Distribution network dispatching operation intelligent identification control method based on cloud platform

Abstract

The invention relates to the technical field of power grid operation control, in particular to a distribution network dispatching operation intelligent identification control method based on a cloud platform, which comprises the following steps: calculating a power consumption representative value of a power consumption area in each time interval according to power consumption data stored by the cloud platform, determining an interval characteristic value of each time interval according to the power consumption representative value, the method comprises the following steps: determining data properties of electricity representative values based on interval characteristic values, determining a parallel region according to the data properties, calculating combined path values in the parallel region to obtain an optimal combined region, and automatically adjusting route configuration by a power distribution network according to the optimal combined region so as to realize uniform distribution of electricity loads and avoid local overload or light load. And meanwhile, the reliability and economy of the power grid are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid operation control, and in particular to a cloud platform-based intelligent identification and control method for distribution network dispatching operation. Background Art

[0002] In modern power systems, distribution network dispatching and operation is a key link in ensuring reliable power supply and efficient utilization.

[0003] The prior art CN110474334A discloses a method for controlling the whole process of distribution network dispatching and operation, including: setting up a fault handling closed-loop control process in the distribution automation system that covers all types of faults in the distribution network and runs through the whole process of fault handling; automatically analyzing and identifying faults and locating tripping points and fault intervals; generating a fault isolation and power transfer plan and providing a corresponding operation sequence; connecting with the OMS information interaction channel and publishing power outage information; providing a one-button sequential control function for the plan; manually resetting the fault point and regenerating the fault isolation and power transfer plan; merging the secondary fault and primary fault handling process; recording the fault and emergency repair content and synchronizing it to the OMS dispatch log to support the selection of safety information; identifying remote control failures and missed reports and false reports, and pushing the list of primary and secondary equipment involved to the defect control process; generating a post-analysis report; and providing a historical data query tool.

[0004] However, as distribution automation continues to improve, distribution scheduling issues will still rely on manual experience, which will make distribution scheduling unable to respond to changes in user demand in real time, resulting in uneven distribution of power resources and affecting the stability and economy of the power grid. Summary of the invention

[0005] The purpose of the present invention is to solve the problems in the background technology and to propose an intelligent identification and control method for distribution network scheduling operation based on a cloud platform.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] The intelligent identification and control method for distribution network dispatching operation based on the cloud platform specifically includes the following steps:

[0008] Step 1: Determine the overall area of ​​power supply of the distribution network and the power supply path of the power grid circuit in the overall area, and divide the overall area of ​​the distribution network into several power consumption areas according to the power supply path. The power consumption data of the power consumption area is collected in real time based on the power collection equipment, and uploaded to the cloud platform for storage;

[0009] Step 2: Set the time interval, calculate the representative power consumption value of the power consumption area in each time interval based on the storage data of the cloud platform, and then calculate the data standard deviation of each time interval based on the representative power consumption value. Use the data standard deviation to determine the stable data in the representative power consumption value, and then take the average of the stable data to obtain the interval characteristic value. Finally, determine the convex data and concave data in the representative power consumption value based on the interval characteristic value;

[0010] Step 3: Take each time interval as a calibration interval in turn, determine the parallel area according to the convexity data and concavity data and the interval characteristic value in the calibration interval, the parallel area includes the first sub-area and the second sub-area, and then obtain the optimal combination area according to the combined path value of the parallel area, and then merge the two power consumption areas in the optimal combination area to obtain the combined power supply area, and the distribution network system automatically adjusts the line configuration according to the line corresponding to the combined power supply area according to the real-time time interval;

[0011] Step 4: Obtain the power supply of the distribution network to the entire area and the power consumption value of the entire area in each time interval, and then determine the simulation model of the unit loss coefficient based on the power transportation path value of the distribution network and the neural network model, and then identify the actual time interval at this time, and determine the power consumption value of the entire area according to the representative value of electricity consumption, and determine the actual power supply at this time interval based on the power consumption value and the unit loss coefficient. Finally, the distribution network supplies power to the power-consuming area according to the actual power supply.

[0012] As a further solution of the present invention, a method for calculating the representative value of electricity consumption includes:

[0013] S1: Take one day as the cycle time point, and divide one day into several time intervals according to the unit time;

[0014] S2: arbitrarily select a power consumption area as the target analysis area, and extract the power consumption data of the target analysis area in the previous cycle time from the storage information of the cloud platform, and the cycle time is the threshold;

[0015] A time interval is selected as a calibration interval, and the representative power consumption value of the target analysis area in the calibration interval is obtained, wherein the power consumption data of the calibration area at each cycle time point is obtained according to the cycle time point in the cycle time, and the average of all power consumption data is taken as the representative power consumption value of the target analysis area in the calibration interval.

[0016] As a further solution of the present invention, a method for determining stable data in the power consumption representative value includes:

[0017] Calculate the representative power consumption values ​​of all power consumption areas in different time intervals, and select a calibration interval in the time interval. Mark the representative power consumption value of the power consumption area in this calibration interval as DYi, i∈[1, I], indicating that there are I power consumption areas;

[0018] based on The data standard deviation u of the calibration interval is obtained, and Dp is the mean value of the representative value of electricity consumption DYi;

[0019] According to the normal distribution algorithm, take the distribution interval Q1, Q1 = [Dp-2u, Dp+2u], compare the power consumption representative value DYi of the calibration interval with the distribution interval, if DYi∈Q1, then mark the corresponding power consumption representative value as stable data, otherwise, The corresponding representative value of electricity consumption is marked as peak data.

[0020] As a further solution of the present invention, a method for determining convexity data and concavity data includes:

[0021] After the comparison between the representative power consumption value DYi and the distribution interval is completed, all stable data in the calibration interval are obtained, and then the mean of the stable data is calculated, and the mean calculation result is marked as the interval characteristic value Tq. Then, the peak data of the calibration interval is marked as Zf, and the peak data Zf is compared with the interval characteristic value Tq. If Zf>Tq, the representative power consumption value corresponding to the peak data Zf is marked as convex data. If Zf<Tq, the representative power consumption value corresponding to the peak data Zf is marked as concave data.

[0022] As a further solution of the present invention, a method for determining a parallel region includes:

[0023] Taking each time interval as a calibration interval in turn, obtaining the power consumption representative value of each power consuming user in the calibration interval, and obtaining the interval characteristic value Tq of the calibration interval at the same time;

[0024] Data selection is performed in the convex data and the concave data, and the inequality B1 is made according to the selected data: Established, where X k represents convex data and concave data, k1 and k2 belong to k, and k1≠k2, n is a positive integer, and b1 is a threshold constant;

[0025] Based on inequality B1, X that makes inequality B1 true k1 and X k2 The corresponding power consumption area is marked as a parallel area, and X k1 The corresponding power consumption area is marked as the first sub-area, and X k2 The corresponding power consumption area is marked as the second sub-area, and the parallel area is composed of the first sub-area and the second sub-area.

[0026] As a further solution of the present invention, when determining the parallel region according to inequality B1, the data properties in the parallel region can only be combined by concave data and concave data and concave data and convex data, and if there is convex data divided by Tq∈[n, n+b1], the power consumption region corresponding to this convex data is directly marked as a parallel region.

[0027] As a further solution of the present invention, a method for obtaining a combined power supply area includes:

[0028] Get all parallel regions in the calibration interval, and get the combined path value LHc of the first sub-region and the second sub-region in the parallel region, based on Determine the optimal combination region, where c represents different parallel regions, and c∈[1, f1], f1 represents a total of f1 parallel regions obtained after operating the inequality B1, Indicates taking The minimum value of the operation;

[0029] According to the optimal combination area, the first sub-area and the second sub-area in the optimal combination area are merged to obtain a combined power supply area, and based on inequality B1, the n value of each optimal combination area is determined;

[0030] The distribution network identifies the real-time time interval. The distribution network system automatically adjusts the line configuration according to the lines in the combined power supply area corresponding to the real-time time interval and the n value, and supplies electricity to the power supply combination area and the power consumption area corresponding to the stable data.

[0031] As a further solution of the present invention, when determining the optimal combination area, in a group During the operation, the first sub-region and the second sub-region of any parallel region do not overlap with the first sub-region and the second sub-region of other parallel regions. If there is overlap, the overlapping combined path value LHc is randomly deleted.

[0032] As a further solution of the present invention, a method for determining the unit loss coefficient includes:

[0033] SS1: Based on the storage information of the cloud platform within the cycle time, the power supply Goj of the distribution network in different time intervals at each cycle time point is collected. At the same time, the power consumption value of the overall area powered by the distribution network in different time intervals is collected and marked as Dzj, where j represents different time intervals;

[0034] The power supply refers to the total amount of electricity provided by the distribution network to the user side, including the amount of electricity consumed by the user and the amount of electricity lost during line transmission. The power consumption value refers to the sum of the power consumption data of all power consumption areas.

[0035] SS2: Measure the power transport distance value Ld of the distribution network. The power transport distance value Ld refers to the sum of the power movement paths between the distribution network and all power consumption areas;

[0036] The power supply Goj and power consumption Dzj in each time interval are taken as data groups, and combined with the power transportation distance Ld, the data groups of the time intervals within the cycle time are taken as test data, and input into the simulation model for simulation training, and the simulation model M1 is obtained according to the simulation training results: Where Hd is the unit loss coefficient, Go is the power supply, Dz is the power consumption value, Go and Dz correspond to each other, a1, a2 and a3 are all fixed factors, and λ is the exponential factor.

[0037] As a further solution of the present invention, a method for determining the actual power supply amount in a time interval includes:

[0038] Identify the actual time interval at this time, obtain the power consumption representative values ​​of all power consumption areas in this time interval, calculate the sum of the power consumption representative values ​​of all power consumption areas, and mark it as DXb;

[0039] according to The optimal solution of the power supply Go is taken, and the optimal solution of the power supply Go is used as the actual power supply in the time interval at this time. Finally, the distribution network supplies power to the power consumption area according to the actual power supply. Hdmin refers to the minimum value of the unit loss coefficient Hd within the limited range. The limited range refers to The limited interval is [Ry1, Ry2], Ry1 and Ry2 are both proportional thresholds, and Ry1≤Ry2.

[0040] Compared with the prior art, the advantages of the present invention are:

[0041] The present invention calculates the representative power consumption value of the power consumption area in each time interval, determines the interval characteristic value of each time interval according to the representative power consumption value, determines the data property of the representative power consumption value based on the interval characteristic value, and then takes the convex data and the concave data according to the data property, and further analyzes to obtain the parallel area, and then calculates the combined path value in the parallel area to determine the optimal combined area, and then the distribution network automatically adjusts the route configuration according to the optimal combined area, thereby realizing the uniform distribution of power load, avoiding local overload or underload, and enhancing the reliability and economy of the power grid;

[0042] The present invention determines a simulation model of the unit loss coefficient of the distribution network based on the historical power supply data and the electric energy values ​​consumed by users stored in the cloud platform, combined with the power transportation distance value of the distribution network, and then determines the actual power supply in the time interval based on the sum of the representative values ​​of power consumption in the power consumption areas in the actual time interval, and supplies power to the power consumption areas according to the actual power supply, thereby improving the utilization efficiency of power resources and reducing transmission losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic diagram of the process method structure of the present invention. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0045] Embodiment 1, refer to Figure 1 , a distribution network dispatching operation intelligent identification control method based on a cloud platform, the method specifically comprises the following steps:

[0046] Step 1: According to the power distribution information, the overall power supply area of ​​the distribution network is determined, and at the same time, according to the power supply path of the power grid circuit, the overall power supply area of ​​the distribution network is divided into several power consumption areas, wherein each branch of the power supply path in the power grid circuit corresponds to a power consumption area, and further, there may be multiple power users in a power consumption area;

[0047] Afterwards, an electricity collection device is installed on each electricity user. The electricity collection device is used to collect the electricity consumption data of the electricity user in real time and upload it to the cloud platform. The cloud platform is used to store the real-time collected electricity consumption data. In this embodiment, the electricity collection device is selected as a smart meter;

[0048] Step 2: Based on the storage information of the cloud platform, the data properties of the power consumption data of the power consumption area in different time intervals are analyzed, wherein the data properties include stable data, convex data and concave data. Specifically, the method for determining the data properties of the power consumption data of the power consumption area in different time intervals includes:

[0049] S1: taking one day as a cycle time point, and dividing one day into a number of time intervals according to the unit time. In this embodiment, the unit time is set to 1 hour, so there are 24 time intervals in one cycle time point;

[0050] S2: arbitrarily select a power consumption area as the target analysis area, and extract the power consumption data of the target analysis area in the previous cycle time from the storage information of the cloud platform, where the cycle time is a threshold. In this embodiment, the cycle time is set to 3 months;

[0051] Select a time interval as a calibration interval, and obtain the power consumption representative value of the target analysis area in the calibration interval, wherein the power consumption data of the calibration area at each cycle time point is obtained according to the cycle time point in the cycle time, and the average of all power consumption data is taken as the power consumption representative value;

[0052] It should be further explained that when taking the average of the power consumption data of the calibration area within the cycle time, it is necessary to identify the abnormal data, delete the identified abnormal data, and then perform the average operation;

[0053] The time intervals of the target analysis area are used as calibration intervals in turn, and the representative value of electricity consumption in each time interval is calculated according to the above method;

[0054] S3: According to the method of step S2, the representative power consumption values ​​of all power consumption areas in different time intervals are calculated, and a calibration interval is selected in the time interval, and the representative power consumption values ​​of the power consumption areas in this calibration interval are marked as DYi, i∈[1, I], indicating that there are I power consumption areas;

[0055] based on The data standard deviation u of the calibration interval is obtained, and Dp is the mean value of the representative value of electricity consumption DYi;

[0056] Then, according to the normal distribution algorithm, the distribution interval Q1 is taken, Q1 = [Dp-2u, Dp+2u], and the power consumption representative value DYi of the calibration interval is compared with the distribution interval. If DYi∈Q1, the corresponding power consumption representative value is marked as stable data. Otherwise, The corresponding representative value of electricity consumption is marked as peak data;

[0057] After the comparison between the power consumption representative value DYi and the distribution interval is completed, all stable data in the calibration interval are obtained, and then the mean of the stable data is calculated, and the mean calculation result is marked as the interval characteristic value Tq, and then the peak data of the calibration interval is marked as Zf, and the peak data Zf is compared with the interval characteristic value Tq. If Zf>Tq, the power consumption representative value corresponding to the peak data Zf is marked as convex data, and if Zf<Tq, the power consumption representative value corresponding to the peak data Zf is marked as concave data. It should be further explained that there is no situation where Zf=Tq here. If Zf=Tq occurs, it means that the front-end data processing is abnormal, and a processing abnormality signal is generated, and the relevant technical personnel are reminded through the terminal device;

[0058] According to the above method, the data properties of the representative values ​​of electricity consumption in different time intervals of all power consumption areas are marked;

[0059] Step 3: According to the data properties of the representative power consumption values ​​of the power consumption areas, set the optimal combination area. The specific setting method includes:

[0060] Take each time interval as the calibration interval in turn, obtain the representative value of electricity consumption of each power consumer in the calibration interval, and based on the data properties, obtain the mean value of stable data in the calibration interval, that is, the interval characteristic value Tq;

[0061] Data selection is performed in the convex data and the concave data, and the inequality B1 is made according to the selected data: Established, where X k represents convex data and concave data, k1 and k2 belong to k, and k1≠k2, n is a positive integer, b1 is a threshold constant, and in this embodiment, b1 is 0.253;

[0062] Then, based on inequality B1, we will find X that makes inequality B1 true. k1 and X k2 The corresponding power consumption area is marked as a parallel area, and X k1 The corresponding power consumption area is marked as the first sub-area, and X k2 The corresponding power consumption area is marked as the second sub-area. At this time, the parallel area consists of the first sub-area and the second sub-area;

[0063] In another embodiment of the present solution, when the parallel region is determined according to inequality B1, the data properties in the parallel region can only be a combination of concave data and concave data and a combination of concave data and convex data, that is, X k1 and X k2 They cannot be convex data at the same time. If there is convex data divided by Tq∈[n, n+b1], the power consumption area corresponding to this convex data is directly marked as a parallel area;

[0064] Get all parallel regions in the calibration interval, and get the combined path value LHc of the first sub-region and the second sub-region in the parallel region, based on Determine the optimal combination region, where c represents different parallel regions, and c∈[1, f1], f1 represents a total of f1 parallel regions obtained after operating the inequality B1, Indicates taking The minimum value of the operation;

[0065] It should be further explained that when determining the optimal combination area, During the operation, the first sub-region and the second sub-region of any parallel region do not overlap with the first sub-region and the second sub-region of other parallel regions. If there is overlap, the overlapping combined path value LHc is randomly deleted;

[0066] Then, according to the optimal combination area, the first sub-area and the second sub-area in the optimal combination area are merged to obtain a combined power supply area, and at the same time, based on inequality B1, the n value of each optimal combination area is determined;

[0067] According to the above method, the power supply combination area of ​​each time interval is determined, and then the distribution network identifies the real-time time interval. The distribution network system automatically adjusts the line configuration according to the line of the combined power supply area corresponding to the real-time time interval and the n value, and supplies electricity to the power supply combination area and the power consumption area corresponding to the stable data, so as to evenly distribute the power load of the distribution network;

[0068] Embodiment 2: Based on Embodiment 1, this embodiment differs from Embodiment 1 in that this embodiment further includes:

[0069] According to the power transmission path of the power consumption area, the unit loss value of the distribution network is determined, and based on the unit loss value, the real-time power supply of the distribution network is determined. The specific method includes:

[0070] SS1: Based on the storage information of the cloud platform within the cycle time, the power supply Goj of the distribution network in different time intervals at each cycle time point is collected;

[0071] At the same time, the power consumption values ​​of the overall area powered by the distribution network in different time intervals are collected and marked as Dzj, where j represents different time intervals;

[0072] It should be further explained that the power supply refers to the total power provided by the distribution network to the user side, including the power consumed by the user and the power lost during line transmission, and the power consumption value refers to the sum of the power consumption data of all power consumption areas;

[0073] SS2: Measure the power transport distance value Ld of the distribution network. The power transport distance value Ld refers to the sum of the power movement paths between the distribution network and all power consumption areas;

[0074] The power supply Goj and power consumption Dzj in each time interval are taken as data groups, and the power transportation distance value is combined. The data groups of the time intervals within the cycle time are taken as test data and input into the simulation model for simulation training. The simulation model M1 is obtained according to the simulation training results: Wherein Hd is the unit loss coefficient, Go is the power supply, Dz is the power consumption value, Go and Dz correspond to each other, a1, a2 and a3 are fixed factors, λ is an exponential factor, and the specific a1, a2, a3 and λ are obtained after multiple iterations of training of the simulation model, and the simulation model in this embodiment uses a neural network model algorithm, and the specific algorithm process is the prior art, which will not be described here;

[0075] Identify the actual time interval at this time, obtain the power consumption representative values ​​of all power consumption areas in this time interval, calculate the sum of the power consumption representative values ​​of all power consumption areas, and mark it as DXb;

[0076] Afterwards according to The optimal solution of the power supply Go is taken, and the optimal solution of the power supply Go is used as the actual power supply in the time interval at this time. Finally, the distribution network supplies power to the power consumption area according to the actual power supply. Hdmin refers to the minimum value of the unit loss coefficient Hd within the limited range. The limited range refers to The limited interval is [Ry1, Ry2], Ry1 and Ry2 are both ratio thresholds, and Ry1≤Ry2, and the specific values ​​of Ry1 and Ry2 are obtained by technical personnel in this field after big data calculation.

[0077] Embodiment 3: This embodiment is based on Embodiment 1 and Embodiment 2, and is used to integrate Embodiment 1 and Embodiment 2 and implement them.

[0078] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. Intelligent identification and control method of distribution network dispatching operation based on cloud platform, It is characterized in that The specific steps include: Step 1: Determine the overall area of ​​power supply of the distribution network and the power supply path of the power grid circuit in the overall area, and divide the overall area of ​​the distribution network into several power consumption areas according to the power supply path. The power consumption data of the power consumption area is collected in real time based on the power collection equipment, and uploaded to the cloud platform for storage; Step 2: Set the time interval, calculate the representative power consumption value of the power consumption area in each time interval based on the storage data of the cloud platform, and then calculate the data standard deviation of each time interval based on the representative power consumption value. Use the data standard deviation to determine the stable data in the representative power consumption value, and then take the average of the stable data to obtain the interval characteristic value. Finally, determine the convex data and concave data in the representative power consumption value based on the interval characteristic value; Step 3: Take each time interval as a calibration interval in turn, determine the parallel area according to the convexity data and concavity data and the interval characteristic value in the calibration interval, the parallel area includes the first sub-area and the second sub-area, and then obtain the optimal combination area according to the combined path value of the parallel area, and then merge the two power consumption areas in the optimal combination area to obtain the combined power supply area, and the distribution network system automatically adjusts the line configuration according to the line corresponding to the combined power supply area according to the real-time time interval; Step 4: Obtain the power supply of the distribution network to the entire area and the power consumption value of the entire area in each time interval, and then determine the simulation model of the unit loss coefficient based on the power transportation path value of the distribution network and the neural network model, and then identify the actual time interval at this time, and determine the power consumption value of the entire area according to the representative value of electricity consumption. Determine the actual power supply at this time interval based on the power consumption value and the unit loss coefficient, and finally the distribution network supplies power to the power-consuming area according to the actual power supply.

2. According to the cloud platform-based intelligent identification and control method for distribution network dispatching operation according to claim 1, It is characterized in that The calculation method of the representative value of electricity consumption includes: S1: Take one day as the cycle time point, and divide one day into several time intervals according to the unit time; S2: arbitrarily select a power consumption area as the target analysis area, and extract the power consumption data of the target analysis area in the previous cycle time from the storage information of the cloud platform, and the cycle time is the threshold; A time interval is selected as a calibration interval, and the representative power consumption value of the target analysis area in the calibration interval is obtained, wherein the power consumption data of the calibration area at each cycle time point is obtained according to the cycle time point in the cycle time, and the average of all power consumption data is taken as the representative power consumption value of the target analysis area in the calibration interval.

3. According to the cloud platform-based intelligent identification and control method for distribution network dispatching operation according to claim 2, It is characterized in that The method for determining the stable data in the representative value of electricity consumption includes: Calculate the representative power consumption values ​​of all power consumption areas in different time intervals, and select a calibration interval in the time interval. Mark the representative power consumption value of the power consumption area in this calibration interval as DYi, i∈[1, I], indicating that there are I power consumption areas; based on The data standard deviation u of the calibration interval is obtained, and Dp is the mean value of the representative value of electricity consumption DYi; According to the normal distribution algorithm, take the distribution interval Q1, Q1 = [Dp-2u, Dp+2u], compare the power consumption representative value DYi of the calibration interval with the distribution interval, if DYi∈Q1, then mark the corresponding power consumption representative value as stable data, otherwise, The corresponding representative value of electricity consumption is marked as peak data.

4. According to the cloud platform-based intelligent identification and control method for distribution network dispatching operation according to claim 3, It is characterized in that Methods for determining convex data and concave data include: After the comparison between the representative power consumption value DYi and the distribution interval is completed, all stable data in the calibration interval are obtained, and then the mean of the stable data is calculated, and the mean calculation result is marked as the interval characteristic value Tq. Then, the peak data of the calibration interval is marked as Zf, and the peak data Zf is compared with the interval characteristic value Tq. If Zf>Tq, the representative power consumption value corresponding to the peak data Zf is marked as convex data. If Zf<Tq, the representative power consumption value corresponding to the peak data Zf is marked as concave data.

5. According to the cloud platform-based intelligent identification and control method for distribution network dispatching operation according to claim 1, It is characterized in that The methods for determining parallel regions include: Taking each time interval as a calibration interval in turn, obtaining the power consumption representative value of each power consuming user in the calibration interval, and obtaining the interval characteristic value Tq of the calibration interval at the same time; Data selection is performed in the convex data and the concave data, and the inequality B1 is made according to the selected data: Established, where X k represents convex data and concave data, k1 and k2 belong to k, and k1≠k2, n is a positive integer, and b1 is a threshold constant; Based on inequality B1, X that makes inequality B1 true k1 and X k2 The corresponding power consumption area is marked as a parallel area, and X k1 The corresponding power consumption area is marked as the first sub-area, and X k2 The corresponding power consumption area is marked as the second sub-area, and the parallel area is composed of the first sub-area and the second sub-area.

6. According to the cloud platform-based intelligent identification and control method for distribution network dispatching operation according to claim 5, It is characterized in that When determining the parallel region according to inequality B1, the data properties in the parallel region can only be a combination of concave data and concave data and a combination of concave data and convex data, and if there is convex data divided by Tq∈[n, n+b1], the power consumption region corresponding to this convex data is directly marked as a parallel region.

7. According to claim 5, the intelligent identification and control method for distribution network dispatching operation based on cloud platform, It is characterized in that Methods for obtaining the combined power supply area include: Get all parallel regions in the calibration interval, and get the combined path value LHc of the first sub-region and the second sub-region in the parallel region, based on Determine the optimal combination region, where c represents different parallel regions, and c∈[1, f1], f1 represents a total of f1 parallel regions obtained after operating the inequality B1, Indicates taking The minimum value of the operation; According to the optimal combination area, the first sub-area and the second sub-area in the optimal combination area are merged to obtain a combined power supply area, and based on inequality B1, the n value of each optimal combination area is determined; The distribution network identifies the real-time time interval. The distribution network system automatically adjusts the line configuration according to the lines in the combined power supply area corresponding to the real-time time interval and the n value, and supplies electricity to the power supply combination area and the power consumption area corresponding to the stable data.

8. According to the cloud platform-based intelligent identification and control method for distribution network dispatching operation according to claim 7, It is characterized in that When determining the optimal combination area, in a group During the operation, the first sub-region and the second sub-region of any parallel region do not overlap with the first sub-region and the second sub-region of other parallel regions. If there is overlap, the overlapping combined path value LHc is randomly deleted.

9. According to the cloud platform-based intelligent identification and control method for distribution network dispatching operation according to claim 1, It is characterized in that Methods for determining the unit loss factor include: SS1: Based on the storage information of the cloud platform within the cycle time, the power supply Goj of the distribution network in different time intervals at each cycle time point is collected. At the same time, the power consumption value of the overall area powered by the distribution network in different time intervals is collected and marked as Dzj, where j represents different time intervals; The power supply refers to the total amount of electricity provided by the distribution network to the user side, including the amount of electricity consumed by the user and the amount of electricity lost during line transmission. The power consumption value refers to the sum of the power consumption data of all power consumption areas. SS2: Measure the power transport distance value Ld of the distribution network. The power transport distance value Ld refers to the sum of the power movement paths between the distribution network and all power consumption areas; The power supply Goj and power consumption Dzj in each time interval are taken as data groups, and combined with the power transportation distance Ld, the data groups of the time intervals within the cycle time are taken as test data, and input into the simulation model for simulation training, and the simulation model M1 is obtained according to the simulation training results: Where Hd is the unit loss coefficient, Go is the power supply, Dz is the power consumption value, Go and Dz correspond to each other, a1, a2 and a3 are all fixed factors, and λ is the exponential factor.

10. The intelligent identification and control method for distribution network dispatching operation based on cloud platform according to claim 9, It is characterized in that Methods for determining the actual power supply amount in a time interval include: Identify the actual time interval at this time, obtain the power consumption representative values ​​of all power consumption areas in this time interval, calculate the sum of the power consumption representative values ​​of all power consumption areas, and mark it as DXb; according to The optimal solution of the power supply Go is taken, and the optimal solution of the power supply Go is used as the actual power supply in the time interval at this time. Finally, the distribution network supplies power to the power consumption area according to the actual power supply. Hdmin refers to the minimum value of the unit loss coefficient Hd within the limited range. The limited range refers to The limited interval is [Ry1, Ry2], Ry1 and Ry2 are both proportional thresholds, and Ry1≤Ry2.

Images