may include the switch status of the device, such as whether the device is in the on state. It is understandable that different types of electrical equipment have different definitions of power on. For example, turning on an electric water heater means using hot water; turning on an air conditioner means turning on the cooling or heating mode; turning on an electric heater means turning on the electric heater for heating.

[0042] For example, deep learning can be used to predict whether the user will turn on electrical equipment during each hour of the next day.

[0043] Step 102: determining a set temperature of the electrical equipment in a second time period in the future based on the startup information of the electrical equipment in the first time period in the future.

[0044] After predicting the power-on information of the electric device in the first time period in the future, the time period of the power-on device in the first time period is taken as the second time period, and then the set temperature of the electric device in the second time period in the future is determined. The number of the second time period can be one or more; the set temperature can include the maximum set temperature and minimum setting temperature ,in, For different electrical equipment ids, It is the hour period 0~23.

[0045] For example, deep learning can be used to predict the maximum and minimum set temperatures that the user can accept in the second time period of the next day.

[0046] Step 103: Determine a power load baseline of the power consumption equipment in the first future time period based on the historical power load data of the power consumption equipment.

[0047] Step 104 , selecting the power load baseline of the power consumption equipment in the second time period in the future from the power load baselines of the power consumption equipment in the first time period in the future.

[0048] Step 105: adjusting the power load data of the electric device based on the difference between the power load baseline of the electric device in the second time period in the future and the power load corresponding to the set temperature.

[0049] In order to estimate whether the power consumption of the power-consuming equipment can be adjusted every hour in the future, it is necessary to obtain the benchmark value or baseline of the power consumption of the power-consuming equipment every hour based on the historical power consumption records of the power-consuming equipment, that is, the power load baseline ,in, For base, For different electrical equipment ids, The hour period is 0~23; based on the power load baseline, the power load that can be adjusted downward by the power equipment is further estimated to determine whether the power equipment can respond to the power peak shaving task. Among them, the power peak shaving task refers to reducing the power demand by adjusting the load of the power equipment during the peak power demand period to achieve the purpose of balancing power supply and demand and avoid overload of the power grid or frequent power shortages.

[0050] Based on the historical power load data of the electrical equipment, determine the power load baseline of the electrical equipment in the first time period in the future. Specifically, through long-term power consumption records, the power consumption patterns of the electrical equipment in different time periods (such as different hours of the day, different seasons, etc.) can be obtained. For example, an air conditioner may use more electricity during the daytime in summer and less electricity at night or in winter. The power load baseline reflects the normal power consumption during these time periods. Among them, the power load baseline can vary with changes in time, season, weather, usage habits and other factors. For example, the power load baseline may be higher during winter heating than when using air conditioning in summer because the load of electrical equipment (such as electric heaters) is higher in winter.

[0051] Historical power load data can be historical power consumption data, which is used to reflect the actual power consumption of power-consuming equipment in a certain period of time in the past. Historical power load data is obtained through long-term monitoring and recording of power consumption, and can include power consumption in a time period, such as hourly, daily, and monthly power consumption; load changes, such as power load fluctuations, reflecting the power demand of equipment or systems in different time periods; power consumption patterns, such as seasonal changes, differences in power consumption between daytime and nighttime, etc.

[0052] In one embodiment, the power load baseline is determined as follows: when the adjustment time of the power load data is a statutory working day, the power load baseline of the power-consuming equipment in the first time period in the future is determined based on the historical power load data of multiple historical statutory working days; when the adjustment time of the power load data is a non-statutory working day, the power load baseline of the power-consuming equipment in the first time period in the future is determined based on the historical power load data of multiple consecutive historical non-statutory working days. Among them, the power load of the first time period (such as each hour) of the historical statutory working day is consistent with the power load corresponding to the user's power consumption behavior habits; the adjustment time of the power load data can be the peak shaving task response day.

[0053] For example, for all selected power-consuming devices, filter the actual power load data of these power-consuming devices every hour of every day for the past 45 days; if it is less than 45 days, use all historical power load data for the calculation of the power load baseline. Calculate for each power-consuming device. When the peak-shaving task response day is a statutory working day (that is, when the next day is a statutory working day), select the first five normal historical statutory working days of the response day to form a load baseline reference day set, where five statutory working days are considered as a complete working week, and the user's habit of using power-consuming devices is mainly based on a working week as a behavior cycle. Then, calculate the power load Pavi (unit W) of the power-consuming device in each response period (such as every hour) of each reference day, and calculate the average load Pav (W) of the five reference days in each response period. If any Pavi<0.75×Pav, the hour of the reference day is judged as an abnormal value that does not conform to the user's behavior habits, and the power load value of the reference day at that hour is removed from the reference day set; at the same time, recursively select the power load data of other historical statutory working days until the power load data of 5 reference days that meet the requirements are selected; recursively forward with 45 days as the upper limit, if the statutory working days 45 days ago still cannot select 5 reference days, the nearest holiday or the day responding to the power peak shaving task is also regarded as a statutory working day to make up 5 reference days. After the reference day is selected, the average power load value of the reference day is calculated, and the average power load value is used as the power load baseline of the power-consuming equipment at each hour. When the peak shaving task response day is a non-legal working day, the three non-legal working days before the response day (such as Saturday) are selected as reference days for baseline load calculation (i.e., reference to the use of electrical equipment by users on the three non-legal working days). If three non-legal working days cannot be selected, the nearest holiday or response day is also regarded as a non-legal working day to make up the three reference days. The calculation method of the power load baseline for non-legal working days is the same as that for statutory working days, i.e., the average power load value of the reference day is calculated, and the average power load value is used as the power load baseline for the electrical equipment at each hour.

[0054] The embodiments of the present invention provide a forecast benchmark for future power demand by determining the power load baseline, optimize power dispatching and load management, and provide data support for power grid regulation measures such as demand response and peak shaving.

[0055] Further, the power load baseline of the power consumption equipment in the future second time period is selected from the power load baseline of the power consumption equipment in the future first time period. For example, if the air conditioner is turned on from 7:00 to 8:00 in the future day, the load baseline data of the time period from 7:00 to 8:00 needs to be extracted.

[0056] Further, based on the difference between the power load baseline of the power consumption equipment in the second time period in the future and the power load corresponding to the set temperature, the power load data of the power consumption equipment is adjusted.

[0057] In one embodiment, a first difference between a power load baseline of the electrical equipment in a second time period in the future and the power load corresponding to a maximum set temperature, as well as a second difference between the power load baseline of the electrical equipment in the second time period in the future and the power load corresponding to a minimum set temperature are determined; when the first difference is 0, the second difference is used as a load adjustment value; when the second difference is 0, 0 is used as the load adjustment value; when the first difference is greater than 0 and the second difference is greater than 0, the load adjustment value is determined based on the first difference and the second difference; based on the load adjustment value, the power load data of the electrical equipment is adjusted.

[0058] For example, for powered-on electrical equipment, the power load baseline of the electrical equipment is used as a benchmark, and the difference between the power load corresponding to the highest set temperature and the lowest set temperature and the baseline is calculated respectively. Based on the difference, the equipment pool that can perform the virtual power plant power peak shaving task is determined.

[0059] (1) Calculate the power load baseline for each electrical device in each hour of the next day Subtract the power load corresponding to the highest set temperature of the predicted output The first difference of is taken as the minimum adjustable load capacity, recorded as , For different electrical equipment ids, For hour period 0~23: ; (2) Calculate the power load baseline for each electrical device in each hour of the next day Subtract the power load corresponding to the lowest set temperature of the predicted output The second difference of is taken as the maximum adjustable load capacity, recorded as : ; (3) Based on and , calculate the adjustable load value (i.e. load adjustment value) of the power equipment predicted to be turned on at each moment ), the calculation method is as follows: ; That is, in the second difference When it is 0, 0 is used as the load adjustment value. ; At the first difference When the second difference is 0, As load regulation value ; When the first difference is greater than 0 and the second difference is greater than 0 (i.e. ),Will As load regulation value .

[0060] In one embodiment, if the prediction result is that the power device is not turned on, the corresponding power load of the power device is theoretically 0, and the adjustable load value (ie, load adjustment value) is the power load baseline at the corresponding moment. However, considering the user experience, when adjusting the peak load of the virtual power plant, it is necessary to avoid directly turning off the power load to 0. In order to reserve a certain adjustment space, the power load baseline can be used to estimate the available power load value. The calculation formula for the proportional reduction method is as follows: ; in, is the load regulation value of the hourly period corresponding to the electrical equipment; this calculation method uses the sigmoid function to convert the power load baseline into a proportional value of 0 to 1, where The larger the value, the larger the adjustable ratio. The smaller the value, the smaller the adjustable ratio. This calculation method is consistent with the prediction that the user will not turn on the electrical equipment, that is, a certain adjustment space is reserved, and it can also estimate the adjustable power load value of each device to the maximum extent according to the power load baseline of different electrical equipment.

[0061] In one embodiment, the power load data of the electrical equipment is adjusted based on the load adjustment value, including: determining the adjustment priority of the electrical equipment based on the load adjustment value and the weight of the electrical equipment; when the load value to be adjusted is less than the load adjustment upper limit value, selecting at least one target electrical equipment based on the adjustment priority of the electrical equipment; the load adjustment upper limit value is the total load adjustment value in a first time period in the future; based on the load adjustment value, adjusting the power load data of the target electrical equipment.

[0062] Specifically, if , then the electrical equipment enters the adjustable equipment pool, and As the adjustable load value, the lowest setting temperature of the predicted output is used as the adjustable temperature of the electrical equipment; for the equipment that is predicted not to be turned on, the standby state is set as the adjustable temperature; if , then the power equipment will not enter the adjustable equipment pool. The sum of all adjustable loads entering the adjustable equipment pool is the upper limit of the adjustable load capacity that the virtual power plant can respond to in each hour of the next day, that is, the upper limit of load regulation. : ; in, The number of devices in the adjustable device pool.

[0063] Further, based on the load adjustment value and the weight of the electrical equipment, the adjustment priority of the electrical equipment is determined, wherein the adjustment priority is determined based on the weighted integral of the electrical equipment, the higher the weighted integral, the higher the adjustment priority; conversely, the lower the adjustment priority. For example, the weighted integral of the equipment entering the adjustable load equipment pool in each hour period is calculated. : ; in, The weights of different types of electrical equipment. For example, the electric water heater category is given priority, followed by air conditioners and electric heaters. Therefore, the weights of electric water heaters, air conditioners, and electric heaters are In descending order, they are , , ( The weight values ​​must add up to 1 and be an arithmetic progression).

[0064] When the load value to be adjusted is less than the load adjustment upper limit, at least one target power device is selected based on the adjustment priority of the power device; then, the power load data of the target power device is adjusted based on the load adjustment value. Sort the adjustable equipment in each hour period in reverse order from large to small. In the next day, the virtual power plant peak shaving regulation task needs to be performed, and the load value to be adjusted for the virtual power plant peak shaving regulation task is less than the load regulation upper limit value. When the system is running, the first adjustable device will be given priority to send commands from the cloud for adjustment.

[0065] The embodiments of the present invention can scientifically manage and adjust the load of electrical equipment, as well as calculate and screen adjustable equipment, so that the virtual power plant can efficiently perform peak shaving and regulation to ensure the stable operation of the power grid during peak power consumption, and optimize the operating status of electrical equipment and extend the service life of equipment. At the same time, it can promote the rational allocation and utilization of power resources and achieve supply and demand balance and efficient operation of the power system.

[0066] The method for adjusting power load data provided by the embodiment of the present invention predicts the startup information of the power equipment in the first time period in the future based on the data set of the power equipment, and the data set includes the historical usage data of the power equipment; based on the startup information of the power equipment in the first time period in the future, determines the set temperature of the power equipment in the second time period in the future; the second time period is the time period for turning on the power equipment in the first time period; based on the historical power load data of the power equipment, determines the power load baseline of the power equipment in the first time period in the future; from the power load baseline of the power equipment in the first time period in the future, selects the power load baseline of the power equipment in the second time period in the future; based on the difference between the power load baseline of the power equipment in the second time period in the future and the power load corresponding to the set temperature, adjusts the power load data of the power equipment. The present invention fully considers the power demand of the user in the process of estimating the adjustable load, and adjusts the power load data on the basis of ensuring the user's experience.

[0067] Based on the above embodiment, the step of predicting the startup information of the electric device in a first future time period based on the data set of the electric device includes: Step 1010, extracting feature data from the historical usage data in the data set, and performing cross-combination of different features on the feature data; Step 1011, extracting effective information from the cross-combination features; the effective information is a feature or feature combination that is correlated with whether the electrical device is turned on; Step 1012: Based on the valid information, predict the startup information of the electrical equipment in the first time period in the future.

[0068] Deep learning can be used to predict whether the user will turn on the electrical device in each hour of the next day. For example, a deep neural network (DNN) model, a decision tree model, a gradient boosting machine (GBM) model, a convolutional neural network (CNN) model, and a long short-term memory network (LSTM) model can be used to predict whether the user will turn on the electrical device in each hour of the next day.

[0069] In one embodiment, the DNN model is used as an example for analysis and explanation. Figure 2 , the DNN model includes: Input layer: Input data is divided into three categories: Continuous Features: including user behavior and environment information; Categorical Features: including device information. These features are converted into Embeddings through their respective embedding layers.

[0070] Middle layers (hidden layers): The embedding vectors of continuous features and categorical features are combined in the middle layer (Concatenated Embeddings). These combined embedding vectors are processed through multiple hidden layers.

[0071] Output layer (Output targets): After being processed by the hidden layer, it is finally output to the target layer.

[0072] Among them, Embeddings is a technology that converts discrete categorical variables (such as categories, labels, etc.) into continuous vectors. Concatenated Embeddings, when there are multiple embedding vectors from different sources, merge them in a certain dimension to form a new vector. This new vector contains the information of all the original embedding vectors, which is convenient for subsequent neural network layers to process. Hidden Layers are layers located between the input layer and the output layer in a deep neural network. These layers extract high-level features from the data by performing nonlinear transformations on the input data, thereby helping the model to better predict and classify.

[0073] Specifically, when the feature data is input into the DNN model, the DNN model can automatically cross-combine different features, and then extract effective information from the cross-combined features, such as the impact of indoor temperature changes and the continuous working time of the equipment on the change of the equipment working mode, which can be expressed through the cross-combination of the features of the DNN model. In the DNN model, in order to reduce the problem of data sparsity, the discrete variables are processed by Embedding and combined with the continuous variables to form the feature data of the input model, and the final output predicts whether the user will turn on the electrical equipment at each time point in the next 24 hours of the day, including electric water heater heating, air conditioning cooling, air conditioning heating, electric heater heating and other behaviors.

[0074] The embodiment of the present invention can more accurately predict whether the electrical equipment is turned on by cross-combining different features of feature data and mining potential relationships, thereby improving the accuracy of the prediction.

[0075] Based on the above embodiment, determining the set temperature of the electrical equipment in the second time period in the future based on the startup information of the electrical equipment in the first time period in the future includes: Step 1020, determining the second time period based on the startup information of the electric device in the first time period in the future; Step 1021, extracting characteristic data of the second time period from the data set; Step 1022: Determine the set temperature of the electrical equipment in the second time period in the future based on the characteristic data of the second time period.

[0076] After predicting the power-on information of the electric device in the first time period in the future, the time period in which the electric device is turned on in the first time period is taken as the second time period, and then the feature data of the second time period is extracted from the data set. Finally, based on the feature data of the second time period, a deep learning method can be used to predict the maximum and minimum set temperatures that the user can accept in the second time period in the future day. For example, a multi-task deep learning (Multi-gate Mixture-of-Experts, MMOE) model, a reinforcement learning (Reinforcement Learning, RL) model, a deep reinforcement learning (Deep Reinforcement Learning, DRL) model, and a transfer learning (Transfer Learning) model can be used to predict the maximum and minimum set temperatures that the user can accept in the second time period in the future day.

[0077] In one embodiment, the MMOE model is used as an example for analysis and explanation. Figure 3 , the MMOE model includes: Input layer: The bottom layer of the model is the input layer, which receives input data.

[0078] Middle layer (Experts and Gates): Experts: There is a group of "expert" modules in the middle, including Expert Module 1 (Expert 0), Expert Module 2 (Expert 1) and Expert Module 3 (Expert 2). These modules are the core computing units of the model and are responsible for processing input data. Gates: There are two gate modules on both sides of the expert module, including Gate Module A (Gate A) and Gate Module B (Gate B). The gate module is used to select and combine the outputs of the expert modules.

[0079] Output layer (Output): Output A (Output A) and Output B (Output B): The two outputs of the model correspond to different tasks. These outputs are further processed by the outputs of the gate module and the expert module through the tower structure (Tower A and Tower B).

[0080] Data flow: The input data first enters the input layer (Input), and then the input data is distributed to the intermediate expert module for processing. The gate module selects and combines the outputs of the expert modules based on the input data and task requirements. For example, GateA may select the outputs of Expert 0 and Expert 1, while Gate B may select the outputs of Expert 1 and Expert 2. The outputs of the gate modules enter the corresponding tower structures (Tower A and Tower B) respectively. The tower structures further process the data and ultimately produce two different outputs (Output A and Output B), corresponding to different tasks. For example, OutputA may be used to predict "extremely cold values" (ie, the minimum set temperature), while Output B may be used to predict "extremely hot values" (ie, the maximum set temperature).

[0081] For users who are predicted to turn on electric water heaters, air conditioners, and electric heaters, the corresponding feature data of these users are screened out, and the maximum and minimum set temperatures of the electrical equipment used by the users at each moment are used as the learning targets of the model; the feature data is input into the MMOE model to predict the maximum and minimum set temperatures that the users can accept in each hour of the next day, so as to determine the user's adjustable comfort zone. The MMOE multi-task model can handle multiple relatively independent learning objectives at the same time, avoiding the problem of insufficient sample data for a certain task, and avoiding repeated calculations, reducing the resource consumption of training multiple models.

[0082] The embodiment of the present invention predicts the maximum and minimum set temperatures that the electrical equipment can accept in each hour of the next day, fully considers the user's electricity demand in the process of estimating the adjustable load, and adjusts the power load data while ensuring the user experience.

[0083] In order to further analyze and illustrate the method for adjusting power load data proposed by the present invention, refer to the following embodiments.

[0084] The embodiment of the present invention mainly implements the adjustment of power load data through the following steps: Step 1: Update the working status information and weather information of electric water heaters, air conditioners, electric heaters and other products in the HIVE (Hadoop Integrated Virtual Environment) database every day. For example, update the data of whether the air conditioner a is turned on every hour of the day, the continuous working time, the average working wind speed, the maximum temperature, the minimum temperature, the average working power and the weather information of the day.

[0085] Step 2, obtain data from the HIVE database and perform feature processing, that is, process the historical working status data of the above-mentioned air-conditioning equipment a into the required feature data, and then store the processed feature data in the python cluster to facilitate subsequent data reading.

[0086] Step 3: Input the processed feature data into Figure 2 In the DNN model, predict whether each type of product will be turned on within each hour of the next day; input the device data with the predicted result of being turned on into Figure 3 In the MMOE model, the set temperature of each type of product in each hour corresponding to the device being turned on the next day is predicted, and then the power load corresponding to the minimum set temperature and the power load corresponding to the maximum set temperature are calculated. For example, it is predicted that the cooling function of the above-mentioned air-conditioning device a will be turned on at 3 pm in the future, and the maximum set temperature from 3 to 4 o'clock is predicted to be 27 degrees Celsius (the corresponding power load to maintain 27 degrees Celsius can be 700W), and the minimum set temperature is 22 degrees Celsius (the corresponding power load to maintain 22 degrees Celsius can be 1200W).

[0087] Step 4, calculate the power load baseline of the power equipment in each hour of the next day, and calculate the adjustable load value of the power equipment in each hour of the next day. The power equipment that meets the requirements enters the adjustable equipment pool and waits to perform the specific virtual power plant power peak shaving task in the next day. At the same time, calculate the total adjustable load capacity limit for each hour in the next day. For example, the power load baseline of the above-mentioned air-conditioning device a at 3 pm is 1000W. It is estimated that if the air-conditioning device a maintains an adjustable load of 27 degrees Celsius from 3 pm to 4 pm in the next day, it will be 1000W-700W=300W. The air-conditioning device a will be included in the adjustable equipment pool, and the upper limit of the adjustable load capacity of the virtual power plant at 3 pm in the next day will be increased by 300W.

[0088] Step 5, wait for the power grid system to issue the virtual power plant peak shaving task. First, judge whether the corresponding hourly period is capable of meeting the power grid peak shaving demand. If so, accept the virtual power plant task issued by the power grid system and select the corresponding equipment from the adjustable equipment pool. Reduce the power consumption of the target equipment by changing the set temperature or heating / cooling status of the equipment until the virtual power plant task is completed.

[0089] The embodiment of the present invention uses a deep learning algorithm to learn the user's habits of using high-power functions of electrical equipment, fully considers the user's possible electricity demand in the process of estimating the adjustable load of the virtual power plant, and recalculates the adjustable load of the virtual power plant while maintaining the user experience as much as possible. This can effectively improve the success rate of C-end users participating in the virtual power plant's electricity peak shaving tasks, and can effectively reduce user interruptions during the execution of the virtual power plant's electricity peak shaving tasks.

[0090] The following is a description of an apparatus for adjusting power load data provided by an embodiment of the present invention. The apparatus for adjusting power load data described below and the method for adjusting power load data described above can be referred to each other.

[0091] refer to Figure 4 The power load data adjustment device provided in the embodiment of the present invention includes a prediction module 401, a set temperature determination module 402, a power load baseline determination module 403, a selection module 404 and an adjustment module 405.

[0092] A prediction module 401 is used to predict the startup information of the electric device in a first time period in the future based on a data set of the electric device; the data set includes historical usage data of the electric device; A set temperature determination module 402 is used to determine the set temperature of the electrical device in a second time period in the future based on the start-up information of the electrical device in the first time period in the future; the second time period is the time period in which the electrical device is turned on in the first time period; the set temperature is a temperature parameter set by the user when using the electrical device; The power load baseline determination module 403 is used to determine the power load baseline of the power consumption equipment in the first future time period based on the historical power load data of the power consumption equipment; A selection module 404 is used to select the power load baseline of the power consumption equipment in the second time period in the future from the power load baseline of the power consumption equipment in the first time period in the future; The adjustment module 405 is used to adjust the power load data of the electric device based on the difference between the power load baseline of the electric device in the second time period in the future and the power load corresponding to the set temperature.

[0093] The power load data adjustment device provided in the embodiment of the present invention predicts the startup information of the power equipment in the first time period in the future based on the data set of the power equipment, and the data set includes the historical usage data of the power equipment; based on the startup information of the power equipment in the first time period in the future, determines the set temperature of the power equipment in the second time period in the future; the second time period is the time period for turning on the power equipment in the first time period; based on the historical power load data of the power equipment, determines the power load baseline of the power equipment in the first time period in the future; from the power load baseline of the power equipment in the first time period in the future, selects the power load baseline of the power equipment in the second time period in the future; based on the difference between the power load baseline of the power equipment in the second time period in the future and the power load corresponding to the set temperature, adjusts the power load data of the power equipment. The present invention fully considers the power demand of the user in the process of estimating the adjustable load, and adjusts the power load data on the basis of ensuring the user's experience.

[0094] In one embodiment, the set temperature includes a maximum set temperature and a minimum set temperature, and the adjustment module 405 is specifically used to: Determine a first difference between the power load baseline of the electrical equipment in the second time period in the future and the power load corresponding to the maximum set temperature, and a second difference between the power load baseline of the electrical equipment in the second time period in the future and the power load corresponding to the minimum set temperature; when the first difference is 0, use the second difference as the load adjustment value; when the second difference is 0, use 0 as the load adjustment value; when the first difference is greater than 0 and the second difference is greater than 0, determine the load adjustment value based on the first difference and the second difference; and adjust the power load data of the electrical equipment based on the load adjustment value.

[0095] In one embodiment, the adjustment module 405 is specifically configured to: Based on the load adjustment value and the weight of the electrical equipment, determine the adjustment priority of the electrical equipment; when the load value to be adjusted is less than the load adjustment upper limit value, select at least one target electrical equipment based on the adjustment priority of the electrical equipment; the load adjustment upper limit value is the total load adjustment value in the first time period in the future; based on the load adjustment value, adjust the power load data of the target electrical equipment.

[0096] In one embodiment, the adjustment module 405 is specifically configured to: When the adjustment time of the power load data is a statutory working day, the power load baseline of the power equipment in the first time period in the future is determined based on the historical power load data of multiple historical statutory working days; the power loads in the first time period of the historical statutory working days all meet the power loads corresponding to the user's power consumption behavior habits; when the adjustment time of the power load data is a non-statutory working day, the power load baseline of the power equipment in the first time period in the future is determined based on the historical power load data of multiple consecutive historical non-statutory working days.

[0097] In one embodiment, the prediction module 401 is specifically configured to: Extract feature data from the historical usage data in the data set, and cross-combine different features of the feature data; extract valid information from the cross-combined features; the valid information is a feature or feature combination that is correlated with whether the electrical device is turned on; based on the valid information, predict the turn-on information of the electrical device in the first time period in the future.

[0098] In one embodiment, a temperature determination module 402 is provided, specifically configured to: Based on the startup information of the electrical equipment in the first time period in the future, the second time period is determined; characteristic data of the second time period is extracted from the data set; based on the characteristic data of the second time period, the set temperature of the electrical equipment in the second time period in the future is determined.

[0099] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the following method: based on the data set of the electrical device, predict the startup information of the electrical device in the first time period in the future; the data set includes the historical usage data of the electrical device; based on the startup information of the electrical device in the first time period in the future, determine the set temperature of the electrical device in the second time period in the future; the second time period is the time period for turning on the electrical device in the first time period; the set temperature is the temperature parameter set by the user when using the electrical device; based on the historical power load data of the electrical device, determine the power load baseline of the electrical device in the first time period in the future; from the power load baseline of the electrical device in the first time period in the future, select the power load baseline of the electrical device in the second time period in the future; based on the difference between the power load baseline of the electrical device in the second time period in the future and the power load corresponding to the set temperature, adjust the power load data of the electrical device.

[0100] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0101] On the other hand, an embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for adjusting the power load data provided in the above-mentioned embodiments is implemented, for example, including: based on a data set of the power-consuming device, predicting the startup information of the power-consuming device in a first time period in the future; the data set includes historical usage data of the power-consuming device; based on the startup information of the power-consuming device in the first time period in the future, determining the set temperature of the power-consuming device in a second time period in the future; the second time period is the time period for turning on the power-consuming device in the first time period; the set temperature is a temperature parameter set by the user when using the power-consuming device; based on the historical power load data of the power-consuming device, determining the power load baseline of the power-consuming device in the first time period in the future; selecting the power load baseline of the power-consuming device in the second time period in the future from the power load baseline of the power-consuming device in the first time period in the future; and adjusting the power load data of the power-consuming device based on the difference between the power load baseline of the power-consuming device in the second time period in the future and the power load corresponding to the set temperature.

[0102] On the other hand, an embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the power load data adjustment method provided by the above-mentioned method embodiments, for example, including: based on a data set of an electric device, predicting the startup information of the electric device in a first time period in the future; the data set includes historical usage data of the electric device; based on the startup information of the electric device in the first time period in the future, determining the set temperature of the electric device in a second time period in the future; the second time period is a time period for turning on the electric device in the first time period; the set temperature is a temperature parameter set by a user when using the electric device; based on the historical power load data of the electric device, determining the power load baseline of the electric device in the first time period in the future; selecting the power load baseline of the electric device in the second time period in the future from the power load baseline of the electric device in the first time period in the future; and adjusting the power load data of the electric device based on the difference between the power load baseline of the electric device in the second time period in the future and the power load corresponding to the set temperature.

[0103] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0106] The above embodiments are only used to illustrate the present invention, but not to limit the present invention. Although the present invention is described in detail with reference to the embodiments, it should be understood by those skilled in the art that various combinations, modifications or equivalent substitutions of the technical solutions of the present invention do not depart from the spirit and scope of the technical solutions of the present invention, and should be included in the scope of the present invention.

Claims

1. A method for adjusting power load data, characterized in that: include: Based on the data set of the electric device, predicting the startup information of the electric device in a first time period in the future; The data set includes historical usage data of the electrical equipment; Determining a set temperature of the electrical equipment in a second time period in the future based on the startup information of the electrical equipment in the first time period in the future; The second time period is a time period during which the electrical device is turned on in the first time period; the set temperature is a temperature parameter set by a user when using the electrical device; Determining a power load baseline of the power consumption equipment in the first future time period based on the historical power load data of the power consumption equipment; Selecting the power load baseline of the power consumption equipment in the second time period in the future from the power load baseline of the power consumption equipment in the first time period in the future; The power load data of the electric device is adjusted based on the difference between the power load baseline of the electric device in the second time period in the future and the power load corresponding to the set temperature.

2. The method for adjusting power load data according to claim 1, characterized in that: The set temperature includes a maximum set temperature and a minimum set temperature; the adjusting the power load data of the power device based on the difference between the power load baseline of the power device in the second time period in the future and the power load corresponding to the set temperature includes: Determine a first difference between the power load baseline of the electrical equipment in the second future time period and the power load corresponding to the maximum set temperature, and a second difference between the power load baseline of the electrical equipment in the second future time period and the power load corresponding to the minimum set temperature; When the first difference is 0, the second difference is used as a load adjustment value; When the second difference is 0, taking 0 as the load adjustment value; When the first difference is greater than 0 and the second difference is greater than 0, determining the load adjustment value based on the first difference and the second difference; Based on the load adjustment value, the power load data of the electrical equipment is adjusted.

3. The method for adjusting power load data according to claim 2, characterized in that: The step of adjusting the power load data of the electrical equipment based on the load adjustment value includes: Determining the adjustment priority of the electrical equipment based on the load adjustment value and the weight of the electrical equipment; In the case where the load value to be adjusted is less than the load adjustment upper limit value, at least one target electrical equipment is selected based on the adjustment priority of the electrical equipment; the load adjustment upper limit value is the total load adjustment value in the first future time period; Based on the load adjustment value, the power load data of the target electrical equipment is adjusted.

4. The method for adjusting power load data according to claim 1, characterized in that: The determining, based on the historical power load data of the power-consuming device, the power load baseline of the power-consuming device in the first future time period includes: In the case where the adjustment time of the power load data is a statutory working day, the power load baseline of the power-consuming equipment in the first time period in the future is determined based on the historical power load data of multiple historical statutory working days; the power load in the first time period of the historical statutory working days all conforms to the power load corresponding to the user's power consumption behavior habits; In the case where the adjustment time of the power load data is a non-statutory working day, the power load baseline of the electrical equipment in the first future time period is determined based on historical power load data of a plurality of consecutive historical non-statutory working days.

5. The method for adjusting power load data according to claim 1, characterized in that: The predicting, based on the data set of the electric device, the startup information of the electric device in the first future time period includes: Extracting feature data from the historical usage data in the data set, and cross-combining different features on the feature data; Extracting effective information from the cross-combination features; the effective information is a feature or feature combination that is relevant to whether the electrical device is turned on; Based on the valid information, the startup information of the electric device in the first time period in the future is predicted.

6. The method for adjusting power load data according to any one of claims 1 to 5, characterized in that: The determining, based on the startup information of the electric device in the first time period in the future, the set temperature of the electric device in the second time period in the future, includes: Determining the second time period based on the startup information of the electric device in the first time period in the future; Extracting characteristic data of the second time period from the data set; Based on the characteristic data of the second time period, a set temperature of the electrical equipment in the second time period in the future is determined.

7. A device for regulating power load data, characterized in that: include: A prediction module, configured to predict, based on a data set of an electric device, startup information of the electric device in a first future time period; The data set includes historical usage data of the electrical equipment; A set temperature determination module is used to determine the set temperature of the electrical device in a second time period in the future based on the start-up information of the electrical device in the first time period in the future; the second time period is a time period for turning on the electrical device in the first time period; the set temperature is a temperature parameter set by the user when using the electrical device; A power load baseline determination module, configured to determine the power load baseline of the power consumption equipment in the first future time period based on the historical power load data of the power consumption equipment; A selection module, configured to select the power load baseline of the power consumption equipment in the second time period in the future from the power load baseline of the power consumption equipment in the first time period in the future; The adjustment module is used to adjust the power load data of the power device based on the difference between the power load baseline of the power device in the second time period in the future and the power load corresponding to the set temperature.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for adjusting the power load data according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for adjusting the power load data according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for adjusting the power load data according to any one of claims 1 to 6 is implemented.

Images