CN-121998284-A - Thermal power plant scheduling method, thermal power plant scheduling device, computer equipment, readable storage medium and program product

CN121998284ACN 121998284 ACN121998284 ACN 121998284ACN-121998284-A

Abstract

The application relates to a thermal power plant scheduling method, a thermal power plant scheduling device, a thermal power plant scheduling computer readable storage medium and a thermal power plant scheduling computer program product. The method comprises the steps of obtaining a sample information set of a thermal power plant, carrying out information division on a plurality of sample information in the sample information set based on preset parameter association information to obtain a plurality of working condition clusters, determining a cluster center of the working condition clusters according to each working condition cluster, wherein each working condition cluster comprises a plurality of intra-cluster samples, determining the intra-cluster sample with the smallest weighted distance from the intra-cluster samples as a target sample, carrying out constraint evaluation on each target sample, and using the target sample with an evaluation result meeting an evaluation condition to control the work of the thermal power plant. By adopting the method, the scheduling flexibility of the thermal power plant can be improved.

Inventors

CHEN HAOYU
CHU JINGCHUN
HAO XIAOLIANG
YOU ZEDONG
WU PENG
SUN HONGYANG
LIANG LING
NIU XINXIN
HE HAONAN
BAI YUXUAN

Assignees

国家能源集团新能源技术研究院有限公司
国家能源投资集团有限责任公司
国能浙能宁东发电有限公司
国能长源能源销售有限公司

Dates

Publication Date: 20260508
Application Date: 20251208

Claims (10)

1. A thermal power plant scheduling method, the method comprising: Acquiring a sample information set of a thermal power plant; dividing information of a plurality of sample information in the sample information set based on preset parameter association information to obtain a plurality of working condition clusters, wherein each working condition cluster comprises at least one part of sample information; determining a cluster center of each working condition cluster according to each working condition cluster, wherein each working condition cluster comprises a plurality of intra-cluster samples; from the intra-cluster samples, determining the intra-cluster sample with the smallest weighted distance between the intra-cluster sample and the cluster center as a target sample; and carrying out constraint evaluation on each target sample, and using the target samples with evaluation results meeting evaluation conditions for controlling the work of the thermal power plant.
2. The method of claim 1, wherein the obtaining a sample information set of a thermal power plant comprises: acquiring equipment information of a thermal power plant, wherein the equipment information comprises a plurality of pieces of real-time working parameter information and constraint information corresponding to the plurality of pieces of working scenes respectively; Responding to a received natural language scheduling instruction, and determining a thermal power plant working scene label matched with the natural language scheduling instruction; determining target constraint information matched with the thermal power plant working scene label from the constraint information; And based on the target constraint information, constraint screening is carried out on each piece of real-time working parameter information, target working parameter information matched with the target constraint information is determined, and a sample information set containing the target working parameter information and risk weights corresponding to the target working parameter information is obtained.
3. The method according to claim 2, wherein the method further comprises: Determining a risk weight of the target working parameter information based on the constraint satisfaction degree between the target working parameter information and the target constraint information; Determining a last history working condition matched with the thermal power plant working scene label based on the thermal power plant working scene label; the obtaining a sample information set containing the target working parameter information and the risk weight corresponding to the target working parameter information includes: And according to the working condition information in the previous history working condition, carrying out information supplement on other working parameter information except the target working parameter information to obtain a sample information set containing the target working parameter information, the other working parameter information and risk weights respectively corresponding to the target working parameter information and the other working parameter information.
4. A method according to claim 3, wherein the obtaining a sample information set including the target operating parameter information, the other operating parameter information, and risk weights respectively corresponding to the target operating parameter information and the other operating parameter information includes: acquiring parameter weights respectively corresponding to the target working parameter information and the other working parameter information; Deleting the working parameter information with the parameter weight not meeting the weight condition to obtain a sample information set containing the target working parameter information, the other working parameter information and risk weights respectively corresponding to the target working parameter information and the other working parameter information which meet the weight condition.
5. The method of claim 1, wherein the performing information division on the plurality of sample information in the sample information set based on the preset parameter association information to obtain a plurality of working condition clusters includes: Inputting the preset parameter association information and the sample information set into a sparse subspace clustering model; and determining a plurality of working condition clusters based on the output of the sparse subspace clustering model.
6. The method according to claim 1, wherein the performing constraint evaluation on each of the target samples, and using the target samples whose evaluation results satisfy the evaluation condition for controlling the operation of the thermal power plant includes: determining an evaluation result of each target sample based on a preset evaluation index system comprising equipment performance constraints, safe operation constraints and environment-friendly emission constraints; And using the target sample with the evaluation result meeting the evaluation condition to control the work of the thermal power plant.
7. A thermal power plant scheduling apparatus, the apparatus comprising: the information set acquisition module is used for acquiring a sample information set of the thermal power plant; The information dividing module is used for dividing the information of a plurality of sample information in the sample information set based on preset parameter association information to obtain a plurality of working condition clusters, wherein each working condition cluster comprises at least one part of sample information; The cluster center determining module is used for determining the cluster center of each working condition cluster according to each working condition cluster, wherein each working condition cluster comprises a plurality of intra-cluster samples; The target sample determining module is used for determining the intra-cluster sample with the smallest weighted distance between the intra-cluster sample and the cluster center from the intra-cluster samples as a target sample; the constraint evaluation module is used for performing constraint evaluation on each target sample, and the target samples with evaluation results meeting evaluation conditions are used for controlling the work of the thermal power plant.
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

Thermal power plant scheduling method, thermal power plant scheduling device, computer equipment, readable storage medium and program product Technical Field The present application relates to the field of intelligent scheduling technology, and in particular, to a thermal power plant scheduling method, apparatus, computer device, computer readable storage medium, and computer program product. Background With the continuous development of the electric power industry technology, a thermal power plant is used as a core link of energy supply, and the dispatching efficiency and stability of the thermal power plant are critical to the overall operation of an energy system. Currently, thermal power plant scheduling technologies have gradually introduced data-driven methods to optimize scheduling strategies by analyzing historical operating data. The traditional scheduling method mainly depends on manual experience or a model based on fixed rules, for example, by setting a fixed load distribution threshold or a simple working condition classification rule, the operation data of the thermal power plant is divided into a plurality of fixed working condition intervals, and then a scheduling scheme is formulated for each interval. However, the actual operation working conditions of the thermal power plant are complex and changeable and are dynamically influenced by multiple factors such as fuel quality, equipment state, environmental conditions and the like, the traditional method is difficult to adapt to the real-time changing requirement due to rough working condition division and stiff scheduling strategy, and the traditional method lacks of deep mining of internal correlation of sample data, so that scheduling parameters cannot be flexibly adjusted to adapt to the optimizing requirements of different working conditions, and therefore, the traditional thermal power plant scheduling method has the problem of poor flexibility. Disclosure of Invention In view of the foregoing, it is desirable to provide a thermal power plant scheduling method, apparatus, computer device, computer readable storage medium, and computer program product that can improve the flexibility of thermal power plant scheduling. In a first aspect, the present application provides a thermal power plant scheduling method, including: Acquiring a sample information set of a thermal power plant; dividing information of a plurality of sample information in the sample information set based on preset parameter association information to obtain a plurality of working condition clusters, wherein each working condition cluster comprises at least one part of sample information; determining a cluster center of each working condition cluster according to each working condition cluster, wherein each working condition cluster comprises a plurality of intra-cluster samples; from the intra-cluster samples, determining the intra-cluster sample with the smallest weighted distance between the intra-cluster sample and the cluster center as a target sample; and carrying out constraint evaluation on each target sample, and using the target samples with evaluation results meeting evaluation conditions for controlling the work of the thermal power plant. In one embodiment, the acquiring the sample information set of the thermal power plant includes: acquiring equipment information of a thermal power plant, wherein the equipment information comprises a plurality of pieces of real-time working parameter information and constraint information corresponding to the plurality of pieces of working scenes respectively; Responding to a received natural language scheduling instruction, and determining a thermal power plant working scene label matched with the natural language scheduling instruction; determining target constraint information matched with the thermal power plant working scene label from the constraint information; And based on the target constraint information, constraint screening is carried out on each piece of real-time working parameter information, target working parameter information matched with the target constraint information is determined, and a sample information set containing the target working parameter information and risk weights corresponding to the target working parameter information is obtained. In one embodiment, the method further comprises: Determining a risk weight of the target working parameter information based on the constraint satisfaction degree between the target working parameter information and the target constraint information; Determining a last history working condition matched with the thermal power plant working scene label based on the thermal power plant working scene label; the obtaining a sample information set containing the target working parameter information and the risk weight corresponding to the target working parameter information includes: And according to the working condition information in the previous history work