CN115829117B - Method and system for predicting electricity consumption in any area in short time based on terminal electricity consumption - Google Patents
Method and system for predicting electricity consumption in any area in short time based on terminal electricity consumption Download PDFInfo
- Publication number
- CN115829117B CN115829117B CN202211504108.5A CN202211504108A CN115829117B CN 115829117 B CN115829117 B CN 115829117B CN 202211504108 A CN202211504108 A CN 202211504108A CN 115829117 B CN115829117 B CN 115829117B
- Authority
- CN
- China
- Prior art keywords
- user
- information
- electricity consumption
- prediction
- grid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for predicting electricity consumption in any area in short time based on terminal electricity consumption information, wherein the method comprises the following steps: collecting terminal electricity consumption information: collecting personal information and power consumption related information of a terminal user; collecting auxiliary weather information: collecting weather information related to user power consumption information, wherein the weather information comprises daily average temperature information and time-period temperature information; preprocessing the collected terminal power consumption information and auxiliary weather information, constructing a prediction model, and predicting the power consumption of the user on a future date selected by the user; associating each user power consumption information with the acquired user position information; short-time prediction is carried out on the electricity consumption of any selected area: and randomly selecting certain map areas in the map, and realizing the prediction of the short-time electricity consumption of the selected areas. According to the invention, the power consumption prediction model is independently built for all power consumption users, and meanwhile, the position information of each user is associated with the map, so that the accurate scheduling of the resources of the region defined on the map at will is realized.
Description
Technical Field
The invention relates to research of a power consumption prediction method, in particular to a short-time prediction method and a short-time prediction system for power consumption of any area based on terminal power consumption information.
Background
The power consumption prediction is crucial in the aspects of power guarantee and power marketing, and the accurate power consumption prediction can provide important data support for reasonable scheduling of power resources and regional marketing of power customers. In the conventional electricity consumption prediction model and system, for a fixed area, supported data are area electricity consumption information, electricity consumption behavior, weather information and the like, such as power supply prediction of administrative areas of province level, city level, county level and the like.
On the other hand, in many occasions, the prediction of the electricity consumption needs to be realized for any geographic area, such as epidemic prevention and control, safety maintenance and stability and other application scenes. The traditional fixed area prediction model uses the power consumption information of the users in the area, and does not model each independent user independently, so that the power consumption prediction of any area in the geographic position cannot be realized, and the application breadth and depth of the power consumption prediction model are restricted.
Disclosure of Invention
The invention mainly solves the technical problems existing in the prior art, and provides a method and a system for predicting the electricity consumption in any area in short time based on terminal electricity consumption information. According to the method, the power consumption prediction model is independently built for all power consumption users, meanwhile, the position information (longitude and latitude coordinates) of each user is associated with the map, and finally, accurate scheduling of resources of an area defined on the map at will is achieved, and more comprehensive and accurate data support is provided.
The technical problems of the invention are mainly solved by the following technical proposal:
a method for predicting the electricity consumption of any area in short time based on terminal electricity consumption comprises the following steps:
step one, collecting terminal electricity consumption information: collecting personal information and power consumption related information of a terminal user, wherein the personal information and the power consumption related information comprise user types, personal user ages, power consumption time periods, daily power consumption and user position information;
step two, collecting auxiliary weather information: collecting weather information related to user power consumption information, wherein the weather information comprises daily average temperature information and time-period temperature information;
step three, short-term prediction of single-user electricity consumption: preprocessing the terminal power consumption information and the auxiliary weather information acquired in the first step and the second step, constructing a prediction model, and predicting the power consumption of the user on the future date selected by the user;
step four, associating the electricity consumption of the user with a map: associating the electricity consumption information of each user with the position information of the user acquired in the step one;
fifthly, predicting the electricity consumption of any selected area in a short time: and randomly selecting certain map areas in the map, and realizing the prediction of the short-time electricity consumption of the selected areas.
Further, the first step specifically includes:
step 1.1, collecting category information of users, wherein the category information is divided into 2 categories: personal users and enterprise users, and record the data;
step 1.2, collecting and recording age, electricity consumption period and daily electricity consumption information of an individual user;
step 1.3, collecting position information of a user, wherein the position information adopts a relative position as a record, and the implementation method comprises the following steps:
a) All areas of the local city where the user is located are treated by gridding, and each grid is numbered sequentially by Arabic numerals;
b) For grid size division, a dynamic division mode is adopted: dividing grids with the length of 100 meters and the width of 100 meters for urban areas with larger population densities; suburban areas with a low population density are meshed with 1000 meters long and 1000 meters wide;
c) Binding the number of the grid where the user is located with the user of the grid area.
Further, the second step specifically includes:
step 2.1, acquiring daily average temperature information of a predicted area required by the last 2 years;
step 2.2, acquiring temperature information of a predicted area required by the next 2 years in a time period of 18:00 of working days to 8:00 of next days;
and 2.3, acquiring the temperature information of the prediction area required by the near 2 years in a non-working day all-day time period.
Further, the third step specifically includes:
step 3.1, preprocessing part of the data in the step one, wherein the preprocessing method comprises the following steps:
a) The user category adopts Boolean type records, 0 represents enterprise users, and 1 represents individual users;
b) The personal user age information is recorded in the form of age groups, and is divided into 3 age groups: under 20 years old, 20-60 years old and over 60 years old;
c) The daily electricity quantity information is directly recorded by the degree of daily electricity quantity;
d) The electricity utilization period information directly digitally records how many hours of electricity utilization behaviors are in total in 24 hours of a day;
step 3.2, preprocessing the data in the step two, wherein the preprocessing method comprises the following steps:
a) Recording the daily average air temperature information of the area where the user is located in the last two years, and directly recording the daily average air temperature information by a temperature numerical value;
b) Recording the temperature information of the time intervals of 18:00-8:00 of the next day of the working day of the area where the user is located in the last two years, and recording only the time interval numbers of which the temperature is higher than 30 degrees and lower than 10 degrees, wherein if the temperature is higher than 30 degrees for 2 time intervals of 18:00-19:00 and 19:00-20:00, recording is carried out 2;
c) Recording the non-working day all-day time-sharing temperature information of the area where the user is located in the last two years, and only recording the time period number of which the temperature is higher than 30 ℃ and lower than 10 ℃;
step 3.3, a cyclic neural network framework is adopted to realize the prediction of the power consumption of each user on the future date, a training sample is the quantitative behaviors of one user and the weather information of a period corresponding to the behaviors, and a sample label is the power consumption degree of the user on the occurrence date;
and 3.4, aiming at all power users, training a short-time power consumption prediction model independently to realize the prediction of the power consumption of the user on the future date selected.
Further, the fourth step specifically includes:
step 4.1, for each grid, calculating the users in the grid through the position information of the users;
step 4.2, associating the grid with the power consumption prediction models of all users of the grid class, wherein the association method is to record the prediction models of the corresponding users;
and 4.3, for each grid, linearly superposing the prediction results of all prediction models related to the grid, namely, the prediction result of certain daily electricity consumption of the grid, and recording the prediction result as grid prediction electricity consumption.
Further, the fifth step specifically includes:
step 5.1, when regular or irregular areas are drawn in the map, calculating grids completely contained in the closed area, namely, all parts of the grids are in the closed area;
step 5.2, inspecting boundary grids of the selected area, solving all boundary grids, and determining how much area proportion of each grid is in the selected area;
step 5.4, linear superposition summation is carried out on the grid prediction electricity consumption which is obtained in the step 5.1 and completely contains the grid, and Sum is obtained 1 ;
Step 5.5, multiplying the boundary grid prediction power consumption in step 5.2 by the percentage of the corresponding grid obtained in step 5.2, and adding all boundary grid data to obtain Sum 2 ;
And 5.6, obtaining sum=sum 1+sum2 to obtain a short-time prediction result of the electricity consumption of any selected area.
A terminal electricity consumption based short-term prediction system for any regional electricity consumption comprises:
the terminal power consumption information acquisition module is used for acquiring terminal power consumption information, including user category, personal user age, power consumption period, daily power consumption and user position information;
the auxiliary weather information acquisition module is used for acquiring auxiliary weather information, including daily average temperature information and time-period temperature information;
the single-user electricity consumption short-time prediction module is used for preprocessing the terminal electricity consumption information and the auxiliary weather information acquired by the terminal electricity consumption information acquisition module and the auxiliary weather information acquisition module, constructing a prediction model and predicting the electricity consumption of the user at a future date selected by the user;
the user electricity consumption and map association module is used for associating the information of each user electricity consumption with the position information of the user acquired in the step one;
and the short-time prediction module for the power consumption of the randomly selected area is used for randomly selecting certain map areas in the map to realize the short-time power consumption prediction of the selected area.
Further, the short-term prediction module of single user power consumption pre-processes the terminal power consumption information and the auxiliary weather information acquired by the terminal power consumption information acquisition module and the auxiliary weather information acquisition module, constructs a prediction model, and predicts the power consumption of the user in future date selected by the user, and specifically comprises:
the method for preprocessing the partial data in the terminal electricity information comprises the following steps:
a) The user category adopts Boolean type records, 0 represents enterprise users, and 1 represents individual users;
b) The personal user age information is recorded in the form of age groups, and is divided into 3 age groups: under 20 years old, 20-60 years old and over 60 years old;
c) The daily electricity quantity information is directly recorded by the degree of daily electricity quantity;
d) The electricity utilization period information directly digitally records how many hours of electricity utilization behaviors are in total in 24 hours of a day;
the auxiliary weather information is preprocessed, and the preprocessing method comprises the following steps:
a) Recording the daily average air temperature information of the area where the user is located in the last two years, and directly recording the daily average air temperature information by a temperature numerical value;
b) Recording the temperature information of the time intervals of 18:00-8:00 of the next day of the working day of the area where the user is located in the last two years, and recording only the time interval numbers of which the temperature is higher than 30 degrees and lower than 10 degrees, wherein if the temperature is higher than 30 degrees for 2 time intervals of 18:00-19:00 and 19:00-20:00, recording is carried out 2;
c) Recording the non-working day all-day time-sharing temperature information of the area where the user is located in the last two years, and only recording the time period number of which the temperature is higher than 30 ℃ and lower than 10 ℃;
the method comprises the steps that a cyclic neural network framework is adopted to realize the prediction of the power consumption of each user on the future date, a training sample is the quantitative behaviors of a certain user and weather information of a period corresponding to the behaviors, and a sample label is the power consumption degree of the user on the occurrence date;
and aiming at all power users, a short-time power consumption prediction model is independently trained, so that the prediction of the power consumption of the user on the selected future date is realized.
Further, the user electricity consumption and map association module associates each piece of user electricity consumption information with the collected user position information in the step one, and specifically includes:
for each grid, calculating users in the grid through the position information of the users;
correlating the grid with the power consumption prediction models of all users of the grid class, wherein the correlation method is to record the prediction models of the corresponding users;
and for each grid, linearly superposing the prediction results of all prediction models related to the grid, namely, the prediction result of certain daily electricity quantity of the grid, and recording the prediction result as the grid prediction electricity quantity.
Further, the short-time prediction module for the power consumption of the arbitrarily selected area randomly selects some map areas in the map to realize the short-time power consumption prediction of the selected areas, and specifically includes:
when a regular or irregular area is drawn in the map, calculating a grid completely contained in the closed area, i.e. all parts of the grid are in the closed area;
inspecting boundary grids of the selected area, solving all the boundary grids, and determining how much area proportion of each grid is in the selected area;
the calculated grid prediction electricity consumption completely containing the grid is subjected to linear superposition summation to obtain Sum 1 ;
Multiplying the predicted power consumption of the boundary grid by the percentage of the obtained corresponding grid, and adding all the boundary grid data to obtain Sum 2 ;
And obtaining sum=sum 1+sum2 to obtain a short-time prediction result of the electricity consumption of any selected area.
The invention has the following beneficial effects: a lightweight electricity consumption prediction model is independently built for each user; the power consumption prediction for all user individuals is realized; dividing a geographic space in a two-level grid mode, and calculating and predicting the power supply quantity of a grid area based on the sum of the power supply quantity predictions of each independent user; and the power consumption prediction of any selected area is realized by calculating the grid number in linkage with the map and any selected area on the map.
Drawings
FIG. 1 is a flow diagram of a method for predicting electricity consumption in any area in short time based on terminal electricity consumption information;
fig. 2 is a block diagram of a system for predicting the electricity consumption of any area in short time based on terminal electricity consumption information.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the embodiment of the invention, taking a certain local market in Hubei province as an example, a method and a system for predicting the electricity consumption in any area in the city in short time based on terminal electricity consumption information are constructed, and the whole system is realized in a software mode.
As shown in fig. 1, an embodiment of the present invention provides a method for predicting power consumption in any area in short time based on terminal power consumption information, including the following steps:
step one, collecting terminal electricity consumption information: personal information and electricity consumption related information of the terminal user are collected, wherein the personal information and the electricity consumption related information comprise user types (personal users or enterprise users), personal user ages, electricity consumption time periods, daily electricity consumption and position information of the users. The specific implementation steps are as follows:
step 1.1, collecting category information of users, wherein the category information is divided into 2 categories: personal users and enterprise users, and record the data;
step 1.2, collecting and recording age, electricity consumption period and daily electricity consumption information of an individual user;
step 1.3, collecting position information of a user, wherein the position information adopts a relative position as a record, and the implementation method comprises the following steps:
a) All areas of the local city where the user is located are treated by gridding, and each grid is numbered sequentially by Arabic numerals;
b) For grid size division, a dynamic division mode is adopted: dividing grids with the length of 100 meters and the width of 100 meters for urban areas with larger population densities; suburban areas with a low population density are meshed with 1000 meters long and 1000 meters wide;
c) Binding the number of the grid where the user is located with the user of the grid area.
Step two, collecting auxiliary weather information: the method for collecting weather information related to the electricity consumption of the user comprises the following specific implementation steps of:
step 2.1, acquiring daily average temperature information of a predicted area required by the last 2 years;
step 2.2, acquiring temperature information of a predicted area required by the next 2 years in a time period of 18:00 of working days to 8:00 of next days;
and 2.3, acquiring the temperature information of the prediction area required by the near 2 years in a non-working day all-day time period.
Step three, short-term prediction of single-user electricity consumption: preprocessing all the data acquired in the first step and the second step, and constructing a prediction model, wherein the specific implementation steps are as follows:
step 3.1, preprocessing part of the data (other data except the grid data) in the step one, wherein the preprocessing method comprises the following steps:
a) The user category adopts Boolean type records, 0 represents enterprise users, and 1 represents individual users;
b) The personal user age information is recorded in the form of age groups, and is divided into 3 age groups: under 20 years old, 20-60 years old and over 60 years old;
c) The daily electricity quantity information is directly recorded by the degree of daily electricity quantity;
d) The electricity utilization period information directly digitally records how many hours of electricity utilization behaviors are in total in 24 hours of a day;
step 3.2, preprocessing the data in the step two, wherein the preprocessing method comprises the following steps:
a) Recording the daily average air temperature information of the area where the user is located in the last two years, and directly recording the daily average air temperature information by a temperature numerical value;
b) Recording the temperature information of the time intervals of 18:00-8:00 of the next day of the working day of the area where the user is located in the last two years, and recording only the time interval numbers of which the temperature is higher than 30 degrees and lower than 10 degrees, wherein if the temperature is higher than 30 degrees for 2 time intervals of 18:00-19:00 and 19:00-20:00, recording is carried out 2;
c) Recording the non-working day all-day time-sharing temperature information of the area where the user is located in the last two years, and only recording the time period number of which the temperature is higher than 30 ℃ and lower than 10 ℃;
and 3.3, adopting a circulating neural network framework to realize the prediction of the power consumption of each user in the future (short time). The training sample is the quantitative behaviors of a certain user and weather information of a period corresponding to the behaviors, and the sample label is the electricity consumption degree of the user on the occurrence day of the behaviors;
and 3.4, aiming at all power users, training a short-time power consumption prediction model independently to realize the prediction of the power consumption of the user on the future date selected.
Step four, associating the electricity consumption of the user with a map: and (3) associating the electricity consumption information of each user with the position information of the user acquired in the step one, wherein the specific implementation steps are as follows:
step 4.1, calculating which users in the grids exist according to the position information of the users for each grid;
step 4.2, associating the grid with the power consumption prediction models of all users of the grid class, wherein the association method is to record the prediction models of which users correspond to each other;
step 4.3, for each grid, linearly superposing the prediction results of all prediction models related to the grid, namely, the prediction result of certain daily electricity consumption of the grid, and recording the prediction result as grid prediction electricity consumption;
fifthly, predicting the electricity consumption of any selected area in a short time: certain map areas are randomly selected (outlined) in the map, so that the short-time electricity consumption prediction of the selected areas is realized, and the specific realization steps are as follows:
step 5.1, when regular or irregular areas are drawn in the map, calculating grids completely contained in the closed area (namely, all parts of the grids are in the closed area);
and 5.2, examining the boundary grids of the selected area (part of the boundary grids is in the range of the selected area), and solving all the boundary grids, wherein the area proportion of each grid is in the selected area.
Step 5.4, the grid prediction electricity consumption which is obtained in the step 5.1 and completely contains the grid is subjected to linear superposition (summation) to obtain Sum 1 ;
Step 5.5, multiplying the boundary grid prediction power consumption in step 5.2 by the percentage of the corresponding grid obtained in step 5.2, and adding all boundary grid data to obtain Sum 2 ;
And 5.6, obtaining sum=sum 1+sum2 to obtain a short-time prediction result of the electricity consumption of any selected area.
As shown in fig. 2, an embodiment of the present invention provides a system for predicting power consumption in any area in short time based on terminal power consumption information, including:
the terminal electricity consumption information collection module 10 is configured to collect terminal electricity consumption information, specifically collect personal information and electricity consumption related information of a terminal user, including information such as a user category (personal user or enterprise user), a personal user age, an electricity consumption period, daily electricity consumption, and location information of the user. Firstly, collecting category information of users, including individual users and enterprise users, and recording Boolean types; secondly, collecting and recording the age, electricity consumption period and daily electricity consumption information of the individual user; and finally, dividing the geographical space of the user by adopting the position information of the user in a plane grid mode, dividing grids by using a town area with larger population density and 100 meters long and 100 meters wide, dividing grids by using a suburban area with smaller population density and 1000 meters long and 1000 meters wide, and recording the grid area where each user is positioned.
In particular, if the user electricity consumption data is greatly affected in an area where a major event or a major event occurs, the area and the electricity consumption data in the period cannot be used as basic data, for example, a large-scale long-time power outage, a large-scale gathering activity, a sports gathering, a flood disaster, and the like. The method is that if a certain area of a certain time period has such events, the user data of the time period is removed and is not used as the basic data of a subsequent training prediction model.
The auxiliary weather information collection module 20 is used for collecting auxiliary weather information, and the main functions of the module are to collect weather information related to user electricity consumption information, including daily average temperature information and time-interval temperature information. Daily average temperature information needs to be collected for data of nearly 2 years for different areas. The time-interval temperature information needs to be considered according to two conditions of working days and non-working days, wherein the working days acquire the time-interval temperature information of 18:00-8:00 of the next day; and acquiring the temperature information of all-day time intervals on a non-working day.
Further, for the case that the temperature information of the partial area in time intervals is difficult to obtain, the temperature information of the adjacent area can be used for replacing the temperature information; for the partial region time-interval information missing condition, simulating missing data by adopting a mode of linear interpolation of adjacent time intervals; and if the outdoor temperature data is too high or too low in a certain period of time, deleting the data, and simulating the data in a difference simulation mode under the condition of information deficiency.
The short-term prediction module 30 for single-user electricity consumption has the main functions of preprocessing all data acquired by the two modules and constructing a prediction model for electricity consumption. For different types of data, different preprocessing modes are adopted: the electricity utilization user category divides the process into individual users and enterprise users; the user age data is processed into three age groups below 20 years old, 20-60 years old and above 60 years old; the daily electricity quantity information is processed into a daily electricity quantity degree value; the electricity utilization period information is the number of hours of electricity utilization behavior in the 24 hours of a day recorded in numerical values; the average daily temperature information in degrees fahrenheit for the area of the user in the last two years is processed into a numerical value (degrees); the time-period temperature information is processed as how many time periods each day have a temperature greater than 30 degrees or less than 10 degrees. The prediction model construction part in the module is realized by adopting a cyclic neural network framework, a training sample is the quantized behaviors of a certain user and the weather information of a period corresponding to the behaviors, and a sample label is the electricity consumption degree of the user on the occurrence day of the behaviors; and aiming at all power users, a short-time power consumption prediction model is independently trained, so that the prediction of the power consumption of the user on the selected future date is realized.
Specifically, in the aspect of constructing the electricity consumption prediction model, a training process of the electricity consumption prediction model is realized by directly adopting a circulating neural network module in a deep learning platform Tensorflow 2.0.
Furthermore, since one electricity consumption prediction model needs to be trained on all users independently and the sample features have probability same distribution features, a basic model can be trained first, and then independent electricity consumption prediction models for all users can be trained according to electricity consumption behavior data of all users. And the training of the basic model adopts the sample data of all users to perform unified training, and after training to a certain step number (the model is obviously converged), the training is stopped, and the basic model is obtained. On the basis of the basic model, the same cyclic neural network frame is selected, a sample set is replaced by the electricity consumption behavior data of each independent user, the basic model is continuously trained, and the electricity consumption prediction model converged on each independent user data sample is obtained.
The main function of the user electricity consumption and map association module 40 is to associate each user electricity consumption information with the user location information collected in the step one. The method is realized by calculating which users exist in each grid according to the position information of the users, and adding the power consumption information of all the users.
Specifically, the grid is superimposed with predicted power consumption data of all users in the grid area, and the output of the module is the predicted power consumption data of the grid area taking the grid as a unit.
The short-term electricity consumption prediction module 50 of any selected area has the main function of randomly selecting (delineating) certain map areas in the map and realizing the short-term electricity consumption prediction of the selected areas. The method is divided into two implementation modes: first, when the selected graduation area contains complete grid, the calculated grid prediction electricity consumption completely containing grid is linearly overlapped (summed) to obtain Sum 1 The method comprises the steps of carrying out a first treatment on the surface of the Secondly, a boundary grid is included in the selected area (part of the boundary grid is in the range of the selected area), how large area of the boundary grid is in the selected area is required to be solved, the area occupation ratio in the grid area is equal to the grid prediction electricity consumption ratio, all the boundary grid prediction electricity consumption is summarized and summed to obtain Sum2; finally sum=sum is obtained 1 +Sum 2 And the result is a short-time prediction result of the electricity consumption of any selected area.
Those of skill would further appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the various illustrative components and steps have been described generally in terms of functionality in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in random access memory, read only memory, electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The foregoing is merely illustrative embodiments of the present invention, and the present invention is not limited thereto, and any changes or substitutions that may be easily contemplated by those skilled in the art within the scope of the present invention should be included in the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims (5)
1. A short-time prediction method for electricity consumption of any area based on terminal electricity consumption is characterized by comprising the following steps: the method comprises the following steps:
step one, collecting terminal electricity consumption information: collecting personal information and power consumption related information of a terminal user, wherein the personal information and the power consumption related information comprise user types, personal user ages, power consumption time periods, daily power consumption and user position information;
step two, collecting auxiliary weather information: collecting weather information related to user power consumption information, wherein the weather information comprises daily average temperature information and time-period temperature information;
step three, short-term prediction of single-user electricity consumption: preprocessing the terminal power consumption information and the auxiliary weather information acquired in the first step and the second step, constructing a prediction model, and predicting the power consumption of the user on the future date selected by the user;
step four, associating the electricity consumption of the user with a map: associating the electricity consumption information of each user with the position information of the user acquired in the step one;
fifthly, predicting the electricity consumption of any selected area in a short time: randomly selecting certain map areas in the map to realize the prediction of the short-time electricity consumption of the selected areas;
the first step specifically comprises:
step 1.1, collecting category information of users, wherein the category information is divided into 2 categories: personal users and enterprise users, and record the data;
step 1.2, collecting and recording age, electricity consumption period and daily electricity consumption information of an individual user;
step 1.3, collecting position information of a user, wherein the position information adopts a relative position as a record, and the implementation method comprises the following steps:
a) All areas of the local city where the user is located are treated by gridding, and each grid is numbered sequentially by Arabic numerals;
b) For grid size division, a dynamic division mode is adopted: dividing grids with the length of 100 meters and the width of 100 meters in a town area; dividing grids with the length of 1000 meters and the width of 1000 meters for suburban areas;
c) Binding the number of the grid where the user is located with the user of the grid;
the fourth step specifically comprises:
step 4.1, for each grid, calculating the electricity consumption of the user in the grid through the position information of the user;
step 4.2, associating the grid with the power consumption prediction models of all users in the grid, wherein the association method is to record the prediction models of the corresponding users;
step 4.3, for each grid, linearly superposing the prediction results of all prediction models associated with the grid to obtain a prediction result of a certain daily electricity quantity of the grid, and recording the prediction result as a grid prediction electricity quantity;
the fifth step specifically comprises:
step 5.1, when a regular or irregular area is drawn in a map, calculating grid prediction electricity consumption of grids completely contained in the area;
step 5.2, inspecting boundary grids of the selected area, and solving how much area proportion of each boundary grid is in the selected area;
step 5.4, performing linear superposition summation on the grid prediction electricity consumption completely containing the grid obtained in the step 5.1 to obtain Sum 1 ;
Step 5.5, multiplying the predicted electricity consumption of the boundary grids by the area proportion of the corresponding grids obtained in the step 5.2 to obtain the electricity consumption of the boundary grids, and adding the electricity consumption of all the boundary grids to obtain Sum 2 ;
Step 5.6, obtaining sum=sum 1 + Sum 2 And (5) a short-time prediction result of the electricity consumption of any selected area.
2. The method for predicting the electricity consumption of any area in short time based on the electricity consumption of the terminal according to claim 1, wherein the method comprises the following steps: the second step specifically comprises:
step 2.1, acquiring daily average temperature information of a predicted area required by the last 2 years;
step 2.2, acquiring temperature information of a predicted area required by the next 2 years in a time period of 18:00 of working days to 8:00 of next days;
and 2.3, acquiring non-working day all-day time-period temperature information of a prediction area required by the next 2 years.
3. The method for predicting the electricity consumption of any area in short time based on the electricity consumption of the terminal according to claim 1, wherein the method comprises the following steps: the third step specifically comprises:
step 3.1, preprocessing the data in the step one, wherein the preprocessing method comprises the following steps:
a) The user category adopts Boolean type records, 0 represents enterprise users, and 1 represents individual users;
b) The personal user age information is recorded in the form of age groups, and is divided into 3 age groups: under 20 years old, 20-60 years old and over 60 years old;
c) Each daily electricity quantity information is directly recorded by the degree of the daily electricity quantity;
d) The electricity utilization period information directly digitally records how many hours of electricity utilization behaviors are in total in 24 hours of a day;
step 3.2, preprocessing the data in the step two, wherein the preprocessing method comprises the following steps:
a) Recording the daily average air temperature information of the area where the user is located in the last two years, and directly recording the daily average air temperature information by a temperature numerical value;
b) Recording the temperature information of the time intervals of 18:00 of the working day and 8:00 of the next day of the region where the user is located in the last two years, and only recording the time interval numbers of which the temperature is higher than 30 ℃ and lower than 10 ℃;
c) Recording the non-working day all-day time-sharing temperature information of the area where the user is located in the last two years, and only recording the time period number of which the temperature is higher than 30 ℃ and lower than 10 ℃;
step 3.3, a cyclic neural network framework is adopted to realize the prediction of the power consumption of each user on the future date, a training sample is the quantitative behaviors of one user and the weather information of a period corresponding to the behaviors, and a sample label is the power consumption degree of the user on the occurrence date of the behaviors;
and 3.4, aiming at each power user, training a short-time power consumption prediction model independently to realize the prediction of the power consumption of the user on the future date selected.
4. Any regional power consumption short-time prediction system based on terminal power consumption information, which is characterized by comprising:
the terminal power consumption information acquisition module is used for acquiring terminal power consumption information, including user types, personal user ages, power consumption time periods, daily power consumption and user position information;
the auxiliary weather information acquisition module is used for acquiring auxiliary weather information, including daily average temperature information and time-period temperature information;
the single-user electricity consumption short-time prediction module is used for preprocessing the terminal electricity consumption information and the auxiliary weather information acquired by the terminal electricity consumption information acquisition module and the auxiliary weather information acquisition module, constructing a prediction model and predicting the electricity consumption of the user at a future date selected by the user;
the user electricity consumption and map association module is used for associating the information of each user electricity consumption with the position information of the user acquired in the step one;
the short-time prediction module of the power consumption of the arbitrarily selected area is used for randomly selecting certain map areas in the map to realize the short-time power consumption prediction of the selected areas;
the terminal electricity consumption information acquisition module is specifically used for:
collecting category information of users, wherein the category information is divided into 2 categories: personal users and enterprise users, and record the data;
collecting and recording age, electricity consumption period and daily electricity consumption information of an individual user;
the method for acquiring the position information of the user, wherein the position information adopts the relative position as a record, comprises the following steps:
a) All areas of the local city where the user is located are treated by gridding, and each grid is numbered sequentially by Arabic numerals;
b) For grid size division, a dynamic division mode is adopted: dividing grids with the length of 100 meters and the width of 100 meters in a town area; dividing grids with the length of 1000 meters and the width of 1000 meters for suburban areas;
c) Binding the number of the grid where the user is located with the user of the grid;
the user electricity consumption and map association module is specifically used for:
for each grid, calculating the electricity consumption of the users in the grid through the position information of the users;
correlating the grid with the power consumption prediction models of all users in the grid, wherein the correlation method is to record the prediction models of the corresponding users;
for each grid, the prediction results of all prediction models associated with the grid are linearly overlapped to obtain the prediction result of certain daily electricity quantity of the grid, and the prediction result is recorded as grid prediction electricity quantity;
the short-time prediction module for the electricity consumption of the arbitrarily selected area is specifically used for:
when a regular or irregular area is drawn in the map, calculating grid prediction electricity consumption of grids completely contained in the area;
inspecting the boundary grids of the selected area, and solving how much area proportion of each boundary grid is in the selected area;
the calculated grid prediction electricity consumption completely containing the grid is subjected to linear superposition summation to obtain Sum 1 ;
Multiplying the predicted power consumption of the boundary grid by the obtained face of the corresponding gridThe product proportion obtains the electricity consumption of the boundary grids, and adds the electricity consumption of all the boundary grids to obtain Sum 2 ;
Sum=sum is obtained 1 + Sum 2 And (5) a short-time prediction result of the electricity consumption of any selected area.
5. The terminal electricity consumption information-based arbitrary area electricity consumption short-time prediction system according to claim 4, wherein: the single-user electricity consumption short-time prediction module is specifically used for:
the data in the terminal electricity utilization information is preprocessed, and the preprocessing method comprises the following steps:
a) The user category adopts Boolean type records, 0 represents enterprise users, and 1 represents individual users;
b) The personal user age information is recorded in the form of age groups, and is divided into 3 age groups: under 20 years old, 20-60 years old and over 60 years old;
c) Each daily electricity quantity information is directly recorded by the degree of the daily electricity quantity;
d) The electricity utilization period information directly digitally records how many hours of electricity utilization behaviors are in total in 24 hours of a day;
the auxiliary weather information is preprocessed, and the preprocessing method comprises the following steps:
a) Recording the daily average air temperature information of the area where the user is located in the last two years, and directly recording the daily average air temperature information by a temperature numerical value;
b) Recording the temperature information of the time intervals of 18:00 of the working day and 8:00 of the next day of the region where the user is located in the last two years, and only recording the time interval numbers of which the temperature is higher than 30 ℃ and lower than 10 ℃;
c) Recording the non-working day all-day time-sharing temperature information of the area where the user is located in the last two years, and only recording the time period number of which the temperature is higher than 30 ℃ and lower than 10 ℃;
the method comprises the steps that a cyclic neural network framework is adopted to realize the prediction of the power consumption of each user on the future date, a training sample is the quantitative behaviors of a certain user and weather information of a period corresponding to the behaviors, and a sample label is the power consumption degree of the user on the occurrence date;
and aiming at each power user, a short-time power consumption prediction model is independently trained, so that the prediction of the power consumption of the user on the selected future date is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211504108.5A CN115829117B (en) | 2022-11-29 | 2022-11-29 | Method and system for predicting electricity consumption in any area in short time based on terminal electricity consumption |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211504108.5A CN115829117B (en) | 2022-11-29 | 2022-11-29 | Method and system for predicting electricity consumption in any area in short time based on terminal electricity consumption |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115829117A CN115829117A (en) | 2023-03-21 |
CN115829117B true CN115829117B (en) | 2023-09-19 |
Family
ID=85532283
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211504108.5A Active CN115829117B (en) | 2022-11-29 | 2022-11-29 | Method and system for predicting electricity consumption in any area in short time based on terminal electricity consumption |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115829117B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117039850B (en) * | 2023-07-12 | 2024-07-26 | 湖北华中电力科技开发有限责任公司 | Abnormal electricity consumption analysis method and system based on space-time ground feature characteristics |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103971296A (en) * | 2014-05-16 | 2014-08-06 | 国家电网公司 | Power purchase method for mathematic model based on electrical loads and temperature |
CN105260803A (en) * | 2015-11-06 | 2016-01-20 | 国家电网公司 | Power consumption prediction method for system |
CN106096774A (en) * | 2016-06-07 | 2016-11-09 | 国网山东省电力公司菏泽供电公司 | A kind of large area region Analyzing Total Electricity Consumption Forecasting Methodology based on gridding method |
CN111210058A (en) * | 2019-12-26 | 2020-05-29 | 深圳供电局有限公司 | Grid-based power distribution network top-down load prediction information method |
CN113505534A (en) * | 2021-07-07 | 2021-10-15 | 南京工程学院 | Load prediction method considering demand response |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11349306B2 (en) * | 2019-06-19 | 2022-05-31 | King Fahd University Of Petroleum And Minerals | Distribution grid fault analysis under load and renewable energy uncertainties |
-
2022
- 2022-11-29 CN CN202211504108.5A patent/CN115829117B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103971296A (en) * | 2014-05-16 | 2014-08-06 | 国家电网公司 | Power purchase method for mathematic model based on electrical loads and temperature |
CN105260803A (en) * | 2015-11-06 | 2016-01-20 | 国家电网公司 | Power consumption prediction method for system |
CN106096774A (en) * | 2016-06-07 | 2016-11-09 | 国网山东省电力公司菏泽供电公司 | A kind of large area region Analyzing Total Electricity Consumption Forecasting Methodology based on gridding method |
CN111210058A (en) * | 2019-12-26 | 2020-05-29 | 深圳供电局有限公司 | Grid-based power distribution network top-down load prediction information method |
CN113505534A (en) * | 2021-07-07 | 2021-10-15 | 南京工程学院 | Load prediction method considering demand response |
Non-Patent Citations (3)
Title |
---|
"A review on renewable energy and electricity requirement forecasting models for smart grid and buildings";T. Ahmad, et al.;《Sustainable Cities and Society》;第55卷;第1-31页 * |
"基于梯度提升决策树的电力物联网用电负荷预测";刘瑾 等;《智慧电力》;第50卷(第8期);第46-53页 * |
"基于资源特征挖掘的风电中长期电量预测方法";孙书凯;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第5期);第C042-703页 * |
Also Published As
Publication number | Publication date |
---|---|
CN115829117A (en) | 2023-03-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Jansa et al. | MEDEX: a general overview | |
Goosse et al. | Using paleoclimate proxy-data to select optimal realisations in an ensemble of simulations of the climate of the past millennium | |
Waliser et al. | The Hadley circulation: Assessing NCEP/NCAR reanalysis and sparse in-situ estimates | |
Hashimoto et al. | Scenario analysis of land-use and ecosystem services of social-ecological landscapes: implications of alternative development pathways under declining population in the Noto Peninsula, Japan | |
Hay et al. | Use of weather types to disaggregate general circulation model predictions | |
Kundzewicz et al. | Climatic change impact on water resources in a systems perspective | |
CN115829117B (en) | Method and system for predicting electricity consumption in any area in short time based on terminal electricity consumption | |
Needelman et al. | Recreational swimming benefits of New Hampshire lake water quality policies: An application of a repeated discrete choice model | |
Bradshaw et al. | Marsh bird occupancy of wetlands managed for waterfowl in the Midwestern USA | |
Schuh et al. | Far-field biogenic and anthropogenic emissions as a dominant source of variability in local urban carbon budgets: A global high-resolution model study with implications for satellite remote sensing | |
CN117009887B (en) | Method and system for finely estimating and analyzing water environment quality of river basin | |
CN113220810A (en) | Multi-source species distribution data processing method and device | |
Hsiung et al. | Impacts of global warming on larval and juvenile transport of Japanese eels (Anguilla japonica) | |
Rajan et al. | A GIS based integrated land use/cover change model to study human-land interactions | |
Mather et al. | Climatology: the challenge for the eighties | |
Michaelis | Climate Change Effects on the Extratropical Transition of Tropical Cyclones in High-Resolution Global Simulations. | |
Thomas et al. | A Data Integration Approach to Estimating Personal Exposures to Air Pollution | |
Hidayat et al. | Modification of The Thermal Comfort Index Based on Perceptions for Urban Tourism Around Jakarta | |
Senftleben | Arctic sea ice in Earth system models: decadal hindcast skill and constraints of long-term projections | |
Cassardo et al. | Analysis of the observations of temperature carried out at the meteorological station of the institute of physics | |
Chen et al. | Climate Change Reduces the Effectiveness of Myanmar’s Protected Area Network | |
Roten | Constraining Sector-Specific CO2 Emissions From the Los Angeles Megacity Using Nasa’s Orbiting Carbon Observatory-3 Instrument | |
Dieterich et al. | Higher quantiles of sea levels rise faster in Baltic Sea Climate projections | |
Hay | Science of Weather, Climate and Ocean Extremes | |
東京大学大学院 | Mechanisms for multi-year ENSO |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |