CN102930354A - Method and device for predicating electricity consumption of residential area - Google Patents
Method and device for predicating electricity consumption of residential area Download PDFInfo
- Publication number
- CN102930354A CN102930354A CN2012104394944A CN201210439494A CN102930354A CN 102930354 A CN102930354 A CN 102930354A CN 2012104394944 A CN2012104394944 A CN 2012104394944A CN 201210439494 A CN201210439494 A CN 201210439494A CN 102930354 A CN102930354 A CN 102930354A
- Authority
- CN
- China
- Prior art keywords
- power consumption
- historical
- data
- following
- residential quarter
- 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.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for predicating electricity consumption of a residential area. The method includes acquiring historical electricity consumption data of the residential area; acquiring historical temperature data real-timely corresponding to the electricity consumption; establishing an electricity consumption predicating model according to the historical temperature data and the historical electricity consumption data; acquiring temperature data in a certain time in the future; and predicating future electricity consumption of the residential area according to the temperature data in a certain time in the future and the predicating model. The historical temperature data and the historical electricity consumption data are used for establishing the electricity consumption predicating model, so that the electricity consumption is predicated according to temperatures.
Description
Technical field
The present invention relates to use electrical domain, be specifically related to a kind of residential quarter power consumption prediction method and device.
Background technology
Along with the development of society and improving constantly of living standards of the people, increasing to the demand of electric energy.Because the simultaneity of electrical energy production and consumption, the production of the electric energy of need to making rational planning for just can make it satisfy consumption.In the prior art mainly by the make rational planning for production of electric energy of the mode that following electricity consumption is predicted.
At present, power consumption prediction mainly is by consideration electrovalence policy and electricity consumption period the impact of power consumption to be carried out.But in real life, the electricity consumption behavior especially electricity consumption of residential quarter can be subject to the impact of the factors such as temperature, season to a great extent.Such as, when temperature drift or when on the low side, the residential quarter can increase power consumption because using air-conditioning.The power consumption in summer also generally can be higher than the power consumption in spring.
Therefore, be badly in need of at present a kind of power consumption prediction method of considering the factor affecting such as temperature.
Summary of the invention
In view of this, the object of the present invention is to provide a kind of power consumption prediction method based on temperature effect.
The embodiment of the invention provides a kind of residential quarter power consumption prediction method, and the method specifically comprises:
Obtain the historical power consumption data of described residential quarter;
Obtain the in real time historical temperature data of correspondence of described power consumption;
According to described historical temperature data and described historical power consumption data, make up the electricity demand forecasting model;
Obtain the temperature data in the following certain hour;
Predict the following power consumption in described residential quarter according to the temperature data in the described following certain hour and described forecast model.
Preferably, described method also comprises:
Store the following power consumption in described residential quarter;
Obtain the actual power consumption of described residential quarter in described following certain hour;
According to described actual power consumption described following power consumption is carried out error analysis, obtain the error analysis result;
Continue to predict described residential quarter power consumption according to described error analysis result.
Preferably, described method also comprises:
Obtain described power consumption in real time corresponding historical season information;
Described according to described historical temperature data and described historical power consumption data, make up the electricity demand forecasting model and comprise:
According to described historical temperature data, described history information in season and described historical power consumption data construct electricity demand forecasting model;
Obtain the information in season in the following certain hour;
Describedly predict that according to the temperature data in the described following certain hour and described forecast model the following power consumption in described residential quarter comprises:
According to the temperature data in the described following certain hour, in the following certain hour season information and described forecast model predict the following power consumption in described residential quarter.
Preferably, the following power consumption in described residential quarter comprises: the following peak value power consumption in the following daily power consumption in described residential quarter and/or described residential quarter.
Preferably, described method also comprises:
Obtain historical electricity price data and the historical electricity consumption period in real time corresponding with described historical power consumption data;
Described according to described historical temperature data and described historical power consumption data, make up the electricity demand forecasting model and comprise:
According to described historical temperature data, described historical electricity price data, described historical electricity consumption period and described historical power consumption data, make up the electricity demand forecasting model;
Obtain the electricity price data in the following certain hour and determine the following electricity consumption period;
Describedly predict that according to the temperature data in the described following certain hour and described forecast model the following power consumption in described residential quarter comprises:
Predict the following power consumption in described residential quarter according to the temperature data in the described following certain hour, electricity price data, following electricity consumption period and described forecast model in the following certain hour
Preferably, described according to described historical temperature data and described historical power consumption data, make up the electricity demand forecasting model and comprise:
Take described historical temperature data as input parameter, take described historical power consumption data as output parameter, make up neural network model.
The embodiment of the invention also discloses a kind of residential quarter power consumption prediction device, described device comprises:
Historical power consumption unit is used for obtaining the historical power consumption data of described residential quarter;
Historical temperature unit is used for obtaining the in real time historical temperature data of correspondence of described power consumption;
The model construction unit links to each other with historical temperature unit with described historical power consumption unit, is used for according to described historical temperature data and described historical power consumption data, makes up the electricity demand forecasting model;
Temperature unit is used for obtaining the temperature data in the following certain hour;
Predicting unit links to each other with described temperature unit with described model construction unit, is used for predicting the following power consumption in described residential quarter according to the temperature data in the described following certain hour and described forecast model.
Preferably, described device also comprises:
Storage unit links to each other with described predicting unit, is used for storing the following power consumption in described residential quarter;
Actual power consumption unit is used for obtaining the actual power consumption of described residential quarter in described following certain hour;
The error analysis unit links to each other with described actual power consumption unit with described storage unit, is used for according to described actual power consumption described following power consumption being carried out error analysis, obtains the error analysis result;
Described predicting unit links to each other with described error analysis unit, and concrete being used for continues to predict the following power consumption in described residential quarter according to described error analysis result.
Preferably, described device also comprises:
Historical season message unit, be used for obtaining described power consumption in real time corresponding historical season information;
Described model construction unit links to each other with described history message unit in season, concrete being used for according to described historical temperature data, described history information in season and described historical power consumption data construct electricity demand forecasting model;
Season, message unit was used for obtaining the interior information in season of following certain hour;
Described predicting unit, with described season message unit link to each other, concrete be used for according to the temperature data in the described following certain hour, in the following certain hour season information and described forecast model predict the following power consumption in described residential quarter.
Preferably, the following power consumption in described residential quarter comprises: the following peak value power consumption in the following daily power consumption in described residential quarter and/or described residential quarter.
Preferably, described device also comprises:
Historical electricity price data cell is used for obtaining the historical electricity price data in real time corresponding with described historical power consumption data;
Segment unit during historical electricity consumption is used for obtaining the historical electricity price data in real time corresponding with described historical power consumption data;
Described model construction unit, segment unit links to each other during with historical electricity consumption with described historical electricity price data cell, concrete being used for according to described historical temperature data, described historical electricity price data, described historical electricity consumption period and described historical power consumption data, make up the electricity demand forecasting model;
The electricity price data cell is used for obtaining the electricity price data in the following certain hour;
Segment unit during electricity consumption is used for determining the following electricity consumption period;
Described predicting unit, segment unit links to each other during with described electricity consumption with described electricity price data cell, and concrete being used for predicted the following power consumption in described residential quarter according to the temperature data in the described following certain hour, electricity price data, following electricity consumption period and described forecast model in the following certain hour.
Preferably, described model construction unit, take described historical power consumption data as output parameter, makes up neural network model at concrete being used for take described historical temperature data as input parameter.
Compare beneficial effect of the present invention with prior art:
The present invention is by utilizing cell history power consumption data and corresponding historical temperature data to make up the electricity demand forecasting model, and the temperature data that obtains following certain hour is predicted, in this process, considered the impact of temperature on the residential quarter electricity consumption, realized based on temperature prediction residential quarter power consumption.
Further, in the preferred embodiment of the present invention, considered season information and electricity price, electricity consumption period on the impact of electricity consumption, relative prior art, to the consideration of electricity consumption influence factor more comprehensively, thereby the accuracy that improved electricity demand forecasting.
Description of drawings
Fig. 1 is the embodiment of the invention 1 method flow diagram;
Fig. 2 is artificial neuron meta-model synoptic diagram in the embodiment of the invention;
Fig. 3 is single hidden layer BP network model structural representation in the embodiment of the invention;
Fig. 4 is the embodiment of the invention 2 method flow diagrams;
Fig. 5 is the embodiment of the invention 3 method flow diagrams;
Fig. 6 is the embodiment of the invention 4 method flow diagrams;
Fig. 7 is the following 7 days daily power consumption chart synoptic diagram of embodiment of the invention small area;
Fig. 8 is the following 7 days peak value power consumption column diagrams in embodiment of the invention residential quarter;
Fig. 9 is the embodiment of the invention 5 structure drawing of device.
Embodiment
In order to make those skilled in the art person understand better the scheme of the embodiment of the invention, below in conjunction with drawings and embodiments the embodiment of the invention is described in further detail.
The embodiment of the invention 1 provides a kind of residential quarter power consumption prediction method, and referring to Fig. 1, the method specifically comprises:
S11, obtain the historical power consumption data of described residential quarter.
Concrete, can from the ammeter of residential quarter, directly reading the historical power consumption data of this residential quarter, and record time corresponding to these power consumption data by peripheral interface is set, the historical power consumption data that then will obtain and corresponding time are stored in the database.
S12, obtain in real time corresponding historical temperature data of described power consumption.
With obtaining historical power consumption data class seemingly, in the present invention, can by peripheral interface being set as with weather bureau interface being set, obtain the historical temperature data corresponding with historical power consumption data.Concrete, can obtain corresponding historical temperature data according to the power consumption data time that records before.
S13, according to described historical temperature data and described historical power consumption data, make up the electricity demand forecasting model.
The multiple model of predicting according to historical data is arranged, such as neural network model in the prior art.This partial content will be described in more detail below.
Temperature data in S14, the following certain hour of acquisition.
S12 is similar with step, can by with the interface of weather bureau, obtain following certain hour such as the temperature data in 7 days.
S15, predict the following power consumption in described residential quarter according to the temperature data in the described following certain hour and described forecast model.
In above-mentioned steps S13, mentioned neural network model, take artificial nerve network model and BP error back propagation neural network model as example, the structure of forecast model has been elaborated among the present invention.
Artificial neural network (Artificial Neural Networks, ANN) model is that a kind of application class is similar to the mathematical model that structure that the cerebral nerve cynapse connects is carried out information processing, is the networking that is formed by the large-scale parallel coupling configuration by some simple elements.Neuron is the basic processing unit of neural network, and it generally is the nonlinear device of the single output of many inputs, and typical artificial neuron meta-model as shown in Figure 2.
Neuronic input/output relation can be described as:
X wherein
j, j=1,2 ..., n is neuronic input signal, θ
iBe threshold value, w
JiThe connection weights of expression from neuron j to neuron i, f are activation function (claiming again transport function), and it must continuously differentiable, and neuron activation functions commonly used in the load prediction is the S type function.
Artificial nerve network model has very strong self study and complicated nonlinear function capability of fitting, is well suited for the load forecast problem, is one of practical Forecasting Methodology that gets the nod in the world.Its outstanding advantages is that a large amount of unstructuredness, non-precision rule are had adaptation function, and characteristics, particularly its self study and adaptation function with imformation memory, autonomous learning, knowledge reasoning and optimization calculating are that traditional algorithm is too far behind to catch up.
When making up artificial nerve network model, need to determine input and output parameter.Among the present invention, need to take historical temperature data as input parameter, make up artificial nerve network model take historical power consumption data as output parameter.When follow-up the prediction, need the temperature data of the following certain hour of input, the parameter of artificial nerve network model output this moment is the power consumption data of following certain hour.
BP (BackPropagation) neural network also claims the error back propagation neural network, the feedforward network that it is comprised of the nonlinear transformation unit.The BP neural network is made of input layer, output layer and hidden layer (hidden layer can be one or more layers), with not connecting between the node layer, the output of every node layer only affects the input of next node layer, referring to accompanying drawing 3, is single hidden layer BP network model structural representation.
The basic thought of BP algorithm is: the study of whole network is comprised of the forward-propagating of input signal and two processes of reverse propagation of error.The forward-propagating process refers to that input signal inputted by input layer, after weights, threshold value and the neuronic transport function effect of network, exports from output layer.If the error between output valve and the expectation value is greater than ormal weight, then revise, change the error anti-spread stage over to, be that error is successively returned to input layer by hidden layer, and error is pressed " Gradient Descent " principle " share " to each layer neuron, thereby obtain the neuronic error signal of each layer, as the foundation of revising weights.More than two processes are repeated multiple times carrying out.The process that weights are constantly revised, the namely training process of network.The output error that this circulation is performed until network is reduced to till the frequency of training of permissible value or arrival setting.
Among the present invention, the process that makes up the BP neural network model is similar with the structure artificial nerve network model, introduces no longer in detail herein.
For further improving the accuracy of prediction, in the embodiment of the invention 2, can carry out error analysis to the result who dopes and utilize error analysis modified result forecast model.Detailed process is as shown in Figure 4:
The following power consumption that prediction obtains in S21, storage above-described embodiment 1.
S22, obtain the actual power consumption of described residential quarter in described following certain hour.
S23, according to described actual power consumption the following power consumption that prediction obtains is carried out error analysis, and the generated error analysis result.
S24, continue to predict the following power consumption of described residential quarter according to above-mentioned error analysis result.Concrete, need to be according to the following power consumption in the described residential quarter of temperature data, forecast model and described error analysis prediction of result of the certain hour of follow-up acquisition.
Mention in the background technology, in different seasons, the power consumption of residential quarter also can be different.In embodiments of the invention 3, also considered the impact of seasonal factor.Referring to Fig. 5, its concrete forecasting process is as follows:
S31, obtain the historical power consumption data of described residential quarter.
S32, obtain in real time corresponding historical temperature data of described power consumption.
S33, obtain described power consumption in real time corresponding historical season information.
S34, according to described historical temperature data, described historical season information and described historical power consumption data construct electricity demand forecasting model.
Temperature data in S35, the following certain hour of acquisition.
Information in season in S36, the following certain hour of acquisition.
S37, according to the temperature data in the described following certain hour, in the following certain hour season information and described forecast model predict the following power consumption in described residential quarter.
Need to prove, in this embodiment, the preferred above-mentioned neural network model of forecast model.This moment, step S34 was specially take historical temperature data, history information in season as input parameter, made up neural network model take historical power consumption data as output parameter.Among the corresponding step S37, need to do input parameter with the information in season in the temperature data in the following certain hour, the following certain hour, its output parameter is the following power consumption of residential quarter.
The prediction of power consumption is multiplex in the production of the follow-up electric energy of making rational planning for.For guaranteeing the consumption of electric energy, the production of electric energy not only needs to guarantee the residential quarter electricity consumption of every day, also needs to guarantee the electricity consumption of residential quarter when the electricity consumption top.Therefore, in a preferred embodiment of the invention, need to dope the daily power consumption of described residential quarter and the peak value power consumption of residential quarter.Wherein also need to record its corresponding time for the peak value power consumption.
In the real life, residential quarter electricity consumption behavior also is subject to the impact of electricity price and electricity consumption period.Such as 8 o'clock to 10 o'clock evening generally many than power consumption after morning, when electricity price was high, power consumption also can obviously reduce.For further improving the accuracy of electricity demand forecasting, in the embodiment of the invention 4, can predict the residential quarter power consumption in conjunction with electricity price data and electricity consumption period.Referring to Fig. 6, this embodiment specifically comprises:
S41, obtain the historical power consumption data of described residential quarter.
S42, historical temperature data, historical electricity price data and the historical electricity consumption period of obtaining the real-time correspondence of described power consumption.
S43, according to described historical temperature data, described historical electricity price data, described historical electricity consumption period and described historical power consumption data, make up the electricity demand forecasting model.
S44, temperature data, the electricity price data in the following certain hour obtained in the following certain hour are also determined the following electricity consumption period.
S45, predict the following power consumption in described residential quarter according to the temperature data in the described following certain hour, electricity price data, following electricity consumption period and described forecast model in the following certain hour.
When this electricity demand forecasting model is neural network model, can historical temperature data, historical electricity price data, historical electricity consumption period are input parameter, make up neural network model take historical power consumption data as output parameter.
Need to prove that in the preferred embodiment of the present invention, above-described embodiment 4 also can in conjunction with the impact of information in season, be predicted the following power consumption in residential quarter.
Check for the convenience of the user contrast, after predicting the following power consumption in residential quarter, can call drawing software and draw, the following power consumption of residential quarter is graphically showed.Concrete, available chart represents peak value power consumption and the peak value power consumption moment in the following certain hour in residential quarter, represents the daily power consumption of residential quarter in following certain hour with column diagram, wherein, the column diagram height represents different days daily power consumption.As shown in Figure 7, be peak value power consumption and peak value power consumption time of every day of following 7 days of certain residential quarter of presenting in diagrammatic form.Fig. 8 is the daily power consumption of certain residential quarter following 7 day every day of representing with column diagram.
Corresponding said method embodiment, the embodiment of the invention 5 also provides a kind of residential quarter power consumption prediction device, and referring to Fig. 9, this device specifically comprises:
Historical power consumption unit 11 is used for obtaining the historical power consumption data of described residential quarter.
Concrete, historical power consumption unit 11 can pass through peripheral interface, directly read the historical power consumption data of this residential quarter from the ammeter of residential quarter, and record time corresponding to these power consumption data, the historical power consumption data that then will obtain and corresponding time are stored in the database.
Historical temperature unit 12 is used for obtaining the in real time historical temperature data of correspondence of described power consumption.
Similar with historical power consumption unit 11, in the present invention, historical temperature unit 12 can by peripheral interface being set as with weather bureau interface being set, obtain the historical temperature data corresponding with historical power consumption data.Concrete, can obtain corresponding historical temperature data according to the power consumption data time that records before.
The multiple model of predicting according to historical data is arranged, such as neural network model in the prior art.This partial content will be described in more detail below.
Temperature unit 14 is used for obtaining the temperature data in the following certain hour.
Similar with historical temperature unit 12, temperature unit 14 can by with the interface of weather bureau, obtain following certain hour such as the temperature data in following 7 days.
Predicting unit 15 links to each other with described temperature unit with described model construction unit, is used for predicting the following power consumption in described residential quarter according to the temperature data in the described following certain hour and described forecast model.
In the specific embodiment of the invention, model construction unit 13 can according to historical temperature data and historical power consumption data, make up neural network model such as artificial nerve network model, BP neural network model.The introduction of relevant neural network model can be referring to the description of embodiment of the method part.
In the time will making up neural network model, model construction unit 13, take historical power consumption data as output parameter, makes up neural network model at concrete being used for take historical temperature data as input parameter.
For further improving the accuracy of prediction, in embodiments of the present invention, can also the result of prediction be carried out error analysis and utilize error analysis modified result forecast model.To this, relative above-described embodiment, described device also comprises:
Storage unit links to each other with described predicting unit, is used for storing the following power consumption in described residential quarter.
Actual power consumption unit is used for obtaining the actual power consumption of described residential quarter in described following certain hour.
The error analysis unit links to each other with described actual power consumption unit with described storage unit, is used for according to described actual power consumption described following power consumption being carried out error analysis, obtains the error analysis result.
Described predicting unit links to each other with described error analysis unit, and concrete being used for continues to predict the following power consumption in described residential quarter according to described error analysis result.Concrete, predicting unit need to be according to the following power consumption in the described residential quarter of temperature data, forecast model and described error analysis prediction of result of the certain hour of follow-up acquisition.
As mentioning in the background technology, in different seasons, the power consumption of residential quarter also can be different.In another embodiment of the present invention, also considered the impact of seasonal factor.Corresponding, said apparatus also comprises:
Historical season message unit, be used for obtaining described power consumption in real time corresponding historical season information.
Described model construction unit links to each other with described history message unit in season, concrete being used for according to described historical temperature data, described history information in season and described historical power consumption data construct electricity demand forecasting model.
Season, message unit was used for obtaining the interior information in season of following certain hour.
Described predicting unit, with described season message unit link to each other, concrete be used for according to the temperature data in the described following certain hour, in the following certain hour season information and described forecast model predict the following power consumption in described residential quarter.
Need to prove, in this embodiment, the preferred above-mentioned neural network model of forecast model.This moment, the model construction unit specifically was used for making up neural network model take historical power consumption data as output parameter take historical temperature data, history information in season as input parameter.Corresponding predicting unit, concrete being used for done input parameter with the information in season in the temperature data in the following certain hour, the following certain hour, and its output parameter is the following power consumption of residential quarter.
The prediction of power consumption is multiplex in the production of the follow-up electric energy of making rational planning for.For guaranteeing the consumption of electric energy, the production of electric energy not only needs to guarantee the residential quarter electricity consumption of every day, also needs to guarantee the electricity consumption of residential quarter when the electricity consumption top.Therefore, in a preferred embodiment of the invention, predicting unit need to dope the daily power consumption of described residential quarter and the peak value power consumption of residential quarter.Wherein also need to record its corresponding time for the peak value power consumption.
In real life, residential quarter electricity consumption behavior also is subject to the impact of electricity price and electricity consumption period.Such as 8 o'clock to 10 o'clock evening generally many than power consumption after morning, when electricity price was high, power consumption also can obviously reduce.For further improving the accuracy of electricity demand forecasting, in embodiments of the present invention, can predict the residential quarter power consumption in conjunction with electricity price data and electricity consumption period.At this moment, relative said apparatus, described device also comprises:
Historical electricity price data cell is used for obtaining the historical electricity price data in real time corresponding with described historical power consumption data.
Segment unit during historical electricity consumption is used for obtaining the historical electricity price data in real time corresponding with described historical power consumption data.
Described model construction unit, segment unit links to each other during with historical electricity consumption with described historical electricity price data cell, concrete being used for according to described historical temperature data, described historical electricity price data, described historical electricity consumption period and described historical power consumption data, make up the electricity demand forecasting model.
The electricity price data cell is used for obtaining the electricity price data in the following certain hour.
Segment unit during electricity consumption is used for determining the following electricity consumption period.
Described predicting unit, segment unit links to each other during with described electricity consumption with described electricity price data cell, and concrete being used for predicted the following power consumption in described residential quarter according to the temperature data in the described following certain hour, electricity price data, following electricity consumption period and described forecast model in the following certain hour.
Wherein, the model construction unit, can also take historical temperature data, historical electricity price data, historical electricity consumption period as input parameter, make up neural network model take historical power consumption data as output parameter.
Need to prove that in the present invention, above-described embodiment also can in conjunction with the impact of information in season, be predicted the following power consumption in residential quarter.
Check for the convenience of the user contrast, described device also comprises graphical display unit, and concrete being used for calls drawing software and draw after predicting the following power consumption in residential quarter, and the following power consumption of residential quarter is graphically showed.
Concrete, graphical display unit available chart represents peak value power consumption and the peak value power consumption moment in the following certain hour in residential quarter, represent the daily power consumption of residential quarter in following certain hour with column diagram, wherein, the column diagram height represents different days daily power consumption.
Need to prove that said apparatus embodiment is corresponding with embodiment of the method, therefore the device part no longer described in detail that relevant portion gets final product referring to embodiment of the method.
More than the embodiment of the invention is described in detail, used embodiment herein the present invention set forth, the explanation of above embodiment just is used for helping to understand method and apparatus of the present invention; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (12)
1. residential quarter power consumption prediction method is characterized in that described method comprises:
Obtain the historical power consumption data of described residential quarter;
Obtain the in real time historical temperature data of correspondence of described power consumption;
According to described historical temperature data and described historical power consumption data, make up the electricity demand forecasting model;
Obtain the temperature data in the following certain hour;
Predict the following power consumption in described residential quarter according to the temperature data in the described following certain hour and described forecast model.
2. method according to claim 1 is characterized in that, described method also comprises:
Store the following power consumption in described residential quarter;
Obtain the actual power consumption of described residential quarter in described following certain hour;
According to described actual power consumption described following power consumption is carried out error analysis, obtain the error analysis result;
Continue to predict described residential quarter power consumption according to described error analysis result.
3. method according to claim 1 is characterized in that, described method also comprises:
Obtain described power consumption in real time corresponding historical season information;
Described according to described historical temperature data and described historical power consumption data, make up the electricity demand forecasting model and comprise:
According to described historical temperature data, described history information in season and described historical power consumption data construct electricity demand forecasting model;
Obtain the information in season in the following certain hour;
Describedly predict that according to the temperature data in the described following certain hour and described forecast model the following power consumption in described residential quarter comprises:
According to the temperature data in the described following certain hour, in the following certain hour season information and described forecast model predict the following power consumption in described residential quarter.
4. method according to claim 1 is characterized in that, the following power consumption in described residential quarter comprises: the following peak value power consumption in the following daily power consumption in described residential quarter and/or described residential quarter.
5. method according to claim 1 is characterized in that, described method also comprises:
Obtain historical electricity price data and the historical electricity consumption period in real time corresponding with described historical power consumption data;
Described according to described historical temperature data and described historical power consumption data, make up the electricity demand forecasting model and comprise:
According to described historical temperature data, described historical electricity price data, described historical electricity consumption period and described historical power consumption data, make up the electricity demand forecasting model;
Obtain the electricity price data in the following certain hour and determine the following electricity consumption period;
Describedly predict that according to the temperature data in the described following certain hour and described forecast model the following power consumption in described residential quarter comprises:
Predict the following power consumption in described residential quarter according to the temperature data in the described following certain hour, electricity price data, following electricity consumption period and described forecast model in the following certain hour.
6. according to claim 1 to 5 each described methods, it is characterized in that, described according to described historical temperature data and described historical power consumption data, make up the electricity demand forecasting model and comprise:
Take described historical temperature data as input parameter, take described historical power consumption data as output parameter, make up neural network model.
7. residential quarter power consumption prediction device is characterized in that described device comprises:
Historical power consumption unit is used for obtaining the historical power consumption data of described residential quarter;
Historical temperature unit is used for obtaining the in real time historical temperature data of correspondence of described power consumption;
The model construction unit links to each other with historical temperature unit with described historical power consumption unit, is used for according to described historical temperature data and described historical power consumption data, makes up the electricity demand forecasting model;
Temperature unit is used for obtaining the temperature data in the following certain hour;
Predicting unit links to each other with described temperature unit with described model construction unit, is used for predicting the following power consumption in described residential quarter according to the temperature data in the described following certain hour and described forecast model.
8. device according to claim 7 is characterized in that, described device also comprises:
Storage unit links to each other with described predicting unit, is used for storing the following power consumption in described residential quarter;
Actual power consumption unit is used for obtaining the actual power consumption of described residential quarter in described following certain hour;
The error analysis unit links to each other with described actual power consumption unit with described storage unit, is used for according to described actual power consumption described following power consumption being carried out error analysis, obtains the error analysis result;
Described predicting unit links to each other with described error analysis unit, and concrete being used for continues to predict the following power consumption in described residential quarter according to described error analysis result.
9. device according to claim 7 is characterized in that, described device also comprises:
Historical season message unit, be used for obtaining described power consumption in real time corresponding historical season information;
Described model construction unit links to each other with described history message unit in season, concrete being used for according to described historical temperature data, described history information in season and described historical power consumption data construct electricity demand forecasting model;
Season, message unit was used for obtaining the interior information in season of following certain hour;
Described predicting unit, with described season message unit link to each other, concrete be used for according to the temperature data in the described following certain hour, in the following certain hour season information and described forecast model predict the following power consumption in described residential quarter.
10. device according to claim 9 is characterized in that, the following power consumption in described residential quarter comprises: the following peak value power consumption in the following daily power consumption in described residential quarter and/or described residential quarter.
11. device according to claim 7 is characterized in that, described device also comprises:
Historical electricity price data cell is used for obtaining the historical electricity price data in real time corresponding with described historical power consumption data;
Segment unit during historical electricity consumption is used for obtaining the historical electricity price data in real time corresponding with described historical power consumption data;
Described model construction unit, segment unit links to each other during with historical electricity consumption with described historical electricity price data cell, concrete being used for according to described historical temperature data, described historical electricity price data, described historical electricity consumption period and described historical power consumption data, make up the electricity demand forecasting model;
The electricity price data cell is used for obtaining the electricity price data in the following certain hour;
Segment unit during electricity consumption is used for determining the following electricity consumption period;
Described predicting unit, segment unit links to each other during with described electricity consumption with described electricity price data cell, and concrete being used for predicted the following power consumption in described residential quarter according to the temperature data in the described following certain hour, electricity price data, following electricity consumption period and described forecast model in the following certain hour.
12. to 11 each described devices, it is characterized in that according to claim 7 described model construction unit, take described historical power consumption data as output parameter, makes up neural network model at concrete being used for take described historical temperature data as input parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210439494.4A CN102930354B (en) | 2012-11-06 | 2012-11-06 | A kind of community power consumption prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210439494.4A CN102930354B (en) | 2012-11-06 | 2012-11-06 | A kind of community power consumption prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102930354A true CN102930354A (en) | 2013-02-13 |
| CN102930354B CN102930354B (en) | 2016-08-10 |
Family
ID=47645148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210439494.4A Active CN102930354B (en) | 2012-11-06 | 2012-11-06 | A kind of community power consumption prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102930354B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473613A (en) * | 2013-09-09 | 2013-12-25 | 武汉理工大学 | Landscape structure-surface temperature-electricity consumption coupling model and application thereof |
| CN104317910A (en) * | 2014-10-27 | 2015-01-28 | 国家电网公司 | Data processing method and device |
| CN104346659A (en) * | 2014-11-26 | 2015-02-11 | 北京邮电大学 | Short-term power generation prediction method applied to high-concentration-ratio photovoltaic power generation system |
| CN104636816A (en) * | 2013-11-07 | 2015-05-20 | 财团法人资讯工业策进会 | Device and method for establishing power utilization model |
| CN104751233A (en) * | 2013-12-27 | 2015-07-01 | 台达电子工业股份有限公司 | Contract capacity optimization system and optimization method |
| CN105717355A (en) * | 2014-07-11 | 2016-06-29 | 英科德技术股份有限公司 | Apparatus, server, system and method for energy measuring |
| CN103854068B (en) * | 2013-12-06 | 2017-02-08 | 国家电网公司 | Method for forecasting residential quarter short-term loads |
| CN106934497A (en) * | 2017-03-08 | 2017-07-07 | 青岛卓迅电子科技有限公司 | Wisdom cell power consumption real-time predicting method and device based on deep learning |
| CN107330548A (en) * | 2017-06-16 | 2017-11-07 | 广东电网有限责任公司惠州供电局 | Residential electricity consumption Forecasting Methodology based on time series models |
| CN110210672A (en) * | 2019-06-04 | 2019-09-06 | 北京百度网讯科技有限公司 | The method and apparatus of electricity demand forecasting, electronic equipment, computer-readable medium |
| CN111523807A (en) * | 2020-04-24 | 2020-08-11 | 广西电网有限责任公司崇左供电局 | Electric energy substitution potential analysis method based on time sequence and neural network |
| CN112163709A (en) * | 2020-10-09 | 2021-01-01 | 珠海格力电器股份有限公司 | Power utilization prompting method and device, storage medium and electronic device |
| CN112907062A (en) * | 2021-02-08 | 2021-06-04 | 国网安徽省电力有限公司蚌埠供电公司 | Power grid electric quantity prediction method, device, medium and terminal integrating temperature characteristics |
| CN112907064A (en) * | 2021-02-08 | 2021-06-04 | 国网安徽省电力有限公司蚌埠供电公司 | Electric quantity prediction method and device based on self-adaptive window, storage medium and terminal |
| CN114456862A (en) * | 2020-11-04 | 2022-05-10 | 中国石油化工股份有限公司 | Optimization method for natural gas cryogenic denitrification pretreatment process parameters |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110161251A1 (en) * | 2005-01-18 | 2011-06-30 | Carey Margaret M | Method and System for Tracking and Budgeting Energy Usage |
| CN102521674A (en) * | 2011-12-07 | 2012-06-27 | 福建省电力有限公司 | Computer generating method for short-term load forecasting in summer in power consumer electricity-utilization information acquisition system |
| CN102682349A (en) * | 2012-05-14 | 2012-09-19 | 云南电力试验研究院（集团）有限公司电力研究院 | Electricity consumption intelligent prediction system and method |
-
2012
- 2012-11-06 CN CN201210439494.4A patent/CN102930354B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110161251A1 (en) * | 2005-01-18 | 2011-06-30 | Carey Margaret M | Method and System for Tracking and Budgeting Energy Usage |
| CN102521674A (en) * | 2011-12-07 | 2012-06-27 | 福建省电力有限公司 | Computer generating method for short-term load forecasting in summer in power consumer electricity-utilization information acquisition system |
| CN102682349A (en) * | 2012-05-14 | 2012-09-19 | 云南电力试验研究院（集团）有限公司电力研究院 | Electricity consumption intelligent prediction system and method |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473613A (en) * | 2013-09-09 | 2013-12-25 | 武汉理工大学 | Landscape structure-surface temperature-electricity consumption coupling model and application thereof |
| CN103473613B (en) * | 2013-09-09 | 2017-01-11 | 武汉理工大学 | Landscape structure-surface temperature-electricity consumption coupling model and application thereof |
| CN104636816A (en) * | 2013-11-07 | 2015-05-20 | 财团法人资讯工业策进会 | Device and method for establishing power utilization model |
| CN103854068B (en) * | 2013-12-06 | 2017-02-08 | 国家电网公司 | Method for forecasting residential quarter short-term loads |
| CN104751233A (en) * | 2013-12-27 | 2015-07-01 | 台达电子工业股份有限公司 | Contract capacity optimization system and optimization method |
| CN105717355A (en) * | 2014-07-11 | 2016-06-29 | 英科德技术股份有限公司 | Apparatus, server, system and method for energy measuring |
| CN104317910A (en) * | 2014-10-27 | 2015-01-28 | 国家电网公司 | Data processing method and device |
| CN104346659A (en) * | 2014-11-26 | 2015-02-11 | 北京邮电大学 | Short-term power generation prediction method applied to high-concentration-ratio photovoltaic power generation system |
| CN106934497A (en) * | 2017-03-08 | 2017-07-07 | 青岛卓迅电子科技有限公司 | Wisdom cell power consumption real-time predicting method and device based on deep learning |
| CN107330548A (en) * | 2017-06-16 | 2017-11-07 | 广东电网有限责任公司惠州供电局 | Residential electricity consumption Forecasting Methodology based on time series models |
| CN110210672A (en) * | 2019-06-04 | 2019-09-06 | 北京百度网讯科技有限公司 | The method and apparatus of electricity demand forecasting, electronic equipment, computer-readable medium |
| CN111523807A (en) * | 2020-04-24 | 2020-08-11 | 广西电网有限责任公司崇左供电局 | Electric energy substitution potential analysis method based on time sequence and neural network |
| CN112163709A (en) * | 2020-10-09 | 2021-01-01 | 珠海格力电器股份有限公司 | Power utilization prompting method and device, storage medium and electronic device |
| CN112163709B (en) * | 2020-10-09 | 2024-04-09 | 珠海格力电器股份有限公司 | Method and device for electricity utilization promotion, storage medium, and electronic device |
| CN114456862A (en) * | 2020-11-04 | 2022-05-10 | 中国石油化工股份有限公司 | Optimization method for natural gas cryogenic denitrification pretreatment process parameters |
| CN114456862B (en) * | 2020-11-04 | 2022-10-21 | 中国石油化工股份有限公司 | Optimization method for natural gas cryogenic denitrification pretreatment process parameters |
| CN112907062A (en) * | 2021-02-08 | 2021-06-04 | 国网安徽省电力有限公司蚌埠供电公司 | Power grid electric quantity prediction method, device, medium and terminal integrating temperature characteristics |
| CN112907064A (en) * | 2021-02-08 | 2021-06-04 | 国网安徽省电力有限公司蚌埠供电公司 | Electric quantity prediction method and device based on self-adaptive window, storage medium and terminal |
| CN112907064B (en) * | 2021-02-08 | 2024-04-02 | 国网安徽省电力有限公司蚌埠供电公司 | Electric quantity prediction method and device based on adaptive window, storage medium and terminal |
| CN112907062B (en) * | 2021-02-08 | 2024-04-02 | 国网安徽省电力有限公司蚌埠供电公司 | Power grid electric quantity prediction method, device, medium and terminal integrating temperature characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102930354B (en) | 2016-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102930354A (en) | Method and device for predicating electricity consumption of residential area | |
| Zahraee et al. | Application of artificial intelligence methods for hybrid energy system optimization | |
| Kankal et al. | Modeling and forecasting of Turkey’s energy consumption using socio-economic and demographic variables | |
| CN105844371A (en) | Electricity customer short-term load demand forecasting method and device | |
| Teng et al. | Use of group method of data handling for transport energy demand modeling | |
| Hafeez et al. | Utilization of EV charging station in demand side management using deep learning method | |
| Wang et al. | A novel decomposition-ensemble forecasting system for dynamic dispatching of smart grid with sub-model selection and intelligent optimization | |
| CN111985695A (en) | Urban complex electricity consumption prediction method and device, electronic equipment and storage medium | |
| Dong et al. | A multifactorial short-term load forecasting model combined with periodic and non-periodic features-a case study of qingdao, China | |
| Alhmoud et al. | Short-term load forecasting for Jordan power system based on NARX-ELMAN neural network and ARMA model | |
| Zhang et al. | Forecasting of electricity prices using deep learning networks | |
| CN112288140A (en) | Keras-based short-term power load prediction method, storage medium and equipment | |
| Pan et al. | Multivariable sales prediction for filling stations via GA improved BiLSTM | |
| Mukherjee et al. | Solar irradiance prediction from historical trends using deep neural networks | |
| Ibrahim et al. | LSTM neural network model for ultra-short-term distribution zone substation peak demand prediction | |
| Rashid et al. | Auto-regressive recurrent neural network approach for electricity load forecasting | |
| Pal et al. | Short-Term Load Forecasting Using Adaptive Neuro-Fuzzy Inference System (ANFIS)” | |
| CN111008723A (en) | Optimization method for design of distributed energy PEV charging station | |
| CN112508734B (en) | Method and device for predicting power generation capacity of power enterprise based on convolutional neural network | |
| Salman et al. | Using recurrent neural network to forecast day and year ahead performance of load demand: A case study of France | |
| Roy et al. | Implementation of encoder-decoder based long short-term memory network for short-term electrical load forecasting | |
| Xia et al. | SCG and LM improved BP neural network load forecasting and programming network parameter settings and data preprocessing | |
| Gupta et al. | Electricity Power Consumption Forecasting Techniques: A survey | |
| Sanjani | The prediction of increase or decrease of electricity cost using fuzzy expert systems | |
| De Nicolao et al. | Short-term load forecasting: A power-regression approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |