CN104573857A - Power grid load rate prediction method based on intelligent algorithm optimization and combination - Google Patents

Abstract

The invention discloses a power grid load rate prediction method based on intelligent algorithm optimization and combination. According to the method, firstly, a large quantity of factors related to the load rate are screened and left on the basis of means such as Granger inspection and the like under the condition that no information is missed, and the analysis accuracy of the factors related to the load rate and the prediction accuracy of the load rate are guaranteed. During load rate prediction, intelligent algorithms such as an RBF neural network, a GRNN neural network, an SVR and the like are considered, advantages of little missing information, avoidance of deep study on internal relations, high prediction accuracy and the like of the intelligent algorithms relative to traditional prediction methods are fully played, and a genetic algorithm is used for optimizing and combining multiple prediction results to further improve the prediction accuracy. The method can be applied to prediction of annual load rates of power grid systems or classified users such as great industrial users, resident users and the like and provides certain theoretical support for related research on load rate power prices.

Description

A kind of load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination

Technical field

The invention belongs to load rate of grid electric powder prediction, particularly relate to a kind of load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination.

Background technology

Rate of load condensate is the index of power capacity producing level.The imagination of carrying out electricity price reform according to customer charge characteristic is just proposed in 2003 national " sales rate of electricity reform schemes ".Country in 2012 begins one's study the sales rate of electricity and rate of load condensate electricity price implementing method formulating and consider rate of load condensate factor, promotes power industry and national economy from extensive to the transition of Compact development with this.Cost factor is the basis of formulating electricity price, shares and calculate the electric cost of different user according to customer charge rate, is the key problem in technology that rate of load condensate electricity price is implemented.Based on this, the forecast analysis of rate of load condensate serves vital effect for the rational of rate of load condensate electricity price and popularization.

But the domestic and international research to load factor estimation is still less at present, but about the technical method relative maturity of load prediction.In load forecast, traditional load forecasting method has regressive prediction model, Random time sequence forecast model, grey forecasting model, expert system approach etc.The limitation of character and the various Forecasting Methodology itself such as consider the influenced many factors of rate of load condensate self, each factor action principle is failed to understand, traditional load forecasting method is difficult to the object reaching Accurate Prediction.Such as, regressive prediction model adopts the too simple linear model of structure to go to solve serious nonlinear problem, cannot the various influence factors of detailed description rate of load condensate; Random time sequence forecast model process when modeling is complicated, also not comprehensive on the consideration of the factor (as weather, economic dispatch) affecting rate of load condensate variation; The range of application of grey forecasting model is less, easily expands for long-term forecasting time error; The undue dependent Rule of expert system approach, universality is poor.

And some intelligent algorithms are as neural network, SVR, genetic algorithm etc., skip going into seriously the inherent action principle of rate of load condensate correlative factor, effectively can solve the mistake existed in traditional prediction method and simplify the problems such as process, omission influence factor, universality difference.And intelligent algorithm ubiquity algorithm parameter many foundations subjective experience is determined, lack the new problem of suitable theoretical direction.In order to head it off, need to reduce predicated error for target, rational optimal combination is carried out to predicting the outcome of relevant different artificial intelligence approach.

Summary of the invention

In order to solve the problem, the object of the present invention is to provide a kind of load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination.

In order to achieve the above object, the load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination provided by the invention comprises: the load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination comprises the following step performed in order:

The first step: combing is carried out to the factor that may impact rate of load condensate, the timed sample sequence number that each factor adopts is at least more than 10;

Second step: utilize normalized formula to be normalized to above-mentioned sequence factor, to eliminate the impact of dimension on prediction: above basic data to be normalized interval [0,1], if data itself are namely interval [0,1] this step is then skipped in, as rate of load condensate itself does not then need to process;

3rd step: adopt comprise RBF neural, GRNN neural network, SVR different prediction algorithms carry out load factor estimation respectively, predicted the outcome;

4th step: through reverse reduction by the above-mentioned data be treated under normal dimension that predict the outcome:

5th step: using average absolute percentage error MAPE as fitness function, is optimized combination based on genetic algorithm to predicting the outcome under different prediction algorithm, finds the weight that difference predicts the outcome, reduces error further, finally obtains optimum prediction result.

In the third step, described normalized formula is as follows:

$y=\frac{x-x_{\min }}{x_{\max }-x_{\min }}---\left(1\right)$

Wherein, x is numerical value before process, and y is numerical value, wherein x after process _max, x _minbe respectively maximal value and the minimum value of this item number certificate.

In the 5th step, described using average absolute percentage error MAPE as fitness function, based on genetic algorithm, combination is optimized to predicting the outcome under different prediction algorithm, find the weight that difference predicts the outcome, reduce error further, the method finally obtaining optimum prediction result adopts following combined prediction mathematical model:

${\hat{y}}_t=\underset{t=1}{\overset{k}{\mathrm{\Σ}}}{w}_i{y}_{\mathrm{it}}(t=\mathrm{1,2},...,n),$ And $\underset{t=1}{\overset{k}{\mathrm{\Σ}}}{w}_i=1---\left(2\right)$

Wherein _,y _it(i=1,2 ..., k; T=1,2 ..., n) be the predicted value of i-th kind of Forecasting Methodology in t, w _iit is the weight coefficient of i-th kind of Forecasting Methodology.

The effect of the load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination provided by the invention:

First the present invention finds out all kinds of factor and respective time series, the accuracy of guaranteed load rate Study on Relative Factors and the precision of load factor estimation that may have an impact to rate of load condensate.When carrying out load factor estimation, consider the intelligent algorithms such as RBF neural, GRNN neural network, SVR, give full play to the advantage that intelligent algorithm drain message is few, do not go into seriously internal relations, the high relative traditional prediction method of precision of prediction, and use genetic algorithm to be optimized combination to improve precision of prediction further to multiple predicting the outcome.The method is mainly used in the load factor estimation of network system or the large sorted users such as industrial user, resident, for the relevant research of rate of load condensate electricity price provides certain theory support.

Accompanying drawing explanation

Fig. 1 is the load rate of grid Forecasting Methodology process flow diagram based on intelligent algorithm optimal combination provided by the invention.

Fig. 2 is RBF genetic algorithm optimization result.

Fig. 3 is GRNN genetic algorithm optimization result.

Fig. 4 is that RBF, GRNN, SVM predict the outcome comparison diagram.

Fig. 5 is genetic algorithm optimization procedure chart.

Fig. 6 is RBF, GRNN, SVM and GA combinational algorithm predicated error comparison diagram.

Embodiment

Below in conjunction with the drawings and specific embodiments, the load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination provided by the invention is described in detail.

First the present invention filters out the factor that may have an impact to yearly load factor in a large number, and then undertaken predicting by multi-intelligence algorithm based on the time series data of many factors and yearly load factor in recent years and be optimized combination in conjunction with genetic algorithm to predicting the outcome, the Software tool related to mainly comprises EXCEL and Matlab.

As shown in Figure 1, the load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination provided by the invention comprises the following step performed in order:

The first step: combing is carried out to the factor that may impact rate of load condensate, the timed sample sequence number adopted is at least more than 10;

Wherein, the factor that may impact load rate of grid size mainly comprises Factors Affecting Economic Development, dsm factor, temperature climatic factor, power grid environment factor and low-carbon economy development factors etc.In order to prevent omitting information of forecasting and cause result of calculation misalignment, need the various basic datas that extensive collection in a large number may be relevant to rate of load condensate;

Second step: utilize normalized formula to be normalized to above-mentioned sequence factor, to eliminate dimension to the impact predicted the outcome: above basic data to be normalized interval [0,1], if data itself are namely interval [0,1] in, then skip this step, as rate of load condensate itself does not then need to process;

3rd step: adopt comprise RBF neural, GRNN neural network, SVR different prediction algorithms carry out load factor estimation respectively, predicted the outcome;

4th step: through reverse reduction by the above-mentioned data be treated under normal dimension that predict the outcome:

5th step: using average absolute percentage error MAPE as fitness function, is optimized combination based on genetic algorithm to predicting the outcome under different prediction algorithm, finds the weight that difference predicts the outcome, reduces error further, finally obtains optimum prediction result.

Due to the incomprehensiveness to future, single Forecasting Methodology often has very large risk, method larger for predicated error is given up blindly and may lose a part of information.In order to strengthen forecasting reliability, above three kinds of prediction algorithms suitably can be combined, being fully utilized the information that various method provides, thus effectively be improved precision of prediction and reliability; The essence of this method is that the optimization of each forecast model weight is determined, finds the weight that difference predicts the outcome, reduces error further.

In second step, described normalized formula is as follows:

$y=\frac{x-x_{\min }}{x_{\max }-x_{\min }}---\left(1\right)$

Wherein, x is numerical value before process, and y is numerical value, wherein x after process _max, x _minbe respectively maximal value and the minimum value of this item number certificate.

In the 4th step, described reverse reduction treatment formula is as follows:

x＝x _min+y×(x _max-x _min) (2)

Wherein, x _max, x _minbe respectively the maximal value in rate of load condensate historical data and minimum value, y is the load factor estimation value before reverse reduction treatment, and x is the load factor estimation value after reverse reduction treatment.

In the 5th step, described using average absolute percentage error MAPE as fitness function, based on genetic algorithm, combination is optimized to predicting the outcome under different Forecasting Methodology, find the weight that difference predicts the outcome, reduce error further, the method finally obtaining optimum prediction result adopts following combined prediction mathematical model:

${\hat{y}}_t=\underset{t=1}{\overset{k}{\mathrm{\Σ}}}{w}_i{y}_{\mathrm{it}}(t=\mathrm{1,2},...,n),$ And $\underset{t=1}{\overset{k}{\mathrm{\Σ}}}{w}_i=1---\left(2\right)$

Wherein, y _it(i=1,2 ..., k; T=1,2 ..., n) be the predicted value of i-th kind of Forecasting Methodology in t, w _iit is the weight coefficient of i-th kind of Forecasting Methodology.

First load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination provided by the invention carries out data preparation, filter out the factor that a large amount of and rate of load condensate exists relation, thus will precision of prediction be caused to decline by drain message, for the correlated influencing factors of rate of load condensate and prediction lay the first stone.And then, obtain predicted value by neural network, support vector machine (SVR) scheduling algorithm and be optimized combination to predicting the outcome, the combination forecasting method that this precision is higher can be used for the prediction of the yearly load factor of network system or sorted users, and the formulation for rate of load condensate electricity price provides certain foundation.

Concrete case:

This example predicts the yearly load factor of 2010-2013 network system based on the relevant historical data of 2000-2009 years of Tianjin in conjunction with RBF neural algorithm, GRNN neural network algorithm, SVR and genetic algorithm, based on the predicted value of each Forecasting Methodology and the difference of actual value, adjustment is optimized to the combining weights of each Forecasting Methodology, sets up more perfect reliable forecast model.

The first step, arranges the correlative factor that may impact yearly load factor, wherein involved factor and the historical data of correspondence as shown in the table:

Table 1 yearly load factor fundamentals of forecasting tables of data

Second step, carries out pre-service to the basic data of above correlative factor.

Above basic data be normalized interval [0,1], formula is as follows:

$y=\frac{x-x_{\min }}{x_{\max }-x_{\min }}---\left(3\right)$

Wherein, x is numerical value before process, and y is numerical value, wherein x after process _max, x _minbe respectively maximal value and the minimum value of this item number certificate.

Basic data after being normalized is as shown in the table:

The basic data of table 2 after screening and normalized

3rd step, adopts RBF neural algorithm, GRNN neural network algorithm and SVR to predict yearly load factor according to the corresponding situation of table 1 respectively.

(1) predict based on RBF neural algorithm

Using the data of 2000-2009 in upper table as training sample, the data of 2010 ~ 2013 years, as test samples, are predicted by RBF neural.In order to reduce predicated error, with the MAPE predicted the outcome for fitness function, the distribution density function Spr of genetic algorithm to RBF neural is adopted to be optimized.

Wherein adopt the fitness function code of genetic algorithm optimization as follows:

Following table is the important parameter adopting genetic algorithm optimization, and unlisted parameter all gets default value:

Table 3 RBF genetic algorithm optimization parameter

Parameter name	Parameter value
		The upper limit	1
Lower limit	0
		Algebraically	50
Population quantity	100

As seen in Figure 2, along with not very increasing of algebraically, the value of MAPE constantly reduces, and optimizes stop in the 50th generation.When Spr=0.084 (0.083849), MAPE obtains optimal value.Spr=0.084 is substituted into neural network predict, the yearly load factor value tentatively obtaining 2010-2013 is respectively 0.471,0.940,1.000,0.793.

(2) predict based on GRNN neural network algorithm

In order to reduce predicated error, with the MAPE predicted the outcome for fitness function, the smoothing factor of genetic algorithm to GRNN neural network is adopted to be optimized.

Wherein adopt the fitness function code of genetic algorithm optimization as follows:

Following table is the important parameter adopting genetic algorithm optimization, and unlisted parameter all gets default value:

Table 4 GRNN genetic algorithm optimization parameter

Parameter name	Value
		The upper limit	1
Lower limit	0
		Algebraically	50

As seen in Figure 3, along with not very increasing of algebraically, the value of MAPE constantly reduces, and optimizes stop in the 50th generation.When Spr=0.930 (0.929996), MAPE obtains optimal value.Spr=0.930 is substituted into neural network predict, the yearly load factor value tentatively obtaining 2010-2013 is respectively-0.0894 ,-0.0894 ,-0.0894 ,-0.0894.

(3) predict based on SVR

In order to reduce predicated error, different parameter values being set and result is compared.

Wherein adopt the code of SVM prediction as follows:

The yearly load factor value tentatively obtaining 2010-2013 is respectively 0.5398,0.5433,0.5450,0.5447.

4th step, the inverse normalized of data is carried out according to following formula:

x＝x _min+y×(x _max-x _min) (4)

Wherein, x _max, x _minbe respectively the maximal value in rate of load condensate historical data and minimum value, y is the load factor estimation value before reverse reduction treatment, and x is the load factor estimation value after reverse reduction treatment.

Data under inverse normalization is treated to normal dimension by predicting the outcome, as shown in the table:

Table 5 to predict the outcome contrast against the difference after normalization

5th step, using average absolute percentage error MAPE as fitness function, is optimized combination based on genetic algorithm to predicting the outcome under different Forecasting Methodology, finds the weight that difference predicts the outcome, reduce error further.

The method of the RBF network of genetic algorithm optimization, the GRNN network of genetic algorithm optimization and support vector machine is used to predict the yearly load factor of 2010 ~ 2013 respectively above.Forecasting Methodology dissimilar above, respectively based on different theories, provides different information, precision also difference to some extent of its prediction.

Undertaken based on the data that load obtains in advance, by respective weights w by the method for the GRNN network of the RBF network of genetic algorithm optimization, genetic algorithm optimization and support vector machine ₁, w ₂and w ₃as the variable of genetic algorithm optimization, encode in floating number mode, by the equality condition constraint matrix representation of weights.Writing with MAPE is the fitness function mix of index, and code is as follows:

Fig. 5 is genetic algorithm optimization procedure chart.Execution result finds, works as w ₁=0, w ₂=0 and w ₃when=1, MAPE reaches minimum.

Fig. 6 is the contrast situation of the average absolute percentage error MAPE after RBF, GRNN, SVM and GA optimal combination, as can be seen from the figure the predicated error after GA optimizes is identical with the predicated error of SVM algorithm, in this example, the precision of prediction of SVM algorithm is apparently higher than RBF and GRNN algorithm, after GA combination, therefore only adopt the result of SVM algorithm.

Claims (3)

1. based on a load rate of grid Forecasting Methodology for intelligent algorithm optimal combination, it is characterized in that: the described load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination comprises the following step performed in order:

The first step: combing is carried out to the factor that may impact rate of load condensate, the timed sample sequence number that each factor adopts is at least more than 10;

Second step: utilize normalized formula to be normalized to above-mentioned sequence factor, to eliminate the impact of dimension on prediction: above basic data to be normalized interval [0,1], if data itself are namely interval [0,1] this step is then skipped in, as rate of load condensate itself does not then need to process;

3rd step: adopt comprise RBF neural, GRNN neural network, SVR different prediction algorithms carry out load factor estimation respectively, predicted the outcome;

4th step: through reverse reduction by the above-mentioned data be treated under normal dimension that predict the outcome:

5th step: using average absolute percentage error MAPE as fitness function, is optimized combination based on genetic algorithm to predicting the outcome under different prediction algorithm, finds the weight that difference predicts the outcome, reduces error further, finally obtains optimum prediction result.

2. the load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination according to claim 1, is characterized in that: in the third step, and described normalized formula is as follows:

$y=\frac{x-x_{\min }}{x_{\max }-x_{\min }}---\left(1\right)$

Wherein, x is numerical value before process, and y is numerical value, wherein x after process _max, x _minbe respectively maximal value and the minimum value of this item number certificate.

3. the load rate of grid Forecasting Methodology based on intelligent algorithm optimal combination according to claim 1, it is characterized in that: in the 5th step, described using average absolute percentage error MAPE as fitness function, based on genetic algorithm, combination is optimized to predicting the outcome under different prediction algorithm, find the weight that difference predicts the outcome, reduce error further, the method finally obtaining optimum prediction result adopts following combined prediction mathematical model:

${\hat{y}}_t=\underset{t=1}{\overset{k}{\mathrm{\Σ}}}{w}_i{y}_{\mathrm{it}}(t=\mathrm{1,2},...,n),$ And $\underset{t=1}{\overset{k}{\mathrm{\Σ}}}{w}_i=1---\left(2\right)$

Wherein, y _it(i=1,2 ..., k; T=1,2 ..., n) be the predicted value of i-th kind of Forecasting Methodology in t, w _iit is the weight coefficient of i-th kind of Forecasting Methodology.