CN-122026380-A - Load allocation method, device, equipment, storage medium and program product of power distribution network

CN122026380ACN 122026380 ACN122026380 ACN 122026380ACN-122026380-A

Abstract

The embodiment of the application provides a load allocation method, device, equipment, storage medium and program product of a power distribution network. The method comprises the steps of obtaining real-time load data and historical load data of each node in a power distribution network, obtaining current flow direction data between every two nodes in the power distribution network, determining dynamic load weight of each node in the power distribution network according to the real-time load data and the historical load data of each node in the power distribution network, constructing a distributed load balance optimization model corresponding to the power distribution network according to the dynamic load weight of each node in the power distribution network and the current flow direction data between every two nodes in the power distribution network, and controlling each node in the power distribution network to execute load allocation operation according to the distributed load balance optimization model corresponding to the power distribution network. The method can regulate and control the node load of the power distribution network in real time under the condition of dynamic change of the node load so as to ensure the load distribution balance of each node of the power distribution network.

Inventors

LIU BINBIN
YUAN XU
CAI YIMEI
XIE WENMIN
LIU PENGHUI
WU ZHAOHONG
FU XINLONG
DU JINGYI

Assignees

广东电网有限责任公司梅州供电局

Dates

Publication Date: 20260512
Application Date: 20260119

Claims (11)

1. A load distribution method for a power distribution network, comprising: acquiring real-time load data and historical load data of each node in a power distribution network, and acquiring current flow direction data between every two nodes in the power distribution network; Determining the dynamic load weight of each node in the power distribution network according to the real-time load data and the historical load data of each node in the power distribution network; Constructing a distributed load balancing optimization model corresponding to the power distribution network according to the dynamic load weight of each node in the power distribution network and the current flow direction data between every two nodes in the power distribution network, wherein the distributed load balancing optimization model comprises the load allocation control direction of each node in the power distribution network; And controlling each node in the power distribution network to execute load allocation operation according to the distributed load balance optimization model corresponding to the power distribution network.
2. The method of claim 1, wherein determining the dynamic load weight for each node in the distribution network based on the real-time load data and the historical load data for each node in the distribution network comprises: determining a load distribution prediction result of the power distribution network according to the real-time load data and the historical load data of each node in the power distribution network, wherein the load distribution prediction result comprises the load distribution condition of each node in the power distribution network in a predicted future time period; and determining the dynamic load weight of each node in the power distribution network according to the load distribution prediction result of the power distribution network.
3. The method of claim 2, wherein determining the load distribution prediction result of the power distribution network according to the real-time load data and the historical load data of each node in the power distribution network comprises: Generating a load time sequence data set of the node according to the real-time load data and the historical load data of the node, wherein the load time sequence data set comprises load time sequence signal data of the node at each historical moment; Performing wavelet decomposition on each load time sequence signal data in the load time sequence data set to obtain a sub-signal set corresponding to at least one frequency band corresponding to the load time sequence data set, wherein the sub-signal set comprises at least one sub-signal; Performing autoregressive moving average modeling on the sub-signal set corresponding to the frequency band to obtain a load prediction sub-model corresponding to the frequency band, wherein the load prediction sub-model has a prediction result; And carrying out wavelet reconstruction processing on the prediction results of the load predictor models to obtain a load matrix corresponding to the power distribution network, wherein the load matrix represents the distribution prediction result of the power distribution network and comprises a load prediction value of each node in the power distribution network in a future time period.
4. The method of claim 2, wherein determining the dynamic load weight of each node in the power distribution network based on the load distribution prediction of the power distribution network comprises: According to the load distribution prediction result of the power distribution network, determining the predicted load ratio of each node in the power distribution network; Regularizing the load duty ratio of each node in the power distribution network to obtain a processed predicted load duty ratio of each node in the power distribution network; and determining the dynamic load weight of each node in the power distribution network according to the processed predicted load duty ratio of each node in the power distribution network and a preset factor, wherein the preset factor represents the node position importance of the node.
5. The method according to claim 1, wherein the constructing a distributed load balancing optimization model corresponding to the power distribution network according to the dynamic load weight of each node in the power distribution network and the current flow direction data between every two nodes in the power distribution network includes: Constructing an objective function according to the dynamic load weight of each node in the power distribution network and a preset dynamic adjustment factor; And constructing a distributed load balancing optimization model corresponding to the power distribution network according to the objective function and current flow direction data between every two nodes in the power distribution network.
6. The method according to any one of claims 1-5, wherein the controlling each node in the power distribution network to perform load balancing operations according to the distributed load balancing optimization model corresponding to the power distribution network includes: generating a load allocation control direction instruction of each node in the power distribution network according to a distributed load balance optimization model corresponding to the power distribution network; and controlling each node in the power distribution network to execute load allocation operation according to the load allocation control direction instruction of each node in the power distribution network.
7. The method according to claim 6, wherein the controlling each node in the power distribution network to perform the load balancing operation according to the load balancing control direction instruction of each node in the power distribution network includes: Converting a load allocation control direction instruction of each node in the power distribution network according to a power distribution network topological structure to obtain an allocation instruction set of the power distribution network, wherein the allocation instruction set comprises allocation instructions of each node; Performing secondary optimization processing on the allocation instruction set of the power distribution network according to preset operation constraint conditions to obtain an optimized allocation instruction set, wherein the optimized allocation instruction set comprises optimized allocation instructions of each node; And sending the optimized allocation instruction of each node to the node so as to execute the corresponding load allocation operation.
8. A load deployment apparatus for a power distribution network, comprising: The acquisition module is used for acquiring real-time load data and historical load data of each node in the power distribution network and acquiring current flow direction data between every two nodes in the power distribution network; the determining module is used for determining the dynamic load weight of each node in the power distribution network according to the real-time load data and the historical load data of each node in the power distribution network; The construction module is used for constructing a distributed load balancing optimization model corresponding to the power distribution network according to the dynamic load weight of each node in the power distribution network and the current flow direction data between every two nodes in the power distribution network, wherein the distributed load balancing optimization model comprises the load allocation control direction of each node in the power distribution network; And the control module is used for controlling each node in the power distribution network to execute load allocation operation according to the distributed load balance optimization model corresponding to the power distribution network.
9. An electronic device is characterized by comprising a memory and a processor; The memory stores computer-executable instructions; The processor executing computer-executable instructions stored in the memory, causing the processor to perform the method of any one of claims 1-7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-7.
11. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-7.

Description

Load allocation method, device, equipment, storage medium and program product of power distribution network Technical Field The present application relates to the field of load allocation technologies of power distribution networks, and in particular, to a load allocation method, apparatus, device, storage medium, and program product for a power distribution network. Background The distribution network, as an important component of the power system, assumes the critical task of transmitting electrical energy from the substation to the consumers. In order to solve the problem of unbalanced load of the power distribution network, load allocation processing is required to be carried out on the power distribution network. In the prior art, load allocation control of a power distribution network is manually performed based on a simple plan control method. However, in the above manner, the manual processing manner is adopted, so that the response speed is slow, and the flexible response capability to the dynamic change of the real-time load is lacking, so that the load distribution of the power distribution network is uneven. Disclosure of Invention The embodiment of the application provides a load allocation method, a load allocation device, load allocation equipment, a load allocation storage medium and a load allocation program product for a power distribution network, which can regulate and control node loads of the power distribution network in real time under the condition of dynamic change of the node loads so as to ensure load distribution balance of all nodes of the power distribution network. In a first aspect, an embodiment of the present application provides a load allocation method for a power distribution network, including: acquiring real-time load data and historical load data of each node in a power distribution network, and acquiring current flow direction data between every two nodes in the power distribution network; Determining the dynamic load weight of each node in the power distribution network according to the real-time load data and the historical load data of each node in the power distribution network; Constructing a distributed load balancing optimization model corresponding to the power distribution network according to the dynamic load weight of each node in the power distribution network and the current flow direction data between every two nodes in the power distribution network, wherein the distributed load balancing optimization model comprises the load allocation control direction of each node in the power distribution network; And controlling each node in the power distribution network to execute load allocation operation according to the distributed load balance optimization model corresponding to the power distribution network. In one possible implementation manner, the determining the dynamic load weight of each node in the power distribution network according to the real-time load data and the historical load data of each node in the power distribution network includes: determining a load distribution prediction result of the power distribution network according to the real-time load data and the historical load data of each node in the power distribution network, wherein the load distribution prediction result comprises the load distribution condition of each node in the power distribution network in a predicted future time period; and determining the dynamic load weight of each node in the power distribution network according to the load distribution prediction result of the power distribution network. In one possible implementation manner, the determining a load distribution prediction result of the power distribution network according to the real-time load data and the historical load data of each node in the power distribution network includes: Generating a load time sequence data set of the node according to the real-time load data and the historical load data of the node, wherein the load time sequence data set comprises load time sequence signal data of the node at each historical moment; Performing wavelet decomposition on each load time sequence signal data in the load time sequence data set to obtain a sub-signal set corresponding to at least one frequency band corresponding to the load time sequence data set, wherein the sub-signal set comprises at least one sub-signal; Performing autoregressive moving average modeling on the sub-signal set corresponding to the frequency band to obtain a load prediction sub-model corresponding to the frequency band, wherein the load prediction sub-model has a prediction result; And carrying out wavelet reconstruction processing on the prediction results of the load predictor models to obtain a load matrix corresponding to the power distribution network, wherein the load matrix represents the distribution prediction result of the power distribution network and comprises a load prediction value of each node in the power distribut