CN117313952A - Load prediction method, device, equipment and storage medium - Google Patents

Abstract

The application relates to a load prediction method, a load prediction device, a load prediction apparatus and a storage medium. The method comprises the following steps: acquiring target behavior data corresponding to each target time period of each family member in a target time interval, wherein the target behavior data corresponds to the household condition of each family member in the target time period; and obtaining load prediction data corresponding to the target time period according to the target time period, the target behavior data and a preset load prediction model. By adopting the method, the accuracy of the load prediction data corresponding to the target time period can be improved, so that the accuracy of the load prediction method is improved.

Description

Load forecasting methods, devices, equipment and storage media

Technical field

This application relates to the field of electric power technology, and in particular to a load forecasting method, device, equipment and storage medium.

Background technique

During the peak period of residents' electricity consumption, the power system will be overloaded. In order to better cope with the load pressure of the power system during the peak period of electricity consumption and enable the power system to operate stably, it is necessary to predict household load data.

In traditional technology, the target control terminal of each household in the power system determines the electrical equipment used in the household based on the power consumption data collected by the electricity meter connected to it, and sets the target control terminal based on the usage of the electrical equipment corresponding to each historical time period in the household. The target load data of the time period is forecasted.

However, traditional load forecasting methods have low accuracy.

Contents of the invention

Based on this, it is necessary to provide a highly accurate load forecasting method, device, equipment and storage medium for the above technical problems.

In the first aspect, this application provides a load forecasting method. The methods include:

Obtain the target behavior data corresponding to each target time period of each family member within the target time interval, and the target behavior data corresponds to the home situation of each family member during the target time period;

According to the target time period, target behavior data and the preset load forecast model, the load forecast data corresponding to the target time period is obtained;

In one embodiment, the method further includes:

Obtain the overall electrical appliance usage data corresponding to each historical time period within the historical time interval, as well as the historical behavior data of each family member in each historical time period; the historical behavior data corresponds to the home situation of each family member in the historical time period;

Based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member in each historical time period, a load forecasting model is obtained.

In one embodiment, a load prediction model is obtained based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavioral data of each family member in each historical time period, including:

For each historical time period, the overall electrical appliance usage data corresponding to the historical time period and the historical behavioral data of each family member are integrated and processed to obtain the electrical appliance usage member data corresponding to the historical time period;

Based on the data of electrical appliance users corresponding to each historical time period, a load prediction model is obtained.

In one embodiment, the overall electrical appliance usage data corresponding to the historical time period and the historical behavioral data of each family member are integrated to obtain the electrical appliance usage member data corresponding to the historical time period, including:

Based on the historical behavioral data, obtain the historical behavioral member data of each family member within the historical time period;

For each family member, based on the historical behavioral member data and overall electrical appliance usage data corresponding to the family member, the first electrical appliance usage member data of each family member in the historical time period is obtained.

For each combination of family members, based on the historical behavioral member data and overall electrical appliance usage data corresponding to the family member, the second electrical appliance usage member data of each member combination in the historical time period is obtained, and the member combination corresponds to multiple family members;

According to the first electrical appliance user data of each family member in the historical time period and the second electrical appliance user data of each member combination in the historical time period, the electrical appliance user data corresponding to the historical time period is obtained.

In one embodiment, load prediction data corresponding to the target time period is obtained based on the target time period, target behavior data and a preset load prediction model, including:

Determine the reference time period corresponding to the target time period from each historical time period within the historical time interval;

If the target behavior data corresponds to each member combination corresponding to the reference time period, then determine the load prediction data corresponding to the target time period based on the second electrical appliance usage member data in each reference time period;

If the target behavior data corresponds to each family member corresponding to the reference time period, then the load prediction data corresponding to the target time period is determined based on the first electrical appliance using member data in each reference time period.

In one embodiment, a load prediction model is obtained based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavioral data of each family member in each historical time period, including:

For each historical time period, based on the overall electrical appliance usage data corresponding to the historical time period and the historical behavioral data of each family member, the electrical appliance usage combination data corresponding to each family member in the historical time period is obtained;

The initial prediction model is iteratively learned using combined electrical appliance usage data to obtain a load prediction model.

In one embodiment, obtaining the overall electrical appliance usage data corresponding to each historical time period within the historical time interval includes:

For each historical time period, obtain the meter reading data corresponding to the historical time period;

The waveform characteristics of the meter reading data are identified, analyzed and processed to obtain the overall electrical appliance usage data.

In a second aspect, this application also provides a load prediction device. Devices include:

The data acquisition module is used to obtain the target behavior data of each family member during the target time period. The target behavior data corresponds to the home situation of each family member during the target time period;

The load forecasting module is used to obtain the load forecast data corresponding to the target time period based on the target time period, target behavior data and the preset load forecast model.

In a third aspect, this application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of the method described in the first aspect are implemented.

In a fourth aspect, this application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, it implements the steps of the method described in the first aspect.

The above-mentioned load forecasting method, device, equipment and storage medium obtain the target behavior data corresponding to each target time period of each family member within the target time interval, and the target behavior data corresponds to the home situation of each family member during the target time period; according to The target time period, target behavior data and the preset load prediction model are used to obtain the load forecast data corresponding to the target time period; in this way, based on the behavioral data of each family member, the load prediction model is used to predict and obtain the load forecast data for the target time period, which avoids In traditional technology, the load forecast data of the target time period is only obtained based on the usage of electrical equipment corresponding to each historical time period, which leads to the problem of low prediction accuracy; in this application, the impact of behavioral data of each family member on the usage of electrical equipment is taken into consideration , can improve the accuracy of the load forecast data corresponding to the target time period, thereby improving the accuracy of the load forecast method.

Description of drawings

Figure 1 is an application environment diagram of the load forecasting method in one embodiment;

Figure 2 is a schematic flowchart of a load forecasting method in one embodiment;

Figure 3 is a schematic flowchart of the steps of obtaining a load prediction model in one embodiment;

Figure 4 is a schematic flowchart of the steps of obtaining a load prediction model in one embodiment;

Figure 5 is a schematic flowchart of the steps of obtaining electrical appliance usage member data in one embodiment;

Figure 6 is a schematic flowchart of the steps of obtaining load forecast data in one embodiment;

Figure 7 is a schematic flowchart of the steps of obtaining a load prediction model in one embodiment;

Figure 8 is a schematic flowchart of the steps of obtaining overall electrical appliance usage data in one embodiment;

Figure 9 is a schematic flowchart of a load prediction method in another embodiment;

Figure 10 is a schematic flow chart of a load prediction method in another embodiment;

Figure 11 is a structural block diagram of a load prediction device in one embodiment;

Figure 12 is an internal structure diagram of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

The load prediction method provided by the embodiment of the present application can be applied in the application environment as shown in Figure 1. Among them, the target control terminal 102 is connected to the smart meter 104, and the smart meter 104 is connected to each electrical device in the home to form overall electrical appliance usage data and send it to the target control terminal 102; the target control terminal 102 is connected to the input device 106, and receives the input device 106 The target behavior data sent; the target control terminal 102 is connected to the collection device 108 and receives the historical behavior data sent by the collection device 108; the target control terminal 102 is also connected to the cloud through the network. Among them, the target control terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets and portable wearable devices. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.; the input device 106 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, and portable wearable devices; the collection device 108 can be, but is not limited to, various smart door locks and fingerprint collectors.

In one embodiment, as shown in Figure 2, a load prediction method is provided. This method is explained by taking the method applied to the target control terminal 102 in Figure 1 as an example, including:

Step 202: Obtain the target behavior data corresponding to each target time period of each family member within the target time interval.

The target time interval refers to the time interval to be predicted using the load prediction method in this embodiment, and the target time period refers to a plurality of uniformly long time periods divided into which the target time interval is divided.

Among them, the target behavior data corresponds to the home situation of each family member during the target time period.

Here, a family can be understood as a house in which a family unit lives, and a family includes at least one family member.

For example, the target time interval is from 0:00 to 24:00 on a certain day, and each target time period is each hour in the target time interval.

For example, the time of leaving home and the time of returning home entered by each family member within the target time interval can be obtained through the input device 106, thereby determining the target behavior data of each target time period. The information entered by family member A through the input device 106 includes that he left the family at 8:20 on that day and returned to the family at 10:20. It can be determined that the target behavior data of family member A in the target time period from 8:00 to 9:00 is at home. status, the target behavior data in the target time period from 9 to 10 o'clock is the away-from-home state, and the target behavior data in the target time period from 10 to 11 o'clock is the home state.

Step 204: Obtain load prediction data corresponding to the target time period based on the target time period, target behavior data and the preset load prediction model.

Among them, the target time period and target behavior data are input into a preset load prediction model, prediction is performed based on the target behavior data based on the load prediction model, and load prediction data corresponding to the target time period is output.

In the above load forecasting method, by obtaining the target behavior data corresponding to each target time period of each family member in the target time interval, the target behavior data corresponds to the home situation of each family member in each target time period; according to the target time period, target Behavioral data and the preset load forecasting model are used to obtain load forecasting data corresponding to the target time period; in this way, based on the target behavior data of each family member, the load forecasting model is used to predict and obtain load forecasting data for the target time period, avoiding the traditional technology that only The load forecast data of the target time period is obtained based on the usage of electrical equipment corresponding to each historical time period, which leads to the problem of low prediction accuracy; in this application, the behavioral data of each family member can reflect the home behavior of each family member in the target time period. The home situation of each family member can have an impact on the usage of electrical equipment. This application incorporates this impact into the prediction process of load forecast data, which can improve the accuracy of load forecast data corresponding to the target time period, thereby improving load forecasting. accuracy of the method.

In one embodiment, based on the embodiment shown in Figure 2, as shown in Figure 3, the method further includes:

Step 302: Obtain the overall electrical appliance usage data corresponding to each historical time period within the historical time interval, and the historical behavior data of each family member in each historical time period.

Among them, the overall electrical appliance usage data is used to indicate each electrical appliance used by the household in each historical time period within the historical time interval.

For example, the historical time period T _j,k represents the period k on the jth day, where k ranges from 1 to 24, that is, T _1,1 represents the period 1 on the first day, corresponding to 0 on the first day. hour to 1 hour. The overall electrical appliance usage data corresponding to each historical time period within the historical time interval can be expressed as shown in Table 1.

Table 1 Overall electrical appliance usage data corresponding to each historical time period

Among them, the historical behavior data corresponds to the home situation of each family member during the historical time period.

For example, the collection device 108 can be used to obtain the time when each family member returns to the family and the time when he leaves the family in each historical time period, and determines the time when each family member returns to the family and the time when he leaves the family. Historical behavioral data of family members in each historical time period.

For example, the family includes three family members: Zhang, Li, and Zhang. The historical behavior data of each family member in each historical time period can be expressed as shown in Table 2.

Table 2 Historical behavioral data of each family member in each historical time period

Among them, the historical behavior data corresponding to period 1 on the first day is Zhang, Li, and Zhang, which means that family members Zhang, Li, and Zhang are all at home during this period.

Step 304: Obtain a load prediction model based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member in each historical time period.

Among them, the load prediction model is used to predict the load data corresponding to the target time period based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member in each historical time period, and obtain the target Load forecast data corresponding to the time period.

The load prediction model may be a statistical model or a machine learning model, which is not limited in this application.

For example, the load prediction model can be a statistical model, such as linear regression, logistic regression, time series analysis model, etc.; or it can be a machine learning model, such as decision tree, random forest, support vector machine, neural network, etc.

In this embodiment, a load prediction model is obtained based on the overall electrical appliance usage data corresponding to each historical time period within the historical time interval and the historical behavioral data of each family member in each historical time period. Based on the overall electrical appliance usage data and historical behavioral data, a load prediction model is obtained. The load situation in the target time period is predicted, and the impact of the behavioral data of each family member on the use of electrical equipment is considered, thereby improving the accuracy of the load forecast data corresponding to the target time period and improving the accuracy of the load forecasting method.

In one embodiment, based on the embodiment shown in Figure 3, as shown in Figure 4, a load forecast is obtained based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member in each historical time period. Models, including:

Step 402: For each historical time period, integrate the overall electrical appliance usage data corresponding to the historical time period and the historical behavior data of each family member to obtain electrical appliance usage member data corresponding to the historical time period.

Among them, the electrical appliance usage member data refers to the integration and processing of the overall electrical appliance usage data corresponding to the historical time period and the historical behavioral data of each family member, and the electrical appliance usage status of each family member in each historical time period is obtained.

For example, according to the overall electrical appliance usage data corresponding to each historical time period shown in Table 1 and the home situation corresponding to the historical behavior data of each family member in each historical time period shown in Table 2, the household conditions of each family member in each historical time period can be obtained. The electrical appliance usage member data corresponding to the time period is obtained, that is, the electrical appliance usage of Zhang, Li, and Zhang in each historical time period is obtained.

Step 404: Obtain a load prediction model based on the electrical appliance usage member data corresponding to each historical time period.

Among them, the load prediction model is used to predict the load data corresponding to the target time period based on the electrical appliance usage member data corresponding to each historical time period, and obtain the load prediction data corresponding to the target time period.

In this embodiment, a load prediction model is obtained based on the data of electrical appliance users corresponding to each historical time period, and the load situation in the target time period is predicted based on the electrical appliance usage of each family member in each historical time period, making full use of historical time. Predicting the use of electrical appliances by each family member in a segment can effectively improve the accuracy of the load forecast data corresponding to the target time period.

In one embodiment, based on the embodiment shown in Figure 4, as shown in Figure 5, the overall electrical appliance usage data corresponding to the historical time period and the historical behavior data of each family member are integrated to obtain the electrical appliances corresponding to the historical time period. Use member data, including:

Step 502: Obtain the historical behavioral member data of each family member within the historical time period based on the historical behavioral data.

Among them, the historical behavior data corresponds to the home situation of each family member in the historical time period, and the historical member data corresponds to the home situation of one of the family members in the historical time period.

For example, according to the historical behavioral data of each family member in each historical time period shown in Table 2, the historical behavioral member data of one of the family members, Zhang Moumou, in each historical time period is as shown in Table 3. Show.

Table 3 Zhang Moumou’s historical behavioral member data in each historical time period

Period 1 Period 2 Period 3 … Period 24 first day Zhang Moumou Zhang Moumou Zhang Moumou … - day Zhang Moumou Zhang Moumou Zhang Moumou … - … … … … … … seventh day - - - … -

Step 504: For each family member, obtain the first electrical appliance usage member data of each family member within the historical time period based on the historical behavioral member data and overall electrical appliance usage data corresponding to the family member.

Among them, the first electrical appliance usage member data of each family member in the historical time period is obtained by integrating the historical behavioral member data of the family member and the overall electrical appliance usage data.

For example, by integrating the home situation corresponding to Zhang's historical behavior member data in each historical time period shown in Table 3 and the overall electrical appliance usage data corresponding to each historical time period shown in Table 1, we can obtain Zhang's The data of members using the first electrical appliance in each historical time period can be expressed as shown in Table 4.

Table 4 Zhang Moumou’s first electrical appliance user data in each historical time period

Period 1 Period 2 Period 3 … Period 24 first day Electrical Appliance 1, Electrical Appliance 6 Electrical Appliance 1, Electrical Appliance 2 Electrical Appliance 1, Electrical Appliance 2, Electrical Appliance 3 … - the next day Electrical Appliance 1, Electrical Appliance 7 Electrical Appliance 1, Electrical Appliance 2 Electrical Appliance 1, Electrical Appliance 2, Electrical Appliance 3 … - … … … … … … seventh day - - - … -

For example, the first electrical appliance user data also includes Zhang's first electrical appliance user data in each historical time period, as shown in Table 5, and Li's first electrical appliance user data in each historical time period. , as shown in Table 6.

Table 5 Zhang’s first electrical appliance user data in each historical time period

Table 6 Li’s first electrical appliance user data in each historical time period

Step 506: For each family member combination, obtain the second electrical appliance usage member data of each member combination within the historical time period based on the historical behavioral member data and overall electrical appliance usage data corresponding to the family member.

Among them, the member combination corresponds to multiple family members.

For example, for a family including three family members: Zhang, Li and Zhang, the member combinations include Zhang and Li, Zhang and Zhang, Li and Zhang, Zhang and Li and Zhang Moumou.

For example, for the above four member combinations, the second electrical appliance usage member data of each member combination in each historical time period can be expressed as shown in Table 7, Table 8, Table 9 and Table 10 respectively.

Table 7 Second appliance usage member data of Zhang and Li in each historical time period

Table 8 Second appliance usage member data of Zhang and Zhang in each historical time period

Period 1 Period 2 Period 3 … Period 24 first day Electrical Appliance 1, Electrical Appliance 6 Electrical Appliance 1, Electrical Appliance 2 Electrical Appliance 1, Electrical Appliance 2, Electrical Appliance 3 … - the next day Electrical Appliance 1, Electrical Appliance 7 Electrical Appliance 1, Electrical Appliance 2 Electrical Appliance 1, Electrical Appliance 2, Electrical Appliance 3 … - … … … … … … seventh day - - - … -

Table 9 Second appliance usage member data of Li and Zhang in each historical time period

Period 1 Period 2 Period 3 … Period 24 first day Electrical Appliance 1, Electrical Appliance 6 Electrical Appliance 1, Electrical Appliance 2 Electrical Appliance 1, Electrical Appliance 2, Electrical Appliance 3 … - the next day Electrical Appliance 1, Electrical Appliance 7 Electrical Appliance 1, Electrical Appliance 2 Electrical Appliance 1, Electrical Appliance 2, Electrical Appliance 3 … - … … … … … … seventh day - - - … -

Table 10 Second appliance usage member data of Zhang, Li and Zhang in each historical time period

Period 1 Period 2 Period 3 … Period 24 first day Electrical Appliance 1, Electrical Appliance 6 Electrical Appliance 1, Electrical Appliance 2 Electrical Appliance 1, Electrical Appliance 2, Electrical Appliance 3 … - the next day Electrical Appliance 1, Electrical Appliance 7 Electrical Appliance 1, Electrical Appliance 2 Electrical Appliance 1, Electrical Appliance 2, Electrical Appliance 3 … - … … … … … … seventh day - - - … -

Step 508: Obtain the electrical appliance user data corresponding to the historical time period based on the first electrical appliance user data of each family member in the historical time period and the second electrical appliance user data of each member combination in the historical time period.

In this embodiment, through the overall electrical appliance usage data corresponding to the historical time period and the historical behavior data of each family member, the first appliance usage member data and the second appliance usage member data can be easily and quickly obtained, and then the appliance usage member data can be obtained. This enables the load forecasting model obtained based on the electrical appliance usage member data to quickly predict the load data corresponding to the target time period, thereby improving the efficiency of the load forecasting method.

In one embodiment, based on the embodiment shown in Figure 5, as shown in Figure 6, load prediction data corresponding to the target time period is obtained based on the target time period, target behavior data and the preset load prediction model, including:

Step 602: Determine the reference time period corresponding to the target time period from each historical time period within the historical time interval.

For example, the target time period G _a,i represents the period i of day a, and the reference time period corresponding to the target time period is T _j,i , that is, the period i of each day in the historical time interval.

Step 604: If the target behavior data corresponds to each member combination corresponding to the reference time period, determine the load prediction data corresponding to the target time period based on the second electrical appliance usage member data in each reference time period.

For example, according to the target behavior data of each family member in the target time period G _a,i , the target behavior data of the target time period G _a,i is that Zhang and Li are at home, which is consistent with the member combination shown in Table 7. Correspondingly, the load prediction data corresponding to the target time period is determined according to the second electrical appliance usage member data corresponding to the reference period T _j,i represented by the i-th column in Table 7.

Step 606: If the target behavior data corresponds to each member combination corresponding to the reference time period, determine the load prediction data corresponding to the target time period based on the second electrical appliance usage member data in each reference time period.

For example, according to the target behavior data of each family member in the target time period G _a,b , the target behavior data in the target time period G _a,b is that Zhang is at home, corresponding to the member combination shown in Table 4, The load forecast data corresponding to the target time period is determined according to the first electrical appliance usage member data corresponding to the reference period T _j,b represented by the b-th column in Table 4.

In a possible implementation, there are multiple first appliance usage member data corresponding to the target behavior data, and the multiple first appliance usage member data can be averaged. According to the average value of the multiple first appliance usage member data Determine the load forecast data corresponding to the target time period.

In this embodiment, the reference time period is determined based on the target time period, the electrical appliance usage data of each family member in the reference time period is quickly determined based on the target behavior data, and the load prediction data corresponding to the target time period is obtained. In order to improve the load prediction method efficiency while improving the accuracy of load forecasting methods.

In one embodiment, based on the embodiment shown in Figure 3, as shown in Figure 7, a load forecast is obtained based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member in each historical time period. Models, including:

Step 702: For each historical time period, obtain the electrical appliance usage combination data corresponding to each family member in the historical time period based on the overall electrical appliance usage data corresponding to the historical time period and the historical behavior data of each family member.

Among them, the electrical appliance usage combination data refers to the combined data formed by combining the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member.

For example, the historical behavior data and the electrical appliance usage combination data corresponding to each historical time period can be expressed as shown in Table 11.

Table 11 Electrical appliance usage combination data corresponding to each historical time period

Step 704: Use the combined electrical appliance usage data to iteratively learn the initial prediction model to obtain a load prediction model.

Enter the electrical appliance usage combination data into the initial prediction model. The electrical appliance usage combination data contains the historical behavior and electrical appliance usage data of family members in each historical time period. Through iterative learning, the parameters in the initial model are updated to obtain the load prediction model.

The initial prediction model may be a machine learning model, such as decision tree, random forest, support vector machine, neural network, etc., which is not limited in this application.

In this embodiment, the initial prediction model is trained based on the combined electrical appliance usage data obtained by combining the overall electrical appliance usage data corresponding to the historical time period and the historical behavior data of each family member. When predicting the load data corresponding to the target time period, The behavioral data and electrical equipment usage of each family member corresponding to the historical time period are considered, thereby improving the accuracy of the load forecast data corresponding to the target time period and improving the accuracy of the load forecasting method.

In one embodiment, as shown in Figure 8, the overall electrical appliance usage data corresponding to each historical time period within the historical time interval is obtained, including:

Step 802: For each historical time period, obtain the meter reading data corresponding to the historical time period.

Step 804: Identify, analyze and process the waveform characteristics of the meter reading data to obtain overall electrical appliance usage data.

Among them, the overall electrical appliance usage data corresponding to each historical time period is obtained by identifying and analyzing the electric meter reading data corresponding to each historical time period. By real-time monitoring of the waveform characteristics and changes of the current and voltage passing through the meter in each historical time period, the switching status and generated load data of different electrical equipment are identified, and each electrical equipment corresponding to the meter reading data is obtained.

In this embodiment, by identifying and analyzing the waveform characteristics of the meter reading data, the overall electrical appliance usage data is obtained. Each historical data can be quickly and accurately identified without substantial modification or intervention to the electrical equipment. The usage of electrical equipment corresponding to the time period.

In one embodiment, as shown in Figure 9, a load forecasting method is provided, which method includes:

Step 902: Obtain the overall electrical appliance usage data corresponding to each historical time period within the historical time interval, and the historical behavior data of each family member in each historical time period.

Optionally, for each historical time period, obtain the electric meter reading data corresponding to the historical time period, identify and analyze the waveform characteristics of the electric meter reading data, and obtain the overall electrical appliance usage data.

Step 904: For each historical time period, obtain the historical behavioral member data of each family member in the historical time period based on the historical behavioral data.

Step 906: For each family member, obtain the first electrical appliance usage member data of each family member in the historical time period based on the historical behavioral member data and overall electrical appliance usage data corresponding to the family member.

Step 908: For each family member combination, obtain the second electrical appliance usage member data of each member combination within the historical time period based on the historical behavioral member data and overall electrical appliance usage data corresponding to the family member.

Step 910: Obtain the electrical appliance user data corresponding to the historical time period based on the first electrical appliance user data of each family member in the historical time period and the second electrical appliance user data of each member combination in the historical time period.

Step 912: Obtain a load prediction model based on the electrical appliance usage member data corresponding to each historical time period.

Step 914: Obtain the target behavior data of each family member corresponding to each target time period within the target time interval.

Step 916: Determine the reference time period corresponding to the target time period from each historical time period within the historical time interval.

Step 918: If the target behavior data corresponds to each member combination corresponding to the reference time period, determine the load prediction data corresponding to the target time period based on the second electrical appliance usage member data in each reference time period.

Step 920: If the target behavior data corresponds to each family member corresponding to the reference time period, determine the load prediction data corresponding to the target time period based on the first electrical appliance usage member data in each reference time period.

In one embodiment, as shown in Figure 10, a load forecasting method is provided, which method includes:

Step 1002: Obtain the overall electrical appliance usage data corresponding to each historical time period within the historical time interval, and the historical behavior data of each family member in each historical time period.

Among them, the historical behavior data corresponds to the home situation of each family member during the historical time period.

Optionally, for each historical time period, obtain the electric meter reading data corresponding to the historical time period; identify and analyze the waveform characteristics of the electric meter reading data to obtain overall electrical appliance usage data.

Step 1004: For each historical time period, based on the overall electrical appliance usage data corresponding to the historical time period and the historical behavior data of each family member, the electrical appliance usage combination data corresponding to each family member in the historical time period is obtained.

Step 1006: Use the combined electrical appliance usage data to iteratively learn the initial prediction model to obtain a load prediction model.

Step 1008: Obtain the target behavior data of each family member corresponding to each target time period within the target time interval.

Among them, the target behavior data corresponds to the home situation of each family member during the target time period.

Step 1010: Obtain load prediction data corresponding to the target time period based on the target time period, target behavior data and the preset load prediction model.

It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments may include multiple steps or stages. These steps or stages are not necessarily executed at the same time, but may be completed at different times. The execution order of these steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

Based on the same inventive concept, embodiments of the present application also provide a load prediction device for implementing the above-mentioned load prediction method. The solution to the problem provided by this device is similar to the solution recorded in the above method. Therefore, for the specific limitations in one or more load prediction device embodiments provided below, please refer to the above limitations on the load prediction method. I won’t go into details here.

In one embodiment, as shown in Figure 11, a load prediction device is provided, including: a data input module 1102 and a load prediction module 1104, wherein:

The data input module 1102 is used to obtain the target behavior data corresponding to each target time period of each family member within the target time interval. The target behavior data corresponds to the home situation of each family member during the target time period;

The load prediction module 1104 is used to obtain load prediction data corresponding to the target time period based on the target time period, target behavior data and a preset load prediction model.

In one embodiment, the data input module 1102 is also used to obtain the overall electrical appliance usage data corresponding to each historical time period within the historical time interval, as well as the historical behavior data of each family member in each historical time period; the historical behavior data is related to each historical time period. Corresponding to the home conditions of family members in historical time periods; the load forecasting device also includes a model generation module, which is used to obtain based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member in each historical time period. Load forecasting model.

In one embodiment, the model generation module is used to integrate, for each historical time period, the overall electrical appliance usage data corresponding to the historical time period and the historical behavioral data of each family member to obtain the electrical appliance usage member data corresponding to the historical time period. ; Based on the data of electrical appliance users corresponding to each historical time period, a load forecasting model is obtained.

In one embodiment, the model generation module is used to obtain the historical behavioral member data of each family member in the historical time period based on the historical behavioral data; for each family member, based on the historical behavioral member data and electrical appliance usage corresponding to the family member The overall data is to obtain the first electrical appliance usage member data of each family member in the historical time period. For each family member's member combination, based on the historical behavioral member data corresponding to the family member and the overall electrical appliance usage data, the historical time of each member combination is obtained. The second appliance usage member data within the segment, the member combination corresponds to multiple family members; based on the first appliance usage member data of each family member in the historical time period and the second appliance usage member data of each member combination in the historical time period , obtain the electrical appliance usage member data corresponding to the historical time period.

In one embodiment, the load prediction module 1104 is used to determine the reference time period corresponding to the target time period from each historical time period within the historical time period; if the target behavior data corresponds to each member combination corresponding to the reference time period, Then determine the load forecast data corresponding to the target time period based on the second electrical appliance user data in each reference time period; if the target behavior data corresponds to each family member corresponding to the reference time period, then determine the load forecast data corresponding to the first time period in each reference time period. The appliance uses member data to determine load forecast data for the target time period.

In one embodiment, for each historical time period, the model generation module obtains the combined electrical appliance usage data corresponding to each family member in the historical time period based on the overall electrical appliance usage data corresponding to the historical time period and the historical behavioral data of each family member. ;Use the electrical appliance usage combined data to iteratively learn the initial prediction model to obtain the load prediction model.

In one embodiment, the data input module 1102 is used to obtain electric meter reading data corresponding to each historical time period within the historical time interval; perform identification and analysis on the waveform characteristics of the electric meter reading data to obtain overall electrical appliance usage data.

Each module in the above load prediction device can be implemented in whole or in part by software, hardware and combinations thereof. Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 12 . The computer device includes a processor, memory, input/output interface, communication interface, display unit and input device. Among them, the processor, memory and input/output interface are connected through the system bus, and the communication interface, display unit and input device are connected to the system bus through the input/output interface. Wherein, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage medium stores operating systems and computer programs. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals. The wireless mode can be implemented through WIFI, mobile cellular network, NFC (Near Field Communication) or other technologies. The computer program when executed by the processor implements a load forecasting method. The display unit of the computer equipment is used to form a visually visible picture, and may be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display or an electronic ink display. The input device of the computer device can be a touch layer covered on the display screen, or it can be a button, trackball or touch pad provided on the computer device casing, or it can be External keyboard, trackpad or mouse, etc.

Those skilled in the art can understand that the structure shown in Figure 12 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Specific computer equipment can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.

In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, it implements the steps in the above method embodiments.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

In one embodiment, a computer program product is provided, including a computer program that implements the steps in each of the above method embodiments when executed by a processor.

It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all It is information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage. In the media, when executed, the computer program may include the processes of the above method embodiments. Any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetic variable memory (Magnetoresistive Random) Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene memory, etc. Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include blockchain-based distributed databases, etc., but are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to this.

The technical features of the above embodiments can be combined in any way. To simplify the description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, all possible combinations should be used. It is considered to be within the scope of this manual.

The above-described embodiments only express several implementation modes of the present application, and their descriptions are relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all fall within the protection scope of the present application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims (10)

1. A load forecasting method, characterized in that the method includes: Obtain target behavior data corresponding to each target time period of each family member within the target time interval, and the target behavior data corresponds to the home situation of each family member within the target time period; According to the target time period, the target behavior data and the preset load prediction model, the load prediction data corresponding to the target time period is obtained. 2. The method according to claim 1, characterized in that, the method further comprises: Obtain the overall electrical appliance usage data corresponding to each historical time period within the historical time interval, as well as the historical behavior data of each family member in each historical time period; the historical behavior data is consistent with the historical behavior data of each family member in the said historical time period. Correspondence to home situations during historical time periods; The load prediction model is obtained based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member in each historical time period. 3. The method of claim 2, wherein the method is obtained based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member in each historical time period. Load forecasting models, including: For each historical time period, the overall electrical appliance usage data corresponding to the historical time period and the historical behavior data of each family member are integrated to obtain the electrical appliance usage member data corresponding to the historical time period; The load prediction model is obtained based on the electrical appliance usage member data corresponding to each historical time period. 4. The method according to claim 3, characterized in that the historical time is obtained by integrating the overall electrical appliance usage data corresponding to the historical time period and the historical behavior data of each family member. The electrical appliance usage member data corresponding to the segment includes: According to the historical behavioral data, obtain the historical behavioral member data of each family member within the historical time period; For each family member, according to the historical behavioral member data corresponding to the family member and the overall electrical appliance usage data, the first electrical appliance usage member data of each family member in the historical time period is obtained, For each member combination of the family members, according to the historical behavioral member data corresponding to the family member and the overall electrical appliance usage data, the second electrical appliance usage member data of each member combination within the historical time period is obtained, The member combination corresponds to multiple family members; According to the first appliance usage member data of each family member in the historical time period and the second appliance usage member data of each member combination in the historical time period, the appliance corresponding to the historical time period is obtained. Use member data. 5. The method according to claim 4, wherein the load prediction data corresponding to the target time period is obtained according to the target time period, the target behavior data and a preset load prediction model, including : Determine a reference time period corresponding to the target time period from each of the historical time periods within the historical time interval; If the target behavior data corresponds to each of the member combinations corresponding to the reference time period, then determine the load prediction corresponding to the target time period based on the second electrical appliance usage member data in each of the reference time periods. data; If the target behavior data corresponds to each of the family members corresponding to the reference time period, then the load prediction corresponding to the target time period is determined based on the first electrical appliance usage member data in each of the reference time periods. data. 6. The method of claim 2, wherein the method is obtained based on the overall electrical appliance usage data corresponding to each historical time period and the historical behavior data of each family member in each historical time period. Load forecasting models, including: For each historical time period, based on the overall electrical appliance usage data corresponding to the historical time period and the historical behavior data of each family member, the electrical appliance corresponding to each family member in the historical time period is obtained. Use combined data; The initial prediction model is iteratively learned using the electrical appliance usage combined data to obtain the load prediction model. 7. The method according to claim 2, characterized in that said obtaining the overall electrical appliance usage data corresponding to each historical time period within the historical time interval includes: For each historical time period, obtain the electric meter reading data corresponding to the historical time period; The waveform characteristics of the electric meter reading data are identified, analyzed and processed to obtain the overall usage data of the electrical appliance. 8. A load prediction device, characterized in that the device includes: A data acquisition module, used to obtain target behavior data of each family member within the target time period, where the target behavior data corresponds to the home situation of each family member within the target time period; A load prediction module is used to obtain load prediction data corresponding to the target time period based on the target time period, the target behavior data and a preset load prediction model. 9. A computer device, comprising a memory and a processor, the memory stores a computer program, characterized in that when the processor executes the computer program, the method of any one of claims 1 to 7 is implemented. step. 10. A computer-readable storage medium with a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.