CN103870885A - Method and device for predicating electric power load characteristic numerical value - Google Patents

Abstract

The invention discloses a method and a device for predicating an electric power load characteristic numerical value. The method for predicating the electric power load characteristic numerical values comprises the following steps: obtaining a meteorological index numerical value; obtaining a linear model function; calculating the electric power load characteristic numerical value according to the meteorological index numerical value and the linear model function. With the adoption of the method and the device disclosed by the invention, the accuracy of predicating the electric power load characteristic numerical value is improved.

Description

Method and the device of prediction electric load character numerical value

Technical field

The present invention relates to electric field, in particular to a kind of method and device of predicting electric load character numerical value.

Background technology

In the work of the short term index prediction of electric system, the height of the accuracy rate of load characteristic numerical prediction, realizes the Real-time Balancing of electric system for power grid enterprises, save the energy, and less loss, increases economic efficiency and have conclusive effect.At present, to electric load character numerical value, prediction can only rely on historical electric load character numerical value to carry out, but the variation of electric load itself is also subject to being permitted multifactorial impact, has caused the not high problem of electric load character numerical value predictablity rate.

For in correlation technique to the not high problem of electric load character numerical value predictablity rate, effective solution is not yet proposed at present.

Summary of the invention

Fundamental purpose of the present invention is to provide a kind of method and device of predicting electric load character numerical value, to solve the not high problem of electric load character numerical value predictablity rate.

To achieve these goals, according to an aspect of the present invention, provide a kind of method of predicting electric load character numerical value, it is characterized in that, having comprised:

Obtain meteorological index numerical value; Obtain linear model function; Calculate electric load character numerical value according to this meteorological index numerical value and this linear model function.

Further, before obtaining meteorological index numerical value, the method also comprises:

Obtain multiple meteorological index; Obtain in the plurality of meteorological index the meteorological index with electric load index related coefficient maximum; Wherein, obtaining meteorological index numerical value comprises: the meteorological index numerical value that obtains the meteorological index of this and electric load index related coefficient maximum.

Further, obtain in the plurality of meteorological index and comprise with the meteorological index of electric load index related coefficient maximum:

Obtain the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, this n is more than or equal to 2; Obtain n the electric load character numerical value of this very first time; Calculate the related coefficient of this first meteorological index and this electric load index according to following formula:

$r_{\mathrm{xy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _xyfor the related coefficient of this first meteorological index and this electric load index, x _ifor i the first meteorological index numerical value in this n the first meteorological index numerical value, y _ifor i electric load character numerical value in this n electric load character numerical value, this x _iwith this y _ifor the numerical value obtaining in the same time mutually, this i=1 ..., n; Obtain n the second meteorological index numerical value of the second meteorological index in this very first time; Calculate the related coefficient of this second meteorological index and this electric load index according to following formula:

$r_{\mathrm{zy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _zyfor the related coefficient of this second meteorological index and this electric load index, z _ifor i the second meteorological index numerical value in this n the second meteorological index numerical value, this z _iwith this y _ifor the numerical value obtaining in the same time mutually; Judge this r _xywith this r _zymagnitude relationship; Wherein, if this r _xybe more than or equal to this r _zy, using this first meteorological index as with the meteorological index of electric load index related coefficient maximum; If this r _xybe less than this r _zy, using this second meteorological index as with the meteorological index of electric load index related coefficient maximum.

Further, before obtaining meteorological index numerical value, the method also comprises:

Obtain multiple meteorological index; Obtain in the plurality of meteorological index the meteorological index with electric load indicator difference degree minimum; Wherein, this obtains meteorological index numerical value and comprises: the meteorological index numerical value that obtains the meteorological index of this and electric load indicator difference degree minimum.

Further, obtain in the plurality of meteorological index and comprise with the meteorological index of electric load indicator difference degree minimum:

Obtain the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, this n is more than or equal to 2; Obtain n the electric load character numerical value of this very first time; Calculate the distance value of this first meteorological index and this electric load index according to following formula:

$d_{\mathrm{xy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _xyfor the distance value of this first meteorological index and this electric load index, x _ifor i the first meteorological index numerical value in this n the first meteorological index numerical value, y _ifor i electric load character numerical value in this n electric load character numerical value, this x _iwith this y _ifor the numerical value obtaining in the same time mutually, this i=1 ..., n; Obtain n the second meteorological index numerical value of the second meteorological index in this very first time; Calculate the distance value of this second meteorological index and this electric load index according to following formula:

$d_{\mathrm{zy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _zyfor the distance value of this second meteorological index and this electric load index, z _ifor i the second meteorological index numerical value in this n the second meteorological index numerical value, this z _iwith this y _ifor the numerical value obtaining in the same time mutually; Judge this d _xywith this d _zymagnitude relationship; Wherein, if this d _xybe more than or equal to this d _zy, using this second meteorological index as with the meteorological index of this electric load diversity factor minimum; If this d _xybe less than this d _zy, using this first meteorological index as with the meteorological index of this electric load diversity factor minimum.

To achieve these goals, according to a further aspect in the invention, provide a kind of device of predicting electric load character numerical value, having comprised:

The first acquisition module, for obtaining meteorological index numerical value; The second acquisition module, for obtaining linear model function; Computing module, for calculating electric load character numerical value according to this meteorological index numerical value and this linear model function.

Further, this device also comprises:

The 3rd acquisition module, obtains multiple meteorological index; First selects module, for obtaining the meteorological index of the plurality of meteorological index and electric load index related coefficient maximum; Wherein, this first acquisition module, for obtaining the meteorological index numerical value of meteorological index of this and electric load index related coefficient maximum.

Further, this first selection module comprises:

The first acquiring unit, for obtaining the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, this n is more than or equal to 2; Second acquisition unit, for obtaining n the electric load character numerical value of this very first time; The first computing unit, for calculate the related coefficient of this first meteorological index and this electric load index according to following formula:

$r_{\mathrm{xy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _xyfor the related coefficient of this first meteorological index and this electric load index, x _ifor i the first meteorological index numerical value in this n the first meteorological index numerical value, y _ifor i electric load character numerical value in this n electric load character numerical value, this x _iwith this y _ifor the numerical value obtaining in the same time mutually, this i=1 ..., n; The 3rd acquiring unit, for obtaining n the second meteorological index numerical value of the second meteorological index in this very first time; The second computing unit, for calculate the related coefficient of this second meteorological index and this electric load index according to following formula:

$r_{\mathrm{zy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _zyfor the related coefficient of this second meteorological index and this electric load index, z _ifor i the second meteorological index numerical value in this n the second meteorological index numerical value, this z _iwith this y _ifor the numerical value obtaining in the same time mutually; The first judging unit, for judging this r _xywith this r _zymagnitude relationship; The first performance element, if for this r _xybe more than or equal to this r _zy, using this first meteorological index as with the meteorological index of electric load index related coefficient maximum, and if this r _xybe less than this r _zy, using this second meteorological index as with the meteorological index of electric load index related coefficient maximum.

Further, this device also comprises:

The 4th acquisition module, for obtaining multiple meteorological index; Second selects module, for obtaining the meteorological index of the plurality of meteorological index and electric load indicator difference degree minimum; Wherein, this first acquiring unit, for obtaining the meteorological index numerical value of meteorological index of this and electric load indicator difference degree minimum.

Further, this second selection module comprises:

The 4th acquiring unit, for obtaining the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, this n is more than or equal to 2; The 5th acquiring unit, for obtaining n the electric load character numerical value of this very first time; The 3rd computing unit, for calculate the distance value of this first meteorological index and this electric load index according to following formula:

$d_{\mathrm{xy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _xyfor the distance value of this first meteorological index and this electric load index, x _ifor i the first meteorological index numerical value in this n the first meteorological index numerical value, y _ifor i electric load character numerical value in this n electric load character numerical value, this x _iwith this y _ifor the numerical value obtaining in the same time mutually, this i=1 ..., n; The 6th acquiring unit, for obtaining n the second meteorological index numerical value of the second meteorological index in this very first time; The 4th computing unit, for calculate the distance value of this second meteorological index and this electric load index according to following formula:

$d_{\mathrm{zy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _zyfor the distance value of this second meteorological index and this electric load index, z _ifor i the second meteorological index numerical value in this n the second meteorological index numerical value, this z _iwith this y _ifor the numerical value obtaining in the same time mutually; The second judging unit, for judging this d _xywith this d _zymagnitude relationship; The second performance element, if for this d _xybe more than or equal to this d _zy, using this second meteorological index as with the meteorological index of this electric load diversity factor minimum, and if this d _xybe less than this d _zy, using this first meteorological index as with the meteorological index of this electric load diversity factor minimum.

The present invention obtains electric load character numerical value by meteorological index numerical evaluation, due to the feature in conjunction with seasonal climate change in the process of prediction, utilize quantitatively the relation between electric load index and meteorological index correlative factor, therefore improved the accuracy rate to the prediction of electric load character numerical value.

Brief description of the drawings

The accompanying drawing that forms the application's a part is used to provide a further understanding of the present invention, and schematic description and description of the present invention is used for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:

Fig. 1 is according to the structural drawing of a kind of device of predicting electric load character numerical value of the embodiment of the present invention;

Fig. 2 is according to the structural drawing of the device of the another kind prediction electric load character numerical value of the embodiment of the present invention;

Fig. 3 is according to the process flow diagram of a kind of method of predicting electric load character numerical value of the embodiment of the present invention; And

Fig. 4 is according to the process flow diagram of the method for the another kind prediction electric load character numerical value of the embodiment of the present invention.

Embodiment

It should be noted that, in the situation that not conflicting, the feature in embodiment and embodiment in the application can combine mutually.Describe below with reference to the accompanying drawings and in conjunction with the embodiments the present invention in detail.

Fig. 1 is according to the structural drawing of a kind of device of predicting electric load character numerical value of the embodiment of the present invention, and as shown in Figure 1, the device of the prediction electric load character numerical value of this embodiment comprises:

The first acquisition module 101, for obtaining meteorological index numerical value.

This meteorological index numerical value can be maximum temperature numerical value, minimum temperature numerical value or rainfall amount numerical value etc.

The second acquisition module 102, for obtaining linear model function;

This linear model function can comprise:

1, linear model function: y=a+b*x(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b is regression parameter);

2, exponential model function 1:y=a*exp (b*x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b is regression parameter);

3, exponential model function 2:y=a*exp (b/x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b is regression parameter);

4, logarithmic model function: y=a+b*ln (x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b is regression parameter);

5, hyperbolic model function 1:y=a+b/x(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b is regression parameter);

6, hyperbolic model function 2:1/y=a+b/x(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b is regression parameter);

7, power function model function: y=a*x^b(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b is regression parameter);

8, sigmoid curve pattern function: 1/y=a+b*exp (x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b is regression parameter);

9, GOMPERTZ curvilinear function: ln (y)=a+b*exp (x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b is regression parameter);

10, parabola model function: y=a+b*x+c*x^2(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b and c are regression parameter);

11, higher order polynomial pattern function: y=a0+a1*x+a2*x^2+...+an*x^n(y is this electric load character numerical value, and x is this meteorological index numerical value, a0, and a1, a2...an is regression parameter).

Wherein, regression parameter can obtain by least-squares parameter estimation method.

Computing module 103, for calculating electric load character numerical value according to this meteorological index numerical value and this linear model function.

This electric load character numerical value can be peak load numerical value, minimum load numerical value or peak-valley difference numerical value.

The device of the prediction electric load character numerical value that the embodiment of the present invention provides, obtain electric load character numerical value by meteorological index numerical evaluation, due to the feature in conjunction with seasonal climate change in the process of prediction, utilize quantitatively the relation between electric load index and meteorological index correlative factor, therefore improved the accuracy rate to the prediction of electric load character numerical value.

Preferably, Fig. 2 is according to the structural drawing of a kind of device of predicting electric load character numerical value of the embodiment of the present invention, and as shown in Figure 2, the device of the prediction electric load character numerical value of this embodiment comprises:

The 3rd acquisition module 201, obtains multiple meteorological index.

First selects module 202, for obtaining the meteorological index of the plurality of meteorological index and electric load index related coefficient maximum.

For example, this related coefficient can be Pearson(Pearson came) related coefficient.

The first acquisition module 203, for obtaining the meteorological index numerical value of meteorological index of this and electric load index related coefficient maximum.

The second acquisition module 204, for obtaining linear model function.

Computing module 205, for calculating electric load character numerical value according to this meteorological index numerical value and this linear model function.

Preferably, this first selection module 202 comprises:

The first acquiring unit, for obtaining the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, this n is more than or equal to 2.

Second acquisition unit, for obtaining n the electric load character numerical value of this very first time.

The first computing unit, for calculate the related coefficient of this first meteorological index and this electric load index according to following formula:

$r_{\mathrm{xy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _xyfor the related coefficient of this first meteorological index and this electric load index, x _ifor i the first meteorological index numerical value in this n the first meteorological index numerical value, y _ifor i electric load character numerical value in this n electric load character numerical value, this x _iwith this y _ifor the numerical value obtaining in the same time mutually, this i=1 ..., n.

The 3rd acquiring unit, for obtaining n the second meteorological index numerical value of the second meteorological index in this very first time.

The second computing unit, for calculate the related coefficient of this second meteorological index and this electric load index according to following formula:

$r_{\mathrm{zy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _zyfor the related coefficient of this second meteorological index and this electric load index, z _ifor i the second meteorological index numerical value in this n the second meteorological index numerical value, this z _iwith this y _ifor the numerical value obtaining in the same time mutually.

The first judging unit, for judging this r _xywith this r _zymagnitude relationship.

The first performance element, if for this r _xybe more than or equal to this r _zy, using this first meteorological index as with the meteorological index of electric load index related coefficient maximum, and if this r _xybe less than this r _zy, using this second meteorological index as with the meteorological index of electric load index related coefficient maximum.

The device of the prediction electric load character numerical value that the embodiment of the present invention provides, obtain electric load character numerical value by meteorological index numerical evaluation, due to the feature in conjunction with seasonal climate change in the process of prediction, utilize quantitatively the relation between electric load index and meteorological index correlative factor, therefore improved the accuracy rate to the prediction of electric load character numerical value.

The device of the prediction electric load character numerical value that preferably, this embodiment provides comprises:

The 4th acquisition module, for obtaining multiple meteorological index.

Second selects module, for obtaining the meteorological index of the plurality of meteorological index and electric load indicator difference degree minimum.

The first acquisition module, for obtaining the meteorological index numerical value of meteorological index of this and electric load indicator difference degree minimum.

The second acquisition module, for obtaining linear model function.

Computing module, for calculating electric load character numerical value according to this meteorological index numerical value and this linear model function.

Preferably, this second selection module comprises:

The 4th acquiring unit, for obtaining the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, this n is more than or equal to 2.

The 5th acquiring unit, for obtaining n the electric load character numerical value of this very first time.

The 3rd computing unit, for calculate the distance value of this first meteorological index and this electric load index according to following formula:

$d_{\mathrm{xy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _xyfor the distance value of this first meteorological index and this electric load index, x _ifor i the first meteorological index numerical value in this n the first meteorological index numerical value, y _ifor i electric load character numerical value in this n electric load character numerical value, this x _iwith this y _ifor the numerical value obtaining in the same time mutually, this i=1 ..., n.

The 6th acquiring unit, for obtaining n the second meteorological index numerical value of the second meteorological index in this very first time.

The 4th computing unit, for calculate the distance value of this second meteorological index and this electric load index according to following formula:

$d_{\mathrm{zy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _zyfor the distance value of this second meteorological index and this electric load index, z _ifor i the second meteorological index numerical value in this n the second meteorological index numerical value, this z _iwith this y _ifor the numerical value obtaining in the same time mutually.

The second judging unit, for judging this d _xywith this d _zymagnitude relationship.

The second performance element, if for this d _xybe more than or equal to this d _zy, using this second meteorological index as with the meteorological index of this electric load diversity factor minimum, and if this d _xybe less than this d _zy, using this first meteorological index as with the meteorological index of this electric load diversity factor minimum.

The device of the prediction electric load character numerical value that the embodiment of the present invention provides, obtain electric load character numerical value by meteorological index numerical evaluation, due to the feature in conjunction with seasonal climate change in the process of prediction, utilize quantitatively the relation between electric load index and meteorological index correlative factor, therefore improved the accuracy rate to the prediction of electric load character numerical value.

Fig. 3 is according to the process flow diagram of a kind of method of predicting electric load character numerical value of the embodiment of the present invention, and as shown in Figure 3, the method for the prediction electric load character numerical value of this embodiment comprises:

Step 101: obtain meteorological index numerical value.

Step 102: obtain linear model function.

This linear model function can comprise:

1, linear model function: y=a+b*x(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

2, exponential model function 1:y=a*exp (b*x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

3, exponential model function 2:y=a*exp (b/x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

4, logarithmic model function: y=a+b*ln (x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

5, hyperbolic model function 1:y=a+b/x(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

6, hyperbolic model function 2:1/y=a+b/x(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

7, power function model function: y=a*x^b(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

8, sigmoid curve pattern function: 1/y=a+b*exp (x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

9, GOMPERTZ curvilinear function: ln (y)=a+b*exp (x) (y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

10, parabola model function: y=a+b*x+c*x^2(y is this electric load character numerical value, and x is this meteorological index numerical value, a, b regression parameter);

11, higher order polynomial pattern function: y=a0+a1*x+a2*x^2+...+an*x^n(y is this electric load character numerical value, and x is this meteorological index numerical value, a0, and a1, a2...an is regression parameter).

Step 103: calculate electric load character numerical value according to this meteorological index numerical value and this linear model function.

The method of the prediction electric load character numerical value that the embodiment of the present invention provides, obtain electric load character numerical value by meteorological index numerical evaluation, due to the feature in conjunction with seasonal climate change in the process of prediction, utilize quantitatively the relation between electric load index and meteorological index correlative factor, therefore improved the accuracy rate to the prediction of electric load character numerical value.

Preferably, Fig. 4 is according to the process flow diagram of a kind of method of predicting electric load character numerical value of the embodiment of the present invention, and as shown in Figure 4, the method for the prediction electric load character numerical value of this embodiment comprises:

Step 201: obtain multiple meteorological index.

Step 202: obtain in the plurality of meteorological index the meteorological index with electric load index related coefficient maximum.

Step 203: the meteorological index numerical value that obtains the meteorological index of this and electric load index related coefficient maximum.

Step 204: obtain linear model function.

Step 205: calculate electric load character numerical value according to this meteorological index numerical value and this linear model function.

Preferably, this step 202 specifically comprises:

Step 2021: obtain the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, this n is more than or equal to 2.

Step 2022: n the electric load character numerical value that obtains this very first time.

Step 2023: the related coefficient of calculating this first meteorological index and this electric load index according to following formula:

$r_{\mathrm{xy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _xyfor the related coefficient of this first meteorological index and this electric load index, x _ifor i the first meteorological index numerical value in this n the first meteorological index numerical value, y _ifor i electric load character numerical value in this n electric load character numerical value, this x _iwith this y _ifor the numerical value obtaining in the same time mutually, this i=1 ..., n.

Step 2024: obtain n the second meteorological index numerical value of the second meteorological index in this very first time.

Step 2025: the related coefficient of calculating this second meteorological index and this electric load index according to following formula:

$r_{\mathrm{zy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _zyfor the related coefficient of this second meteorological index and this electric load index, z _ifor i the second meteorological index numerical value in this n the second meteorological index numerical value, this z _iwith this y _ifor the numerical value obtaining in the same time mutually.

Step 2026: judge this r _xywith this r _zymagnitude relationship, if this r _xybe more than or equal to this r _zy, execution step 2027, if this r _xybe less than this r _zy, execution step 2028.

Step 2027: using this first meteorological index as with the meteorological index of electric load index related coefficient maximum, flow process finishes.

Step 2028: using this second meteorological index as with the meteorological index of electric load index related coefficient maximum, flow process finishes.

The method of the prediction electric load character numerical value that the embodiment of the present invention provides, obtain electric load character numerical value by meteorological index numerical evaluation, due to the feature in conjunction with seasonal climate change in the process of prediction, utilize quantitatively the relation between electric load index and meteorological index correlative factor, therefore improved the accuracy rate to the prediction of electric load character numerical value.

The method of the prediction electric load character numerical value that preferably, this embodiment provides comprises:

Step 301: obtain multiple meteorological index.

Step 302: obtain in the plurality of meteorological index the meteorological index with electric load indicator difference degree minimum.

Step 303: the meteorological index numerical value that obtains the meteorological index of this and electric load indicator difference degree minimum.

Step 304: obtain linear model function.

Step 305: calculate electric load character numerical value according to this meteorological index numerical value and this linear model function.

Preferably, this step 302 specifically comprises:

Step 3021: obtain the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, this n is more than or equal to 2.

Step 3022: n the electric load character numerical value that obtains this very first time.

Step 3023: the distance value that calculates this first meteorological index and this electric load index according to following formula:

$d_{\mathrm{xy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _xyfor the distance value of this first meteorological index and this electric load index, x _ifor i the first meteorological index numerical value in this n the first meteorological index numerical value, y _ifor i electric load character numerical value in this n electric load character numerical value, this x _iwith this y _ifor the numerical value obtaining in the same time mutually, this i=1 ..., n.

Step 3024: obtain n the second meteorological index numerical value of the second meteorological index in this very first time.

Step 3025: the distance value that calculates this second meteorological index and this electric load index according to following formula:

$d_{\mathrm{zy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _zyfor the distance value of this second meteorological index and this electric load index, z _ifor i the second meteorological index numerical value in this n the second meteorological index numerical value, this z _iwith this y _ifor the numerical value obtaining in the same time mutually.

Step 3026: judge this d _xywith this d _zymagnitude relationship, if this d _xybe more than or equal to this d _zyexecution step 3047, if this d _xybe less than this d _zy, execution step 3048.

Step 3027: using this second meteorological index as with the meteorological index of this electric load diversity factor minimum, flow process finishes.

Step 3028: using this first meteorological index as with the meteorological index of this electric load diversity factor minimum, flow process finishes.

The method of the prediction electric load character numerical value that the embodiment of the present invention provides, obtain electric load character numerical value by meteorological index numerical evaluation, due to the feature in conjunction with seasonal climate change in the process of prediction, utilize quantitatively the relation between electric load index and meteorological index correlative factor, therefore improved the accuracy rate to the prediction of electric load character numerical value.

It should be noted that, can in the computer system such as one group of computer executable instructions, carry out in the step shown in the process flow diagram of accompanying drawing, and, although there is shown logical order in flow process, but in some cases, can carry out shown or described step with the order being different from herein.

Obviously, those skilled in the art should be understood that, above-mentioned of the present invention each module or each step can realize with general calculation element, they can concentrate on single calculation element, or be distributed on the network that multiple calculation elements form, alternatively, they can be realized with the executable program code of calculation element, thereby, they can be stored in memory storage and be carried out by calculation element, or they are made into respectively to each integrated circuit modules, or the multiple modules in them or step are made into single integrated circuit module to be realized.Like this, the present invention is not restricted to any specific hardware and software combination.

The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any amendment of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.

Claims (10)

1. a method of predicting electric load character numerical value, is characterized in that, comprising:

Obtain meteorological index numerical value;

Obtain linear model function;

Calculate electric load character numerical value according to described meteorological index numerical value and described linear model function.

2. method according to claim 1, is characterized in that, before obtaining meteorological index numerical value, described method also comprises:

Obtain multiple meteorological index;

Obtain in described multiple meteorological index the meteorological index with electric load index related coefficient maximum;

Wherein, obtaining meteorological index numerical value comprises:

Obtain the meteorological index numerical value of the meteorological index of described and electric load index related coefficient maximum.

3. method according to claim 2, is characterized in that, obtains in described multiple meteorological index and comprises with the meteorological index of electric load index related coefficient maximum:

Obtain the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, described n is more than or equal to 2;

Obtain n the electric load character numerical value of the described very first time;

Calculate the related coefficient of described the first meteorological index and described electric load index according to following formula:

$r_{\mathrm{xy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _xyfor the related coefficient of described the first meteorological index and described electric load index, x _ifor i the first meteorological index numerical value in described n the first meteorological index numerical value, y _ifor i electric load character numerical value in described n electric load character numerical value, described x _iwith described y _ifor the numerical value obtaining in the same time mutually, described i=1 ..., n;

Obtain n the second meteorological index numerical value of the second meteorological index in the described very first time;

Calculate the related coefficient of described the second meteorological index and described electric load index according to following formula:

$r_{\mathrm{zy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _zyfor the related coefficient of described the second meteorological index and described electric load index, z _ifor i the second meteorological index numerical value in described n the second meteorological index numerical value, described z _iwith described y _ifor the numerical value obtaining in the same time mutually;

Judge described r _xywith described r _zymagnitude relationship;

Wherein, if described r _xybe more than or equal to described r _zy, using described the first meteorological index as with the meteorological index of electric load index related coefficient maximum;

If described r _xybe less than described r _zy, using described the second meteorological index as with the meteorological index of electric load index related coefficient maximum.

4. method according to claim 1, is characterized in that, before obtaining meteorological index numerical value, described method also comprises:

Obtain multiple meteorological index;

Obtain in described multiple meteorological index the meteorological index with electric load indicator difference degree minimum;

Wherein, described in, obtaining meteorological index numerical value comprises:

Obtain the meteorological index numerical value of the meteorological index of described and electric load indicator difference degree minimum.

5. method according to claim 4, is characterized in that, obtains in described multiple meteorological index and comprises with the meteorological index of electric load indicator difference degree minimum:

Obtain the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, described n is more than or equal to 2;

Obtain n the electric load character numerical value of the described very first time;

Calculate the distance value of described the first meteorological index and described electric load index according to following formula:

$d_{\mathrm{xy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _xyfor the distance value of described the first meteorological index and described electric load index, x _ifor i the first meteorological index numerical value in described n the first meteorological index numerical value, y _ifor i electric load character numerical value in described n electric load character numerical value, described x _iwith described y _ifor the numerical value obtaining in the same time mutually, described i=1 ..., n;

Obtain n the second meteorological index numerical value of the second meteorological index in the described very first time;

Calculate the distance value of described the second meteorological index and described electric load index according to following formula:

$d_{\mathrm{zy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _zyfor the distance value of described the second meteorological index and described electric load index, z _ifor i the second meteorological index numerical value in described n the second meteorological index numerical value, described z _iwith described y _ifor the numerical value obtaining in the same time mutually;

Judge described d _xywith described d _zymagnitude relationship;

Wherein, if described d _xybe more than or equal to described d _zy, using described the second meteorological index as with the meteorological index of described electric load diversity factor minimum;

If described d _xybe less than described d _zy, using described the first meteorological index as with the meteorological index of described electric load diversity factor minimum.

6. a device of predicting electric load character numerical value, is characterized in that, comprising:

The first acquisition module, for obtaining meteorological index numerical value;

The second acquisition module, for obtaining linear model function;

Computing module, for calculating electric load character numerical value according to described meteorological index numerical value and described linear model function.

7. device according to claim 6, is characterized in that, described device also comprises:

The 3rd acquisition module, obtains multiple meteorological index;

First selects module, for obtaining the meteorological index of described multiple meteorological index and electric load index related coefficient maximum;

Wherein, described the first acquisition module, for obtaining the meteorological index numerical value of meteorological index of described and electric load index related coefficient maximum.

8. device according to claim 7, is characterized in that, described first selects module to comprise:

The first acquiring unit, for obtaining the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, described n is more than or equal to 2;

Second acquisition unit, for obtaining n the electric load character numerical value of the described very first time;

The first computing unit, for calculate the related coefficient of described the first meteorological index and described electric load index according to following formula:

$r_{\mathrm{xy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{x_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _xyfor the related coefficient of described the first meteorological index and described electric load index, x _ifor i the first meteorological index numerical value in described n the first meteorological index numerical value, y _ifor i electric load character numerical value in described n electric load character numerical value, described x _iwith described y _ifor the numerical value obtaining in the same time mutually, described i=1 ..., n;

The 3rd acquiring unit, for obtaining n the second meteorological index numerical value of the second meteorological index in the described very first time;

The second computing unit, for calculate the related coefficient of described the second meteorological index and described electric load index according to following formula:

$r_{\mathrm{zy}}=\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}{{\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{z_i}{n})}^2\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\frac{y_i}{n})}^2\right]}^{\frac{1}{2}}},$

Wherein, r _zyfor the related coefficient of described the second meteorological index and described electric load index, z _ifor i the second meteorological index numerical value in described n the second meteorological index numerical value, described z _iwith described y _ifor the numerical value obtaining in the same time mutually;

The first judging unit, for judging described r _xywith described r _zymagnitude relationship;

The first performance element, if for described r _xybe more than or equal to described r _zy, using described the first meteorological index as with the meteorological index of electric load index related coefficient maximum, and if described r _xybe less than described r _zy, using described the second meteorological index as with the meteorological index of electric load index related coefficient maximum.

9. device according to claim 6, is characterized in that, described device also comprises:

The 4th acquisition module, for obtaining multiple meteorological index;

Second selects module, for obtaining the meteorological index of described multiple meteorological index and electric load indicator difference degree minimum;

Wherein, described the first acquiring unit, for obtaining the meteorological index numerical value of meteorological index of described and electric load indicator difference degree minimum.

10. device according to claim 9, is characterized in that, described second selects module to comprise:

The 4th acquiring unit, for obtaining the first meteorological index at individual the first meteorological index numerical value of the n of the very first time, described n is more than or equal to 2;

The 5th acquiring unit, for obtaining n the electric load character numerical value of the described very first time;

The 3rd computing unit, for calculate the distance value of described the first meteorological index and described electric load index according to following formula:

$d_{\mathrm{xy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _xyfor the distance value of described the first meteorological index and described electric load index, x _ifor i the first meteorological index numerical value in described n the first meteorological index numerical value, y _ifor i electric load character numerical value in described n electric load character numerical value, described x _iwith described y _ifor the numerical value obtaining in the same time mutually, described i=1 ..., n;

The 6th acquiring unit, for obtaining n the second meteorological index numerical value of the second meteorological index in the described very first time;

The 4th computing unit, for calculate the distance value of described the second meteorological index and described electric load index according to following formula:

$d_{\mathrm{zy}}={\left[\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(z_i-y_i)}^2\right]}^{\frac{1}{2}},$

Wherein, d _zyfor the distance value of described the second meteorological index and described electric load index, z _ifor i the second meteorological index numerical value in described n the second meteorological index numerical value, described z _iwith described y _ifor the numerical value obtaining in the same time mutually;

The second judging unit, for judging described d _xywith described d _zymagnitude relationship;

The second performance element, if for described d _xybe more than or equal to described d _zy, using described the second meteorological index as with the meteorological index of described electric load diversity factor minimum, and if described d _xybe less than described d _zy, using described the first meteorological index as with the meteorological index of described electric load diversity factor minimum.

Images