CN111210055B - Prediction method and prediction system for electricity consumption behavior of power consumer - Google Patents
Prediction method and prediction system for electricity consumption behavior of power consumer Download PDFInfo
- Publication number
- CN111210055B CN111210055B CN201911348876.4A CN201911348876A CN111210055B CN 111210055 B CN111210055 B CN 111210055B CN 201911348876 A CN201911348876 A CN 201911348876A CN 111210055 B CN111210055 B CN 111210055B
- Authority
- CN
- China
- Prior art keywords
- air temperature
- user
- psychological field
- electricity consumption
- psychological
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 126
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000012937 correction Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000005290 field theory Methods 0.000 claims abstract description 16
- 238000012706 support-vector machine Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims abstract description 9
- 125000003275 alpha amino acid group Chemical group 0.000 claims description 9
- 150000001875 compounds Chemical class 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000003672 processing method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 51
- 230000008859 change Effects 0.000 description 10
- 230000008901 benefit Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 238000005457 optimization Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power consumption behavior prediction method and a power consumption behavior prediction system for an electric power user, wherein the method comprises the steps of obtaining historical power consumption data of the required user and historical air temperature data of a place where the user is located; constructing an air temperature psychological field model according to the acquired historical electricity consumption data and historical air temperature data of the user; the obtained historical power consumption data and the historical air temperature data of the user are used as input vectors of an SVM support vector machine, and a predicted initial value of the current user is obtained through calculationAccording to the predicted initial value of electricity consumption and by combining the air temperature psychological field model and the multi-scene set method, the current predicted air temperature psychological field intensity is calculated; carrying out standardization processing on the air temperature psychological field intensity in the prediction period to obtain a correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory; calculating final predicted value of user electricity consumption behavior by combining initial value of user electricity consumption and correction coefficientThe invention can effectively ensure the normal operation of the power network and reduce the economic loss of the power company.
Description
Technical Field
The invention relates to the technical field of power, in particular to a power consumption behavior prediction method and a power consumption behavior prediction system for power users.
Background
The electricity consumption behavior of the power consumer refers to the electricity consumption activity generated by the consumer as an electricity consumption main body under the influence of external environment factors, and is mainly reflected in the change condition of the electricity consumption load of the consumer. Through effectively grasping the electricity consumption behavior of the power consumer, better electric power service can be provided for the consumer, the power supply load pressure of a power supply unit is reduced, the error judgment of the future electric power demand caused by abnormal electricity consumption behavior is avoided, serious economic loss is caused for an electric power company, and the normal operation of an electric power network is influenced. Therefore, how to effectively predict the electricity usage behavior of the user is important to ensure the normal operation of the power network. However, the current technology does not provide an effective and accurate power consumer electricity behavior prediction method and prediction system for the electricity consumer electricity behavior prediction, i.e. the load prediction problem, in the power system.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a power consumer electricity consumption behavior prediction method and a power consumer electricity consumption behavior prediction system so as to effectively and accurately predict the power consumer electricity consumption behavior, thereby effectively ensuring the normal operation of a power network and reducing the economic loss of an electric company.
In order to achieve the above purpose, the technical scheme of the invention is as follows:
in a first aspect, an embodiment of the present invention provides a method for predicting electricity consumption behavior of a power consumer, including:
acquiring the required historical electricity consumption data of a user and the historical air temperature data of the place where the user is located;
constructing an air temperature psychological field model according to the acquired historical electricity consumption data and historical air temperature data of the user;
the obtained historical power consumption data and the historical air temperature data of the user are used as input vectors of an SVM support vector machine, so that a predictive power consumption initial value of the current user is calculated based on an SVM regression estimation method
According to the predicted initial value of electricity consumption and by combining the air temperature psychological field model and the multi-scene set method, the current predicted air temperature psychological field intensity is calculated;
carrying out standardization processing on the air temperature psychological field intensity in the prediction period to obtain a correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory;
calculating final predicted value of user electricity consumption behavior by combining initial value of user electricity consumption and correction coefficient
In a second aspect, an embodiment of the present invention provides a power consumer electricity behavior prediction system, including:
the data acquisition device is used for acquiring the required historical electricity consumption data of the user and the historical air temperature data of the place where the user is located;
the first data processor is used for processing and generating an air temperature psychological field model according to the historical electricity consumption data and the historical air temperature data of the user transmitted by the data acquisition unit; and the method is used for taking the acquired historical electricity consumption data and the historical air temperature data of the user as input vectors of an SVM support vector machine so as to calculate and obtain a predicted initial value of electricity consumption of the current user based on an SVM regression estimation method
The second data processor is used for calculating the current predicted air temperature psychological field intensity according to the predicted electricity initial value and the air temperature psychological field model transmitted by the first data processor and by combining a multi-scene set operation processing method; then, the air temperature psychological field intensity in the prediction period is subjected to standardized processing, and a correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory is obtained; finally, the final predicted value of the electricity consumption behavior of the user is calculated by combining the initial value of the electricity consumption of the user and the correction coefficient
Compared with the prior art, the invention has the beneficial effects that:
the electricity consumption behavior prediction method for the electric power user provided by the embodiment obtains the field strength mathematical expression of the air temperature psychological field by considering the formation of the air temperature psychological field, and is independent of the existing electricity consumption psychological model. Meanwhile, the air temperature is used as an input variable, and the existing power load prediction methods such as an SVM regression estimation method are utilized to calculate the power consumption behavior prediction initial value of the power consumer, so that the real-time performance of load prediction is maintained; when the air temperature psychological field intensity under the actual prediction scene is calculated, an air temperature multi-scene set method is adopted, so that the error of the obtained air temperature psychological field intensity can be reduced, and the real-time load prediction initial value is corrected by taking the air temperature psychological field intensity after optimization treatment as a correction coefficient, so that the predicted electricity consumption behavior of a user is closer to the psychological expectation of the user, and the method has the advantages of good prediction instantaneity, easiness in realization of a model, effective and accurate prediction result and the like, thereby effectively ensuring the normal operation of an electric power network and reducing the economic loss of an electric power company.
The power consumption behavior prediction system for the power consumer firstly acquires historical power consumption and historical air temperature data of the power consumer through the data acquisition device, then transmits the acquired data to the first data processor, generates an air temperature psychological field model through operation processing, takes the acquired air temperature data as an input variable, calculates a power consumption behavior prediction initial value of the power consumer by using the existing power load prediction methods such as an SVM regression estimation method and the like, and keeps the advantage of load prediction instantaneity; the result of the operation processing of the first data processor is transmitted to the second data processor, and the second data processor adopts an air temperature multi-scene set operation processing method when calculating the air temperature psychological field intensity under the actual prediction scene, so that the error of the obtained air temperature psychological field intensity can be reduced, and the real-time load prediction initial value is corrected by taking the air temperature psychological field intensity after the optimization processing as a correction coefficient, so that the electricity utilization result of the user predicted by the second data processor is closer to the psychological expectation of the user, and the method has the advantages of good prediction instantaneity, easiness in realization of a model, effective and accurate prediction result and the like, thereby effectively ensuring the normal operation of an electric power network and reducing the economic loss of an electric company.
Drawings
FIG. 1 is a flowchart of a power consumer electricity consumption behavior prediction method provided in embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of equipotential line distribution of a psychological field of air temperature;
FIG. 3 is a schematic diagram of an SVM network structure;
fig. 4 is a schematic diagram of the power consumption behavior prediction system for power consumer provided in embodiment 2 of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and detailed description.
The electricity consumption behavior of the power consumer refers to the electricity consumption activity generated by the consumer as an electricity consumption main body under the influence of external environment factors, and is mainly reflected in the change condition of the electricity consumption load of the consumer. The existing load prediction technology comprises a regression analysis method, a gray system theory method, a wavelet analysis method, an artificial neural network method and the like, and the prediction is performed from the simple point of view of data analysis. Since the behavioral subjects of power consumers are people with thinking and emotion cognition, the prediction of their power consumption behavior must take into account the influence of the psychological factors of the consumer. However, the influence of psychological factors is difficult to express in an accurate data form, and thus can be quantified by introducing a psychological field conceptual model by referring to the theory of fields in physics. The basic formula of the psychological field is that
B＝f(P·E) (1)
In the formula (1), f is a function of personal characteristics and environment; b represents personal behavior; p represents a personal attribute; e represents the external environment. Psychological field basic formulas exhibit personal behavior that is affected by both personal and environmental attributes. In a psychological field, a person is a generating source of the field, but an object in the field is not affected by the generating source, and the person reacts to the environment in the psychological field under the constraint of own characteristics. That is, the psychological field does not change the motion state of the object in the field, but judges the action intensity of the object in the field on the person through the field form, and then changes the behavior state of the object.
Example 1:
referring to fig. 1, the power consumption behavior prediction method for the power consumer provided in this embodiment includes the following steps:
101. acquiring the required historical electricity consumption data of a user and the historical air temperature data of the place where the user is located; the historical electricity consumption data of the user can be obtained from a power grid system where the user is located, and the historical air temperature data can be obtained from a weather bureau system where the user is located.
102. Constructing an air temperature psychological field model according to the acquired historical electricity consumption data and historical air temperature data of the user;
103. the obtained historical power consumption data and the historical air temperature data of the user are used as input vectors of an SVM support vector machine, so that a predictive power consumption initial value of the current user is calculated based on an SVM regression estimation method
The SVM support vector machine can be used for solving the nonlinear regression estimation problem including load prediction, has the characteristics of strong prediction capability, high convergence speed, global optimization and the like, and is widely applied to load prediction of an electric power system. The basic idea of nonlinear SVR is to map an input vector into a high-dimensional feature space through a nonlinear mapping determined in advance, and then perform linear regression in the high-dimensional space, thereby obtaining the effect of nonlinear regression in the original space.
The implementation of the regression estimation method based on SVM support vector machine adopts the structure shown in FIG. 3, wherein alpha is as follows i -α i * Is the network weight, x 1 ,x 2 ,…x m In this step, the input vector quantity is the historical electricity consumption data and the historical air temperature data of the user, so that the initial value of the predicted electricity consumption can be calculated based on the SVM regression estimation method by combining the processes
That is, in this step, the initial value of the power consumption behavior prediction of the power consumer is calculated by using the existing power load prediction method such as the SVM regression estimation method using the air temperature as the input variable, and the advantage of the real-time performance of the load prediction is maintained.
104. According to the predicted initial value of electricity consumption and by combining the air temperature psychological field model and the multi-scene set method, the current predicted air temperature psychological field intensity is calculated.
105. Carrying out standardization processing on the air temperature psychological field intensity in the prediction period to obtain a correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory;
106. calculating final predicted value of user electricity consumption behavior by combining initial value of user electricity consumption and correction coefficient
Therefore, the electricity consumption behavior prediction method for the electric power user provided by the embodiment obtains the field intensity mathematical expression of the air temperature psychological field by considering the formation of the air temperature psychological field, and is independent of the existing electricity consumption psychological model. Meanwhile, the air temperature is used as an input variable, and the existing power load prediction methods such as an SVM regression estimation method are utilized to calculate the power consumption behavior prediction initial value of the power consumer, so that the real-time performance of load prediction is maintained; when the air temperature psychological field intensity under the actual prediction scene is calculated, an air temperature multi-scene set method is adopted, so that the error of the obtained air temperature psychological field intensity can be reduced, and the real-time load prediction initial value is corrected by taking the air temperature psychological field intensity after optimization treatment as a correction coefficient, so that the predicted electricity consumption behavior of a user is closer to the psychological expectation of the user, and the method has the advantages of good prediction instantaneity, easiness in realization of a model, effective and accurate prediction result and the like, thereby effectively ensuring the normal operation of an electric power network and reducing the economic loss of an electric power company.
Specifically, the step 102 includes:
(1) Basic field intensity modeling of air temperature psychological field
The psychological pressure of the power consumer can be generated due to the influence of the surrounding environment in the process of developing the power consumption activities, and the psychological pressure is closely related to the current power consumption of the consumer and the relative change of the air temperature. Meanwhile, the electricity utilization activities of the power consumers have certain purposes, so that psychological drive is generated on the psychology of the consumers. The actual electricity usage behavior of the electricity consumer is shown when both psychological drive and psychological stress act together.
In the air temperature psychological field model of the electricity utilization behavior of the user, the air temperature psychological field is set to be a scalar field, and the change of the field intensity shows the perception of the electric power user on the relative change of the air temperature. The field source of the field intensity is dynamic, and the field intensity is only influenced by the power consumption of a user and the change state of the air temperature. The user can adjust the electricity consumption behavior of the user to reflect the acting force generated by the temperature change in the psychological field, and the acting force is closely related to the field intensity of the current temperature at the position in the psychological field and the current electricity consumption of the user. It follows that the basic field strength of the user air temperature psychological field in the relative direction of change of the user air temperature is expressed as follows:
in the formula (2): e is represented byThe basic field intensity value of the formed user air temperature psychological field; t is the current air temperature value in the psychological field; p is the electricity consumption of the power consumer; t (T) ε Is a correction value, the size of which is related to the psychological characteristics of the electricity used by the user.
(2) Equipotential line segmentation expression modeling of air temperature psychological field
The electricity consumption behavior of the electricity user can be described by constructing a section expression of equipotential lines of the air temperature psychological field when the electricity user develops the air temperature psychological field model. Obviously, if the air temperature is close to the comfortable temperature area of the user, the smaller the electricity consumption of the user is, the smaller the pressure felt by the user is, and the smaller the field intensity of the air temperature psychological field is; the opposite is true. From this, a basic form of the equipotential line distribution of the psychoair temperature field as shown in fig. 2 can be obtained.
In fig. 2, the horizontal axis X and the vertical axis Y are variables of the same dimension as the air temperature, and the distance between the origin of coordinates and any point on the equipotential line represents the air temperature. On the same equipotential line corresponding to a certain determined power, the air temperature psychological field intensity effect is the same for the user regardless of the air temperature change condition. The psychoair equation line corresponding to an example of fig. 2 can be described by the following equation:
in the formula (3), a < b < c, r in this example 1 ＜r 3 ＜r 2 . The electricity consumption psychological factors of the user based on the air temperature can be quantified by analyzing the determined air temperature psychological field equipotential line distribution condition, and the electricity consumption psychological factors are integrated into the electricity consumption behavior prediction technology of the user.
Step 104 includes: calculating initial value of prediction power consumption by SVM regression estimation methodThen, the predicted electricity consumption initial value is determined by the model of the equipotential lines of the air temperature psychological field shown in FIG. 1>The temperature psychological field intensity range is located. Assume thatThe temperature interval corresponding to the temperature psychological field intensity range is [ T ] 1 ,T 2 ]And->Falls at radius r p0 Within the equipotential line range of the air temperature psychological field intensity, the predicted air temperature psychological field intensity can be calculated according to the formula (2) and the following formula:
T 1 ＝r p0 (4)
0≤T ε,i ≤r p0 (5)
in the formula (7), the amino acid sequence of the compound,is->The corresponding air temperature psychological field intensity under a certain air temperature scene in the air temperature psychological field intensity range; in the formula (12), i is the number of the air temperature scene sets taken, and +.>The predicted air temperature psychological field intensity is calculated by combining an air temperature psychological field model and a multi-scene set method.
Steps 105 and 106 then include: let t be the predicted period of time obtained by the above calculation n Temperature psychology at each momentField strength, i.e.It is normalized as follows:
in the formula (8), the amino acid sequence of the compound,the predicted air temperature psychological field intensity after the normalization treatment is regarded as a correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory. Therefore, the process of correcting and predicting the electricity consumption initial value by the air temperature psychological field theory is carried out according to the following formula
In the formula (14), the amino acid sequence of the compound,and the final predicted value of the electricity consumption behavior of the user based on the correction of the air temperature psychological field theory is obtained.
In summary, the power consumer electricity consumption behavior prediction method provided by the embodiment has the following technical advantages compared with the prior art:
1. the method is suitable for predicting the user load under the condition of air temperature fluctuation, and considers the psychological factor influence of the air temperature fluctuation on the actual electricity utilization behavior of the user.
2. The method provides an air temperature psychological field intensity model for electricity behavior prediction and provides an equipotential line segmentation model thereof so as to quantify key psychological influence factors in electricity activities such as air temperature, and is suitable for research modeling of influence of various air temperature factors on electricity behaviors in actual situations.
3. The method combines with the regression estimation prediction technology based on SVM on the basis of constructing a perfect user air temperature psychological field model, thereby forming a reasonable user electricity consumption behavior prediction means.
4. When the method calculates the field intensity of the air temperature psychological field under the actual predicted scene, the field intensity of the air temperature psychological field is predicted to be closer to a true value by adopting an air temperature multi-scene set method. By taking the standardized air temperature psychological field intensity as a correction coefficient, the real-time load prediction initial value is corrected, so that the predicted user electricity consumption behavior fully considers the psychological factors of the user, and the method has reliable theoretical applicability. The method has good prediction instantaneity, is easy to realize and suitable for popularization in practical application, and can effectively ensure normal operation of the power network and reduce economic loss of the power company.
Example 2:
referring to fig. 4, the power consumer electricity consumption behavior prediction system provided in this embodiment includes:
the data collector 401 is configured to collect and obtain the required historical electricity consumption data of the user and the historical air temperature data of the location of the user; in this embodiment, the data collector may use an existing data capturing tool, such as a silicon valley data tool, growth io, and then capture historical electricity consumption data and historical air temperature data of the location of the user from the power grid system and the weather bureau system where the user is located; after capturing the relevant data, the relevant data is transmitted to the first data processor 402;
a first data processor 402, configured to generate an air temperature psychological field model through operation processing according to the historical electricity consumption data and the historical air temperature data of the user transmitted by the data collector 401; and the method is used for taking the acquired historical electricity consumption data and the historical air temperature data of the user as input vectors of an SVM support vector machine so as to calculate and obtain a predicted initial value of electricity consumption of the current user based on an SVM regression estimation method
A second data processor 403 for calculating according to the predicted electricity consumption initial value and the air temperature psychological field model transmitted by the first data processor 402 and combining the multi-scene set operation processing methodCalculating the current predicted air temperature psychological field intensity; then, the air temperature psychological field intensity in the prediction period is subjected to standardized processing, and a correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory is obtained; finally, the final predicted value of the electricity consumption behavior of the user is calculated by combining the initial value of the electricity consumption of the user and the correction coefficient
Therefore, the power consumption behavior prediction system of the electric power user provided by the implementation firstly acquires the historical power consumption and the historical air temperature data of the user through the data acquisition device, then transmits the acquired data to the first data processor, generates an air temperature psychological field model through operation processing, uses the acquired air temperature data as an input variable, calculates a power consumption behavior prediction initial value of the electric power user by using the existing power load prediction methods such as an SVM regression estimation method, and keeps the real-time performance of load prediction; the result of the operation processing of the first data processor is transmitted to the second data processor, and the second data processor adopts an air temperature multi-scene set operation processing method when calculating the air temperature psychological field intensity under the actual prediction scene, so that the error of the obtained air temperature psychological field intensity can be reduced, and the real-time load prediction initial value is corrected by taking the air temperature psychological field intensity after the optimization processing as a correction coefficient, so that the electricity utilization result of the user predicted by the second data processor is closer to the psychological expectation of the user, and the method has the advantages of good prediction instantaneity, easiness in realization of a model, effective and accurate prediction result and the like, thereby effectively ensuring the normal operation of an electric power network and reducing the economic loss of an electric company.
The specific working principle of the data collector 401 in this embodiment corresponds to step 101 in embodiment 1, the operation processing procedure of the first data processor 402 corresponds to steps 102 and 103 in embodiment 1, and the operation processing procedure of the second data processor 403 corresponds to steps 104 to 106 in embodiment 1, so that the working principle and operation processing procedure of the data collector 401, the first data processor 402, and the second data processor 403 will not be described in detail in this embodiment.
As a preference of the electricity consumption behavior prediction system of the present embodiment, the system further includes a client for receiving the final predicted value calculated by the second data receiving processor 403The client can be a mobile phone, a computer or a tablet personal computer, so that a worker can remotely and real-timely know the final result of the operation.
The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement the same, and are not intended to limit the scope of the present invention. All equivalent changes or modifications made in accordance with the essence of the present invention are intended to be included within the scope of the present invention.
Claims (2)
1. The power consumption behavior prediction method for the power consumer is characterized by comprising the following steps of:
acquiring the required historical electricity consumption data of a user and the historical air temperature data of the place where the user is located;
constructing an air temperature psychological field model according to the acquired historical electricity consumption data and historical air temperature data of the user;
the obtained historical power consumption data and the historical air temperature data of the user are used as input vectors of an SVM support vector machine, so that a predictive power consumption initial value of the current user is calculated based on an SVM regression estimation method
According to the predicted initial value of electricity consumption and by combining the air temperature psychological field model and the multi-scene set method, the current predicted air temperature psychological field intensity is calculated;
carrying out standardization processing on the air temperature psychological field intensity in the prediction period to obtain a correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory;
calculating the user power consumption by combining the initial value of the user power consumption and the correction coefficientFinal predicted value of electrical behavior
The air temperature psychological field model comprises:
basic field intensity model of air temperature psychological field:
in the formula (2): e is the basic field intensity value of the user air temperature psychological field; t is the current air temperature value in the psychological field; p is the electricity consumption of the power consumer; t (T) ε Is a correction value;
model of equipotential line segmentation expression of air temperature psychological field: if the air temperature is closer to the comfortable temperature area of the user, the lower the electricity consumption of the user is, the lower the pressure felt by the user is, and the lower the field intensity of the air temperature psychological field is; the opposite is the case;
the calculating the current predicted air temperature psychological field intensity according to the predicted electricity consumption initial value and by combining the air temperature psychological field model and the multi-scene set method comprises the following steps:
determining a predicted initial value of electricity consumption according to an equipotential line segmentation expression model of an air temperature psychological fieldThe field intensity range of the air temperature psychological field is assumed to be +.>The temperature interval corresponding to the temperature psychological field intensity range is [ T ] 1 ,T 2 ]And->Falls at radius r p0 Within the equipotential line range of the air temperature psychological field intensity, the predicted air temperature psychological field intensity is calculated by the following formula (2):
T 1 ＝r p0 (4)
0≤T ε,i ≤r p0 (5)
in the formula (6), the amino acid sequence of the compound,is->The corresponding air temperature psychological field intensity under a certain air temperature scene in the air temperature psychological field intensity range; in the formula (6), i is the number of the air temperature scene sets taken, and +.>The predicted air temperature psychological field intensity is calculated by combining an air temperature psychological field model and a multi-scene set method; t (T) ε,i The air temperature correction value corresponding to the air temperature scene set i;
carrying out standardization processing on the air temperature psychological field intensity in the prediction period, and obtaining a correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory comprises the following steps:
let t be calculated from equation (7) for the predicted period n The psychological field strength of air temperature at each moment, i.eIt is normalized as follows:
in the formula (8), the amino acid sequence of the compound,that is, the predicted psychological field intensity of air temperature after standardized treatment is regarded as the basis of air temperatureCorrecting and predicting a correction coefficient of an electricity initial value by using a psychological field theory;
the final predicted value of the electricity consumption behavior of the user is calculated by combining the initial value of the electricity consumption of the user and the correction coefficientThe method comprises the following steps:
in the formula (14), the amino acid sequence of the compound,and the final predicted value of the electricity consumption behavior of the user based on the correction of the air temperature psychological field theory is obtained.
2. A power consumer electricity usage behavior prediction system, comprising:
the data acquisition device is used for acquiring the required historical electricity consumption data of the user and the historical air temperature data of the place where the user is located;
the first data processor is used for processing and generating an air temperature psychological field model according to the historical electricity consumption data and the historical air temperature data of the user transmitted by the data acquisition unit; and the method is used for taking the acquired historical electricity consumption data and the historical air temperature data of the user as input vectors of an SVM support vector machine so as to calculate and obtain a predicted initial value of electricity consumption of the current user based on an SVM regression estimation method
The second data processor is used for calculating the current predicted air temperature psychological field intensity according to the predicted electricity initial value and the air temperature psychological field model transmitted by the first data processor and by combining a multi-scene set operation processing method; then, the air temperature psychological field intensity in the prediction period is subjected to standardized processing, and a correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory is obtained; finally, the initial value of the electricity consumption of the user and the correction coefficient are combined to calculate the electricity consumptionFinal predicted value of household electricity behavior
The air temperature psychological field model comprises:
basic field intensity model of air temperature psychological field:
in the formula (2): e is the basic field intensity value of the user air temperature psychological field; t is the current air temperature value in the psychological field; p is the electricity consumption of the power consumer; t (T) ε Is a correction value;
model of equipotential line segmentation expression of air temperature psychological field: if the air temperature is closer to the comfortable temperature area of the user, the lower the electricity consumption of the user is, the lower the pressure felt by the user is, and the lower the field intensity of the air temperature psychological field is; the opposite is the case;
the operation processing of the second data processor to calculate the current predicted air temperature psychological field intensity comprises the following steps:
determining a predicted initial value of electricity consumption according to an equipotential line segmentation expression model of an air temperature psychological fieldThe field intensity range of the air temperature psychological field is assumed to be +.>The temperature interval corresponding to the temperature psychological field intensity range is [ T ] 1 ,T 2 ]And->Falls at radius r p0 Within the equipotential line range of the air temperature psychological field intensity, the predicted air temperature psychological field intensity is calculated by the following formula (2):
T 1 ＝r p0 (4)
0≤T ε,i ≤r p0 (5)
in the formula (6), the amino acid sequence of the compound,is->The corresponding air temperature psychological field intensity under a certain air temperature scene in the air temperature psychological field intensity range; in the formula (6), i is the number of the air temperature scene sets taken, and +.>The predicted air temperature psychological field intensity is calculated by combining an air temperature psychological field model and a multi-scene set method; t (T) ε,i The air temperature correction value corresponding to the air temperature scene set i;
the second data processor performs standardization processing on the air temperature psychological field intensity in the prediction period, and the operation processing process for obtaining the correction coefficient for correcting the predicted electricity consumption initial value based on the air temperature psychological field theory is as follows:
let t be calculated from equation (7) for the predicted period n The psychological field strength of air temperature at each moment, i.eIt is normalized as follows:
in the formula (8), the amino acid sequence of the compound,namely, the predicted air temperature psychological field intensity after standardized treatment is regarded asCorrecting and predicting a correction coefficient of an initial value of electricity consumption based on an air temperature psychological field theory;
the second data processor combines the initial value of the user electricity consumption and the correction coefficient to calculate the final predicted value of the user electricity consumption behaviorThe operation processing mode of (a) is as follows:
in the formula (9), the amino acid sequence of the compound,and the final predicted value of the electricity consumption behavior of the user based on the correction of the air temperature psychological field theory is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911348876.4A CN111210055B (en) | 2019-12-24 | 2019-12-24 | Prediction method and prediction system for electricity consumption behavior of power consumer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911348876.4A CN111210055B (en) | 2019-12-24 | 2019-12-24 | Prediction method and prediction system for electricity consumption behavior of power consumer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111210055A CN111210055A (en) | 2020-05-29 |
| CN111210055B true CN111210055B (en) | 2023-09-29 |
Family
ID=70789310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911348876.4A Active CN111210055B (en) | 2019-12-24 | 2019-12-24 | Prediction method and prediction system for electricity consumption behavior of power consumer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111210055B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010182287A (en) * | 2008-07-17 | 2010-08-19 | Steven C Kays | Intelligent adaptive design |
| CN104008430A (en) * | 2014-05-29 | 2014-08-27 | 华北电力大学 | Method for establishing virtual reality excavation dynamic smart load prediction models |
| CN106529728A (en) * | 2016-11-16 | 2017-03-22 | 国网江苏省电力公司经济技术研究院 | Load zone prediction method with consideration of demand response measure |
| CN110222908A (en) * | 2019-06-19 | 2019-09-10 | 贵州电网有限责任公司 | A kind of short-term electricity demand forecasting method based on data-driven |
| CN110610294A (en) * | 2019-08-13 | 2019-12-24 | 浙江大学 | Electricity selling company electric quantity package design method considering user consumption psychology |
| CN111178613A (en) * | 2019-12-24 | 2020-05-19 | 贵州电网有限责任公司贵安供电局 | Comprehensive prediction method and system for user electricity utilization behavior |
-
2019
- 2019-12-24 CN CN201911348876.4A patent/CN111210055B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010182287A (en) * | 2008-07-17 | 2010-08-19 | Steven C Kays | Intelligent adaptive design |
| CN104008430A (en) * | 2014-05-29 | 2014-08-27 | 华北电力大学 | Method for establishing virtual reality excavation dynamic smart load prediction models |
| CN106529728A (en) * | 2016-11-16 | 2017-03-22 | 国网江苏省电力公司经济技术研究院 | Load zone prediction method with consideration of demand response measure |
| CN110222908A (en) * | 2019-06-19 | 2019-09-10 | 贵州电网有限责任公司 | A kind of short-term electricity demand forecasting method based on data-driven |
| CN110610294A (en) * | 2019-08-13 | 2019-12-24 | 浙江大学 | Electricity selling company electric quantity package design method considering user consumption psychology |
| CN111178613A (en) * | 2019-12-24 | 2020-05-19 | 贵州电网有限责任公司贵安供电局 | Comprehensive prediction method and system for user electricity utilization behavior |
Non-Patent Citations (4)
| Title |
|---|
| 基于动态电价的需求响应下短期负荷预测研究;刘文等;《电力***及其自动化学报》(第09期);118-124 * |
| 基于多元大数据平台的用电行为分析构架研究;郝然等;《电力自动化设备》(第08期);26-33 * |
| 基于电量分析的配网用户用电需求量预测研究;麦琪;;新型工业化(06);54-63 * |
| 智能电网下计及用户侧互动的发电日前调度计划模型;刘小聪等;《中国电机工程学报》(第01期);57-65 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111210055A (en) | 2020-05-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A satellite image data based ultra-short-term solar PV power forecasting method considering cloud information from neighboring plant | |
| Wang et al. | Research and application of a hybrid forecasting framework based on multi-objective optimization for electrical power system | |
| Su et al. | A new hybrid model optimized by an intelligent optimization algorithm for wind speed forecasting | |
| US20160055507A1 (en) | Forecasting market prices for management of grid-scale energy storage systems | |
| CN110675275B (en) | Electric load regulation and control method and system for demand side response application of virtual power plant | |
| Wang et al. | Optimal capacity design for hybrid energy storage system supporting dispatch of large-scale photovoltaic power plant | |
| CN110119493B (en) | Electric power system event sensing method based on compressed PMU data and local outlier factor | |
| CN115409649A (en) | Wind power plant energy management system and method thereof | |
| Hu et al. | Ensemble learning based convex approximation of three-phase power flow | |
| CN111210051B (en) | User electricity consumption behavior prediction method and system | |
| CN116937569A (en) | Intelligent energy storage method and device for photovoltaic power generation and electronic equipment | |
| CN111178613B (en) | Comprehensive prediction method and system for user electricity consumption behavior | |
| Jung et al. | Data-driven evaluation of building demand response capacity | |
| CN111210055B (en) | Prediction method and prediction system for electricity consumption behavior of power consumer | |
| CN117081088B (en) | Power grid load dispatching control method and device, computer equipment and storage medium | |
| WO2022040255A1 (en) | Methods, systems, and computer readable media for model-free privacy preserving thermal load management | |
| CN103428320B (en) | Smart cell phone power dissipation estimation method based on model fitting | |
| CN117117983A (en) | Thermal power plant peak regulation management method and system combining power distribution network requirements | |
| Wang et al. | Control strategies of large-scale residential air conditioning loads participating in demand response programs | |
| CN114006392B (en) | Energy storage node capacity demand estimation system of distributed power system | |
| Lei et al. | Performance of existing methods in baselining demand response from commercial building HVAC fans | |
| KR20220117432A (en) | Power system, method and apparatus for clustering of power system | |
| Yao et al. | Storage size determination for grid-connected wind power system based on power spectral density analysis | |
| CN113497444A (en) | Distributed wind power peak regulation system and method considering source load change rate difference characteristics | |
| Zhang et al. | Variation Characteristics Analysis and Short-Term Forecasting of Load Based on CEEMDAN |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210317 Address after: No.17 Binhe Road, Nanming District, Guiyang City, Guizhou Province Applicant after: Guizhou Power Grid Co.,Ltd. Address before: 550025 in the south of high end equipment manufacturing industrial park, Gui'an New District, Guiyang City, Guizhou Province Applicant before: GUIAN POWER SUPPLY BUREAU, GUIZHOU POWER GRID Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |