Load prediction method and system based on distribution transformer district under multiple loads

Abstract

The invention discloses a load prediction method and system based on a distribution transformer district under multiple loads, and the method comprises the following steps: dividing the prediction time of a to-be-tested distribution transformer district into 12 time periods according to months; performing statistics on historical power data in each time period; performing statistics on historical meteorological data in each time period; performing data processing based on the historical power data and the historical meteorological data, and outputting a predicted average load P of the transformer area under multiple loads; performing load prediction analysis according to the predicted average load P, and outputting a prediction analysis result; according to the invention, based on the historical power utilization data of the distribution transformer district and the number of the newly added charging piles, the influence of photovoltaic, wind power and other load sides is considered at the same time, the change of the distribution transformer load rate under multiple loads is combined with the historical data, and the accuracy and reliability of power load prediction of the distribution transformer district are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution of power grids, and in particular to a load prediction method and system based on a distribution transformer area under multiple loads. Background Art

[0002] As the types of electrical equipment increase day by day, and more and more loads such as photovoltaic, wind power, and charging cars are connected, the distribution area is overloaded. Especially during the peak summer period, affected by charging cars, the power load level basically reaches the highest peak in a year, and serious overload is prone to occur. If a fault occurs, the daily electricity consumption of residents will be greatly affected.

[0003] A relatively accurate power load forecast is a technical means to effectively solve the problem of overload in the distribution area. By analyzing the historical data of the distribution area, it can make early predictions, so that the power system can be prepared and laid out in advance to avoid heavy overload in the distribution area. Therefore, it is necessary to study related technologies to ensure the quality of power supply and electricity experience of residents. Summary of the invention

[0004] The purpose of the present invention is to provide a load prediction method and system based on distribution transformer substations under multiple loads, so as to more accurately predict the power load and thus ensure the power supply quality and electricity consumption experience of residents.

[0005] To achieve the purpose of the present invention, the technical solution provided by the present invention is as follows:

[0006] First aspect

[0007] The present invention provides a load prediction method based on a distribution transformer area under multiple loads, comprising the following steps:

[0008] Step S1: Divide the prediction time of the distribution transformer area to be tested into 12 time periods according to the month;

[0009] Step S2: Count the historical power data in each time period, the historical power data includes the daily average load P t , Photovoltaic access load P pv 、Wind power access load P dwg、 Charging pile load P c ;

[0010] Step S3: Count the historical meteorological data in each time period, the historical meteorological data includes the highest temperature T in the time period max , average temperature during the period T t , the lowest temperature during the period T min ;

[0011] Step S4: Based on the historical power data and historical meteorological data, data processing is performed to output the predicted average load P of the substation under multiple loads;

[0012] Step S5: Perform load forecasting analysis according to the predicted average load P, and output the forecasting analysis result; specifically including:

[0013] Step S5.1: Calculate the line current i according to the predicted average load P t_j_m , the formula is as follows:

[0014]

[0015] Where Ve is the rated voltage of the system;

[0016] Step S5.2: According to the line current i t_j_m , and conduct predictive analysis, as follows:

[0017]

[0018] Where m is the number of loads, i is l is the statistical current of each line, l is the number of lines in the substation, N ij_m is the number of line contacts;

[0019] Let N ij_m =(l-1)-N, N is the iteration value, when the value is 1 to m, the iterative judgment is performed under the premise of satisfying the above formula:

[0020] When l-1=N, N ij_m <0, since the minimum number of line connections is 0, at this time the line has no connection, then this state has the most variable load combinations to meet the connection requirements, and the number of connections needs to be increased. Therefore, the conversion requirement change of line capacity is the largest, and the number of connections needs to be increased;

[0021] When l-1<N, the number of contacts is positive. In this case, P is used as the prediction result, but it is not the optimal solution.

[0022] When l-1=N, there is no need to reserve capacity space for subsequent loads and there is no need to perform optimization iterations on the line. At this time, P is the optimal solution.

[0023] The predicted average load P is calculated by the following steps, specifically including:

[0024] Step S4.1: Calculate the load growth rate k1 in each time period;

[0025]

[0026] In the formula, j represents the number of months, and t is 12;

[0027] Step S4.2: Calculate the comprehensive load growth rate k2;

[0028]

[0029] Step S4.3: Calculate the load growth rate k3 considering the ambient meteorological conditions;

[0030]

[0031] Step S4.4: Calculate the predicted average load P of the area under multiple loads based on k1, k2, and k3.

[0032] Wherein, in the step S4.4, the predicted average load P is calculated by the following formula:

[0033] P=(1+k1+k2+k3)P t .

[0035] Second aspect

[0036] Corresponding to the above method, the present invention provides a load prediction system based on a distribution transformer area under multiple loads, comprising the following units: a time period division unit, a historical power data statistics unit, a historical meteorological data statistics unit, a predicted average load calculation unit, and a load prediction analysis unit;

[0037] The time period division unit is used to divide the predicted time of the distribution transformer area to be tested into 12 time periods according to the month;

[0038] The historical power data statistics unit is used to count the historical power data in each time period, and the historical power data includes the daily average load P t , Photovoltaic access load P pv 、Wind power access load P dwg、 Charging pile load P c ;

[0039] The historical meteorological data statistics unit is used to count the historical meteorological data in each time period, and the historical meteorological data includes the highest temperature T in the time period. max , average temperature during the period T t , the lowest temperature during the period T min ;

[0040] The predicted average load calculation unit is used to perform data processing based on the historical power data and historical meteorological data, and output the predicted average load P of the substation under multiple loads;

[0041] The load forecasting and analysis unit is used to perform load forecasting and analysis according to the predicted average load P, and output the forecasting and analysis result; specifically includes:

[0042] Step S5.1: Calculate the line current i according to the predicted average load P t_j_m , the formula is as follows:

[0043]

[0044] Where Ve is the rated voltage of the system;

[0045] Step S5.2: According to the line current i t_j_m , and conduct predictive analysis, as follows:

[0046]

[0047] Where m is the number of loads, i l is the statistical current of each line, l is the number of lines in the substation, N ij_m is the number of line contacts;

[0048] Let N ij_m =(l-1)-N, N is the iteration value, when the value is 1 to m, the iterative judgment is performed under the premise of satisfying the above formula:

[0049] When l-1=N, N ij_m <0, since the minimum number of line connections is 0, at this time the line has no connection, then this state has the most variable load combinations to meet the connection requirements, and the number of connections needs to be increased. Therefore, the conversion requirement change of line capacity is the largest, and the number of connections needs to be increased;

[0050] When l-1<N, the number of contacts is positive. In this case, P is used as the prediction result, but it is not the optimal solution.

[0051] When l-1=N, there is no need to reserve capacity space for subsequent loads and there is no need to perform optimization iterations on the line. At this time, P is the optimal solution.

[0052] The predicted average load P is calculated by the following steps, specifically including:

[0053] Step S4.1: Calculate the load growth rate k1 in each time period;

[0054]

[0055] In the formula, j represents the number of months, and t is 12;

[0056] Step S4.2: Calculate the comprehensive load growth rate k2;

[0057]

[0058] Step S4.3: Calculate the load growth rate k3 considering the ambient meteorological conditions;

[0059]

[0060] Step S4.4: Calculate the predicted average load P of the area under multiple loads based on k1, k2, and k3.

[0061] Wherein, in the step S4.4, the predicted average load P is calculated by the following formula:

[0062] P=(1+k1+k2+k3)P t .

[0063] Compared with the prior art, the power load prediction method for the distribution transformer area described in the present invention is based on the historical power consumption data of the distribution transformer area and the number of newly added charging piles, while taking into account the influence of load sides such as photovoltaic and wind power, and combining the changes in the load rate of the distribution transformer under multiple loads with the historical data, thereby improving the accuracy and reliability of the power load prediction in the distribution transformer area, providing a basis for the later power grid adjustment, power capacity expansion, new connections, power dispatching, accident prevention, etc., and taking load prediction as the starting point to ensure the quality and reliability of users' power consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic diagram of a method flow chart provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] like Figure 1 As shown, this embodiment provides a load prediction method based on a distribution transformer area under multiple loads, including the following steps:

[0067] Step S1: Divide the prediction time of the distribution transformer area to be tested into 12 time periods according to the month;

[0068] Step S2: Count the historical power data in each time period, the historical power data includes the daily average load P t , Photovoltaic access load P pv 、Wind power access load P dwg、 Charging pile load P c ;

[0069] Step S3: Count the historical meteorological data in each time period, the historical meteorological data includes the highest temperature T in the time period max , average temperature during the period T t , the lowest temperature during the period T min ;

[0070] Step S4: Based on the historical power data and historical meteorological data, data processing is performed to output the predicted average load P of the substation under multiple loads;

[0071] The predicted average load P is calculated by the following steps, specifically including:

[0072] Step S4.1: Calculate the load growth rate k1 in each time period;

[0073]

[0074] In the formula, j represents the number of months, and t is 12;

[0075] Step S4.2: Calculate the comprehensive load growth rate k2;

[0076]

[0077] Step S4.3: Calculate the load growth rate k3 considering the ambient meteorological conditions;

[0078]

[0079] Step S4.4: Calculate the predicted average load P of the area under multiple loads based on k1, k2, and k3.

[0080] Wherein, in the step S4.4, the predicted average load P is calculated by the following formula:

[0081] P=(1+k1+k2+k3)P t .

[0083] Step S5: Perform load forecasting analysis according to the predicted average load P, and output the forecasting analysis result; specifically including:

[0084] Step S5.1: Calculate the line current i according to the predicted average load P t_j_m , the formula is as follows:

[0085]

[0086] Where Ve is the rated voltage of the system;

[0087] Step S5.2: According to the line current it_j_m , and conduct predictive analysis, as follows:

[0088]

[0089] Where m is the number of loads, i is l is the statistical current of each line, l is the number of lines in the substation, N ij_m is the number of line contacts;

[0090] Let N ij_m =(l-1)-N, N is the iteration value, when the value is 1 to m, the iterative judgment is performed under the premise of satisfying the above formula:

[0091] When l-1=N, N ij_m <0, since the minimum number of line connections is 0, at this time the line has no connection, then this state has the most variable load combinations to meet the connection requirements, and the number of connections needs to be increased. Therefore, the conversion requirement change of line capacity is the largest, and the number of connections needs to be increased;

[0092] When l-1<N, the number of contacts is positive. In this case, P is used as the prediction result, but it is not the optimal solution.

[0093] When l-1=N, there is no need to reserve capacity space for subsequent loads and there is no need to perform optimization iterations on the line. At this time, P is the optimal solution.

[0094] Second aspect

[0095] Corresponding to the above method, the present invention provides a load prediction system based on a distribution transformer area under multiple loads, comprising the following units: a time period division unit, a historical power data statistics unit, a historical meteorological data statistics unit, a predicted average load calculation unit, and a load prediction analysis unit;

[0096] The time period division unit is used to divide the predicted time of the distribution transformer area to be tested into 12 time periods according to the month;

[0097] The historical power data statistics unit is used to count the historical power data in each time period, and the historical power data includes the daily average load P t , Photovoltaic access load P pv 、Wind power access load P dwg、 Charging pile load P c ;

[0098] The historical meteorological data statistics unit is used to count the historical meteorological data in each time period, and the historical meteorological data includes the highest temperature T in the time period. max , average temperature during the period T t , the lowest temperature during the period T min ;

[0099] The predicted average load calculation unit is used to perform data processing based on the historical power data and historical meteorological data, and output the predicted average load P of the substation under multiple loads;

[0100] The predicted average load P is calculated by the following steps, specifically including:

[0101] Step S4.1: Calculate the load growth rate k1 in each time period;

[0102]

[0103] In the formula, j represents the number of months, and t is 12;

[0104] Step S4.2: Calculate the comprehensive load growth rate k2;

[0105]

[0106] Step S4.3: Calculate the load growth rate k3 considering the ambient meteorological conditions;

[0107]

[0108] Step S4.4: Calculate the predicted average load P of the area under multiple loads based on k1, k2, and k3.

[0109] Wherein, in the step S4.4, the predicted average load P is calculated by the following formula:

[0110] P=(1+k1+k2+k3)P t .

[0111] The load forecasting and analysis unit is used to perform load forecasting and analysis according to the predicted average load P, and output the forecasting and analysis result; specifically includes:

[0112] Step S5.1: Calculate the line current i according to the predicted average load P t_j_m , the formula is as follows:

[0113]

[0114] Where Ve is the rated voltage of the system;

[0115] Step S5.2: According to the line current i t_j_m , and conduct predictive analysis, as follows:

[0116]

[0117] Where m is the number of loads, i lis the statistical current of each line, l is the number of lines in the substation, N ij_m is the number of line contacts;

[0118] Let N ij_m =(l-1)-N, N is the iteration value, when the value is 1 to m, the iterative judgment is performed under the premise of satisfying the above formula:

[0119] When l-1=N, N ij_m <0, since the minimum number of line connections is 0, at this time the line has no connection, then this state has the most variable load combinations to meet the connection requirements, and the number of connections needs to be increased. Therefore, the conversion requirement change of line capacity is the largest, and the number of connections needs to be increased;

[0120] When l-1<N, the number of contacts is positive. In this case, P is used as the prediction result, but it is not the optimal solution.

[0121] When l-1=N, there is no need to reserve capacity space for subsequent loads and there is no need to perform optimization iterations on the line. At this time, P is the optimal solution.

[0122] The power load prediction method for the distribution transformer area described in the present invention is based on the historical power consumption data of the distribution transformer area and the number of newly added charging piles, while taking into account the influence of the load side such as photovoltaic and wind power, and combining the changes in the distribution transformer load rate under multiple loads with the historical data, thereby improving the accuracy and reliability of the power load prediction in the distribution transformer area, providing a basis for the later power grid adjustment, power capacity expansion, additional communication, power dispatching, accident prevention, etc., and taking load prediction as the starting point to ensure the quality and reliability of users' power consumption.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate and explain the present invention, and are not intended to limit the present invention to the scope of the described embodiments. In addition, those skilled in the art can understand that the present invention is not limited to the above embodiments, and more variations and modifications can be made according to the teachings of the present invention, and these variations and modifications all fall within the scope of the protection claimed by the present invention.

Claims

1. A load forecasting method for distribution transformer substations under multiple loads, characterized in that: The following steps are involved: Step S1: Divide the prediction time of the distribution transformer area to be tested into 12 time periods according to the month; Step S2: Count the historical power data in each time period, the historical power data includes the daily average load P t , Photovoltaic access load P pv 、Wind power access load P dwg、 Charging pile load P c ; Step S3: Count the historical meteorological data in each time period, the historical meteorological data includes the highest temperature T in the time period max , average temperature during the period T t , the lowest temperature during the period T min ; Step S4: Based on the historical power data and historical meteorological data, data processing is performed to output the predicted average load P of the substation under multiple loads; Step S5: Perform load forecasting analysis according to the predicted average load P, and output the forecasting analysis result; specifically including: Step S5.1: Calculate the line current i according to the predicted average load P t_j_m , the formula is as follows: Where Ve is the rated voltage of the system; Step S5.2: According to the line current i t_j_m , and conduct predictive analysis, as follows: Where m is the number of loads, i is l is the statistical current of each line, l is the number of lines in the substation, N ij_m is the number of line contacts; Let N ij_m =(l-1)-N, N is the iteration value, when the value is 1 to m, the iterative judgment is performed under the premise of satisfying the above formula: When l-1=N, N ij_m <0, since the minimum number of line connections is 0, at this time the line has no connection, then this state has the most variable load combinations to meet the connection requirements, and the number of connections needs to be increased. Therefore, the conversion requirement change of line capacity is the largest, and the number of connections needs to be increased; When l-1<N, the number of contacts is positive. In this case, P is used as the prediction result, but it is not the optimal solution. When l-1=N, there is no need to reserve capacity space for subsequent loads and there is no need to perform optimization iterations on the line. At this time, P is the optimal solution.

2. A load forecasting method based on distribution transformer area under multiple loads according to claim 1, characterized in that: The predicted average load P is calculated by the following steps, specifically including: Step S4.1: Calculate the load growth rate k1 in each time period; In the formula, j represents the number of months, and t is 12; Step S4.2: Calculate the comprehensive load growth rate k2; Step S4.3: Calculate the load growth rate k3 considering the ambient meteorological conditions; Step S4.4: Calculate the predicted average load P of the area under multiple loads based on k1, k2, and k3.

3. A load forecasting method based on distribution transformer area under multiple loads according to claim 2, characterized in that: In step S4.4, the predicted average load P is calculated by the following formula: P=(1+k1+k2+k3)P t 。 4. A load forecasting system based on distribution transformer substation under multiple loads, characterized in that: It includes the following units: time period division unit, historical power data statistics unit, historical meteorological data statistics unit, predicted average load calculation unit, and load prediction analysis unit; The time period division unit is used to divide the predicted time of the distribution transformer area to be tested into 12 time periods according to the month; The historical power data statistics unit is used to count the historical power data in each time period, and the historical power data includes the daily average load P t , Photovoltaic access load P pv 、Wind power access load P dwg、 Charging pile load P c ; The historical meteorological data statistics unit is used to count the historical meteorological data in each time period, and the historical meteorological data includes the highest temperature T in the time period. max , average temperature during the period T t , the lowest temperature during the period T min ; The predicted average load calculation unit is used to perform data processing based on the historical power data and historical meteorological data, and output the predicted average load P of the substation under multiple loads; The load forecasting and analysis unit is used to perform load forecasting and analysis according to the predicted average load P, and output the forecasting and analysis result; specifically includes: Step S5.1: Calculate the line current i according to the predicted average load P t_j_m , the formula is as follows: Where Ve is the rated voltage of the system; Step S5.2: According to the line current i t_j_m , and conduct predictive analysis, as follows: Where m is the number of loads, i is l is the statistical current of each line, l is the number of lines in the substation, N ij_m is the number of line contacts; Let N ij_m =(l-1)-N, N is the iteration value, when the value is 1 to m, the iterative judgment is performed under the premise of satisfying the above formula: When l-1=N, N ij_m <0, since the minimum number of line connections is 0, at this time the line has no connection, then this state has the most variable load combinations to meet the connection requirements, and the number of connections needs to be increased. Therefore, the conversion requirement change of line capacity is the largest, and the number of connections needs to be increased; When l-1<N, the number of contacts is positive. In this case, P is used as the prediction result, but it is not the optimal solution. When l-1=N, there is no need to reserve capacity space for subsequent loads and there is no need to perform optimization iterations on the line. At this time, P is the optimal solution.

5. A load prediction system based on distribution transformer area under multiple loads according to claim 4, characterized in that: The predicted average load P is calculated by the following steps, specifically including: Step S4.1: Calculate the load growth rate k1 in each time period; In the formula, j represents the number of months, and t is 12; Step S4.2: Calculate the comprehensive load growth rate k2; Step S4.3: Calculate the load growth rate k3 considering the ambient meteorological conditions; Step S4.4: Calculate the predicted average load P of the area under multiple loads based on k1, k2, and k3.

6. A load prediction system based on distribution transformer substations under multiple loads according to claim 5, characterized in that: In step S4.4, the predicted average load P is calculated by the following formula: P=(1+k1+k2+k3)P t 。

Images