CN-121984113-A - Intelligent scheduling method and system for power grid tasks in multi-cloud environment

CN121984113ACN 121984113 ACN121984113 ACN 121984113ACN-121984113-A

Abstract

The invention provides an intelligent dispatching method and system for power grid tasks in a multi-cloud environment, wherein the method comprises the steps of enabling an edge cloud to synchronously transmit acquired power grid operation parameters and power grid resource parameters to a private cloud and a public cloud, constructing a power grid digital twin body based on the power grid operation parameters and combining a power grid physical topological structure, responding to a fault trigger signal, updating operation state parameters of a fault area in the power grid digital twin body to obtain a visualized fault association diagram, determining a preliminary dispatching scheme of power grid resources based on the power grid resource parameters and the fault association diagram and combining a power grid physical topological structure and a fault type identifier, performing simulation verification optimization on the preliminary dispatching scheme based on the power grid digital twin body to obtain a target dispatching scheme, and distributing dispatching instructions of the target dispatching scheme to power grid control terminals of corresponding areas. The invention solves the problems of delayed response and insufficient resource cooperation of the traditional scheduling.

Inventors

LIN ZHENJIE
CHEN YUXU
LV JINTAO
CHEN CHENGKUI
OUYANG BO

Assignees

南网数字运营软件科技(广东)有限公司

Dates

Publication Date: 20260505
Application Date: 20251229

Claims (10)

1. The intelligent scheduling method for the power grid tasks in the multi-cloud environment is characterized by comprising the following steps of: synchronously transmitting the acquired power grid operation parameters and power grid resource parameters to private cloud and public cloud based on the edge cloud, wherein the multi-cloud environment comprises the edge cloud, the private cloud and the public cloud; Constructing a power grid digital twin body based on the power grid operation parameters in combination with a power grid physical topological structure, and updating the operation state parameters of a fault area in the power grid digital twin body in response to a fault trigger signal to obtain a visual fault association diagram; Determining a preliminary scheduling scheme of the power grid resources based on the power grid resource parameters and the fault association diagram and combining a power grid physical topological structure and a fault type identifier; And carrying out simulation verification optimization on the preliminary scheduling scheme based on the power grid digital twin body to obtain a target scheduling scheme, and distributing scheduling instructions of the target scheduling scheme to power grid control terminals of corresponding areas.
2. The intelligent scheduling method for power grid tasks in a multi-cloud environment according to claim 1, wherein the performing simulation verification optimization on the preliminary scheduling scheme based on the power grid digital twin body to obtain a target scheduling scheme comprises: Constructing a multi-dimensional simulation scene mapping group based on a fault association diagram of the power grid digital twin body, a power grid physical topological structure and a power grid resource allocation path in the preliminary scheduling scheme, wherein the multi-dimensional simulation scene mapping group comprises resource interaction boundaries of a fault area and a non-fault area and power grid equipment operation constraint conditions; Determining a real-time execution track of the preliminary adjustment scheme in a simulation environment based on a resource interaction boundary of the multi-dimensional simulation scene mapping group and a grid equipment operation constraint condition, and gradually deducing an execution process of the preliminary scheduling scheme according to a time sequence of grid operation based on the real-time execution track to determine an overall operation index of the grid under each time node, wherein the real-time execution track comprises a starting time sequence, a resource transmission rate and a fault area recovery progress of each grid equipment; determining a conflict threshold value of resource allocation and equipment bearing capacity based on a matching relation between a resource transmission rate and equipment starting time sequence in the real-time execution track, and carrying out conflict recognition based on the conflict threshold value and an integral operation index of each time node to obtain a conflict risk point in the preliminary scheduling scheme, wherein the conflict risk point comprises resource overload conflict, equipment starting time sequence conflict and fault recovery path conflict; Determining an association path of each conflict risk point with a fault area and a non-fault area based on the area position and the influence range of the conflict risk point and combining the fault association graph of the power grid digital twin body, and determining a source node causing conflict risk based on the association path and a power grid physical topological structure; And optimizing the preliminary adjustment scheme based on the root node and the multi-dimensional simulation scene mapping group to obtain the target scheduling scheme.
3. The intelligent scheduling method for power grid tasks in a multi-cloud environment according to claim 2, wherein the optimizing the preliminary adjustment scheme based on the root node and the multi-dimensional simulation scene mapping group to obtain the target scheduling scheme comprises: Determining adjustment directions for different root nodes based on the types and the operation constraints of the root nodes, and constructing conflict resolution adjustment rules based on the adjustment scheme, the resource interaction boundary of the multi-dimensional simulation scene mapping group and the equipment constraint condition, wherein the adjustment directions comprise resource allocation amount adjustment, equipment starting time sequence adjustment and path optimization adjustment; based on the adjustment range and the adjustment scheme in the conflict resolution adjustment rule, combining the preliminary adjustment scheme, determining local parameters to be corrected, and correcting the preliminary adjustment scheme based on the local parameters and the implementation execution track to obtain a preliminary correction scheme, wherein the local parameters comprise resource allocation proportion, equipment starting time and fault recovery path nodes; constructing a verification index system of secondary simulation based on the primary correction scheme and combining the resource constraint and the topology constraint of the multi-dimensional simulation scene mapping group, and executing secondary simulation deduction under the same simulation scene based on the verification index system to obtain a real-time execution track of the primary correction scheme and operation indexes of all time nodes, wherein the verification index system comprises core indexes of conflict resolution effect, resource utilization rate and power supply stability; And determining the optimized lifting amplitude of the preliminary correction scheme based on the real-time execution track and the operation index of the preliminary correction scheme, and judging based on the optimized lifting amplitude and the elimination state of the conflict risk point to obtain the target scheduling scheme, wherein the lifting amplitude is the difference ratio of the core operation index after correction and before correction.
4. The intelligent scheduling method for power grid tasks in a cloud environment according to claim 3, wherein the determining based on the optimized lifting amplitude and the elimination state of collision risk points to obtain the target scheduling scheme includes: If all conflict risk points are completely eliminated and the lifting amplitude of the core operation index meets the power grid operation requirement, determining the primary correction scheme as a target scheduling scheme, and if the conflict exists or the index does not reach the standard, re-identifying the conflict risk points, and correcting and optimizing again until the target scheduling scheme meeting the requirement is obtained.
5. The intelligent scheduling method for power grid tasks in a multi-cloud environment according to claim 1, wherein the determining a preliminary scheduling scheme for power grid resources based on the power grid resource parameters and the fault correlation diagram and combining a power grid physical topology structure and a fault type identifier comprises: Traversing all power grid elements which are directly connected or indirectly communicated with a fault trigger point in a fault associated graph based on connection node information of all power grid elements in the power grid physical topological structure and in combination with a space distribution range of a fault area in the fault associated graph to obtain a fault influence power grid element group, and carding communication paths among the elements according to connection sequences of the elements in the power grid topological relation based on the fault influence power grid element group to obtain a power grid element connection path group; Analyzing limiting conditions exerted by different fault types on functions of corresponding elements based on fault attributes corresponding to fault type identifiers and inherent functions of elements in fault influence power grid element groups to obtain functional constraint requirements of each fault influence power grid element, wherein the functional constraint requirements comprise a power range, a voltage range and a frequency range which allow the elements to operate; Based on the current state, the resource type and the resource parameter of the power grid resource in the power grid resource parameters, combining the function types of all elements in the fault influence power grid element group, screening the power grid resource which is in an idle state or can be flexibly adjusted currently and the resource parameter is matched with the function type of the fault influence element to obtain an available power grid resource group; Judging whether each available power grid resource can be accessed to a corresponding node of a certain element connection path or not based on the connection node attribute of each path in the power grid element connection path group and the access node requirement of each resource in the available power grid resource group, and constructing a matching relation of the resource and the path based on a judgment result; And performing resource allocation and planning based on the functional constraint requirements, the matching relation of the resources and the paths, the power grid element connection path group and the power grid physical topological structure to obtain the preliminary scheduling scheme.
6. The intelligent scheduling method for power grid tasks in a cloud environment according to claim 5, wherein the performing resource allocation and planning based on the functional constraint requirements, the matching relationship between resources and paths, the power grid element connection path group and the power grid physical topology structure to obtain the preliminary scheduling scheme includes: based on the matching relation of the functional constraint requirements of each fault influence element and the resources and paths, aiming at each successfully matched resource path combination, analyzing and screening whether the output parameters of the corresponding available power grid resources meet the functional constraint requirements of all the fault influence elements on the paths or not to obtain target resource subgroups corresponding to each path; based on the scale of the target resource subgroup and the fault influence degree of each path in the power grid element connection paths, carrying out priority ranking on all the power grid element connection paths in the fault influence region, and carrying out access response speed ranking on resources in the target resource subgroup corresponding to each path to obtain a resource allocation priority sequence; Determining a unique access node of each target resource based on the priority of each path in the resource allocation priority sequence and the access sequence of the corresponding resource in combination with the connection state and the load condition of each node in the power grid physical topological structure, planning the path from the unique access node to the corresponding fault influencing element of the target resource based on the connection path of the element in the power grid physical topological structure, and obtaining a transmission path; and integrating the unique access node based on each target resource with the transmission path by combining the target resource subgroup and the output parameters of each resource to obtain the preliminary scheduling scheme.
7. The intelligent scheduling method for power grid tasks in a multi-cloud environment according to claim 6, wherein the preliminary scheduling scheme comprises a target resource list corresponding to each power grid element connection path, access node positions of all target resources, specific paths of resource transmission, access sequences of resources and output parameter setting values of all resources.
8. The intelligent dispatching system for the power grid tasks in the multi-cloud environment is characterized by being applied to the intelligent dispatching method for the power grid tasks in the multi-cloud environment according to any one of claims 1 to 7, and comprises the following steps: The data synchronous transmission module is used for synchronously transmitting the acquired power grid operation parameters and power grid resource parameters to private cloud and public cloud based on the edge cloud, wherein the multi-cloud environment comprises the edge cloud, the private cloud and the public cloud; the fault visualization module is used for constructing a power grid digital twin body based on the power grid operation parameters and combining a power grid physical topological structure, responding to a fault trigger signal and updating the operation state parameters of a fault area in the power grid digital twin body to obtain a visualized fault association diagram; the scheme generation module is used for determining a preliminary scheduling scheme of the power grid resources based on the power grid resource parameters and the fault association diagram and combining a power grid physical topological structure and fault type identification; And the scheme optimization and distribution module is used for carrying out simulation verification optimization on the preliminary scheduling scheme based on the power grid digital twin body to obtain a target scheduling scheme, and distributing scheduling instructions of the target scheduling scheme to power grid control terminals of corresponding areas.
9. The electronic equipment is characterized by comprising a memory and a processor, wherein the memory is used for storing a computer software program, and the processor is used for reading and executing the computer software program, and when the processor executes the computer software program, the intelligent scheduling method for the power grid tasks in the multi-cloud environment is realized.
10. A non-transitory computer readable storage medium, wherein a computer software program is stored in the storage medium, and when the computer software program is executed by a processor, the method for intelligently scheduling power grid tasks in a multi-cloud environment according to any one of claims 1 to 7 is implemented.

Description

Intelligent scheduling method and system for power grid tasks in multi-cloud environment Technical Field The invention relates to the technical field of computers, in particular to an intelligent scheduling method and system for power grid tasks in a cloud environment. Background With the improvement of the permeability of new energy and the diversified development of the load of the power grid, the scale and the complexity of the modern power grid are continuously increased, and the fault scene is characterized by strong burst, wide influence range and quick dynamic change, so that the requirements on the response speed, the resource cooperative efficiency and the scene adaptation capability of the emergency dispatch after the power grid faults are more severe. The intelligent scheduling of the power grid tasks is used as a core technology for guaranteeing the reliability of power supply after faults, and the core aim is to quickly integrate whole network resources and accurately match power supply requirements after the faults occur, so that the quick recovery and stable operation of power supply are realized. Meanwhile, the existing dispatching is generally limited to a single area or a single cloud platform, lacks a cross-area and cross-level resource cooperative mechanism, is difficult to quickly access cross-area resources, has the problems of information transmission interruption and data asynchronization, easily causes low resource allocation efficiency, cannot realize optimal integration of whole network resources, and further aggravates the problem of power supply recovery lag. Disclosure of Invention The invention provides an intelligent scheduling method and system for power grid tasks in a multi-cloud environment, which are used for solving the problems of delayed response and insufficient resource cooperation in the traditional scheduling, realizing the optimal integration of whole network resources, improving the response speed and resource allocation efficiency of emergency scheduling after power grid faults, and ensuring the rapid recovery and stable operation of power supply. In a first aspect, the present invention provides an intelligent scheduling method for power grid tasks in a multi-cloud environment, including: synchronously transmitting the acquired power grid operation parameters and power grid resource parameters to private cloud and public cloud based on the edge cloud, wherein the multi-cloud environment comprises the edge cloud, the private cloud and the public cloud; Constructing a power grid digital twin body based on the power grid operation parameters in combination with a power grid physical topological structure, and updating the operation state parameters of a fault area in the power grid digital twin body in response to a fault trigger signal to obtain a visual fault association diagram; Determining a preliminary scheduling scheme of the power grid resources based on the power grid resource parameters and the fault association diagram and combining a power grid physical topological structure and a fault type identifier; And carrying out simulation verification optimization on the preliminary scheduling scheme based on the power grid digital twin body to obtain a target scheduling scheme, and distributing scheduling instructions of the target scheduling scheme to power grid control terminals of corresponding areas. The invention also provides an intelligent dispatching system for the power grid tasks in the multi-cloud environment, which is applied to the intelligent dispatching method for the power grid tasks in the multi-cloud environment according to the first aspect, and comprises the following steps: The data synchronous transmission module is used for synchronously transmitting the acquired power grid operation parameters and power grid resource parameters to private cloud and public cloud based on the edge cloud, wherein the multi-cloud environment comprises the edge cloud, the private cloud and the public cloud; the fault visualization module is used for constructing a power grid digital twin body based on the power grid operation parameters and combining a power grid physical topological structure, responding to a fault trigger signal and updating the operation state parameters of a fault area in the power grid digital twin body to obtain a visualized fault association diagram; the scheme generation module is used for determining a preliminary scheduling scheme of the power grid resources based on the power grid resource parameters and the fault association diagram and combining a power grid physical topological structure and fault type identification; And the scheme optimization and distribution module is used for carrying out simulation verification optimization on the preliminary scheduling scheme based on the power grid digital twin body to obtain a target scheduling scheme, and distributing scheduling instructions of the target scheduling scheme to power g