CN-122026549-A - Operation planning method, device, computer equipment and program product of power distribution network

CN122026549ACN 122026549 ACN122026549 ACN 122026549ACN-122026549-A

Abstract

The application relates to an operation planning method, an operation planning device, computer equipment, a computer readable storage medium and a computer program product of a power distribution network. The method comprises the steps of obtaining historical operation data of a power distribution network, determining abnormal occurrence time, collecting initial data in a preset period before the occurrence time, preprocessing the initial data to obtain a processed power grid data set, constructing a directed chain graph of the power distribution network, using a continuous behavior subchain with the largest load response intensity value change degree in the directed chain graph as an abnormal candidate chain, determining a cause intensity value of the abnormal candidate chain, determining an abnormal cause chain in the abnormal candidate chain, matching the abnormal cause chain with a candidate strategy behavior chain corresponding to a current operation plan of the power distribution network to obtain behavior chain matching degree, and carrying out evasion correction on the current operation plan based on the behavior chain matching degree to obtain a corrected operation plan. By adopting the method, the operation safety of the power distribution network can be improved.

Inventors

ZHAO XIANGYU
LIU CHANGSHENG
FENG QINYU
SHEN RUI
Cao shang
XIAO PEI
LIU JIAXU
YU JINGXING
ZHANG HUANMING
Zhou Ruiye
LIANG LINGYU
GUO SHUAI

Assignees

南方电网人工智能科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (10)

1. A method of operation planning for a power distribution network, the method comprising: acquiring historical operation data of a power distribution network, and determining abnormal occurrence time in the historical operation data; Collecting historical operation data in a preset period before the occurrence time as initial data, and preprocessing the initial data to obtain a processed power grid data set; Constructing a directed chain graph of the power distribution network based on the power grid data set; Determining a load response intensity value of each node in the directed chain graph based on the directed chain graph; The continuous behavior subchain with the greatest degree of load response intensity value change in the directed chain graph is used as an abnormal candidate chain, the inducement intensity value of the abnormal candidate chain is determined, and an abnormal inducement chain is determined in the abnormal candidate chain; Matching the abnormal cause chain with a candidate strategy behavior chain corresponding to the current operation plan of the power distribution network to obtain a behavior chain matching degree; And carrying out avoidance correction on the current operation plan based on the behavior chain matching degree to obtain a corrected operation plan.
2. The method according to claim 1, wherein the method further comprises: determining a load disturbance value of the corrected operation plan; Comparing the maximum value of the load disturbance value with a preset dynamic avoidance threshold, and judging that the power distribution network is successful in avoiding the abnormality under the condition that the maximum value is smaller than the dynamic avoidance threshold; and under the condition that the maximum value is greater than or equal to the dynamic avoidance threshold value, judging that the power distribution network fails in abnormal avoidance.
3. The method of claim 1, wherein the grid dataset includes a control behavior sequence, a topology state, and a load response state for the power distribution grid, wherein constructing a directed chain graph for the power distribution grid based on the grid dataset includes: For the control behavior sequence at each moment, determining the time delay of which the change degree of the delay function between the control behavior sequence and the subsequent topological structure change exceeds a preset degree and the maximum response time delay between the control behavior sequence and the node load response; Taking the sum of the time delay and the maximum response time delay as a comprehensive delay weight from a behavior node to a result node; defining a control behavior sequence as a behavior node set, and positioning a topological structure state and a load response state as a result node set; and constructing a directed chain graph of the power distribution network based on the behavior node set, the result node set and the comprehensive delay weight.
4. A method according to claim 3, wherein said determining a load response intensity value for each node in the directed chain graph based on the directed chain graph comprises: Extracting a node sequence of a topological structure state in the directed chained graph, and calculating a topological offset measurement value of each moment of a node based on the node sequence; extracting a load response state sequence, calculating the load change rates of all nodes based on the load response state sequence, and aggregating to obtain a first load response intensity value of each moment of the nodes; And taking the sum of the topological offset measurement value and the first load response intensity value as the load response intensity value of each node in the directed chain graph.
5. The method according to claim 4, wherein said determining the cause intensity value of the abnormal candidate chain as the abnormal candidate chain by using the continuous behavior sub-chain with the greatest degree of variation of the load response intensity value in the directed chain graph, and determining the abnormal cause chain among the abnormal candidate chains, comprises: Determining all continuous behavior subchains in the directed chain graph in a preset analysis interval; Taking the sum value of the load response intensity values of all the behavior nodes in the continuous behavior sub-chain as the load response intensity value of the corresponding continuous behavior sub-chain; Taking the continuous behavior subchain with the largest load response intensity value variation degree as an abnormal candidate chain; Taking the sum of the load response intensity values of all behavior nodes in the abnormal candidate chain as the inducement intensity value of the abnormal candidate chain; and taking the abnormal candidate chain with the incentive intensity value being greater than or equal to a preset incentive threshold as an abnormal incentive chain.
6. The method of claim 5, wherein the determining of the predetermined incentive threshold comprises: Determining the overall level and standard deviation of disturbance intensity based on the load response intensity values of all behavior nodes in the analysis interval; Taking the product of the standard deviation and a preset adjusting factor as a sensitivity index; Determining the number of behavior nodes which cause the change degree of the network topology structure to be larger than the preset change degree in the abnormal candidate chain, and taking the product of the number of the behavior nodes and the preset penalty coefficient as the structure complexity compensation; and taking the sum value among the whole level, the sensitivity index and the structural complexity compensation as a preset incentive threshold value.
7. An operation planning device for an electric distribution network, the device comprising: The determining module is used for acquiring historical operation data of the power distribution network and determining abnormal occurrence time in the historical operation data; The processing module is used for collecting historical operation data in a preset period before the occurrence time as initial data, and preprocessing the initial data to obtain a processed power grid data set; the construction module is used for constructing a directed chain graph of the power distribution network based on the power grid data set; The determining module is further used for determining load response intensity values of all nodes in the directed chain graph based on the directed chain graph; The determining module is further used for taking the continuous behavior subchain with the greatest load response intensity value change degree in the directed chain graph as an abnormal candidate chain, determining the incentive intensity value of the abnormal candidate chain and determining an abnormal incentive chain in the abnormal candidate chain; The matching module is used for matching the abnormal incentive chain with a candidate strategy behavior chain corresponding to the current operation plan of the power distribution network to obtain a behavior chain matching degree; and the correction module is used for carrying out avoidance correction on the current operation plan based on the behavior chain matching degree to obtain a corrected operation plan.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

Description

Operation planning method, device, computer equipment and program product of power distribution network Technical Field The present application relates to the technical field of smart grid planning, and in particular, to an operation planning method, an apparatus, a computer device, a computer readable storage medium and a computer program product for a power distribution network. Background The power system dispatching and operation planning belongs to a key link of intelligent power grid development, and is a core component in technical evolution such as energy Internet, active power distribution network, distributed dispatching system and the like. The power distribution network is used as an intermediate carrier for connecting the power supply side and the load side, and the running state of the power distribution network has direct influence on the stability, flexibility and safety of the whole power system. In the actual operation process, the power distribution network scheduling strategy not only covers basic tasks such as power flow allocation, voltage control and load prediction, but also associates multidimensional dynamic behaviors such as topology structure adjustment, distributed power supply access, fault self-healing recovery and the like. In the related technology, in the existing power distribution network operation abnormality recognition and early warning mechanism, the system mostly depends on single-point judgment of static indexes such as voltage, current and load fluctuation, numerical abnormality triggering of a result level is mainly focused, and systematic causal relation among a preamble operation behavior, a response evolution process and abnormality is ignored. Under the mechanism, although the system can monitor abnormal phenomena such as voltage out-of-limit or reverse current of a certain node, the scheduling-response chain-type inducement behind the abnormal phenomena is difficult to identify, and the abnormal operation logic cannot be restored. The identification logic of the splitting property is easy to miss key front operation nodes or weak disturbance signals in actual scenes such as scheduling optimization, topology adjustment or equipment switching, so that the system cannot perform early warning interception when an initial incentive occurs. Disclosure of Invention In view of the foregoing, it is desirable to provide an operation planning method, apparatus, computer device, computer readable storage medium and computer program product for an electric distribution network, which can improve operation planning safety of the electric distribution network. In a first aspect, the present application provides a method for operation planning of a power distribution network, including: acquiring historical operation data of a power distribution network, and determining abnormal occurrence time in the historical operation data; Collecting historical operation data in a preset period before the occurrence time as initial data, and preprocessing the initial data to obtain a processed power grid data set; Constructing a directed chain graph of the power distribution network based on the power grid data set; Determining a load response intensity value of each node in the directed chain graph based on the directed chain graph; The continuous behavior subchain with the greatest degree of load response intensity value change in the directed chain graph is used as an abnormal candidate chain, the inducement intensity value of the abnormal candidate chain is determined, and an abnormal inducement chain is determined in the abnormal candidate chain; Matching the abnormal cause chain with a candidate strategy behavior chain corresponding to the current operation plan of the power distribution network to obtain a behavior chain matching degree; And carrying out avoidance correction on the current operation plan based on the behavior chain matching degree to obtain a corrected operation plan. In one embodiment, the method further comprises: determining a load disturbance value of the corrected operation plan; Comparing the maximum value of the load disturbance value with a preset dynamic avoidance threshold, and judging that the power distribution network is successful in avoiding the abnormality under the condition that the maximum value is smaller than the dynamic avoidance threshold; and under the condition that the maximum value is greater than or equal to the dynamic avoidance threshold value, judging that the power distribution network fails in abnormal avoidance. In one embodiment, the power grid data set includes a control behavior sequence, a topology structure state and a load response state of the power distribution network, and the constructing a directed chain graph of the power distribution network based on the power grid data set includes: For the control behavior sequence at each moment, determining the time delay of which the change degree of the delay function between t