Power grid adjustable resource evaluation method and device based on cloud edge collaboration, terminal equipment and storage medium

Abstract

The invention discloses a power grid adjustable resource evaluation method and device based on cloud edge collaboration, terminal equipment and a storage medium. The method comprises the steps of obtaining power data in a to-be-evaluated power region; performing sequence distribution according to the power data and a preset data volume threshold value, and generating a corresponding cloud sequence and an edge sequence; transmitting the cloud sequence and the corresponding first power data used for representing the cloud sequence to a cloud server, so that the cloud server performs splitting to obtain second power data, and issuing the cloud sequence and the second power data to the edge device; transmitting the edge sequence and corresponding third power data used for representing the edge sequence to the edge device, so that the edge device obtains a resource parameter threshold value of the adjustable resource according to calculation; and performing evaluation according to the resource parameter threshold and the power data to obtain an adjustable resource evaluation result of the to-be-evaluated power region. By implementing the method and the system, the power grid adjustable resource evaluation based on cloud edge collaboration is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid resource assessment, and in particular to a method, device, terminal equipment and storage medium for assessing adjustable power grid resources based on cloud-edge collaboration. Background Art

[0002] With the continuous expansion of the power grid and the rapid development of clean energy, the power system is facing increasingly complex coordination and management issues of dispatchable resources. The main purpose of grid adjustable resource assessment is to evaluate the capacity and usage of various dispatchable resources in order to achieve optimal grid dispatch and reasonable resource allocation.

[0003] At present, the application of edge computing in power systems is increasing, and the collaborative work between cloud and edge devices has become particularly important. Most of the existing adjustable resource evaluation methods only rely on information from the cloud, ignoring the value of edge devices in the actual data processing process. Therefore, it is difficult to evaluate the resource allocation between cloud and edge devices, resulting in errors in the evaluation results. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, terminal device and storage medium for evaluating adjustable resources of a power grid based on cloud-edge collaboration, which can effectively solve the problem that the prior art is difficult to evaluate the resource allocation between cloud and edge devices, resulting in errors in the evaluation results.

[0005] An embodiment of the present invention provides a method for evaluating adjustable resources of a power grid based on cloud-edge collaboration, which is applicable to a cloud server and an edge device. The method includes:

[0006] Acquire power data of several power nodes in the power area to be evaluated; wherein the power data includes: voltage data, current data and electric heating temperature data;

[0007] Perform sequence allocation according to the power data and a preset data volume threshold, and generate a cloud sequence and an edge sequence corresponding to the power data;

[0008] The cloud sequence and the first power data corresponding to the cloud sequence are transmitted to the cloud server, so that the cloud server splits the cloud sequence and the first power data corresponding to the cloud sequence to obtain the second power data after splitting, and sends the cloud sequence and the second power data to the edge device;

[0009] Transmitting the edge sequence and the third power data corresponding to the edge sequence to the edge device, so that the edge device calculates the resource parameter threshold of the adjustable resource according to the edge sequence, the second power data and the third power data;

[0010] An evaluation is performed according to the resource parameter threshold and the power data to obtain an evaluation result of adjustable resources in the power area to be evaluated.

[0011] Furthermore, performing sequence allocation according to the power data and a preset data volume threshold to generate a cloud sequence and an edge sequence corresponding to the power data includes:

[0012] determining a power data amount of the power data according to the power data;

[0013] According to the comparison between the power data volume and a preset data volume threshold, the power data whose power data volume is less than the data volume threshold is assigned an edge sequence, and an edge sequence of the power data corresponding to the power data volume less than the data volume threshold is generated;

[0014] The power data whose power data volume is greater than or equal to the data volume threshold is allocated to a cloud sequence, and a cloud sequence of the power data corresponding to the power data volume greater than or equal to the data volume threshold is generated.

[0015] Furthermore, transmitting the cloud sequence and the first power data corresponding to the cloud sequence to the cloud server includes:

[0016] Using the cloud sequence as a first identification code of the cloud server; and storing first power data corresponding to the cloud sequence in a first transmission space;

[0017] Acquire a first permission for representing a first transmission space according to the first identification code, and monitor a space lock state of a cloud server;

[0018] When it is detected that the space lock state of the cloud server is in progress, taking out the first power data from the first transmission space according to the first authority, and transmitting the cloud sequence and the first power data to the cloud server;

[0019] Wherein, when it is detected that the space lock state of the cloud server is in an idle state, the space lock state of the cloud server continues to be monitored.

[0020] Furthermore, the cloud server is used to split the cloud sequence and the first power data corresponding to the cloud sequence to obtain the second power data after splitting;

[0021] The method comprises: performing splitting according to the cloud sequence and the first power data corresponding to the cloud sequence to obtain second power data after splitting, including:

[0022] According to the cloud sequence and the preset number of split stacks, the cloud sequence is equally divided according to the number of split stacks to obtain an equally divided cloud sequence;

[0023] Constructing folders corresponding to the number of split stacks according to the equally divided cloud sequence; and splitting the corresponding first power data according to the equally divided cloud sequence to obtain a number of target power data;

[0024] Each target power data is stored in a corresponding file to obtain second power data representing the split.

[0025] Further, the edge device is used to calculate a resource parameter threshold of the adjustable resource according to the edge sequence, the second power data and the third power data;

[0026] Calculating a resource parameter threshold of an adjustable resource according to the edge sequence, the second power data, and the third power data includes:

[0027] Obtain the number of edge devices and a first processing amount used to represent the data processing amount of the computing node; wherein the first processing amount of the computing node in each edge device is consistent;

[0028] Obtaining a target processing amount by adding the data amount of the second power data and the data amount of the third power data;

[0029] Calculate the number of computing nodes according to the target processing volume, the number of edge devices, and the first processing volume;

[0030] Generate a plurality of node model data corresponding to the number of computing nodes according to the second power data, the third power data and the number of computing nodes;

[0031] Several node model data are input into the preset edge computing model of the corresponding edge device for sorting to obtain the resource parameter threshold of the adjustable resource.

[0032] Further, an evaluation is performed according to the resource parameter threshold and the power data to obtain an evaluation result of adjustable resources of the power area to be evaluated, including:

[0033] According to the resource parameter threshold, determining a first parameter threshold for indicating a resource shortage state and a second parameter threshold for indicating a resource surplus state; wherein the second parameter threshold is greater than the first parameter threshold;

[0034] Comparing according to the power data amount of the power data, the first parameter threshold and the second parameter threshold;

[0035] When the amount of power data is less than the first parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as resource scarcity;

[0036] When the power data amount is greater than the first parameter threshold and less than the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as normal resources;

[0037] When the power data amount is equal to the first parameter threshold or equal to the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as normal resources;

[0038] When the power data amount is greater than the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as excess resources.

[0039] Furthermore, it also includes:

[0040] Determine the corresponding resource allocation plan according to the adjustable resource evaluation result;

[0041] When the evaluation result of adjustable resources is marked as resource shortage, the adjustable resources of the power area adjacent to the power area to be evaluated and whose evaluation result of adjustable resources is surplus resources are used as supplementary resources for the power area to be evaluated;

[0042] When the adjustable resource assessment result is marked as normal resources, the adjustable resources of the power area to be assessed are kept unchanged;

[0043] When the evaluation result of the adjustable resources is marked as excess resources, the adjustable resources are transported to the power area adjacent to the power area to be evaluated and the evaluation result of the adjustable resources is that the power area is resource-scarce, as a supplementary resource for the adjacent power area.

[0044] As an improvement of the above solution, another embodiment of the present invention provides a power grid adjustable resource evaluation device based on cloud-edge collaboration, including:

[0045] A power data acquisition module is used to acquire power data of several power nodes in the power area to be evaluated; wherein the power data includes: voltage data, current data and electric heating temperature data;

[0046] A sequence generation module, used to perform sequence allocation according to the power data and a preset data volume threshold, and generate a cloud sequence and an edge sequence corresponding to the power data;

[0047] A cloud splitting module, used to transmit the cloud sequence and the first power data corresponding to the cloud sequence to a cloud server, so that the cloud server splits the cloud sequence and the first power data corresponding to the cloud sequence to obtain second power data after splitting, and sends the cloud sequence and the second power data to the edge device;

[0048] an edge computing module, configured to transmit the edge sequence and third power data corresponding to the edge sequence to an edge device, so that the edge device calculates a resource parameter threshold of an adjustable resource according to the edge sequence, the second power data and the third power data;

[0049] The resource evaluation module is used to perform evaluation according to the resource parameter threshold and the power data to obtain an evaluation result of adjustable resources in the power area to be evaluated.

[0050] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements a method for evaluating adjustable resources of a power grid based on cloud-edge collaboration as described in the above embodiment.

[0051] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a method for evaluating adjustable power grid resources based on cloud-edge collaboration as described in the above embodiment.

[0052] By implementing the present invention, at least the following beneficial effects are achieved:

[0053] The present invention provides a method, device, terminal device and storage medium for evaluating adjustable resources of a power grid based on cloud-edge collaboration, and the method is applicable to cloud servers and edge devices; the method includes: obtaining power data of several power nodes in a power area to be evaluated; wherein the power data includes: voltage data, current data and electric temperature data; performing sequence allocation according to the power data and a preset data volume threshold, and generating a cloud sequence and an edge sequence corresponding to the power data; transmitting the cloud sequence and the first power data corresponding to the cloud sequence to the cloud server, so that the cloud server splits the cloud sequence according to the cloud sequence and the first power data corresponding to the cloud sequence, obtains the second power data after the split, and sends the cloud sequence and the second power data to the edge device; transmitting the edge sequence and the third power data corresponding to the edge sequence to the edge device, so that the edge device calculates the resource parameter threshold of the adjustable resource according to the edge sequence, the second power data and the third power data; performing evaluation according to the resource parameter threshold and the power data, and obtaining the evaluation result of the adjustable resources in the power area to be evaluated. By dividing the power data into different cloud sequences and edge sequences, the cloud server only splits the power data and sends the split data to the edge device, so that the power data can be calculated in the edge device to obtain the adjustable resource evaluation result, thereby realizing the collaborative work of the remote server and the edge device. The edge device calculates the resource parameter threshold according to the power data allocated by the edge sequence and the power data sent by the remote server, combining the advantages of local real-time data and global historical data, thereby improving the accuracy of the evaluation result; through sequence allocation, the power data is effectively distributed between the cloud and edge devices, ensuring load balancing of data processing, avoiding single-point overload of the cloud server, and improving the adjustable resource evaluation efficiency of the entire power grid area. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flowchart of a method for evaluating adjustable resources of a power grid based on cloud-edge collaboration provided by an embodiment of the present invention;

[0055] Figure 2 It is a structural diagram of a power grid adjustable resource assessment device based on cloud-edge collaboration provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] See also Figure 1 , is a flow chart of a method for evaluating adjustable resources of a power grid based on cloud-edge collaboration provided by an embodiment of the present invention, including:

[0058] S1. Obtain power data of several power nodes in the power area to be evaluated; wherein the power data includes: voltage data, current data and electric heating temperature data;

[0059] S2. Perform sequence allocation according to the power data and a preset data volume threshold, and generate a cloud sequence and an edge sequence corresponding to the power data;

[0060] S3, transmitting the cloud sequence and the first power data corresponding to the cloud sequence to the cloud server, so that the cloud server splits the cloud sequence and the first power data corresponding to the cloud sequence to obtain the second power data after splitting, and sends the cloud sequence and the second power data to the edge device;

[0061] S4, transmitting the edge sequence and the third power data corresponding to the edge sequence to the edge device, so that the edge device calculates the resource parameter threshold of the adjustable resource according to the edge sequence, the second power data and the third power data;

[0062] S5. Perform evaluation according to the resource parameter threshold and the power data to obtain an evaluation result of adjustable resources in the power area to be evaluated.

[0063] Specifically, there are several power nodes in the power area to be evaluated, and data acquisition equipment is arranged at each power node to collect power data; the preset data volume threshold device has different numerical ranges and is used to allocate sequences; the first power data represents the power data corresponding to the cloud sequence; the second power data represents the power data after the first power data is split; the third power data represents the power data corresponding to the edge sequence; the resource parameter threshold of the adjustable resources represents the normal resource parameter range of the dispatchable resources in the power area to be evaluated.

[0064] Preferably, the area to be evaluated is composed of a number of power nodes, and the number of the power nodes is recorded as i, where i=1, 2, 3, ..., n, where n is a natural number and n is an integer, and a data acquisition device is correspondingly associated with each numbered power node. The power data acquisition device includes: a power sensor, a signal filtering module, and a signal conversion module; the power sensor includes a voltage sensor, a current sensor, and a temperature sensor, and the voltage data, current data, and electric temperature data between every two power nodes are respectively collected through the voltage sensor, the current sensor, and the temperature sensor. A micro-database and a calibration program are provided in the power sensor, and the micro-database stores standard data values ​​of voltage, current, and electric temperature, which are respectively recorded as V 标 , A 标 and C 标 , obtain the voltage data, current data and electric heating temperature data collected by the power sensor, and record their values ​​as V, A and C respectively.

[0065] The micro-database is set with access rules. When the micro-database is requested to access, the micro-database sends a random sequence code generated by a random function to the administrator. The administrator obtains the IP address of the visitor who accesses the micro-database and sends an email to the IP address. The email stores the generated random sequence code. The visitor accesses the micro-database through the random sequence code and enters V, A and C into the micro-database. After the micro-database detects that data has been stored, it starts the verification program and checks the data according to V. 标 , A 标 , C 标 , V, A and C to obtain the ratio, which are recorded as ratio coefficients X1, X2 and X3 respectively, and X1=V / V 标 、X2=A / A 标 、X3=C / C 标 ;

[0066] When X1∈[1.2, 1.4] or X2∈[1.3, 1.5] or X3∈[1.1, 1.3], the power sensor re-collects the power data, and the voltage data, current data and electric heating temperature data are set with corresponding alarm thresholds. When the alarm threshold is reached, the voltage data, current data and electric heating temperature data are compressed into a data packet and transmitted to the administrator; when X1∈[1, 1.2) or X2∈[1, 1.3) or X3∈[1, 1.1), the voltage data, current data and electric heating temperature data are summarized and converted into a data stream and transmitted to the signal filtering module;

[0067] After the signal filter module obtains the data stream, it continues to filter the data stream into filtered data streams with different values, sets the reserved filtering frequency band and the eliminated filtering frequency band, and the filtered data stream in the reserved filtering frequency band is saved and transmitted to the signal conversion module, and the filtered data stream in the eliminated filtering frequency band is eliminated; the filtered data stream corresponds to different signal quantities, and after the signal conversion module obtains the filtered data stream, it synchronously obtains the signal quantity corresponding to the filtered data stream, first amplifies the value of its signal quantity to the set signal conversion quantity value interval, and then converts the filtered data stream into a digital signal, eliminating the noise generated in the process of converting the filtered data stream into a digital signal. The voltage data, current data, and electric heating temperature data collected by the data acquisition device are collectively referred to as power data. The access rules set by the micro database serve the purpose of monitoring the behavior of visitors, preventing malicious access, and ensuring the security of power data.

[0068] In a preferred embodiment of the present invention, power data of several power nodes in the power area to be evaluated are first obtained; wherein the power data includes: voltage data, current data and electric temperature data; then, sequence allocation is performed according to the power data and a preset data volume threshold to generate a cloud sequence and an edge sequence corresponding to the power data; then, the cloud sequence and the first power data corresponding to the cloud sequence are transmitted to a cloud server, so that the cloud server splits the cloud sequence according to the cloud sequence and the first power data corresponding to the cloud sequence to obtain the second power data after the split, and sends the cloud sequence and the second power data to the edge device; then, the edge sequence and the third power data corresponding to the edge sequence are transmitted to the edge device, so that the edge device calculates the resource parameter threshold of the adjustable resource according to the edge sequence, the second power data and the third power data; finally, an evaluation is performed according to the resource parameter threshold and the power data to obtain an evaluation result of the adjustable resources in the power area to be evaluated. By dividing the power data into different cloud sequences and edge sequences, the cloud server only splits the power data and sends the split data to the edge device, so that the power data can be calculated in the edge device to obtain adjustable resource evaluation results, thereby realizing the collaborative work of the remote server and the edge device. The edge device calculates the resource parameter threshold according to the power data allocated by the edge sequence and the power data sent by the remote server, combining the advantages of local real-time data and global historical data, thereby improving the accuracy of the evaluation results.

[0069] Preferably, performing sequence allocation according to the power data and a preset data volume threshold to generate a cloud sequence and an edge sequence corresponding to the power data includes:

[0070] determining a power data amount of the power data according to the power data;

[0071] According to the comparison between the power data volume and a preset data volume threshold, the power data whose power data volume is less than the data volume threshold is assigned an edge sequence, and an edge sequence of the power data corresponding to the power data volume less than the data volume threshold is generated;

[0072] The power data whose power data volume is greater than or equal to the data volume threshold is allocated to a cloud sequence, and a cloud sequence of the power data corresponding to the power data volume greater than or equal to the data volume threshold is generated.

[0073] In a preferred embodiment of the present invention, the power data volume of the power data is determined according to the power data, which is recorded as data; the preset data volume threshold is recorded as D1; ​​the cloud sequence and the edge sequence are recorded as L 云 and L 边 When data>D1, the power data corresponding to data is assigned cloud sequence L 云 ; When data≦D1, assign edge sequence L to the power data corresponding to data 边 .

[0074] Specifically, transmitting the cloud sequence and the first power data corresponding to the cloud sequence to the cloud server includes:

[0075] Using the cloud sequence as a first identification code of the cloud server; and storing first power data corresponding to the cloud sequence in a first transmission space;

[0076] Acquire a first permission for representing a first transmission space according to the first identification code, and monitor a space lock state of a cloud server;

[0077] When it is detected that the space lock state of the cloud server is in progress, taking out the first power data from the first transmission space according to the first authority, and transmitting the cloud sequence and the first power data to the cloud server;

[0078] Wherein, when it is detected that the space lock state of the cloud server is in an idle state, the space lock state of the cloud server continues to be monitored.

[0079] In a preferred embodiment of the present invention, a temporary data transmission space for power data communication with a cloud server is established, which is recorded as the first transmission space Room1, and the cloud sequence is used as the first identification code of the cloud server and as the unique first identification code of the first transmission space. 云The first identification code represented by the first identification code is used to obtain the first permission to enter the first transmission space Room1. After entering Room1, the cloud server synchronously starts the space lock. The space lock state is set to be in progress and idle state. When the space lock obtains the first identification code, it is in progress state, otherwise, the space lock is idle state; when the space lock state of the cloud server is detected to be in progress state, the power data data stored in Room1 is marked as data1, and then the cloud sequence L 云 And the first power data data1 is transmitted to the cloud server.

[0080] Preferably, the cloud server is used to split the cloud sequence and the first power data corresponding to the cloud sequence to obtain the second power data after splitting;

[0081] The method comprises: performing splitting according to the cloud sequence and the first power data corresponding to the cloud sequence to obtain second power data after splitting, including:

[0082] According to the cloud sequence and the preset number of split stacks, the cloud sequence is equally divided according to the number of split stacks to obtain an equally divided cloud sequence;

[0083] Constructing folders corresponding to the number of split stacks according to the equally divided cloud sequence; and splitting the corresponding first power data according to the equally divided cloud sequence to obtain a number of target power data;

[0084] Each target power data is stored in a corresponding file to obtain second power data representing the split.

[0085] In a preferred embodiment of the present invention, the numerical value of the first power data data1 is denoted as Data1. Several splitting stacks are set at the cloud server, and data1 is input into the several splitting stacks as an input parameter. For example, the concurrent number of splitting stacks is set to 3, that is, 3 splitting stacks are allowed to perform splitting work at the same time; the 3 splitting stacks split the first power data data1 into three equal parts of target power data, and build a data folder for each equal part of power data, and the data folder is used to store each equal part of target power data. The splitting stack has a corresponding stack number S, S is a natural integer, and the stack number S is used as the identification number of the corresponding data folder; data folders with different identification numbers are aggregated, and after the data folders are encrypting the data, a data interaction space is synchronously established, and the data folders are sent to the edge device through the data interaction space. The cloud server takes the data folder to be sent as the target sender, obtains the identification number corresponding to the target sender, and takes the edge device that needs to receive the data folder as the target receiver; establishes a mapping relationship between the target sender and the target receiver, takes the identification number and the permission identification code as the sequence pair of the mapping relationship, denoted as H, and marks the permission identification code as P, with H=S-P; after the target receiver (edge ​​device) obtains the data folder, it deconstructs the data folder, and the data file contains the second power data. The deconstructed second power data continues to perform edge computing in the edge device. By dividing different distinction sequences, the power data with large numerical values ​​is assigned to L in the distinction sequence. 云 , the power data with small numerical value is assigned L in the distinguishing sequence 边 The cloud server only disassembles and sends the power data, which reduces the load pressure of the cloud server; the first identification code, the authority identification code and the space lock all play a role in protecting data security. When the space lock is in progress, it can no longer be accessed by entering other identity identification codes.

[0086] In another preferred embodiment of the present invention, the second power data sent by the cloud server is stored in the edge device, and the edge device is provided with a master database and a slave database. After the second power data is sent, an edge computing model is generated in the edge device, and data backup is performed synchronously, and transfer queue one and transfer queue two are set; through transfer queue one, the power data after data backup is transferred to the master database for storage, and when external IP intrusion, data redundancy or data loss risk exceeding the set protection threshold is detected in the master database, the operation permission of the transfer queue two between the master database and the slave database is obtained; the power data stored in the master database is transferred to any one of the slave databases connected to the master database, and the transfer time, the number of the transfer queue two and the primary key value of the slave database are recorded, and a traceability code is generated, and the traceability code is used to obtain detailed information on the storage of power data.

[0087] Specifically, the edge device is used to calculate the resource parameter threshold of the adjustable resource according to the edge sequence, the second power data and the third power data;

[0088] Calculating a resource parameter threshold of an adjustable resource according to the edge sequence, the second power data, and the third power data includes:

[0089] Obtain the number of edge devices and a first processing amount used to represent the data processing amount of the computing node; wherein the first processing amount of the computing node in each edge device is consistent;

[0090] Obtaining a target processing amount by adding the data amount of the second power data and the data amount of the third power data;

[0091] Calculate the number of computing nodes according to the target processing volume, the number of edge devices, and the first processing volume;

[0092] Generate a plurality of node model data corresponding to the number of computing nodes according to the second power data, the third power data and the number of computing nodes;

[0093] Several node model data are input into the preset edge computing model of the corresponding edge device for sorting to obtain the resource parameter threshold of the adjustable resource.

[0094] Preferably, computing nodes are provided in the edge device, and each computing node is provided with a fixed numerical processing capacity, the first processing capacity, denoted as D`; the third power data is marked as data2, and the numerical value of the third power data corresponding to data2 is denoted as Data2. The data volume of the second power data is consistent with the data volume of the first power data, denoted as Data1. The target processing capacity is obtained by adding Data1 and Data2, and then the number of computing nodes is calculated according to the target processing capacity, the number of edge devices and the first processing capacity, denoted as N. After the second power data and the third power data enter the edge device, they are calculated by N computing nodes, and N node model data are generated accordingly. Then, each node model data is trained with a preset edge computing model, and the node model data that does not meet the set model modeling standard value is filtered out, and the other node model data is used as modeling data; the computing node corresponding to the filtered node model data is connected to the real-time monitoring of the administrator, and the computing node is filtered out through the real-time monitoring. The number of filtering times is detected, and the number of filtering times is recorded as N. 滤 , when N 滤When it is greater than or equal to the set replacement threshold, the computing node is destroyed and replaced with a new computing node; an edge computing model is generated according to the node model data of several computing nodes, and the upper limit of the computing power of the edge computing model is Data2. When the edge device subsequently receives the second power data with a numerical value greater than or equal to Data2, the number of computing nodes is increased, and the edge computing model is updated in real time until the computing power of the edge computing model meets the received numerical value.

[0095] The edge computing model of the computing node constructs an initial machine learning model at each edge device through deep learning technology, and uses several computing nodes corresponding to each edge device as input nodes of the initial machine learning model; uses the node model data corresponding to each computing node as the input item of the input node; defines the initial machine learning model corresponding to each edge device, and the output nodes corresponding to the several input nodes are respectively used to output the resource parameter thresholds of the dispatchable resources of the power demand area corresponding to each edge device; when all input nodes input the corresponding input items, the initial machine learning model sorts all the input items, and uses the input item with the smallest sorting result and the input item with the largest sorting result as the resource parameter thresholds of the dispatchable resources under the corresponding power demand area; the resource parameter thresholds include the scarcity threshold (first parameter threshold) when the existing dispatchable resources in the power demand area are in scarcity and the surplus threshold (second parameter threshold) when the dispatchable resources are in surplus, and the first parameter threshold and the second parameter threshold are respectively denoted as η 匮乏 and η 过剩 , where 0<η 匮乏 <η 过剩 , that is, the edge computing model corresponding to each edge device is used to calculate the resource normal parameter interval (resource parameter threshold) of the dispatchable resources in the corresponding power demand area, that is, the resource normal parameter interval is between the first parameter threshold and the second parameter threshold. The power data is calculated in the edge device and the edge computing model is generated. The edge computing model is updated in real time to maintain a high model accuracy.

[0096] In a preferred embodiment of the present invention, an evaluation is performed according to the resource parameter threshold and the power data to obtain an evaluation result of adjustable resources of the power area to be evaluated, including:

[0097] According to the resource parameter threshold, determining a first parameter threshold for indicating a resource shortage state and a second parameter threshold for indicating a resource surplus state; wherein the second parameter threshold is greater than the first parameter threshold;

[0098] Comparing according to the power data amount of the power data, the first parameter threshold and the second parameter threshold;

[0099] When the amount of power data is less than the first parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as resource scarcity;

[0100] When the power data amount is greater than the first parameter threshold and less than the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as normal resources;

[0101] When the power data amount is equal to the first parameter threshold or equal to the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as normal resources;

[0102] When the power data amount is greater than the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as excess resources.

[0103] In an illustrative manner, according to the resource parameter threshold, a first parameter threshold η for indicating a resource shortage state is determined. 匮乏 and a second parameter threshold η for indicating a resource surplus state 过剩 ; Wherein, the second parameter threshold is greater than the first parameter threshold; the amount of power data corresponding to the amount of existing dispatchable resources in the power area to be evaluated is recorded as τ, and when the amount of power data is less than the first parameter threshold, τ<η 匮乏 , the adjustable resource evaluation result of the power area to be evaluated is marked as resource shortage; when the power data amount is greater than the first parameter threshold and less than the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as resource normal; when the power data amount is equal to the first parameter threshold or equal to the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as resource normal, that is, η 匮乏 ≤τ≤η 过剩 , the adjustable resource evaluation result of the power area to be evaluated is marked as normal resources; when the amount of power data is greater than the second parameter threshold, τ>η 过剩 , the adjustable resource evaluation result of the power area to be evaluated is marked as excess resources. The first parameter threshold is the minimum limit value of the amount of dispatchable resources in the power area to be evaluated under normal circumstances, and the second parameter threshold is the maximum limit value of the amount of dispatchable resources in the power area to be evaluated under normal circumstances. When the amount of dispatchable resources in the power area to be evaluated is between the minimum limit value and the maximum limit value, the corresponding power demand area is in normal operation, otherwise it is in abnormal operation.

[0104] In another preferred embodiment of the present invention, it also includes:

[0105] Determine the corresponding resource allocation plan according to the adjustable resource evaluation result;

[0106] When the evaluation result of adjustable resources is marked as resource shortage, the adjustable resources of the power area adjacent to the power area to be evaluated and whose evaluation result of adjustable resources is surplus resources are used as supplementary resources for the power area to be evaluated;

[0107] When the adjustable resource assessment result is marked as normal resources, the adjustable resources of the power area to be assessed are kept unchanged;

[0108] When the evaluation result of the adjustable resources is marked as excess resources, the adjustable resources are transported to the power area adjacent to the power area to be evaluated and the evaluation result of the adjustable resources is that the power area is resource-scarce, as a supplementary resource for the adjacent power area.

[0109] Specifically, if the resource status is "resource scarcity", the corresponding resource allocation measure is: obtain the dispatchable resources in the power area adjacent to the power area for supplementation; if the resource status is "resource surplus", the corresponding resource allocation measure is: transport the dispatchable resources of the power area to other power areas adjacent to it; after the resource allocation measures corresponding to "resource surplus" and "resource scarcity" are processed, the resource status of the corresponding power demand area is changed to "resource normal" state. After determining the corresponding resource allocation scheme, record the number of times the resource status of the corresponding power area is changed to "resource normal" state, record it as A, obtain the number of times the resource allocation scheme is executed, record it as B, generate the decision coefficient according to A and B, record it as Y, and Y = A / B; when the decision coefficient Y∈[0.7, 1], mark the resource allocation scheme corresponding to the decision coefficient at this time as the best resource allocation scheme. After adopting the optimal resource allocation scheme, the power operation parameters generated by the operation of the power system are obtained, and the power operation parameters include voltage parameters, current parameters, power parameters, power parameters and frequency parameters; a monitoring period is set, denoted as T, T = [T1, T2], and the power operation data is monitored in real time within a monitoring period T. When the voltage parameter is less than or equal to the set voltage effective value, an operation fault coefficient 1 is generated; when the current parameter does not belong to the set current standard value range, an operation fault coefficient 2 is generated; when the power parameter is greater than or equal to the power alarm value, an operation fault coefficient 3 is generated; the operation fault coefficient 1, the operation fault coefficient 2 and the operation fault coefficient 3 are summarized to generate a comprehensive fault coefficient, marked as α; the power parameter is marked as w, the frequency parameter is marked as f, and the standard power is set, marked as w 标 , set the standard frequency, denoted as f 标 , if w / w 标=DQ1, f / f mark =DQ2, then the power system establishes an interactive space and synchronously generates a monitoring report in the interactive space, and records all recorded power operation parameters in the monitoring report. DQ1 is the power alarm threshold, and DQ2 is the frequency alarm threshold; the comprehensive fault coefficient reflects the severity of the fault of the power system. The higher the comprehensive fault coefficient, the more serious the fault of the power system; when the comprehensive fault coefficient reaches the set scheme replacement threshold, the current best resource allocation scheme is replaced with the best resource allocation scheme represented by other decision coefficients.

[0110] By implementing this embodiment, the edge device is responsible for processing local data and responding quickly, and the cloud server is responsible for splitting and sending power data with large data volumes. This collaborative work makes it possible to quickly process the evaluation of adjustable resources in the power area; and as the power area expands or the amount of data increases, the system can be expanded by adding more edge devices. At the same time, the cloud server can seamlessly integrate power data with large data volumes to maintain the effectiveness of the evaluation; the use of edge devices reduces dependence on centralized data on cloud servers and reduces data transmission costs. At the same time, edge devices reduce the burden on cloud servers and reduce the consumption of cloud computing resources. By dividing the power data into different cloud sequences and edge sequences, the cloud server only splits the power data and sends the split data to the edge device, so that the power data can be calculated in the edge device to obtain the adjustable resource evaluation result, thereby realizing the collaborative work of the remote server and the edge device. The edge device calculates the resource parameter threshold according to the power data allocated by the edge sequence and the power data sent by the remote server, combining the advantages of local real-time data and global historical data, thereby improving the accuracy of the evaluation result; through sequence allocation, the power data is effectively distributed between the cloud and edge devices, ensuring load balancing of data processing, avoiding single-point overload of the cloud server, and improving the adjustable resource evaluation efficiency of the entire power grid area.

[0111] See also Figure 2 , is a structural diagram of a power grid adjustable resource evaluation device based on cloud-edge collaboration provided by an embodiment of the present invention, including:

[0112] A power data acquisition module is used to acquire power data of several power nodes in the power area to be evaluated; wherein the power data includes: voltage data, current data and electric heating temperature data;

[0113] A sequence generation module, used to perform sequence allocation according to the power data and a preset data volume threshold, and generate a cloud sequence and an edge sequence corresponding to the power data;

[0114] A cloud splitting module, used to transmit the cloud sequence and the first power data corresponding to the cloud sequence to a cloud server, so that the cloud server splits the cloud sequence and the first power data corresponding to the cloud sequence to obtain second power data after splitting, and sends the cloud sequence and the second power data to the edge device;

[0115] an edge computing module, configured to transmit the edge sequence and third power data corresponding to the edge sequence to an edge device, so that the edge device calculates a resource parameter threshold of an adjustable resource according to the edge sequence, the second power data and the third power data;

[0116] The resource evaluation module is used to perform evaluation according to the resource parameter threshold and the power data to obtain an evaluation result of adjustable resources in the power area to be evaluated.

[0117] The present invention provides a power grid adjustable resource evaluation device based on cloud-edge collaboration, which acquires power data of several power nodes in a power area to be evaluated according to a power data acquisition module; wherein the power data includes: voltage data, current data and electric temperature data; in a sequence generation module, sequence allocation is performed according to the power data and a preset data volume threshold, and a cloud sequence and an edge sequence corresponding to the power data are generated; through a cloud splitting module, the cloud sequence and the first power data corresponding to the cloud sequence are transmitted to a cloud server, so that the cloud server splits the cloud sequence and the first power data corresponding to the cloud sequence to obtain the second power data after the split, and sends the cloud sequence and the second power data to an edge device; through an edge computing module, the edge sequence and the third power data corresponding to the edge sequence are transmitted to the edge device, so that the edge device calculates the resource parameter threshold of the adjustable resource according to the edge sequence, the second power data and the third power data; finally, in a resource evaluation module, an evaluation is performed according to the resource parameter threshold and the power data to obtain an adjustable resource evaluation result of the power area to be evaluated. By dividing the power data into different cloud sequences and edge sequences, the cloud server only splits the power data and sends the split data to the edge device, so that the power data can be calculated in the edge device to obtain the adjustable resource evaluation result, thereby realizing the collaborative work of the remote server and the edge device. The edge device calculates the resource parameter threshold according to the power data allocated by the edge sequence and the power data sent by the remote server, combining the advantages of local real-time data and global historical data, thereby improving the accuracy of the evaluation result; through sequence allocation, the power data is effectively distributed between the cloud and edge devices, ensuring load balancing of data processing, avoiding single-point overload of the cloud server, and improving the adjustable resource evaluation efficiency of the entire power grid area.

[0118] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0119] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0120] Another embodiment of the present invention further provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a method for evaluating adjustable resources of a power grid based on cloud-edge collaboration as described in the above embodiment is implemented. The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory.

[0121] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0122] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device or other volatile solid-state storage device.

[0123] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a method for evaluating adjustable power grid resources based on cloud-edge collaboration as described in the above embodiment.

[0124] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0125] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for evaluating adjustable resources of a power grid based on cloud-edge collaboration, characterized in that: Applicable to cloud servers and edge devices; The method comprises: Acquire power data of several power nodes in the power area to be evaluated; wherein the power data includes: voltage data, current data and electric heating temperature data; Perform sequence allocation according to the power data and a preset data volume threshold, and generate a cloud sequence and an edge sequence corresponding to the power data; The cloud sequence and the first power data corresponding to the cloud sequence are transmitted to the cloud server, so that the cloud server splits the cloud sequence and the first power data corresponding to the cloud sequence to obtain the second power data after splitting, and sends the cloud sequence and the second power data to the edge device; Transmitting the edge sequence and the third power data corresponding to the edge sequence to the edge device, so that the edge device calculates the resource parameter threshold of the adjustable resource according to the edge sequence, the second power data and the third power data; An evaluation is performed according to the resource parameter threshold and the power data to obtain an evaluation result of adjustable resources in the power area to be evaluated.

2. A method for evaluating adjustable resources of a power grid based on cloud-edge collaboration as claimed in claim 1, characterized in that: Sequence allocation is performed according to the power data and a preset data volume threshold to generate a cloud sequence and an edge sequence corresponding to the power data, including: determining a power data amount of the power data according to the power data; According to the comparison between the power data volume and a preset data volume threshold, the power data whose power data volume is less than the data volume threshold is assigned an edge sequence, and an edge sequence of the power data corresponding to the power data volume less than the data volume threshold is generated; The power data whose power data volume is greater than or equal to the data volume threshold is allocated to a cloud sequence, and a cloud sequence of the power data corresponding to the power data volume greater than or equal to the data volume threshold is generated.

3. The method for evaluating adjustable resources of a power grid based on cloud-edge collaboration according to claim 1, characterized in that: The cloud sequence and the first power data corresponding to the cloud sequence are transmitted to the cloud server, including: Using the cloud sequence as a first identification code of the cloud server; and storing first power data corresponding to the cloud sequence in a first transmission space; Acquire a first permission for representing a first transmission space according to the first identification code, and monitor a space lock state of a cloud server; When it is detected that the space lock state of the cloud server is in progress, taking out the first power data from the first transmission space according to the first authority, and transmitting the cloud sequence and the first power data to the cloud server; Wherein, when it is detected that the space lock state of the cloud server is in an idle state, the space lock state of the cloud server continues to be monitored.

4. The method for evaluating adjustable resources of a power grid based on cloud-edge collaboration according to claim 1, characterized in that: A cloud server, used for splitting the cloud sequence and the first power data corresponding to the cloud sequence to obtain second power data after splitting; The method comprises: performing splitting according to the cloud sequence and the first power data corresponding to the cloud sequence to obtain second power data after splitting, including: According to the cloud sequence and the preset number of split stacks, the cloud sequence is equally divided according to the number of split stacks to obtain an equally divided cloud sequence; Constructing folders corresponding to the number of split stacks according to the equally divided cloud sequence; and splitting the corresponding first power data according to the equally divided cloud sequence to obtain a number of target power data; Each target power data is stored in a corresponding file to obtain second power data representing the split.

5. The method for evaluating adjustable resources of a power grid based on cloud-edge collaboration according to claim 1, characterized in that: an edge device, configured to calculate a resource parameter threshold of an adjustable resource according to the edge sequence, the second power data, and the third power data; Calculating a resource parameter threshold of an adjustable resource according to the edge sequence, the second power data, and the third power data includes: Obtain the number of edge devices and a first processing amount used to represent the data processing amount of the computing node; wherein the first processing amount of the computing node in each edge device is consistent; Obtaining a target processing amount by adding the data amount of the second power data and the data amount of the third power data; Calculate the number of computing nodes according to the target processing volume, the number of edge devices, and the first processing volume; Generate a plurality of node model data corresponding to the number of computing nodes according to the second power data, the third power data and the number of computing nodes; Several node model data are input into the preset edge computing model of the corresponding edge device for sorting to obtain the resource parameter threshold of the adjustable resource.

6. A method for evaluating adjustable resources of a power grid based on cloud-edge collaboration as claimed in claim 2, characterized in that: An evaluation is performed according to the resource parameter threshold and the power data to obtain an evaluation result of adjustable resources in the power area to be evaluated, including: According to the resource parameter threshold, determining a first parameter threshold for indicating a resource shortage state and a second parameter threshold for indicating a resource surplus state; wherein the second parameter threshold is greater than the first parameter threshold; Comparing according to the power data amount of the power data, the first parameter threshold and the second parameter threshold; When the amount of power data is less than the first parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as resource scarcity; When the power data amount is greater than the first parameter threshold and less than the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as normal resources; When the power data amount is equal to the first parameter threshold or equal to the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as normal resources; When the power data amount is greater than the second parameter threshold, the adjustable resource evaluation result of the power area to be evaluated is marked as excess resources.

7. A method for evaluating adjustable resources of a power grid based on cloud-edge collaboration as claimed in claim 6, characterized in that: Also includes: Determine the corresponding resource allocation plan according to the adjustable resource evaluation result; When the evaluation result of adjustable resources is marked as resource shortage, the adjustable resources of the power area adjacent to the power area to be evaluated and whose evaluation result of adjustable resources is surplus resources are used as supplementary resources for the power area to be evaluated; When the adjustable resource assessment result is marked as normal resources, the adjustable resources of the power area to be assessed are kept unchanged; When the evaluation result of the adjustable resources is marked as excess resources, the adjustable resources are transported to the power area adjacent to the power area to be evaluated and the evaluation result of the adjustable resources is that the power area is resource-scarce, as a supplementary resource for the adjacent power area.

8. A power grid adjustable resource evaluation device based on cloud-edge collaboration, characterized in that: include: A power data acquisition module is used to acquire power data of several power nodes in the power area to be evaluated; wherein the power data includes: voltage data, current data and electric heating temperature data; A sequence generation module, used to perform sequence allocation according to the power data and a preset data volume threshold, and generate a cloud sequence and an edge sequence corresponding to the power data; A cloud splitting module, used to transmit the cloud sequence and the first power data corresponding to the cloud sequence to a cloud server, so that the cloud server splits the cloud sequence and the first power data corresponding to the cloud sequence to obtain second power data after splitting, and sends the cloud sequence and the second power data to the edge device; an edge computing module, configured to transmit the edge sequence and third power data corresponding to the edge sequence to an edge device, so that the edge device calculates a resource parameter threshold of an adjustable resource according to the edge sequence, the second power data and the third power data; The resource evaluation module is used to perform evaluation according to the resource parameter threshold and the power data to obtain an evaluation result of adjustable resources in the power area to be evaluated.

9. A terminal device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a method for evaluating adjustable resources of a power grid based on cloud-edge collaboration as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a method for evaluating adjustable resources of a power grid based on cloud-edge collaboration as described in any one of claims 1 to 7.

Images