Power distribution network reactive compensation control method and system based on multi-source data analysis

Abstract

The invention discloses a power distribution network reactive compensation control method and system based on multi-source data analysis, and relates to the technical field of power distribution network reactive compensation. The method comprises the following steps: acquiring multi-source data of a console area to be controlled at the same moment in a monitoring period, classifying the running state of a current reactive compensation mechanism by using a running state judgment function value, and constructing a recurrent neural network model taking preprocessed time sequence data as input; acquiring historical data features of the influence factor data and real-time data features of the real-time data by using the trained neural network model, and determining the running state of the current reactive compensation mechanism through feature matching. The instantaneous power and the compensation capacity of the reactive compensation mechanism in the current operation state and the difference value between the instantaneous power under the current compensation capacity and the instantaneous power sampling value are calculated respectively, and a reactive compensation adjustment strategy of the power distribution network is determined according to the comparison result of the difference value calculation result and the reactive power given value under the current voltage.

Description

Technical Field

[0001] The present invention relates to the technical field of reactive power compensation for distribution networks, and in particular to a reactive power compensation control method and system for distribution networks based on multi-source data analysis. Background Art

[0002] With the current distribution network having a wide variety of distributed power generation installed capacity, the proportion of power generation installed capacity mainly based on photovoltaics and supplemented by energy storage, hydropower, wind power, biomass power generation, etc. has increased, and the complexity of the distribution network system has also increased accordingly, which has put forward higher requirements for grid reactive power regulation and power quality control.

[0003] Due to the increase in the proportion of distributed photovoltaic access in some local areas, the load sent down by the power grid has been greatly reduced, resulting in significant changes in the load characteristics of many distribution network lines. The operating characteristics of the distribution network are highly volatile. The traditional reactive compensation control strategy of the distribution network does not dynamically match the reactive compensation mechanism under the high-frequency variable operating characteristics. During the operation of the reactive compensation mechanism of the distribution network, there are often continuous overcompensation, step-up and step-down power output situations, which makes it difficult to achieve coordinated control of the reactive compensation of the distribution network and its own operating power, resulting in a deviation between the control result and the required target quantity. The accuracy and intelligence of the control are low, and it cannot meet the increasingly complex distribution network dispatching needs. To this end, we propose a reactive compensation control method and system for distribution networks based on multi-source data analysis. Summary of the invention

[0004] The main purpose of the present invention is to provide a distribution network reactive power compensation control method and system based on multi-source data analysis, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] The reactive power compensation control method of distribution network based on multi-source data analysis includes:

[0007] Step 1: Obtain the node operation data, main user side voltage data, and power factor λ of the control area at the same time t within the monitoring period T. t , according to the power factor λ t Construct the running state judgment function f1(λ t ) and f2(λ t ), using the function value to classify the operating status of the reactive power compensation mechanism in the period from t to t+1 within the current monitoring period T;

[0008] Operation status judgment function f1(λ t ) is:

[0009]

[0010] Operation status judgment function f2(λ t ) is:

[0011]

[0012] Where, t, t+1∈T; N is the number of data sampling times within the monitoring period T;

[0013] The operating status includes:

[0014] The first operating state in which the power factor increases steadily;

[0015] The second operating state in which the power factor is steadily decreasing;

[0016] A third operating state in which the power factor remains unchanged;

[0017] a fourth operating state in which the power factor fluctuates and increases;

[0018] The fifth operating state is one in which the power factor fluctuates and decreases.

[0019] The classification principles of the operating status are:

[0020] When f1(λ t )=-1, and f2(λ t )=1, the operating state is the first operating state in which the power factor increases steadily;

[0021] When f1(λ t )=1, and f2(λ t )=1, the operating state is the second operating state in which the power factor decreases steadily;

[0022] When f1(λ t )=0, the operating state is the third operating state in which the power factor remains unchanged;

[0023] When f1(λ t )=-1, and f2(λ t )=-1, the operating state is the fourth operating state in which the power factor fluctuates and increases;

[0024] When f1(λ t )=1, and f2(λ t )=-1, the operating state is the fifth operating state in which the power factor fluctuates and decreases.

[0025] Step 2: Taking the node operation data and the main user side voltage data as influencing factors, the correlation analysis between the influencing factors and the power factor of the reactive power compensation mechanism is performed to obtain the correlation coefficient r between the i-th influencing factor and the power factor of the reactive power compensation mechanism under different operating conditions.i ;

[0026] Step 3: Extract the time series data of various influencing factors of the reactive compensation mechanism under different operating conditions for preprocessing, build a recurrent neural network model with the preprocessed time series data as input, train the neural network model, and use the trained neural network model to obtain the historical data characteristics of the influencing factor data It is expressed as the jth historical data feature of the i-th influencing factor under the k-th operating state;

[0027] Among them, the output layer of the trained neural network model is removed and the last hidden layer is retained to obtain the historical data characteristics of the i-th influencing factor data.

[0028] Step 4: Obtain the real-time data of the influencing factors, and use the neural network model to extract the real-time data features x of the real-time data ij , x ij The jth real-time data feature represented as the i-th influencing factor is matched with the historical data feature, and the current operating state of the reactive power compensation mechanism is determined according to the matching result;

[0029] The determination process includes:

[0030] Step S41: Calculate the real-time data features x respectively ij and the historical data characteristics of the kth operating state The feature matching degree between The calculation formula is:

[0031] Step S42: Obtain the matching degree of each feature The maximum value among the calculated results in, k=1,2,...,K; K is the type of operation status;

[0032] Step S43: Taking the maximum feature matching degree as the The corresponding operating state is used as the current operating state of the reactive power compensation mechanism.

[0033] Step 5: Calculate the instantaneous power s and compensation capacity Q of the reactive power compensation mechanism under the current operating state respectively c , calculate the difference △s between the instantaneous power under the compensation capacity in the current operating state and the instantaneous power sampling value s', where △s = s-s', compare the calculated result of the difference △s with the reactive power given value Q under the current voltage, and determine the reactive compensation adjustment strategy of the distribution network according to the comparison result;

[0034] The principle for determining the reactive power set value Q is:

[0035]

[0036] Q max is the maximum reactive output value of the reactive compensation mechanism; U1, U2, U3, and U4 are all voltage per unit values, and U1<U2<U3<U4; U is the voltage value of the reactive compensation mechanism;

[0037] Compensation capacity Q c The calculation formula is:

[0038]

[0039] Where, β is the average load rate of the substation within the monitoring period T; P max is the average power and power consumption of the electrical equipment in the control area; is the load power factor angle before reactive power compensation; is the load power factor angle after reactive power compensation.

[0040] The principles for determining the reactive power compensation adjustment strategy of the distribution network are:

[0041] If △s>Q, the reactive compensation power of the distribution network is adjusted in the direction of reduction;

[0042] If △s<Q, the reactive compensation power of the distribution network will be adjusted in the direction of increasing.

[0043] Distribution network reactive power compensation control system based on multi-source data analysis, including:

[0044] Used to obtain the node operation data, main user side voltage data, power factor λ of the control area at the same time t within the monitoring period T t Data acquisition module;

[0045] Used to obtain the power factor λ t Construct the running state judgment function f1(λ t ) and f2(λ t ), an operation status classification module for classifying the operation status of the reactive power compensation mechanism in the period from t to t+1 within the current monitoring period T using a function value;

[0046] Used to obtain the correlation coefficient r between the i-th influencing factor and the power factor of the reactive compensation mechanism under different operating conditions i Data association analysis module;

[0047] Historical data features used to obtain influencing factor data and real-time data features x ij Feature extraction module;

[0048] An operating state determination module for performing feature matching between the real-time data features and the historical data features, and determining the current operating state of the reactive power compensation mechanism according to the matching result;

[0049] Used to calculate the instantaneous power s and compensation capacity Q of the reactive power compensation mechanism in the current operating state c Current state quantity acquisition module;

[0050] The module is used to calculate the difference △s between the instantaneous power under the compensation capacity in the current operating state and the instantaneous power sampling value s', and compare the calculated result of the difference △s with the reactive power given value Q under the current voltage, and determine the reactive compensation adjustment strategy of the distribution network according to the comparison result.

[0051] The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0052] The present invention has the following beneficial effects:

[0053] Compared with the prior art, by acquiring multi-source data of the control area at the same time in the monitoring cycle, including node operation data, main user side voltage data, and power factor, the operation state of the current reactive power compensation mechanism is classified using the operation state judgment function value, and the node operation data and the main user side voltage data are used as influencing factors. The correlation analysis between the influencing factors and the power factor of the reactive power compensation mechanism is performed, and the correlation coefficient between the influencing factors and the power factor of the reactive power compensation mechanism under different operation states is obtained. A recurrent neural network model with preprocessed time series data as input is constructed, and the influencing factors are obtained using the trained neural network model. The historical data features of the data and the real-time data features of the real-time data are used to determine the current operating status of the reactive compensation mechanism by performing feature matching, and the instantaneous power and compensation capacity of the reactive compensation mechanism in the current operating state and the difference between the instantaneous power and the instantaneous power sampling value under the current compensation capacity are calculated respectively. According to the comparison result of the difference calculation result with the reactive power given value under the current voltage, the reactive compensation adjustment strategy of the distribution network is determined, which can realize the coordinated control of the reactive compensation of the distribution network and its own operating power, reduce the deviation between the control result and the required target quantity, improve the accuracy and intelligence of the control, and meet the increasingly complex distribution network scheduling needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flow chart of the reactive power compensation control method of the distribution network based on multi-source data analysis of the present invention;

[0055] Figure 2 It is a structural diagram of the reactive power compensation control system of the distribution network based on multi-source data analysis of the present invention. DETAILED DESCRIPTION

[0056] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0057] The specific implementation process of the technical solution of the present invention includes the following steps:

[0058] Step 1: Obtain the node operation data, main user side voltage data, and power factor λ of the control area at the same time t within the monitoring period T. t .

[0059] Step 2: According to the obtained power factor λ t Construct the running state judgment function f1(λ t ) and f2(λ t ), the function value is used to classify the operating status of the reactive power compensation mechanism in the period from t to t+1 within the current monitoring period T, and the operating status includes: a first operating status in which the power factor increases steadily; a second operating status in which the power factor decreases steadily; a third operating status in which the power factor remains unchanged; a fourth operating status in which the power factor increases in a fluctuating manner; and a fifth operating status in which the power factor decreases in a fluctuating manner.

[0060] Among them, the running state judgment function f1(λ t ) is:

[0061]

[0062] Operation status judgment function f2(λ t ) is:

[0063]

[0064] Where, t, t+1∈T; N is the number of data sampling times within the monitoring period T;

[0065] The classification principles of operating status are:

[0066] When f1(λ t )=-1, and f2(λ t )=1, the operating state is the first operating state in which the power factor increases steadily;

[0067] When f1(λ t )=1, and f2(λ t )=1, the operating state is the second operating state in which the power factor decreases steadily;

[0068] When f1(λ t )=0, the operating state is the third operating state in which the power factor remains unchanged;

[0069] When f1(λ t )=-1, and f2(λ t )=-1, the operating state is the fourth operating state in which the power factor fluctuates and increases;

[0070] When f1(λ t )=1, and f2(λ t )=-1, the operating state is the fifth operating state in which the power factor fluctuates and decreases.

[0071] Step 3: Take the node operation data and the main user side voltage data as influencing factors, conduct correlation analysis between the influencing factors and the power factor of the reactive power compensation mechanism, and obtain the correlation coefficient r between the i-th influencing factor and the power factor of the reactive power compensation mechanism under different operating conditions. i ;

[0072] The steps of association analysis include:

[0073] Step S31: Determine the parent sequence and the characteristic sequence;

[0074] Generally, the parent sequence is composed of target performance, which is a data sequence reflecting the characteristic factors of target performance; the characteristic sequence is composed of all influencing factors, which is a data sequence affecting the characteristic factors of target performance; therefore, the time series data of the power factor of the reactive compensation mechanism is used as the parent sequence, and the time series data of the influencing factors is used as the characteristic sequence;

[0075] Step S32: performing standardization processing on each data in the data sequence;

[0076] The processing formula is: Among them, e h is the hth data value in the parent sequence; E h is the standardized value of the hth data in the parent sequence; is the mean of the data in the parent sequence; f qh is the hth data value of the qth type of data in the feature sequence; F qh is the standardized value of the hth data of the qth category in the feature sequence; is the mean of the qth type of data in the feature sequence;

[0077] Step S33: Calculate the correlation coefficient ξ of all data points in the data sequence qh ;

[0078] The calculation formula is:

[0079]

[0080] In the formula,

[0081] To obtain |E h -F qh |After calculating the minimum value of the result, take the minimum value of all calculated minimum values;

[0082] To obtain |E h -F qh |After calculating the maximum value of the result, take the maximum value of all the calculated maximum values; ρ is the resolution coefficient, and its value range is (0,1];

[0083] Step S34: Calculate the correlation value according to the calculation result of the correlation coefficient, and the calculation formula is:

[0084]

[0085] In the formula, R q is the correlation coefficient between the qth influencing factor and the power factor of the reactive power compensation mechanism; Q is the type of influencing factor.

[0086] Step 4: Extract the time series data of various influencing factors of the reactive power compensation mechanism under different operating conditions for preprocessing; the preprocessing method includes:

[0087] Linear Normalization

[0088] Linearly scale the time series data range to a specific interval, usually [0,1] or [-1,1]. The calculation formula is: Where X is the original data, X min and X max are the minimum and maximum values ​​of the band respectively.

[0089] Z-score normalization

[0090] By standardizing the time series data, its mean is 0 and its variance is 1. The calculation formula is: Where μ is the mean of the band and σ is the standard deviation of the band.

[0091] Step 5: Build a recurrent neural network model with preprocessed time series data as input, train the neural network model, and use the trained neural network model to obtain the historical data features of the influencing factor data It is expressed as the jth historical data feature of the i-th influencing factor under the k-th operating state;

[0092] Among them, a long short-term memory network or a gated recurrent control unit is usually used as the basic unit of the recurrent neural network model, and the preprocessed time series data is passed to the RNN layer. During the training process, the parameters of the model are adjusted, and a number of data are selected to verify the adjusted model to improve the accuracy and generalization ability of the model. On the trained recurrent neural network model, the output layer of the trained neural network model is removed and the last hidden layer is retained to obtain the historical data characteristics of the i-th influencing factor data.

[0093] Step 6: Obtain real-time data of influencing factors and use the neural network model to extract real-time data features x ij , x ij It is represented as the jth real-time data feature of the i-th influencing factor;

[0094] Step 7: Match the real-time data features with the historical data features, and determine the current operating status of the reactive power compensation mechanism according to the matching results;

[0095] The specific process includes:

[0096] Step S71: Calculate the real-time data features x respectively ij and the historical data characteristics of the kth operating state The feature matching degree between The calculation formula is:

[0097] Step S72: Obtain the matching degree of each feature The maximum value among the calculated results in, k=1,2,...,K; K is the type of operation status;

[0098] Step S73: Taking the maximum feature matching degree as the The corresponding operating state is used as the operating state of the current reactive power compensation mechanism.

[0099] Step 8: Calculate the instantaneous power s and compensation capacity Q of the reactive power compensation mechanism under the current operating state respectively c ;

[0100] Compensation capacity Q c The calculation formula is:

[0101]

[0102] Where, β is the average load rate of the substation within the monitoring period T; P max is the average power and power consumption of the electrical equipment in the control area; is the load power factor angle before reactive power compensation; is the load power factor angle after reactive power compensation.

[0103] Step 9: Calculate the difference △s between the instantaneous power at the compensation capacity in the current operating state and the instantaneous power sampling value s', where △s = s-s';

[0104] Step 10: Compare the calculated result of the difference △s with the reactive power given value Q under the current voltage, and determine the reactive power compensation adjustment strategy of the distribution network according to the comparison result;

[0105] Among them, the determination principle of reactive power set value Q is:

[0106]

[0107] Q max is the maximum reactive output value of the reactive compensation mechanism; U1, U2, U3, and U4 are all voltage per unit values, and U1<U2<U3<U4; U is the voltage value of the reactive compensation mechanism;

[0108] The principles for determining the reactive power compensation adjustment strategy of the distribution network are:

[0109] If △s>Q, the reactive compensation power of the distribution network is adjusted in the direction of reduction;

[0110] If △s<Q, the reactive compensation power of the distribution network will be adjusted in the direction of increasing.

[0111] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A reactive power compensation control method for a distribution network based on multi-source data analysis, characterized in that: include: Step 1: Obtain the node operation data, main user side voltage data, and power factor λ of the control area at the same time t within the monitoring period T. t , according to the power factor λ t Construct the running state judgment function f1(λ t ) and f2(λ t ), using the function value to classify the operating status of the reactive power compensation mechanism in the period from t to t+1 within the current monitoring period T; Step 2: Taking the node operation data and the main user side voltage data as influencing factors, the correlation analysis between the influencing factors and the power factor of the reactive power compensation mechanism is performed to obtain the correlation coefficient r between the i-th influencing factor and the power factor of the reactive power compensation mechanism under different operating conditions. i ; Step 3: Extract the time series data of various influencing factors of the reactive compensation mechanism under different operating conditions for preprocessing, build a recurrent neural network model with the preprocessed time series data as input, train the neural network model, and use the trained neural network model to obtain the historical data characteristics of the influencing factor data It is expressed as the jth historical data feature of the i-th influencing factor under the k-th operating state; Step 4: Obtain the real-time data of the influencing factors, and use the neural network model to extract the real-time data features x of the real-time data ij , x ij The jth real-time data feature represented as the i-th influencing factor is matched with the historical data feature, and the current operating state of the reactive power compensation mechanism is determined according to the matching result; Step 5: Calculate the instantaneous power s and compensation capacity Q of the reactive power compensation mechanism under the current operating state respectively c , calculate the difference △s between the instantaneous power under the compensation capacity in the current operating state and the instantaneous power sampling value s', where △s = s-s', compare the calculated result of the difference △s with the reactive power given value Q under the current voltage, and determine the reactive compensation adjustment strategy of the distribution network according to the comparison result.

2. The reactive power compensation control method for distribution network based on multi-source data analysis according to claim 1 is characterized in that: Operation status judgment function f1(λ t ) is: Operation status judgment function f2(λ t ) is: Where, t, t+1∈T; N is the number of data sampling times within the monitoring period T.

3. The reactive power compensation control method for distribution network based on multi-source data analysis according to claim 1 is characterized in that: The operating status includes: The first operating state in which the power factor increases steadily; The second operating state in which the power factor is steadily decreasing; A third operating state in which the power factor remains unchanged; a fourth operating state in which the power factor fluctuates and increases; The fifth operating state is one in which the power factor fluctuates and decreases.

4. The reactive power compensation control method for distribution network based on multi-source data analysis according to claim 1, characterized in that: The classification principles of the operating status are: When f1(λ t )=-1, and f2(λ t )=1, the operating state is the first operating state in which the power factor increases steadily; When f1(λ t )=1, and f2(λ t )=1, the operating state is the second operating state in which the power factor decreases steadily; When f1(λ t )=0, the operating state is the third operating state in which the power factor remains unchanged; When f1(λ t )=-1, and f2(λ t )=-1, the operating state is the fourth operating state in which the power factor fluctuates and increases; When f1(λ t )=1, and f2(λ t )=-1, the operating state is the fifth operating state in which the power factor fluctuates and decreases.

5. The reactive power compensation control method for distribution network based on multi-source data analysis according to claim 1, characterized in that: The principle for determining the reactive power set value Q is: Q max It is the maximum reactive output value of the reactive compensation mechanism; U1, U2, U3, and U4 are all voltage standard values, and U1<U2<U3<U4; U is the voltage value of the reactive compensation mechanism.

6. The reactive power compensation control method for distribution network based on multi-source data analysis according to claim 1, characterized in that: Compensation capacity Q c The calculation formula is: Where, β is the average load rate of the substation within the monitoring period T; P max is the average power and power consumption of the electrical equipment in the control area; is the load power factor angle before reactive power compensation; is the load power factor angle after reactive power compensation.

7. The reactive power compensation control method for distribution network based on multi-source data analysis according to claim 1, characterized in that: In step 4, the process of determining the operating status of the current reactive power compensation mechanism includes: Step S41: Calculate the real-time data features x respectively ij and the historical data characteristics of the kth operating state The feature matching degree between The calculation formula is: Step S42: Obtain the matching degree of each feature The maximum value among the calculated results in, k=1,2,...,K; K is the type of operation status; Step S43: Taking the maximum feature matching degree as the The corresponding operating state is used as the current operating state of the reactive power compensation mechanism.

8. The reactive power compensation control method for distribution network based on multi-source data analysis according to claim 1, characterized in that: The principles for determining the reactive power compensation adjustment strategy of the distribution network are: If △s>Q, the reactive compensation power of the distribution network is adjusted in the direction of reduction; If △s<Q, the reactive compensation power of the distribution network will be adjusted in the direction of increasing.

9. A reactive power compensation control system for a distribution network based on multi-source data analysis, characterized in that: The system is used to implement the steps of the reactive power compensation control method for a distribution network based on multi-source data analysis according to any one of claims 1 to 8, including: Used to obtain the node operation data, main user side voltage data, power factor λ of the control area at the same time t within the monitoring period T t Data acquisition module; Used to obtain the power factor λ t Construct the running state judgment function f1(λ t ) and f2(λ t ), an operation status classification module for classifying the operation status of the reactive power compensation mechanism in the period from t to t+1 within the current monitoring period T using a function value; Used to obtain the correlation coefficient r between the i-th influencing factor and the power factor of the reactive compensation mechanism under different operating conditions i Data association analysis module; Historical data features used to obtain influencing factor data and real-time data features x ij Feature extraction module; An operating state determination module for performing feature matching between the real-time data features and the historical data features, and determining the current operating state of the reactive power compensation mechanism according to the matching result; Used to calculate the instantaneous power s and compensation capacity Q of the reactive power compensation mechanism in the current operating state c Current state quantity acquisition module; The module is used to calculate the difference △s between the instantaneous power under the compensation capacity in the current operating state and the instantaneous power sampling value s', and compare the calculated result of the difference △s with the reactive power given value Q under the current voltage, and determine the reactive compensation adjustment strategy of the distribution network according to the comparison result.

10. The distribution network reactive power compensation control system based on multi-source data analysis according to claim 9, characterized in that: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of any one of claims 1-8 of the reactive power compensation control method for a distribution network based on multi-source data analysis when executing the program.

Images