Estimation and analysis system for openable capacity of power distribution network line

Abstract

The invention relates to the technical field of power distribution networks, and discloses a power distribution network line openable capacity estimation and analysis system. Comprising the steps of screening out a target line from power distribution network lines, calculating the power supply interval duration of the target line, expanding the power supply interval duration into an estimation period, obtaining capacity estimation data of a to-be-estimated region, estimating the openable capacity of a next sub-interval through a neural network estimation model, selecting a capacity opening mode of the to-be-estimated region, and formulating a capacity opening strategy. Compared with the prior art, the method can avoid the interference influence of a large number of power distribution network lines with extremely small power supply capacity, can accurately estimate the openable capacity of the power distribution network line of the to-be-estimated region at the future moment in advance, can find the abnormal condition of the power distribution network line in advance, and improves the estimation accuracy. And the risk hidden danger of outward excessive power supply caused by insufficient openable capacity of the power distribution network line is avoided, so that the safety of capacity opening operation of the power distribution network line is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution networks, and more particularly to a system for estimating and analyzing the open capacity of distribution network lines. Background Art

[0002] The open capacity of a distribution network line refers to the maximum power load that the distribution line can accept under certain conditions. In order to better optimize the operation of the distribution network, promote the rational development and utilization of distributed new energy, and ensure the safe, stable and economical operation of the distribution network, it is necessary to accurately and reasonably analyze the open capacity of the regional distribution network, and through regular release of the open capacity of the regional power grid, achieve coordinated development of all links in the distribution network and meet the needs of high-quality construction of the power system.

[0003] Patent application with reference publication number CN116702394A discloses a method and device for estimating the available photovoltaic capacity of a distribution network. The method preprocesses collected power system data, constructs a power system model based on the preprocessed power system data, sets preset constraints on the power system model to obtain a model to be calculated, calculates full-time simulation results corresponding to each typical scenario based on preset grid parameters, several typical scenarios, photovoltaic installed capacity, and the model to be calculated, and selects the smallest full-time simulation result as the available photovoltaic capacity.

[0004] When estimating and analyzing the open capacity of the existing distribution network, real-time power data under multiple scenarios and multiple states of the power system is obtained and combined with the model to calculate the current open capacity of the distribution network line. For example, in the above-mentioned patent application, it constructs a power system model based on the preprocessed power system data, calculates the full-time simulation calculation results corresponding to the typical scenario, and realizes the real-time calculation effect of the open capacity. Although it can achieve accurate estimation of the open capacity, the real-time estimation method cannot make an advance estimate of the open capacity of the distribution network line at a future time, so that it is impossible to discover in advance the abnormal phenomenon of reduced open capacity that may occur in the future, and further, it is impossible to formulate corresponding opening strategies in advance for the abnormal phenomenon, resulting in a lag in the estimation and analysis of the open capacity, and the inability to ensure the safety of the open operation of the distribution network line capacity.

[0005] In view of this, the present invention proposes a distribution network line open capacity estimation and analysis system to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned objectives, the present invention provides the following technical solution: a distribution network line open capacity estimation and analysis system, comprising:

[0007] The line screening module is used to identify the power supply attributes of all distribution network lines in the area to be assessed one by one, including long-term power supply, short-term power supply, and ineffective power supply, and screen target lines from the distribution network lines based on the effective power supply criteria;

[0008] The cycle extension module is used to obtain the basic operation and maintenance parameters of the target line, calculate the power supply interval duration of the target line, and extend the power supply interval duration to the estimated cycle;

[0009] The data acquisition module is used to divide the estimation period into continuous sub-intervals and obtain the capacity estimation data of the target line in the sub-interval in the area to be estimated in the power supply mode. The capacity estimation data includes the total installed capacity, maximum power supply load, safety reserve capacity, photovoltaic grid-connected capacity, reported installed capacity and account cancellation capacity;

[0010] A model estimation module is used to input the capacity estimation data into a neural network estimation model for estimating the open capacity, so as to estimate the open capacity of the next subinterval;

[0011] The opening strategy module is used to select the capacity opening mode of the area to be estimated based on the estimated open capacity. The capacity opening modes include unrestricted opening mode, semi-restricted opening mode and fully restricted opening mode, and formulate corresponding capacity opening strategies.

[0012] Furthermore, the identification method of long-term power supply, short-term power supply and invalid power supply includes:

[0013] Query the power database to obtain the line distribution map of the area to be assessed, and mark the A distribution network lines in the line distribution map one by one;

[0014] Using the preset marking interval as the standard, mark B non-adjacent power supply moments, and query the power supply status values ​​of the A distribution network lines at the B power supply moments one by one;

[0015] Count the number of power supply moments with a power supply status value of "1-1" and record it as a power supply high value, and record one third of the number of power supply moments as a power supply critical value;

[0016] When the power supply high value is equal to B, the power supply attribute of the distribution network line is long-term power supply;

[0017] When the power supply critical value is less than or equal to the power supply high value, and the power supply high value is less than B, the power supply attribute of the distribution network line is short-term power supply;

[0018] When the power supply high value is less than the power supply critical value, the power supply attribute of the distribution network line is invalid power supply.

[0019] Furthermore, the effective power supply criterion is: the power supply capacity of the target line is greater than the lower limit of the power supply capacity;

[0020] Target line screening methods include:

[0021] Draw the regional boundary of the area to be assessed on the line distribution map, and mark the two intersection points of the distribution network lines with long-term and short-term power supply attributes and the regional boundary along the power transmission direction as the entry point and exit point respectively;

[0022] Query the real-time power supply load of the entry and export points one by one to obtain the entry capacity and export capacity, and then obtain the power supply capacity by subtracting the entry capacity from the export capacity;

[0023] The distribution network lines whose power supply capacity is greater than the lower limit of the power supply capacity are recorded as target lines, and C target lines are obtained.

[0024] Furthermore, the basic operation and maintenance parameters include the power supply start time and the power supply end time;

[0025] The calculation method of the power supply interval duration includes:

[0026] Query the power database one by one to find D power supply events in which C target lines supply power to the area to be assessed, and find the power supply power at each power supply moment in the D power supply events;

[0027] The power supply start time is recorded as the first time the power supply power exceeds the lower power limit. After the power supply start time, the power supply end time is recorded as the first time the power supply power falls below the lower power limit.

[0028] The duration between the start time and the end time of power supply is recorded as the sub-interval duration, and D sub-interval durations are obtained. The D sub-interval durations are accumulated and averaged to obtain the power supply interval duration;

[0029] The expression for the power supply interval duration is:

[0030]

[0031] Where GD sc SC is the power supply interval duration, zd is the duration of the d-th subinterval.

[0032] Further, the extended methods for estimating the period include:

[0033] The first power supply moment among the D power supply events is recorded as the starting moment, and the power supply power at the starting moment is recorded as the starting power;

[0034] After the starting time, the first time the power supply power is less than the starting time is recorded as the extended time, and the duration between the starting time and the extended time is recorded as the sub-duration, obtaining D sub-durations;

[0035] The maximum value of the sub-durations is recorded as the extended duration, and an extended duration is added to the power supply interval duration to extend the power supply interval duration to the estimated period.

[0036] Furthermore, the method for obtaining the total installed capacity includes:

[0037] In E subintervals, the power generation of the main substations corresponding to the C target lines is queried one by one through the power database to obtain the C main transformer capacities;

[0038] Multiply C main transformer capacities by the corresponding distribution network connection coefficients, and add up the C product values ​​one by one to obtain E total installed capacities;

[0039] The expression for total installed capacity is:

[0040] Where ZJ rle is the total installed capacity of the e-th subinterval, e=1,2...E,ZB rles is the sth main transformer capacity in the eth subinterval, BW xses is the sth distribution network connection coefficient of the eth subinterval.

[0041] Furthermore, the method for obtaining photovoltaic grid-connected capacity includes:

[0042] The power generation status of all photovoltaic power stations in the area to be assessed is identified one by one through the power database, and the photovoltaic power stations with effective power generation status are recorded as target photovoltaic stations, and F target photovoltaic stations are obtained;

[0043] In E subintervals, the total power generation of F target photovoltaic stations is counted one by one to obtain F photovoltaic power generation;

[0044] After accumulating the F photovoltaic power generation amounts one by one, the accumulated value is multiplied by the photovoltaic grid-connected coefficient to obtain E photovoltaic grid-connected capacities;

[0045] The expression of photovoltaic grid-connected capacity is:

[0046]

[0047] Where, GF bwe is the photovoltaic grid-connected capacity of the e-th subinterval, GF XS is the photovoltaic grid-connected coefficient, GF fdef is the f-th photovoltaic power generation in the e-th subinterval.

[0048] Furthermore, the training method of the neural network estimation model includes:

[0049] Collect multiple sets of capacity estimation data and available capacity corresponding to the capacity estimation data in advance;

[0050] The capacity estimation data is converted into multiple feature vectors using a sliding window method. The available capacity is converted into labels corresponding to the capacity estimation data based on the sliding step size. One feature vector corresponds to one label and forms a set of training data. Multiple sets of training data constitute a training set. The capacity estimation data are arranged in the order of collection time, and the prediction time step size Q, sliding step size W, and sliding window length Y are preset.

[0051] The feature vector is used as the input of the model, and the open capacity of the next subinterval after the predicted time step Q is used as the output. The subsequent open capacity of each training set is used as the prediction target. The model is trained with the minimized sum of prediction errors as the training target to generate a neural network estimation model that estimates the open capacity of the next subinterval based on the capacity estimation data of the previous subinterval.

[0052] Furthermore, the selection method of the unrestricted open mode, the semi-restricted open mode and the fully restricted open mode includes:

[0053] The open capacity KF of the next subinterval will be estimated rl and the preset first open threshold KF yz1 and the second open threshold KF yz2 Compare, KF yz1 Less than KF yz2 ;

[0054] When KF rl Less than KF yz1 When you are using the Sync function, select the fully restricted open mode;

[0055] When KF yz1 Less than or equal to KF rl , and KF rl Less than KF yz2 When selecting the semi-restricted open mode;

[0056] When KF rl Greater than or equal to KF yz2 When you open the game, select the unlimited open mode.

[0057] Furthermore, the capacity opening strategy includes a capacity full opening strategy, a capacity semi-opening strategy, and a capacity non-opening strategy;

[0058] Methods for formulating the fully open capacity strategy, the partially open capacity strategy, and the closed capacity strategy include:

[0059] When the capacity opening mode is the fully restricted opening mode, a capacity non-opening strategy is formulated;

[0060] When the capacity opening mode is the semi-restricted opening mode, a capacity semi-opening strategy is formulated;

[0061] When the capacity opening mode is the unlimited opening mode, a capacity full opening strategy is formulated.

[0062] The technical effects and advantages of the system for estimating and analyzing the open capacity of distribution network lines of the present invention are as follows:

[0063] The present invention identifies the power supply attributes of all distribution network lines in the area to be estimated one by one, and selects the target lines from the distribution network lines based on the effective power supply criteria. This can avoid the interference of a large number of distribution network lines with extremely small power supply capacity, and also reduce the subsequent calculation burden. By obtaining the basic operation and maintenance parameters of the target line, the power supply interval of the target line is calculated, and the power supply interval is expanded to the estimation period, which can ensure that the collected relevant data remains reasonable and accurate, and avoids the phenomenon of too much or too little data collection due to too long or too short collection time. At the same time, by obtaining the capacity of the target line in the sub-interval of the area to be estimated By estimating the data and combining it with the neural network estimation model to estimate the open capacity of the next sub-interval, the open capacity of the distribution network lines in the estimated area at the future moment can be estimated in advance and accurately, so that abnormal situations can be discovered in advance when the open capacity of the distribution network lines is about to be too low, and the appropriate capacity opening mode and capacity opening strategy can be selected to perform safe and stable capacity opening operations on the distribution network lines when the open capacity does not meet the standards, avoiding the risk of excessive power supply due to insufficient open capacity of the distribution network lines, thereby ensuring the safety of the capacity opening operation of the distribution network lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic diagram of a module of a distribution network line open capacity estimation and analysis system provided in the first embodiment of the present invention;

[0065] Figure 2 A schematic flow chart of a method for estimating and analyzing the available capacity of distribution network lines provided in the second embodiment of the present invention;

[0066] Figure 3 This is a structural diagram of an electronic device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0067] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0068] Example 1: Please refer to Figure 1As shown, the system for estimating and analyzing the open capacity of distribution network lines described in this embodiment includes:

[0069] The line screening module identifies the power supply attributes of all distribution network lines in the area to be assessed one by one, and selects the target lines from the distribution network lines based on the effective power supply criteria;

[0070] The area to be measured is the area where the distribution network lines for which open capacity estimation analysis is required are located. The power supply attribute is a specific representation of the power supply type of the distribution network lines within the area where the estimated area is located. This allows for an accurate representation of whether all distribution network lines passing through the estimated area are providing power, and provides an analysis basis for whether the distribution network lines are providing power load to the estimated area.

[0071] Power supply attributes include long-term power supply, short-term power supply, and ineffective power supply. Long-term power supply refers to the ability of the distribution network to provide long-term, continuous, and stable power supply to the area to be assessed. Short-term power supply refers to the ability of the distribution network to provide short-term, discontinuous, and intermittent power supply to the area to be assessed. Ineffective power supply refers to the inability of the distribution network to provide sufficient and effective power supply to the area to be assessed.

[0072] Methods for identifying long-term power supply, short-term power supply, and invalid power supply include:

[0073] The line distribution map of the area to be assessed is retrieved from the power database, and the A distribution network lines in the line distribution map are marked one by one. The line distribution map is an electronic map of the layout of all distribution network lines in the area to be assessed, which can provide a basis for the subsequent screening of target lines.

[0074] Using the preset marking interval as the standard, mark B non-adjacent power supply moments, and query the power supply status values ​​of the A distribution network lines at the B power supply moments one by one; the power supply status value is used to numerically indicate whether the distribution network line is currently in a normal and safe power supply state. The power supply status values ​​include "1-1", "1-0", "0-1" and "0-0". When the power supply status value is "1-0", "0-1" and "0-0", the distribution network line is not in a normal and safe power supply state. The preset marking interval is used to indicate the time span between two adjacent power supply moments, which can ensure that the two adjacent power supply moments maintain independence and that the power supply status values ​​of the two adjacent power supply moments are sufficient to change at least once.

[0075] Count the number of power supply moments with a power supply status value of "1-1" and record it as a power supply high value, and record one third of the number of power supply moments as a power supply critical value;

[0076] When the power supply high value is equal to B, it means that the distribution network line is in the power supply state at B power supply moments, and the power supply attribute of the distribution network line is long-term power supply;

[0077] When the power supply critical value is less than or equal to the power supply high value, and the power supply high value is less than B, it means that the distribution network line is in an intermittent power supply state at B power supply moments, and the power supply attribute of the distribution network line is short-term power supply;

[0078] When the power supply high value is less than the power supply critical value, it means that the distribution network line is in an invalid power supply state at B power supply moments, and the power supply attribute of the distribution network line is invalid power supply.

[0079] After obtaining the power supply attributes of the distribution network lines, it is necessary to screen out target lines from the distribution network lines based on the power supply attributes that meet the subsequent estimation and analysis of the available capacity in the estimated area, so that the target lines can serve as the basis for subsequent capacity calculations.

[0080] When selecting target lines, it is necessary to select from the distribution network lines corresponding to long-term and short-term power supply, and ensure that the selected target lines are reasonable and accurate within the constraints of effective power supply criteria;

[0081] The effective power supply criterion is that the power supply capacity of the target line is greater than the lower limit of the power supply capacity. This can avoid the interference effects of a large number of distribution network lines with extremely small power supply capacity, which can be ignored. This reduces the number of target lines and the subsequent calculation burden.

[0082] Target line screening methods include:

[0083] Draw the regional boundary of the area to be assessed on the line distribution map, and mark the two intersection points of the distribution network lines with long-term and short-term power supply attributes and the regional boundary along the power transmission direction as the entry point and exit point respectively;

[0084] Query the real-time power supply load of the entry and export points one by one to obtain the entry capacity and export capacity, and then obtain the power supply capacity by subtracting the entry capacity from the export capacity;

[0085] Distribution network lines with power supply capacities greater than the power supply capacity lower limit are designated as target lines, resulting in C target lines. The power supply capacity lower limit is a numerical representation of the minimum power supply capacity corresponding to the target line, ensuring that the target line's power supply capacity can change at the minimum possible rate.

[0086] The cycle extension module obtains the basic operation and maintenance parameters of the target line, calculates the power supply interval of the target line, and expands the power supply interval into the estimated cycle;

[0087] Basic operation and maintenance parameters refer to the basic data of the target line when it supplies power to the area to be assessed on a daily basis. They can represent the comprehensive power supply situation of the target line, thus providing data support for the subsequent calculation of the effective interval duration.

[0088] Basic operation and maintenance parameters include the power supply start time and power supply end time. The power supply start time refers to the time when the target line first supplies power to the area to be assessed during a power supply event, and the power supply end time refers to the time when the target line last supplies power to the area to be assessed during a power supply event.

[0089] After obtaining the power supply start time and power supply end time, the average power supply duration of each power supply event can be analyzed and calculated based on multiple power supply start times and power supply end times, and the interval duration between two adjacent power supply events can be expressed by the power supply interval duration, which provides a basis for subsequent estimation cycles.

[0090] The calculation method of the power supply interval duration includes:

[0091] Query the power database one by one to find D power supply events in which C target lines supply power to the area to be assessed, and find the power supply power at each power supply moment in the D power supply events;

[0092] The first time the power supply exceeds the lower power limit is recorded as the power supply start time. After the power supply start time, the first time the power supply falls below the lower power limit is recorded as the power supply end time. The lower power limit is the minimum power supply value on the target line that can affect the calculation of the power supply interval, thereby ensuring that the power supply corresponding to the power supply interval is kept within a reasonable range.

[0093] The duration between the start time and the end time of power supply is recorded as the sub-interval duration, and D sub-interval durations are obtained. The D sub-interval durations are accumulated and averaged to obtain the power supply interval duration;

[0094] The expression for the power supply interval duration is:

[0095]

[0096] Where GD sc SC is the power supply interval duration, zd is the duration of the d-th subinterval.

[0097] After calculating the power supply interval, it is necessary to extend it based on the power supply interval to obtain the specific duration of the estimation cycle for the target line in the area to be estimated, ensuring that the duration corresponding to the estimation cycle can fully and accurately include the comprehensive power supply situation of the target line in the area to be estimated;

[0098] Extensions to the estimation cycle include:

[0099] The first power supply moment among the D power supply events is recorded as the starting moment, and the power supply power at the starting moment is recorded as the starting power;

[0100] After the starting time, the first time the power supply power is less than the starting time is recorded as the extended time, and the duration between the starting time and the extended time is recorded as the sub-duration, obtaining D sub-durations;

[0101] The maximum value of the sub-durations is recorded as the extended duration, and an extended duration is added to the power supply interval duration to extend the power supply interval duration to the estimated period.

[0102] It should be noted that after the estimation period is obtained, the estimation period at this time can be used as the data collection time range for the open capacity estimation analysis of the target line in the area to be estimated, thereby ensuring that the collected relevant data can remain in a reasonable and accurate state, and also ensuring that the amount of collected data can be within a reasonable range.

[0103] The data acquisition module divides the estimation period into continuous subintervals and, in power supply mode, obtains capacity estimation data for the target line in the area to be estimated in the subintervals. The capacity estimation data includes total installed capacity, maximum power supply load, safety reserve capacity, PV grid-connected capacity, reported installed capacity, and account cancellation capacity.

[0104] Since the estimation period is the total length of time used to collect data for the target lines in the estimated area over the past period, the estimation period spans a large period and the fluctuation range of the relevant available capacity within the estimation period is also large, resulting in a relatively rough estimation and analysis of the available capacity. To achieve a refined and accurate estimation and analysis, it is necessary to divide the estimation period with a long span into sub-intervals with shorter spans and continuous states on the timeline.

[0105] When dividing the estimation period into subintervals, it is necessary to ensure that any two adjacent subintervals are continuous on the timeline, that is, the last moment of the previous subinterval is the first moment of the next subinterval, and the duration of each subinterval is equal. Finally, the estimation period is divided into E subintervals.

[0106] The power supply mode refers to the target line in the area to be estimated being in a normal power supply mode, thereby ensuring that the subsequent capacity estimation data is collected in a normal and reasonable mode.

[0107] Capacity estimation data refers to comprehensive data on the impact of target lines on the size of available capacity within the sub-interval of the area to be estimated, and serves as the data basis for subsequent available capacity estimation analysis;

[0108] Capacity estimation data includes total installed capacity, maximum power supply load, safety reserve capacity, photovoltaic grid-connected capacity, reported installed capacity and account cancellation capacity;

[0109] The total installed capacity refers to the maximum installed power supply capacity of the C target lines in the estimated area within the E sub-intervals. It can be used to represent the maximum power supply capacity of the estimated area and serve as the basis for subsequent open capacity estimation analysis. The larger the total installed capacity, the larger the open capacity of the estimated area.

[0110] Methods for obtaining total installed capacity include:

[0111] In E subintervals, the power generation of the main substations corresponding to the C target lines is queried one by one through the power database to obtain the C main transformer capacities;

[0112] Multiply C main transformer capacities by the corresponding distribution network connection coefficients, and add up the C product values ​​one by one to obtain E total installed capacities. The distribution network connection coefficient is used to indicate the proportion of the target line's main transformer capacity to the total capacity of the area to be assessed. The distribution network connection coefficient is obtained by querying the power database.

[0113] The expression for total installed capacity is:

[0114]

[0115] Where ZJ rle is the total installed capacity of the e-th subinterval, e=1,2...E,ZB rles is the sth main transformer capacity in the eth subinterval, BW xses is the sth distribution network connection coefficient of the eth subinterval.

[0116] The maximum power supply load refers to the maximum power supply capacity of the C target lines in the area to be estimated within E subintervals, and serves as the capacity data already used in the area to be estimated. When the maximum power supply load is larger, the available capacity of the area to be estimated is smaller; the maximum power supply load is obtained by querying the power database.

[0117] The safety reserve capacity refers to the capacity that needs to be reserved within the E sub-intervals of the C target lines in the area to be assessed to meet the power supply needs in unexpected emergency situations. It serves as the insurmountable safety bottom line of the power supply capacity in the area to be assessed. The larger the safety reserve capacity, the smaller the open capacity in the area to be assessed. The safety reserve capacity is obtained by querying the power database.

[0118] The photovoltaic grid-connected capacity refers to the amount of photovoltaic new energy power supply capacity received by the C target lines in the estimated area within the E sub-intervals. It can be used to represent the power supply capacity of the target lines in the estimated area. The larger the photovoltaic grid-connected capacity, the larger the open capacity of the estimated area.

[0119] Methods for obtaining photovoltaic grid-connected capacity include:

[0120] The power generation status of all photovoltaic power stations in the area to be assessed is identified one by one through the power database, and photovoltaic power stations with effective power generation status are recorded as target photovoltaic stations, obtaining F target photovoltaic stations. The power generation status is used to represent the operating status of the photovoltaic power station, and the power generation status includes effective power generation and ineffective power generation. Effective power generation refers to the photovoltaic power station's good power generation status, and ineffective power generation refers to the photovoltaic power station's poor power generation status.

[0121] In E subintervals, the total power generation of F target photovoltaic stations is counted one by one to obtain F photovoltaic power generation;

[0122] After cumulatively adding up the F photovoltaic power generation amounts, the cumulative value is multiplied by the photovoltaic grid-connection coefficient to obtain E photovoltaic grid-connected capacities. The photovoltaic grid-connection coefficient is used to indicate the extent to which the photovoltaic power station contributes to the total capacity of the area to be assessed. The photovoltaic grid-connection coefficient is obtained by querying the power database.

[0123] The expression of photovoltaic grid-connected capacity is:

[0124]

[0125] Where, GF bwe is the photovoltaic grid-connected capacity of the e-th subinterval, GF xs is the photovoltaic grid-connected coefficient, GF fdef is the f-th photovoltaic power generation in the e-th subinterval.

[0126] The reported installed capacity refers to the power supply capacity of C target lines in the area to be estimated that have been reported and prepared for installation for power generation within E subintervals. It can be used to represent the power supply capacity that will be generated in the area to be estimated. The larger the reported installed capacity, the larger the open capacity of the area to be estimated. The reported installed capacity is obtained by querying the power database.

[0127] The cancellation capacity refers to the electricity consumption corresponding to the cancellation of users within E subintervals of C target lines in the area to be estimated, which can be used to represent the power supply capacity that is no longer in use in the area to be estimated. The larger the cancellation capacity, the larger the available capacity in the area to be estimated. The cancellation capacity is obtained by querying the power database.

[0128] The model estimation module inputs the capacity estimation data into the neural network estimation model for estimating the open capacity, and estimates the open capacity of the next sub-interval;

[0129] Once the capacity estimation data for each sub-interval of the area to be assessed is obtained, the capacity estimation data can be input into the pre-trained neural network estimation model. Based on the actual capacity estimation data, the corresponding available capacity can be estimated, thereby achieving a rapid and accurate estimation effect of the available capacity for each sub-interval of the area to be assessed.

[0130] The open capacity refers to the capacity that can be opened and provided with safe power supply to the outside in the area to be assessed, corresponding to the actual total installed capacity, maximum power supply load, safety reserved capacity, photovoltaic grid-connected capacity, reported installed capacity and account cancellation capacity. It is obtained through statistics in the power database.

[0131] The neural network estimation model is trained based on a large amount of historical capacity estimation data of different types and sizes and available capacity, and is used as an estimation and analysis tool for the available capacity of the area to be estimated, to achieve fast and accurate estimation results;

[0132] The training methods for the neural network estimation model include:

[0133] Collect multiple sets of capacity estimation data and available capacity corresponding to the capacity estimation data in advance;

[0134] The capacity estimation data is converted into multiple feature vectors using a sliding window method. The available capacity is converted into labels corresponding to the capacity estimation data based on the sliding step size. One feature vector corresponds to one label and forms a set of training data. Multiple sets of training data constitute a training set. The capacity estimation data are arranged in the order of collection time, and the prediction time step size Q, sliding step size W, and sliding window length Y are preset.

[0135] The feature vector is used as the input of the model, and the open capacity of the next subinterval after the predicted time step Q is used as the output. The subsequent open capacity of each training set is used as the prediction target. The model is trained with the minimized sum of prediction errors as the training target to generate a neural network estimation model that estimates the open capacity of the next subinterval based on the capacity estimation data of the previous subinterval.

[0136] Exemplarily, the neural network estimation model adopts either CNN or AlexNet;

[0137] The calculation formula for the prediction error is:

[0138] zk=(ak-wk) 2 ;

[0139] Where zk is the prediction error, k is the group number of the feature vector; ak is the predicted state value corresponding to the k-th group of feature vectors, and wk is the actual state value corresponding to the k-th group of training data;

[0140] Specifically, a simple example of the sliding window method is as follows: assuming that capacity estimation data (Q1, Q2, Q3, Q4, Q5, Q6) is used to train a time prediction model to predict the value of one time step in the future, a sliding window of length 4 and a sliding step of length 1 can be used to generate a predicted future training set and a prediction target. For example, the training sets are (Q1, Q2, Q3, Q4) and (Q2, Q3, Q4, Q5), and the prediction targets are (E5) and (E6), where E5 is the available capacity corresponding to the capacity estimation data of the next subinterval at the time of collection of Q4, and E6 is the available capacity corresponding to the capacity estimation data of the next subinterval at the time of collection of Q5.

[0141] By inputting the collected capacity estimation data into the neural network estimation model, the available capacity of the next sub-interval can be estimated, thereby achieving accurate and advance estimation of the available capacity of the area to be estimated at future times.

[0142] The opening strategy module selects the capacity opening model for the area to be estimated based on the estimated open capacity and formulates the corresponding capacity opening strategy;

[0143] The capacity opening mode indicates the degree of capacity opening in the next sub-interval of the region to be assessed, based on the estimated amount of open capacity in the next sub-interval. Based on different capacity opening modes, it can provide guidance for specific measures for subsequent capacity optimization, ensuring that the distribution network lines in the region to be assessed can maintain safe and good power supply capacity development results.

[0144] The capacity opening modes include unrestricted opening mode, semi-restricted opening mode and fully restricted opening mode. Unrestricted opening mode means that the power supply capacity of the distribution network lines in the area to be assessed is open without any restrictions. Semi-restricted opening mode means that the power supply capacity of the distribution network lines in the area to be assessed is open with slight restrictions. Fully restricted opening mode means that the power supply capacity of the distribution network lines in the area to be assessed is open with strict restrictions.

[0145] The selection methods for unrestricted open mode, semi-restricted open mode and fully restricted open mode include:

[0146] The open capacity KF of the next subinterval will be estimated rl and the preset first open threshold KF yz1 and the second openable threshold KF yz2 Compare, KF yz1 Less than KF yz2 The preset first and second openable thresholds are used to represent the critical values ​​of the openable capacity corresponding to the unrestricted open mode, the semi-restricted open mode, and the fully restricted open mode, thereby ensuring the accurate selection of the subsequent specific capacity opening mode;

[0147] When KF rl Less than KF yz1 When , it means that the estimated open capacity of the next sub-interval is less than the preset first open threshold. At this time, the capacity of the next sub-interval in the estimated area to provide safe power supply to the outside is very small, and the capacity opening process needs to be strictly restricted. In this case, the full restriction opening mode is selected;

[0148] When KF yz1 Less than or equal to KF rl , and KF rl Less than KF yz2 When , it means that the estimated openable capacity of the next sub-interval is greater than or equal to the preset first openable threshold, and less than the preset second openable threshold. At this time, the capacity of the next sub-interval in the estimated area to provide safe power supply to the outside is slightly less, and the capacity opening process needs to be slightly restricted, so the semi-restricted opening mode is selected;

[0149] When KF rl Greater than or equal to KF yz2 When , it means that the estimated open capacity of the next sub-interval is greater than or equal to the preset second open threshold. At this time, the next sub-interval in the area to be estimated has a large capacity for safe power supply to the outside, and the capacity opening process does not need to be restricted, so the unlimited opening mode is selected.

[0150] The capacity opening strategy is a specific measure formulated based on different capacity opening modes to open up the available capacity in the area to be assessed for external power supply. It can optimize and control the capacity that can be opened up for external power supply in the area to be assessed at any time in the future, ensuring that the distribution network lines in the area to be assessed can maintain security and stability even when the capacity is opened up.

[0151] Capacity opening strategies include full capacity opening strategy, semi-open capacity opening strategy, and closed capacity opening strategy. Full capacity opening strategy refers to a strategy where all available capacity is open to external power supply, semi-open capacity opening strategy refers to a strategy where half of available capacity is open to external power supply, and closed capacity opening strategy refers to a strategy where only part of available capacity is open to external power supply.

[0152] Methods for formulating the fully open capacity strategy, the partially open capacity strategy, and the closed capacity strategy include:

[0153] When the capacity opening mode is the fully restricted opening mode, if the capacity of the area to be assessed is opened to the outside for power supply, it will cause greater risks to the distribution network lines in the area to be assessed, so a capacity non-opening strategy is formulated;

[0154] When the capacity opening mode is semi-restricted opening mode, when the capacity of the area to be assessed is opened to the outside for power supply, it will cause slight risks to the distribution network lines in the area to be assessed, so a semi-open capacity strategy is formulated;

[0155] When the capacity opening mode is the unlimited opening mode, when the capacity of the area to be assessed is opened to the outside for power supply, no risk will be caused to the distribution network lines in the area to be assessed, and a full capacity opening strategy will be formulated.

[0156] In this embodiment, by identifying the power supply attributes of all distribution network lines in the area to be estimated one by one, and screening out target lines from the distribution network lines based on effective power supply criteria, it is possible to avoid the interference of a large number of distribution network lines with extremely small power supply capacity, and also reduce the subsequent calculation burden. By obtaining the basic operation and maintenance parameters of the target line, the power supply interval of the target line is calculated, and the power supply interval is expanded to the estimation period, it is possible to ensure that the collected relevant data remains reasonable and accurate, and avoid the phenomenon of too much or too little data collection due to too long or too short collection time. At the same time, by obtaining the capacity of the target line in the sub-interval of the area to be estimated, By using the estimated capacity data and combining it with the neural network estimation model to estimate the open capacity of the next sub-interval, the open capacity of the distribution network lines in the estimated area at the future moment can be estimated in advance and accurately, so that abnormal situations can be discovered in advance when the open capacity of the distribution network lines is about to be too low, and the appropriate capacity opening mode and capacity opening strategy can be selected to perform safe and stable capacity opening operations on the distribution network lines when the open capacity does not meet the standards, avoiding the risk of excessive power supply due to insufficient open capacity of the distribution network lines, thereby ensuring the safety of the capacity opening operation of the distribution network lines.

[0157] Example 2: Please refer to Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description of the first embodiment. A method for estimating and analyzing the open capacity of distribution network lines is provided, which is implemented based on a system for estimating and analyzing the open capacity of distribution network lines and includes:

[0158] S1: Identify the power supply attributes of all distribution network lines in the area to be assessed one by one. Power supply attributes include long-term power supply, short-term power supply, and ineffective power supply. Based on the effective power supply criterion, select the target lines from the distribution network lines.

[0159] S2: Obtain the basic operation and maintenance parameters of the target line, calculate the power supply interval of the target line, and expand the power supply interval into an estimated period;

[0160] S3: Divide the estimation period into continuous subintervals and, in power supply mode, obtain capacity estimation data for the target line in the area to be estimated in the subintervals. The capacity estimation data includes total installed capacity, maximum power supply load, safety reserve capacity, PV grid-connected capacity, reported installed capacity, and account cancellation capacity.

[0161] S4: inputting the capacity estimation data into the neural network estimation model for estimating the open capacity, and estimating the open capacity of the next sub-interval;

[0162] S5: Based on the estimated open capacity, select the capacity opening mode for the area to be estimated. The capacity opening modes include unrestricted opening mode, semi-restricted opening mode and fully restricted opening mode, and formulate the corresponding capacity opening strategy.

[0163] Example 3: Please refer to Figure 3 As shown, this embodiment discloses an electronic device, including a processor and a memory;

[0164] Wherein, the memory stores a computer program that can be called by the processor;

[0165] The processor executes the method for estimating and analyzing the openable capacity of distribution network lines by calling the computer program stored in the memory.

[0166] Since the electronic device introduced in this embodiment is an electronic device used to implement a method for estimating and analyzing the open capacity of a distribution network line in Example 2 of this application, based on the method for estimating and analyzing the open capacity of a distribution network line introduced in the embodiment of this application, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application will not be described in detail here. As long as a person skilled in the art implements the electronic device used in the method for estimating and analyzing the open capacity of a distribution network line in the embodiment of this application, it falls within the scope of protection of this application.

[0167] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A distribution network line open capacity estimation and analysis system, characterized in that: include: The line screening module is used to identify the power supply attributes of all distribution network lines in the area to be assessed one by one, including long-term power supply, short-term power supply and invalid power supply, and screen the target lines from the distribution network lines based on the effective power supply criteria; The cycle extension module is used to obtain the basic operation and maintenance parameters of the target line, calculate the power supply interval duration of the target line, and extend the power supply interval duration to an estimated cycle; The data acquisition module is used to divide the estimation period into continuous sub-intervals and obtain the capacity estimation data of the target line in the sub-interval in the area to be estimated in the power supply mode. The capacity estimation data includes the total installed capacity, the maximum power supply load, the safety reserved capacity, the photovoltaic grid-connected capacity, the reported installed capacity and the account cancellation capacity; A model estimation module is used to input the capacity estimation data into a neural network estimation model for estimating the open capacity, so as to estimate the open capacity of the next sub-interval; The opening strategy module is used to select the capacity opening mode of the area to be estimated based on the estimated open capacity. The capacity opening modes include unrestricted opening mode, semi-restricted opening mode and fully restricted opening mode, and formulate corresponding capacity opening strategies.

2. A distribution network line open capacity estimation and analysis system according to claim 1, characterized in that: Methods for identifying long-term power supply, short-term power supply and invalid power supply include: The line distribution map of the area to be assessed is queried through the power database, and A distribution network lines in the line distribution map are marked one by one; Using the preset marking interval as the standard, mark B non-adjacent power supply moments, and query the power supply status values ​​of A distribution network lines at B power supply moments one by one; The number of power supply moments with a power supply status value of "1-1" is counted and recorded as a power supply high value, and one third of the number of power supply moments is recorded as a power supply critical value; When the high power supply value is equal to B, the power supply attribute of the distribution network line is long-term power supply; When the power supply critical value is less than or equal to the power supply high value, and the power supply high value is less than B, the power supply attribute of the distribution network line is short-term power supply; When the power supply high value is less than the power supply critical value, the power supply attribute of the distribution network line is invalid power supply.

3. A distribution network line open capacity estimation and analysis system according to claim 2, characterized in that: The effective power supply criterion is: the power supply capacity of the target line is greater than the lower limit of the power supply capacity; The target line screening methods include: Draw the regional boundary of the area to be assessed on the line distribution map, and mark the two intersection points of the distribution network lines with long-term power supply and short-term power supply attributes and the regional boundary along the power transmission direction as entry points and export points respectively; Query the real-time power supply load of the entry point and the export point one by one, obtain the entry capacity and the export capacity, and obtain the power supply capacity by subtracting the entry capacity from the export capacity; The distribution network lines whose power supply capacity is greater than the lower limit of the power supply capacity are recorded as target lines, and C target lines are obtained.

4. A distribution network line open capacity estimation and analysis system according to claim 3, characterized in that: Basic operation and maintenance parameters include power supply start time and power supply end time; The calculation method of the power supply interval duration includes: Through the power database, query one by one the D power supply events in which the C target lines supply power to the area to be estimated, and query the power supply power at each power supply moment in the D power supply events; The power supply time when the power supply power is greater than the power lower limit for the first time is recorded as the power supply start time, and after the power supply start time, the power supply time when the power supply power is less than the power lower limit for the first time is recorded as the power supply end time; The duration between the power supply start time and the power supply end time is recorded as the sub-interval duration, D sub-interval durations are obtained, and the D sub-interval durations are accumulated and averaged to obtain the power supply interval duration; The expression of power supply interval duration is: In the formula, GD sc SC is the power supply interval duration, zd is the duration of the dth subinterval.

5. A distribution network line open capacity estimation and analysis system according to claim 4, characterized in that: Extended methods for estimating cycles include: The first power supply moment among the D power supply events is recorded as the starting moment, and the power supply power at the starting moment is recorded as the starting power; After the starting time, the power supply time when the power supply power is less than the starting time for the first time is recorded as the extension time, and the duration from the starting time to the extension time is recorded as the sub-duration, and D sub-durations are obtained; The maximum value of the sub-durations is recorded as the extended duration, and an extended duration is added to the power supply interval duration to extend the power supply interval duration to the estimated period.

6. A distribution network line open capacity estimation and analysis system according to claim 5, characterized in that: The methods for obtaining the total installed capacity include: In the E sub-intervals, the power generation of the main substations corresponding to the C target lines is queried one by one through the power database to obtain the C main transformer capacities; Multiply C main transformer capacities by the corresponding distribution network connection coefficients, and add up the C product values ​​one by one to obtain E total installed capacities; The expression of total installed capacity is: In the formula, ZJ rle is the total installed capacity of the e-th sub-interval, e=1,2...E, ZB rles is the capacity of the sth main transformer in the eth subinterval, BW xses is the sth distribution network connection coefficient of the eth subinterval.

7. A distribution network line open capacity estimation and analysis system according to claim 6, characterized in that: Methods for obtaining photovoltaic grid-connected capacity include: The power generation status of all photovoltaic power stations in the area to be estimated is identified one by one through the power database, and the photovoltaic power stations with effective power generation status are recorded as target photovoltaic stations, and F target photovoltaic stations are obtained; In the E sub-intervals, the total power generation of the F target photovoltaic stations is counted one by one to obtain F photovoltaic power generation; After accumulating the F photovoltaic power generation one by one, the accumulated value is multiplied by the photovoltaic grid-connected coefficient to obtain E photovoltaic grid-connected capacities; The expression of photovoltaic grid-connected capacity is: In the formula, GF bwe is the photovoltaic grid-connected capacity of the e-th sub-interval, GF xs is the photovoltaic grid-connected coefficient, GF fdef is the f-th PV power generation in the e-th subinterval.

8. A distribution network line open capacity estimation and analysis system according to claim 7, characterized in that: The training methods for the neural network estimation model include: Collect multiple sets of capacity estimation data and available capacity corresponding to the capacity estimation data in advance; The capacity estimation data is converted into multiple feature vectors using a sliding window method. The available capacity is converted into labels corresponding to the capacity estimation data according to the sliding step. One feature vector corresponds to one label and constitutes a set of training data. Multiple sets of training data constitute a training set. The capacity estimation data are arranged in the order of collection time. The prediction time step Q, sliding step W and sliding window length Y are preset. The feature vector is used as the input of the model, and the open capacity of the next subinterval after the predicted time step Q is used as the output. The subsequent open capacity of each training set is used as the prediction target. The model is trained with the minimized sum of prediction errors as the training target to generate a neural network estimation model that estimates the open capacity of the next subinterval based on the capacity estimation data of the previous subinterval.

9. A distribution network line open capacity estimation and analysis system according to claim 8, characterized in that: The selection methods of the unrestricted open mode, the semi-restricted open mode and the fully restricted open mode include: The estimated open capacity KF of the next subinterval rl The preset first open threshold KF yz1 and the second open threshold KF yz2 Compare, KF yz1 Less than KF yz2 ; When KF rl Less than KF yz1 When you select the fully restricted open mode; When KF yz1 Less than or equal to KF rl , and KF rl Less than KF yz2 When, select the semi-restricted open mode; When KF rl Greater than or equal to KF yz2 When you select Unrestricted Open Mode.

10. A distribution network line open capacity estimation and analysis system according to claim 9, characterized in that: Capacity opening strategies include full capacity opening strategy, semi-capacity opening strategy and non-capacity opening strategy; Methods for formulating the full capacity opening strategy, the semi-capacity opening strategy, and the capacity non-opening strategy include: When the capacity opening mode is the full-restriction opening mode, a capacity non-opening strategy is formulated; When the capacity opening mode is the semi-restricted opening mode, a capacity semi-opening strategy is formulated; When the capacity opening mode is the unlimited opening mode, a capacity full opening strategy is formulated.

Images