Multi-source cooperative optimization method and device for power distribution network, equipment and storage medium

Abstract

The application relates to the technical field of artificial intelligence, and discloses a multi-source cooperative optimization method and device for a power distribution network, equipment and a storage medium, wherein the method comprises the following steps: obtaining a plurality of power supply microgrids, grouping the plurality of power supply microgrids into a plurality of power supply microgrid groups, selecting a target power supply microgrid from the plurality of power supply microgrids, obtaining parameters of the target power supply microgrid, establishing a target function, and calculating the selected target power supply microgrid and corresponding power supply switching time by using a group optimization intelligent algorithm. The application has the beneficial effects that economic consumption of the overall power distribution network when crossing a fault is reduced, and microgrid power supply cooperative stability is improved, so that an ideal power supply scheme can be intelligently provided for a designated power distribution network after a fault, and economic consumption and power supply stability are taken into account.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of multi-source collaborative optimization for power distribution networks, and in particular to a multi-source collaborative optimization method, device, equipment and storage medium for power distribution networks. BACKGROUND

[0002] When a power distribution network fault occurs, the existing multi-microgrid active collaborative control method based on maximum economic benefit and minimum power reduction of microgrid, but due to different real-time electricity prices of different microgrids in actual use, and different microgrid reserves, even if the reduction is minimum, it may also lead to poor stability problem in multi-microgrid collaboration for power distribution network fault according to the above-mentioned multi-microgrid active collaborative control method, and multiple switching of power supply microgrids may be required. There is no solution in the prior art that takes into account the above parameters, resulting in an unsatisfactory solution for power supply using multi-microgrids. SUMMARY

[0003] Therefore, it is necessary to propose a multi-source collaborative optimization method, device, equipment and storage medium for power distribution networks for the existing multi-source collaborative optimization problem of power distribution networks.

[0004] A multi-source collaborative optimization method for power distribution networks, the method comprising:

[0005] When a specified power distribution network fault occurs, a plurality of power supply microgrids available for power supply to the specified power distribution network are obtained;

[0006] The plurality of power supply microgrids are divided into a plurality of power supply microgrid groups; one of the power supply microgrid groups includes at least one power supply microgrid;

[0007] The first energy value of each of the power supply microgrids consumed by the energy storage in the specified power distribution network fault time in a historical preset time period is obtained, and the second energy value of the current energy storage of each of the power supply microgrids is obtained;

[0008] The power supply value of each of the power supply microgrids is calculated based on the first energy value and the second energy value corresponding to each of the power supply microgrids, and the power supply microgrid with a power supply value greater than a preset value is recorded as a target power supply microgrid;

[0009] The third energy value required by the specified power distribution network is obtained, and the unit electricity price of each of the target power supply microgrids is obtained, and a target function is set Where Y is the target function, Min(.) represents the minimum value, K n,t represents the second energy value of the tth microgrid in the nth power supply microgrid group, C n,tThe unit electricity price of the t-th microgrid in the n-th power supply microgrid group is represented by h, which is a parameter. When the t-th microgrid in the n-th power supply microgrid group is the target power supply microgrid, h = 1. If it is not the target power supply microgrid, h = 0. w is a hyperparameter, M represents the number of target power supply microgrids selected, K represents the third energy value, and Z represents the switching stability parameter value related to the selection of target power supply microgrids.

[0010] The target power supply microgrid and its corresponding power supply switching time are selected in the objective function by optimizing the objective function using the group optimization intelligent algorithm. The power supply program is then set according to the selected target power supply microgrid and its corresponding power supply switching time to supply power to the specified distribution network.

[0011] Further, the step of obtaining the third energy value required by the designated distribution network and the unit electricity price of each of the target power supply microgrids, and setting the objective function, includes:

[0012] Obtain the time interval between the switching time and the fault start time when switching to the t-th power supply microgrid in the n-th group;

[0013] Calculate the time percentage sequence based on the time interval value;

[0014] The average difference in time proportion between each data point and its left and right data points in the time proportion sequence is used as the interval value of each data point. If the current data point is the leftmost or rightmost data point, the corresponding time proportion difference is obtained as the corresponding data point interval value.

[0015] The switching stability parameter value is calculated based on the data point interval value.

[0016] Furthermore, the swarm optimization intelligent algorithm is one of the following: whale algorithm, particle swarm algorithm, genetic algorithm, gray wolf algorithm, and cuckoo algorithm.

[0017] Furthermore, the step of optimizing the target power supply microgrid and its corresponding power supply switching time in the objective function based on the swarm optimization intelligent algorithm includes:

[0018] Set optimization variable conditions; wherein, the optimization variable conditions include at least the sum of the second energy values ​​of the selected target power supply microgrid being greater than or equal to the third energy value;

[0019] The target power supply microgrid and its corresponding power supply switching time are selected in the objective function based on the optimization variable conditions and the swarm optimization intelligent algorithm.

[0020] Furthermore, the step of dividing the plurality of power supply microgrids into plurality of power supply microgrid groups includes:

[0021] Obtain the location information of each of the power supply microgrids;

[0022] Select a preset number of cluster centers;

[0023] The power supply microgrids are clustered using the k-means clustering method to obtain multiple power supply microgrid groups.

[0024] Furthermore, after the steps of optimizing the objective function using the swarm optimization intelligent algorithm to select the target power supply microgrid and its corresponding power supply switching time, and setting the power supply program to supply power to the designated distribution network based on the selected target power supply microgrid and its corresponding power supply switching time, the method further includes:

[0025] Determine whether the power supply duration of the selected target microgrid meets the estimated duration;

[0026] If the estimated duration is not met, another target power supply microgrid will be selected from the power supply microgrid group to which the target power supply microgrid belongs, until the estimated duration is reached.

[0027] Further, the step of optimizing the objective function using the swarm optimization intelligent algorithm to select the target power supply microgrid and its corresponding power supply switching time, and setting the power supply program to supply power to the designated distribution network based on the selected target power supply microgrid and its corresponding power supply switching time, includes:

[0028] According to the unit electricity price of the selected target power supply microgrid, the power supply sequence of each target power supply microgrid is set from low to high.

[0029] Calculate the corresponding power switching time based on the power supply sequence of each selected target power supply microgrid, and set the power supply program to supply power to the designated distribution network.

[0030] A multi-source collaborative optimization device for power distribution networks, the device comprising:

[0031] The first acquisition module is used to acquire multiple power supply microgrids that can be used to supply power to the specified distribution network when the specified distribution network fails.

[0032] A grouping module is used to divide the multiple power supply microgrids into multiple power supply microgrid groups; wherein one of the power supply microgrid groups includes at least one power supply microgrid.

[0033] The second acquisition module is used to acquire the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids.

[0034] The calculation module is used to calculate the power supply value corresponding to each of the power supply microgrids based on the first energy value and the second energy value corresponding to each of the power supply microgrids, and to record the power supply microgrids whose power supply value is greater than a preset value as the target power supply microgrids;

[0035] The third acquisition module is used to acquire the third energy value required by the specified distribution network, as well as the unit electricity price of each of the target power supply microgrids, and to set the objective function. Where Y is the objective function, Min(.) represents taking the minimum value, and K n,t C represents the second energy value of the t-th microgrid in the n-th power supply microgrid group. n,t The unit electricity price of the t-th microgrid in the n-th power supply microgrid group is represented by h, which is a parameter. When the t-th microgrid in the n-th power supply microgrid group is the target power supply microgrid, h = 1. If it is not the target power supply microgrid, h = 0. w is a hyperparameter, M represents the number of target power supply microgrids selected, K represents the third energy value, and Z represents the switching stability parameter value related to the selection of target power supply microgrids.

[0036] The power supply module is used to optimize the objective function by using the group optimization intelligent algorithm to select the target power supply microgrid and the corresponding power supply switching time, and to set the power supply program according to the selected target power supply microgrid and the corresponding power supply switching time to supply power to the designated distribution network.

[0037] A computer device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps:

[0038] When a specified distribution network fails, multiple power supply microgrids that can be used to supply power to the specified distribution network are obtained;

[0039] The multiple power supply microgrids are divided into multiple power supply microgrid groups; one of the power supply microgrid groups includes at least one power supply microgrid.

[0040] Obtain the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids;

[0041] Based on the first energy value and the second energy value corresponding to each of the power supply microgrids, the power supply value corresponding to each power supply microgrid is calculated, and the power supply microgrid with the power supply value greater than the preset value is recorded as the target power supply microgrid;

[0042] Obtain the third energy value required by the specified distribution network and the unit electricity price of each target power supply microgrid, and set the objective function. Where Y is the objective function, Min(.) represents taking the minimum value, and K n,t C represents the second energy value of the t-th microgrid in the n-th power supply microgrid group. n,t The unit electricity price of the t-th microgrid in the n-th power supply microgrid group is represented by h, which is a parameter. When the t-th microgrid in the n-th power supply microgrid group is the target power supply microgrid, h = 1. If it is not the target power supply microgrid, h = 0. w is a hyperparameter, M represents the number of target power supply microgrids selected, K represents the third energy value, and Z represents the switching stability parameter value related to the selection of target power supply microgrids.

[0043] The target power supply microgrid and its corresponding power supply switching time are selected in the objective function by optimizing the objective function using a group optimization intelligent algorithm. A power supply program is then set based on the selected target power supply microgrid and its corresponding power supply switching time to supply power to the specified distribution network. A computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0044] When a specified distribution network fails, multiple power supply microgrids that can be used to supply power to the specified distribution network are obtained;

[0045] The multiple power supply microgrids are divided into multiple power supply microgrid groups; one of the power supply microgrid groups includes at least one power supply microgrid.

[0046] Obtain the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids;

[0047] Based on the first energy value and the second energy value corresponding to each of the power supply microgrids, the power supply value corresponding to each power supply microgrid is calculated, and the power supply microgrid with the power supply value greater than the preset value is recorded as the target power supply microgrid;

[0048] Obtain the third energy value required by the specified distribution network and the unit electricity price of each target power supply microgrid, and set the objective function. Where Y is the objective function, Min(.) represents taking the minimum value, and K n,t C represents the second energy value of the t-th microgrid in the n-th power supply microgrid group. n,t The unit electricity price of the t-th microgrid in the n-th power supply microgrid group is represented by h, which is a parameter. When the t-th microgrid in the n-th power supply microgrid group is the target power supply microgrid, h = 1. If it is not the target power supply microgrid, h = 0. w is a hyperparameter, M represents the number of target power supply microgrids selected, K represents the third energy value, and Z represents the switching stability parameter value related to the selection of target power supply microgrids.

[0049] The target power supply microgrid and its corresponding power supply switching time are selected in the objective function by optimizing the objective function using the group optimization intelligent algorithm. The power supply program is then set according to the selected target power supply microgrid and its corresponding power supply switching time to supply power to the specified distribution network.

[0050] The beneficial effects of this invention are as follows: By acquiring multiple power supply microgrids and grouping them into multiple power supply microgrid groups, a target power supply microgrid is selected from these groups. Then, the parameters of the target power supply microgrid are obtained to establish an objective function. A swarm optimization intelligent algorithm is used to calculate the selected target power supply microgrid and its corresponding power supply switching time. This reduces the economic consumption of the overall distribution network during fault crossings and improves the coordinated stability of microgrid power supply. Therefore, it can intelligently provide an ideal power supply scheme after a specified distribution network fault, balancing economic consumption and power supply stability. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] in:

[0053] Figure 1 This is an application environment diagram of a multi-source collaborative optimization method for power distribution networks in one embodiment;

[0054] Figure 2 This is a flowchart for multi-source collaborative optimization of a power distribution network in one embodiment;

[0055] Figure 3 This is a structural block diagram of a multi-source collaborative optimization device for a power distribution network in one embodiment;

[0056] Figure 4 The multi-source collaborative optimization for power distribution networks is illustrated in the structural block diagram of a computer device in one embodiment. Detailed Implementation

[0057] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Figure 1 This is a diagram illustrating a multi-source collaborative optimization application environment for a power distribution network in one embodiment. (Refer to...) Figure 1This multi-source collaborative optimization method for power distribution networks is applied to a multi-source collaborative optimization system for power distribution networks. The system includes a terminal 110 and a server 120. The terminal 110 and server 120 are connected via a network. The terminal 110 can be a desktop terminal or a mobile terminal, specifically a mobile phone, tablet computer, laptop computer, or other similar devices. The server 120 can be a standalone server or a server cluster consisting of multiple servers. The terminal 110 is used to acquire energy value data, and the server 120 is used to calculate the selected target power supply microgrid and the corresponding power supply switching time based on the acquired data.

[0059] like Figure 2 As shown, in one embodiment, a multi-source collaborative optimization method for a power distribution network is provided. This method can be applied to both terminals and servers; this embodiment illustrates its application to a server. The multi-source collaborative optimization method for a power distribution network specifically includes the following steps:

[0060] S1: When a specified distribution network fails, obtain multiple power supply microgrids that can be used to supply power to the specified distribution network;

[0061] S2: Divide the plurality of power supply microgrids into a plurality of power supply microgrid groups; wherein one of the power supply microgrid groups includes at least one power supply microgrid;

[0062] S3: Obtain the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids;

[0063] S4: Calculate the power supply value corresponding to each power supply microgrid based on the first energy value and the second energy value corresponding to each power supply microgrid, and record the power supply microgrid with the power supply value greater than the preset value as the target power supply microgrid;

[0064] S5: Obtain the third energy value required by the specified distribution network and the unit electricity price of each of the target power supply microgrids, and set the objective function. Where Y is the objective function, Min(.) represents taking the minimum value, and K n,t C represents the second energy value of the t-th microgrid in the n-th power supply microgrid group. n,t The unit electricity price of the t-th microgrid in the n-th power supply microgrid group is represented by h, which is a parameter. When the t-th microgrid in the n-th power supply microgrid group is the target power supply microgrid, h = 1. If it is not the target power supply microgrid, h = 0. w is a hyperparameter, M represents the number of target power supply microgrids selected, K represents the third energy value, and Z represents the switching stability parameter value related to the selection of target power supply microgrids.

[0065] S6: Optimize the objective function using the group optimization intelligent algorithm to find the target power supply microgrid and the corresponding power supply switching time. Set the power supply program according to the selected target power supply microgrid and the corresponding power supply switching time to supply power to the specified distribution network.

[0066] As described in step S1 above, when a designated distribution network fails, multiple power supply microgrids that can be used to supply power to the designated distribution network are obtained. This can be done by obtaining relevant data from the microgrid's nodes, such as its stored energy data, and then determining whether it can supply power to the designated distribution network based on the actual situation. If it meets the requirements for supplying power to the designated distribution network, the corresponding power supply microgrid can be obtained.

[0067] As described in step S2 above, the multiple power supply microgrids are divided into multiple power supply microgrid groups; one of the power supply microgrid groups includes at least one power supply microgrid; the grouping method is not limited, and in some embodiments, they can be classified according to the unit electricity price or located according to distance, which is not limited in this application.

[0068] As described in step S3 above, the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids are obtained. That is, each power supply microgrid has its own consumption. Therefore, in addition to obtaining its second energy value, it is also necessary to obtain the first energy value of the average energy consumption of energy storage during the specified distribution network fault time. The first energy value can be estimated by averaging the energy consumption of the microgrid based on historical data.

[0069] As described in step S4 above, the power supply value corresponding to each power supply microgrid is calculated based on the first energy value and the second energy value corresponding to each power supply microgrid, and the power supply microgrid with a power supply value greater than a preset value is recorded as the target power supply microgrid. Power can only be supplied to the designated distribution network if the power supply value is greater than the preset value; otherwise, if the power is too low, frequent switching will occur, which is not conducive to the operation of the designated distribution network.

[0070] As described in step S5 above, the third energy value required by the designated distribution network and the unit electricity price of each target power supply microgrid are obtained, and an objective function is set. The objective function takes into account the unit electricity price of each target microgrid and the switching time (i.e., the stability of each target power supply microgrid). The specific setting method will be explained in detail later and will not be repeated here.

[0071] As described in step S6 above, the target power supply microgrid and its corresponding power supply switching time are selected in the objective function by optimizing the objective function using the swarm optimization intelligent algorithm. A power supply program is then set based on the selected target power supply microgrid and its corresponding power supply switching time to supply power to the designated distribution network. After calculation using the swarm optimization intelligent algorithm, the selected target power supply microgrid and its corresponding power supply switching time can be obtained. Then, the program is set to execute the corresponding operations, which can reduce the economic consumption of the overall distribution network when crossing faults and improve the coordinated stability of microgrid power supply. Therefore, it can intelligently provide an ideal power supply scheme after a fault in the designated distribution network, balancing economic consumption and power supply stability.

[0072] In one embodiment, step S5, which involves obtaining the third energy value required by the specified distribution network and the unit electricity price of each target power supply microgrid, and setting the objective function, includes:

[0073] S501: Obtain the time interval between the switching time and the fault start time when switching to the t-th power supply microgrid in the nth group;

[0074] S502: Calculate the time percentage sequence based on the time interval value;

[0075] S503: The average difference in time proportion between each data point in the time proportion sequence and the data points to its left and right is used as the interval value of each data point. If the current data point is the leftmost or rightmost data point, the corresponding time proportion difference is obtained as the corresponding data point interval value.

[0076] S504: Calculate the switching stability parameter value based on the data point interval value.

[0077] As described in steps S501-S504 above, the limitation on the switching stability parameter value is implemented. Specifically, groups with more than or equal to 2 power supply microgrids in the current solution set are obtained, and the power supply ratio of all power supply microgrids in these groups relative to K is obtained as a sequence {P}, where the power supply of the t-th power supply microgrid in the n-th group is K. n,t The corresponding percentage of electricity consumption is The larger the proportion of P, the greater the power supply of the power microgrid. Therefore, when switching power microgrids, the more similar power microgrids are switched, the more stable the power supply will be, because the substitutability is greater. In addition, the more uniform the switching time distribution of all power microgrids, the more stable the overall power supply will be.

[0078] Then, obtain the groups with more than or equal to 2 power supply microgrids in the current solution set, and obtain the time ratio sequence {Q} of the switching time relative to the fault time for all power supply microgrids in these groups, where R n,tLet R be the time interval between the switching time and the fault start time when switching to the nth microgrid in the tth group, where R is the expected fault time of the faulty distribution network (expected repair time), and the corresponding time percentage is:

[0079] After obtaining the time proportion sequence {Q}, if the time proportion value Q in the time proportion sequence {Q} is more evenly distributed, it means that the current solution set provides more stable power supply to the faulty distribution network. However, if there is a large P value and the adjacent switching time is too short, it means that when the power supply microgrid has a problem, the overall stability of the power grid depends too much on the single power supply grid. Therefore, the adjacent switching time should be longer in order to make the current solution set provide more stable power supply to the faulty distribution network.

[0080] Therefore, the formula for calculating the value of Z is:

[0081] The average difference in time percentage between each data point in {Q} and its left and right data points is taken as the interval value S of each data point. If it is the leftmost or rightmost data point, the corresponding difference in time percentage is taken as the corresponding data point interval value S.

[0082] The interval value S should be uniformly distributed and relatively large. However, for data points with high P values, the interval should be relatively small. The larger the P value, the smaller the interval value of the nearby data points should be.

[0083] This leads to the overall Z:

[0084] Z = exp(VU)

[0085] U is the mean value of S corresponding to each data point of {Q}. The larger the value, the larger the overall interval distribution. In this case, the distribution is relatively dispersed. Within a limited fault time, there should be as many power supply microgrids as possible to switch, so as to prevent over-reliance on a single power supply microgrid and thus ensure overall stability. The e4p(-4) function is then used to perform a negative correlation mapping on it.

[0086] V is the weighted variance / entropy value of the S value corresponding to each data point of {Q}. The smaller the value, the more uniform the overall interval distribution. The intervals between the data points are consistent and the distribution is uniform, which means the greater the risk resistance.

[0087] When calculating V, it is necessary to obtain the variance weight values ​​corresponding to each data point. When obtaining the weight values ​​W for each data point in {Q}, for data points with high P values, their local data density should be high. However, this will cause significant fluctuations in the variance calculation. Therefore, the larger the P value corresponding to each data point in {Q} and the higher the local density, the lower the weight of that data point in the variance calculation. If the P value is large and the density is low, the weight is large; if the P value is small, the weight value should be closer to 1, indicating a normal weight. Jm represents the local density of a single data point. It is calculated by establishing a time window and obtaining the ratio of the number of data points (switching power supply microgrids) within the time window to the maximum number of power supply microgrids that can be switched within the time window. The length of the time window is one-tenth of the fault time and can be adjusted by the implementer according to the specific implementation scenario.

[0088] Jm' is the mean of all data points with respect to that local density, and then... A value less than 1 indicates that the local density of the data point is greater than the mean. A value greater than 1 indicates that the local density of the data point is less than the mean. When the value is equal to 1, it means that the local density of the data point is equal to the mean. Then e4p(0) is 1, which means that the weight is 1.

[0089] p represents the percentage of electricity consumption corresponding to a single data point. The larger the value, the higher the local density should be. P' is the average percentage of electricity consumption corresponding to all data points.

[0090] If (p-P') is less than or equal to 0, then relu(p-P')+1) is always 1, indicating that the weight allocation is based solely on the interval density distribution. The +1 is to prevent jm from failing when (p-P') is less than or equal to 0. When (p-P') is less than or equal to 0, the data allocation should be related to density, not to the percentage of electricity consumption.

[0091] If (p-P') is greater than 0, and the larger the value of (p-P'), the more local density is needed for that data point. If the value is greater than 1 and the smaller jm is, the higher the weight of the current data should be, and the weight should be greater than 1. Greater than 1, and the smaller jm is, The larger the value of p-P' is, the larger the value of (relu(p-P')+1) is, and the larger the value of (relu(p-P')+1) is, the greater the value of e4p mapping. A value greater than 1 indicates that the data is more unstable and therefore has a greater weight when calculating variance.

[0092] If the local density is at this time When jm is less than 1 and larger, it indicates that the weight of the current data should be smaller, meaning that the calculation of variance is less dependent on this data, so that the calculated variance is relatively stable. Less than 1, and the larger jm is, The smaller the value of (p-P'), the larger the value of (p-P'). If (relu(p-P')+1) is greater than 1, then... The smaller the value is (less than 0), the better its e4p mapping results. The smaller the variance, the better. This allows us to obtain the variance weights of all data points, and then calculate V based on the weighted variance, ultimately yielding the objective function of the power supply microgrid.

[0093] In one embodiment, the origin of the objective function is explained as follows:

[0094] Because there may be a situation where a microgrid has limited power reserves but cheap electricity, when supplying power to a faulty distribution network, it may be necessary to switch the power supply microgrid to another microgrid during the power supply process to ensure that the expected fault time of the faulty distribution network can be covered.

[0095] Therefore, this solution selects to group multiple power supply microgrids that have collectively passed the expected fault time into a group. The number of power supply microgrids in a group is greater than or equal to 1 and less than 5, where 5 is the acceptable number of microgrid switching times during power supply, which can be adjusted by the implementer according to the specific implementation scenario.

[0096] If a microgrid data set for a given group is 1, it indicates that during the entire fault period, power is supplied to this microgrid while supplying power to the faulty distribution network. In this case, the power supply price for that group is the power supply quantity multiplied by the historical average power price during the fault period. The historical average power price during the fault period is calculated as the average of the power prices of this microgrid within the past 10 days during the fault period.

[0097] If the data of a power supply microgrid in one group is greater than 1, then when the expected fault time of the faulty distribution network is crossed, the power supply microgrid needs to be switched. The switching logic is as follows:

[0098] Obtain the average energy storage consumption E of the first microgrid in the nth group over a historical 10-day period during the fault time. n,1 Where n is the group number, the historical normal consumption of the microgrid is obtained to prevent the normal operation from being disrupted by its power supply during a fault. The 10-day period can be adjusted by the implementer according to the specific implementation scenario. Then, the current energy storage capacity F of the first microgrid in the nth group is calculated. n,1The system sets a minimum power reserve G, where G = 50. G can be adjusted by the implementer according to the specific implementation scenario to prevent subsequent normal operation from being disrupted due to power supply failure during a fault. G is used to ensure that the power grid can continue to supply power normally after power is restored.

[0099] When optimizing the objective function, the power supply of the first microgrid in the nth group is K. n,1 If K n,1 -(F n,1 -E n,1 If -G)>0, it means that the energy storage is sufficient to supply power. If K n,1 -(F n,1 -E n,1 If -G)≤0, it indicates insufficient energy storage. If the first microgrid in the nth group needs to supply power to the faulty distribution network, then the power supply microgrid needs to be switched during the distribution network power supply period. When selecting the power supply microgrid, (F) n,1 -E n,1 -G)>0, otherwise it means that the power supply microgrid does not have extra reserve power for power supply.

[0100] When determining the switching time of the power supply microgrid, the average energy storage consumption curve of the first microgrid in the nth group over a historical 10-day period during the fault time is obtained, where K n,1 =(F n,1 -E n,1 The switching point is the time point of -G), where the electricity consumption for the Cth microgrid is K. n,1 ×C n,1 Where C n,1 This represents the average electricity price of the microgrid during the required power supply period when the first microgrid in the nth group provides power.

[0101] When switching to a new power supply microgrid, the new power supply microgrid is selected from microgrids that have never been supplied with power and microgrids that have never been supplied with power.

[0102] This leads to the objective function:

[0103]

[0104] N is the number of power supply microgrid groups.

[0105] n represents the traversal of N.

[0106] h indicates that when the power supply microgrid is used, the value of h is 1, and when the power supply microgrid is not used, h = 0. That is, when switching power supply microgrids in the same group, the microgrid is selected from the power supply microgrids where h = 0 and h value is not equal to 1.

[0107] T is the total number of power supply microgrids in group t, where T≤5.

[0108] t represents the traversal of T.

[0109] w is a hyperparameter used to adjust the weight of N.

[0110] Therefore, the number of power supply microgrids with h=1 is limited, and M is the total number of power supply microgrids with h=1 before the current solution is updated. The smaller the value of M, the fewer power supply microgrids are used, and thus the switching frequency is reduced.

[0111] Where K represents the average power consumption of the current faulty distribution network during the fault period (from the start of the fault to the expected end of the fault) over the preceding 10 days, plus a conservative power consumption value. The power supply between all microgrids and the power required to cross the faulty distribution network should be minimized. The closer the value is to 0, the smaller the difference in power supply between all power supply microgrids and the power required to cross the fault distribution network. The conservative power value is set to 10, which can be adjusted by the implementer according to the specific implementation scenario.

[0112] Where Z represents the switching stability of groups with two or more power supply microgrids in the current solution set during power supply microgrid switching. If power supply microgrid switching is required, multiple factors may interfere during the switching process, causing problems in individual power supply microgrids and affecting the overall stability of the power supply to the faulty distribution network. Therefore, the power supply switching time point within groups with two or more power supply microgrids in the current solution set is obtained. To minimize the impact of a single power supply microgrid switching time point on the overall faulty distribution network, the switching stability Z during the overall power supply microgrid switching is calculated. By solving the objective function, the stability of Z in the optimal solution set is maximized, thereby reducing the impact of a single power supply microgrid switching on the overall faulty distribution network.

[0113] In one embodiment, the swarm optimization intelligent algorithm is one of the following: whale algorithm, particle swarm algorithm, genetic algorithm, gray wolf algorithm, and cuckoo algorithm.

[0114] In one embodiment, step S6, which optimizes the target power supply microgrid and its corresponding power supply switching time in the objective function based on the swarm optimization intelligent algorithm, includes:

[0115] S601: Set optimization variable conditions; wherein, the optimization variable conditions include at least the sum of the second energy values ​​of the selected target power supply microgrid being greater than or equal to the third energy value;

[0116] S602: Based on the optimization variable conditions and the swarm optimization intelligent algorithm, optimize the objective function to solve for the selected target power supply microgrid and the corresponding power supply switching time.

[0117] As described in steps S601-S602 above, when using the existing swarm optimization intelligent algorithm to optimize and solve the objective function, the optimization variable is the power supply of each power supply microgrid. The constraints of the optimization variable are: 1) it needs to meet its own normal energy storage requirements; 2) it conforms to the Distflow second-order cone power flow model; 3) it meets the voltage and branch transmission power constraints; 4) it meets the power exchange constraints between the distribution network and the transmission network; and 5) it meets the power exchange constraints between the distribution network and the microgrid. Among these, 2 to 5 are known contents. The constraint 1 is that the sum of the second energy values ​​of the selected target power supply microgrid is greater than or equal to the third energy value.

[0118] In one embodiment, step S2, which divides the plurality of power supply microgrids into a plurality of power supply microgrid groups, includes:

[0119] S201: Obtain the location information of each of the power supply microgrids;

[0120] S202: Select a preset number of cluster centers;

[0121] S203: Cluster each of the power supply microgrids according to the k-means clustering method to obtain multiple power supply microgrid groups.

[0122] As described in steps S201-S203 above, grouping can be performed based on location information. Specifically, k cluster centers are selected, and the distance from each data point to the K centroids is calculated. Each data point is assigned to the nearest centroid, forming K clusters. The centroid of each cluster is recalculated, which is the mean of all data points belonging to that cluster. The steps of assigning centroids and recalculating centroids are repeated until the centroids no longer change (or change very little), or the maximum number of iterations is reached, thereby achieving grouping based on geographical location.

[0123] In one embodiment, after step S6, which involves optimizing the objective function using a swarm optimization algorithm to determine the target power supply microgrid and its corresponding power supply switching time, and then setting a power supply procedure based on the selected target power supply microgrid and its corresponding power supply switching time to supply power to the designated distribution network, the method further includes:

[0124] S701: Determine whether the power supply duration of the selected target power supply microgrid meets the estimated duration;

[0125] S702: If the estimated duration is not met, another target power supply microgrid is selected from the power supply microgrid group to which the target power supply microgrid is located to supply power until the estimated duration is reached.

[0126] As described in steps S701-S702 above, in actual operation, the selected target power supply microgrid may experience unforeseen circumstances, resulting in insufficient power supply and a shorter power supply duration than the estimated duration. In this case, other target power supply microgrids can be selected from the power supply microgrid group to supply power until the estimated duration is reached. Of course, if there are multiple other target power supply microgrids, the cheaper one can be selected based on the unit electricity price.

[0127] In one embodiment, step S6, which involves optimizing the objective function using a swarm optimization algorithm to select the target power supply microgrid and its corresponding power supply switching time, and then setting a power supply program based on the selected target power supply microgrid and its corresponding power supply switching time to supply power to the designated distribution network, includes:

[0128] S611: Set the power supply sequence of each target power supply microgrid from low to high according to the unit electricity price of the selected target power supply microgrid;

[0129] S612: Calculate the corresponding power supply switching time according to the power supply sequence of each selected target power supply microgrid, and set the power supply program to supply power to the designated distribution network.

[0130] As described in steps S611-S612 above, since the repair time of the designated distribution network is uncertain, in order to maximize economic benefits, the power supply sequence of each target power supply microgrid can be set from low to high according to the unit electricity price of the selected target power supply microgrids. Then, the corresponding power supply switching time is calculated according to the power supply sequence of each selected target power supply microgrid, and a power supply program is set to supply power to the designated distribution network. In some embodiments, if it is necessary to ensure the stability of the designated distribution network, the power supply microgrid with the highest energy storage can be selected for power supply.

[0131] The beneficial effects of this invention are as follows: By acquiring multiple power supply microgrids and grouping them into multiple power supply microgrid groups, a target power supply microgrid is selected from these groups. Then, the parameters of the target power supply microgrid are obtained to establish an objective function. A swarm optimization intelligent algorithm is used to calculate the selected target power supply microgrid and its corresponding power supply switching time. This reduces the economic consumption of the overall distribution network during fault crossings and improves the coordinated stability of microgrid power supply. Therefore, it can intelligently provide an ideal power supply scheme after a specified distribution network fault, balancing economic consumption and power supply stability.

[0132] Reference Figure 3 The present invention also provides a multi-source collaborative optimization device for distribution networks, the device comprising:

[0133] The first acquisition module 10 is used to acquire multiple power supply microgrids that can be used to supply power to the specified distribution network when the specified distribution network fails.

[0134] Grouping module 20 is used to divide the multiple power supply microgrids into multiple power supply microgrid groups; wherein one of the power supply microgrid groups includes at least one power supply microgrid;

[0135] The second acquisition module 30 is used to acquire the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids.

[0136] The calculation module 40 is used to calculate the power supply value corresponding to each of the power supply microgrids based on the first energy value and the second energy value corresponding to each of the power supply microgrids, and to record the power supply microgrids whose power supply value is greater than a preset value as the target power supply microgrids;

[0137] The third acquisition module 50 is used to acquire the third energy value required by the specified distribution network and the unit electricity price of each of the target power supply microgrids, and to set the objective function. Where Y is the objective function, Min(.) represents taking the minimum value, and K n,t C represents the second energy value of the t-th microgrid in the n-th power supply microgrid group. n,t The unit electricity price of the t-th microgrid in the n-th power supply microgrid group is represented by h, which is a parameter. When the t-th microgrid in the n-th power supply microgrid group is the target power supply microgrid, h = 1. If it is not the target power supply microgrid, h = 0. w is a hyperparameter, M represents the number of target power supply microgrids selected, K represents the third energy value, and Z represents the switching stability parameter value related to the selection of target power supply microgrids.

[0138] The power supply module 60 is used to optimize the objective function by solving the target power supply microgrid and the corresponding power supply switching time according to the group optimization intelligent algorithm, and to set the power supply program according to the selected target power supply microgrid and the corresponding power supply switching time to supply power to the designated distribution network.

[0139] Figure 4 An internal structural diagram of a computer device in one embodiment is shown. This computer device can specifically be a terminal or a server. Figure 4 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement a multi-source collaborative optimization method. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to implement the multi-source collaborative optimization method. Those skilled in the art will understand that... Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0140] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps:

[0141] When a specified distribution network fails, multiple power supply microgrids that can be used to supply power to the specified distribution network are obtained;

[0142] The multiple power supply microgrids are divided into multiple power supply microgrid groups; one of the power supply microgrid groups includes at least one power supply microgrid.

[0143] Obtain the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids;

[0144] Based on the first energy value and the second energy value corresponding to each of the power supply microgrids, the power supply value corresponding to each power supply microgrid is calculated, and the power supply microgrid with the power supply value greater than the preset value is recorded as the target power supply microgrid;

[0145] Obtain the third energy value required by the specified distribution network and the unit electricity price of each target power supply microgrid, and set the objective function. Where Y is the objective function, Min(.) represents taking the minimum value, and K n,t C represents the second energy value of the t-th microgrid in the n-th power supply microgrid group. n,t The unit electricity price of the t-th microgrid in the n-th power supply microgrid group is represented by h, which is a parameter. When the t-th microgrid in the n-th power supply microgrid group is the target power supply microgrid, h = 1. If it is not the target power supply microgrid, h = 0. w is a hyperparameter, M represents the number of target power supply microgrids selected, K represents the third energy value, and Z represents the switching stability parameter value related to the selection of target power supply microgrids.

[0146] The target power supply microgrid and its corresponding power supply switching time are selected in the objective function by optimizing the objective function using the group optimization intelligent algorithm. The power supply program is then set according to the selected target power supply microgrid and its corresponding power supply switching time to supply power to the specified distribution network.

[0147] It reduces the economic consumption of the overall distribution network when crossing faults and improves the stability of microgrid power supply coordination, thus intelligently providing an ideal power supply solution after a fault in a designated distribution network, taking into account both economic consumption and power supply stability.

[0148] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the following steps:

[0149] When a specified distribution network fails, multiple power supply microgrids that can be used to supply power to the specified distribution network are obtained;

[0150] The multiple power supply microgrids are divided into multiple power supply microgrid groups; one of the power supply microgrid groups includes at least one power supply microgrid.

[0151] Obtain the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids;

[0152] Based on the first energy value and the second energy value corresponding to each of the power supply microgrids, the power supply value corresponding to each power supply microgrid is calculated, and the power supply microgrid with the power supply value greater than the preset value is recorded as the target power supply microgrid;

[0153] Obtain the third energy value required by the specified distribution network and the unit electricity price of each target power supply microgrid, and set the objective function. Where Y is the objective function, Min(.) represents taking the minimum value, and K n,t C represents the second energy value of the t-th microgrid in the n-th power supply microgrid group. n,t The unit electricity price of the t-th microgrid in the n-th power supply microgrid group is represented by h, which is a parameter. When the t-th microgrid in the n-th power supply microgrid group is the target power supply microgrid, h = 1. If it is not the target power supply microgrid, h = 0. w is a hyperparameter, M represents the number of target power supply microgrids selected, K represents the third energy value, and Z represents the switching stability parameter value related to the selection of target power supply microgrids.

[0154] The target power supply microgrid and its corresponding power supply switching time are selected in the objective function by optimizing the objective function using the group optimization intelligent algorithm. The power supply program is then set according to the selected target power supply microgrid and its corresponding power supply switching time to supply power to the specified distribution network.

[0155] It reduces the economic consumption of the overall distribution network when crossing faults and improves the stability of microgrid power supply coordination, thus intelligently providing an ideal power supply solution after a fault in a designated distribution network, taking into account both economic consumption and power supply stability.

[0156] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0157] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0158] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A multi-source collaborative optimization method for power distribution networks, characterized in that, The method includes: When a specified distribution network fails, multiple power supply microgrids that can be used to supply power to the specified distribution network are obtained; The multiple power supply microgrids are divided into multiple power supply microgrid groups; one of the power supply microgrid groups includes at least one power supply microgrid. Obtain the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids; Based on the first energy value and the second energy value corresponding to each of the power supply microgrids, the power supply value corresponding to each power supply microgrid is calculated, and the power supply microgrid with the power supply value greater than the preset value is recorded as the target power supply microgrid; Obtain the third energy value required by the specified distribution network and the unit electricity price of each target power supply microgrid, and set the objective function. Where Y is the objective function, This indicates taking the minimum value. This represents the second energy value of the t-th microgrid in the n-th power supply microgrid group. Let represent the unit electricity price of the t-th microgrid in the n-th microgrid group. h is a parameter; if the t-th microgrid in the n-th microgrid group is the target microgrid, then h = 1; otherwise, h = 0. For hyperparameters, Indicates the number of target power supply microgrids selected. Z represents the third energy value, and Z represents the switching stability parameter value related to the selected target power supply microgrid; The target power supply microgrid and its corresponding power supply switching time are selected in the objective function by optimizing the objective function using the group optimization intelligent algorithm. The power supply program is then set according to the selected target power supply microgrid and its corresponding power supply switching time to supply power to the specified distribution network.

2. The multi-source collaborative optimization method for power distribution networks according to claim 1, characterized in that, The step of obtaining the third energy value required for the specified distribution network and the unit electricity price of each target power supply microgrid, and setting the objective function, includes: Obtain the time interval between the switching time and the fault start time when switching to the t-th power supply microgrid in the n-th group; Calculate the time percentage sequence based on the time interval values; The average difference in time proportion between each data point and its left and right data points in the time proportion sequence is used as the interval value of each data point. If the current data point is the leftmost or rightmost data point, the corresponding time proportion difference is obtained as the corresponding data point interval value. The switching stability parameter value is calculated based on the data point interval value.

3. The multi-source collaborative optimization method for power distribution networks according to claim 1, characterized in that, The swarm optimization intelligent algorithm mentioned is one of the following: whale algorithm, particle swarm algorithm, genetic algorithm, gray wolf algorithm, and cuckoo algorithm.

4. The multi-source collaborative optimization method for power distribution networks according to claim 1, characterized in that, The steps of optimizing the objective function using the swarm optimization intelligent algorithm to determine the target power supply microgrid and its corresponding power supply switching time include: Set optimization variable conditions; wherein, the optimization variable conditions include at least the sum of the second energy values ​​of the selected target power supply microgrid being greater than or equal to the third energy value; The target power supply microgrid and its corresponding power supply switching time are selected in the objective function based on the optimization variable conditions and the swarm optimization intelligent algorithm.

5. The multi-source collaborative optimization method for power distribution networks according to claim 1, characterized in that, The step of dividing the multiple power supply microgrids into multiple power supply microgrid groups includes: Obtain the location information of each of the power supply microgrids; Select a preset number of cluster centers; The power supply microgrids are clustered using the k-means clustering method to obtain multiple power supply microgrid groups.

6. The multi-source collaborative optimization method for power distribution networks according to claim 1, characterized in that, After the steps of optimizing the objective function using the swarm optimization intelligent algorithm to select the target power supply microgrid and its corresponding power supply switching time, and setting the power supply program to supply power to the designated distribution network based on the selected target power supply microgrid and its corresponding power supply switching time, the method further includes: Determine whether the power supply duration of the selected target microgrid meets the estimated duration; If the estimated duration is not met, other target power supply microgrids will be selected from the power supply microgrid group to which the target power supply microgrid belongs, until the estimated duration is reached.

7. The multi-source collaborative optimization method for power distribution networks according to claim 1, characterized in that, The steps of optimizing the objective function using a swarm optimization algorithm to select the target power supply microgrid and its corresponding power supply switching time, and setting a power supply program to supply power to the designated distribution network based on the selected target power supply microgrid and its corresponding power supply switching time, include: Based on the unit electricity price of the selected target power supply microgrids, the power supply sequence of each target power supply microgrid is set from low to high. Calculate the corresponding power switching time based on the power supply sequence of each selected target power supply microgrid, and set the power supply program to supply power to the designated distribution network.

8. A multi-source collaborative optimization device for power distribution networks, characterized in that, The device includes: The first acquisition module is used to acquire multiple power supply microgrids that can be used to supply power to the specified distribution network when the specified distribution network fails. A grouping module is used to divide the multiple power supply microgrids into multiple power supply microgrid groups; wherein one of the power supply microgrid groups includes at least one power supply microgrid. The second acquisition module is used to acquire the first energy value of the average energy consumption of each of the power supply microgrids during the specified distribution network fault time within a historical preset time period, and the second energy value of the current energy storage of each of the power supply microgrids. The calculation module is used to calculate the power supply value corresponding to each of the power supply microgrids based on the first energy value and the second energy value corresponding to each of the power supply microgrids, and to record the power supply microgrids whose power supply value is greater than a preset value as the target power supply microgrids; The third acquisition module is used to acquire the third energy value required by the specified distribution network, as well as the unit electricity price of each of the target power supply microgrids, and to set the objective function. Where Y is the objective function, This indicates taking the minimum value. This represents the second energy value of the t-th microgrid in the n-th power supply microgrid group. Let represent the unit electricity price of the t-th microgrid in the n-th microgrid group. h is a parameter; if the t-th microgrid in the n-th microgrid group is the target microgrid, then h = 1; otherwise, h = 0. For hyperparameters, Indicates the number of target power supply microgrids selected. Z represents the third energy value, and Z represents the switching stability parameter value related to the selected target power supply microgrid; The power supply module is used to optimize the objective function by using the group optimization intelligent algorithm to select the target power supply microgrid and the corresponding power supply switching time, and to set the power supply program according to the selected target power supply microgrid and the corresponding power supply switching time to supply power to the designated distribution network.

9. A computer-readable storage medium, characterized in that, The system contains a computer program that, when executed by a processor, causes the processor to perform the steps of the multi-source collaborative optimization method for a distribution network as described in any one of claims 1 to 7.

10. A computer device, characterized in that, The device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the multi-source collaborative optimization method for a distribution network as described in any one of claims 1 to 7.

Images