CN-121073156-B - Power planning optimization method based on artificial intelligence

CN121073156BCN 121073156 BCN121073156 BCN 121073156BCN-121073156-B

Abstract

The invention relates to the technical field of data processing, in particular to an artificial intelligence-based power planning optimization method, which comprises the following steps of collecting data; determining an abnormal event, predicting parameters, determining candidate shutdown devices, determining high risk devices, determining target shutdown devices, generating a power planning scheme, and adjusting thresholds. According to the invention, abnormal events are judged to occur according to the total power consumption by collecting multidimensional data in real time, the load loss and the residual time length are predicted by combining a preset model, the residual time length, the heat consumption rate, the vibration frequency and the rotor rotating speed are used for determining high-risk equipment, target shutdown equipment is determined according to the active power, the climbing rate and the load loss of the high-risk equipment, and the threshold value is dynamically adjusted according to the total power consumption and the rotor rotating speed based on a power planning scheme, so that the problems of low shutdown decision accuracy and response lag caused by complex operation background and excessive dependence on the model of a power system are effectively solved.

Inventors

DAI QIQI
GONG JIAWEI
ZHANG JIA
LUO GANG
ZHANG YUAN
LI SONGQIAO
LI JIAHUI
CHEN JUNZHI
LI YINGXUE
ZHANG XUETING
CHEN RIHUAN
ZHANG YANHONG
WANG WEI
WU TONGYU
WU HAO

Assignees

国网江西省电力有限公司经济技术研究院

Dates

Publication Date: 20260512
Application Date: 20251106

Claims (9)

1. An artificial intelligence-based power planning optimization method is characterized by comprising the following steps: Collecting the total electricity consumption of a power system in a responsible area of a power plant, the heat consumption rate, active power, rotor rotation speed, climbing rate and vibration frequency of a bearing of each device to be tested in the power plant in real time; Judging that an abnormal event occurs according to the total power consumption and a preset deviation threshold value; Based on the abnormal event, predicting to obtain a load loss and a residual duration according to a preset artificial intelligent model and the total power consumption, wherein the load loss refers to the total power consumption load to be lost in a future period of time due to large-scale shutdown and production stopping prediction, and the residual duration refers to the time from the current moment to the maximum predicted load loss; judging a plurality of candidate shutdown devices according to the residual duration, the heat consumption rate and the vibration frequency; determining a plurality of high-risk devices according to the vibration frequency, the rotor rotating speed and a preset index threshold value of each candidate shutdown device, wherein the preset index threshold value is a critical value for screening real high-risk devices from the candidate devices; determining a plurality of target shutdown devices according to the active power, the climbing rate and the load loss of each high-risk device; Generating a power planning scheme according to all the target shutdown devices; Based on the power planning scheme, adjusting the preset deviation threshold or the preset index threshold according to the total power consumption and the rotor rotating speed in a preset adjustment time; the process for judging the occurrence of the abnormal event according to the total power consumption and the preset deviation threshold comprises the following steps: calculating electricity consumption deviation according to the total electricity consumption and the historical total electricity consumption; and judging that the electricity consumption requirement is reduced according to the comparison result of the electricity consumption deviation and the preset deviation threshold value so as to judge that the abnormal event occurs.
2. The artificial intelligence based power planning optimization method of claim 1, wherein determining a number of candidate shutdown devices based on the remaining time period, the heat rate, and the vibration frequency comprises: Judging that a shutdown demand event occurs according to a comparison result of the residual duration and a preset shutdown duration; Based on the shutdown demand event, a number of candidate shutdown devices are determined from the heat rate and the vibration frequency.
3. The artificial intelligence based power planning optimization method of claim 2, wherein determining a number of candidate shutdown devices based on the heat rate and the vibration frequency comprises: Calculating the change rate of all the heat consumption rates from the initial time to each time within the preset judging time to obtain a plurality of heat consumption rate change rates; calculating the change rate of all the vibration frequencies from the initial time to each time within the preset judging time to obtain a plurality of frequency change rates; and judging a plurality of candidate shutdown devices according to all the heat consumption rate change rates and all the frequency change rates.
4. The artificial intelligence based power planning optimization method of claim 3, wherein determining a number of candidate shutdown devices based on all the heat rate change rates and all the frequency change rates comprises: calculating energy-frequency synergy according to all the heat rate change rates and all the frequency change rates; And judging the equipment to be tested as the candidate shutdown equipment according to the comparison result of the energy-frequency coordination degree and a preset coordination degree threshold value, and obtaining a plurality of candidate shutdown equipment.
5. The artificial intelligence based power planning optimization method of claim 4, wherein determining a number of high risk devices based on the vibration frequency, the rotor speed, and a preset index threshold for each of the candidate shutdown devices comprises: calculating a frequency fluctuation value according to the vibration frequency in a preset determined time period; calculating a rotational speed fluctuation value according to the rotational speed of the rotor within the preset determined time period; and determining a plurality of high-risk devices according to the frequency fluctuation value, the rotating speed fluctuation value and a preset index threshold value.
6. The artificial intelligence based power planning optimization method of claim 5, wherein determining a number of high risk devices from the frequency fluctuation value, the rotational speed fluctuation value, and a preset exponent threshold comprises: Calculating a risk index according to the frequency fluctuation value and the rotation speed fluctuation value; And judging the candidate shutdown equipment as the high-risk equipment according to the comparison result of the risk index and the preset index threshold value so as to determine a plurality of high-risk equipment.
7. The artificial intelligence based power planning optimization method of claim 6, wherein determining a number of target shutdown devices based on the active power, the ramp rate, and the load loss amount of each of the high risk devices comprises: Calculating a total curtailable capacity from the active power of all the high risk devices; Determining a curtailable list according to the risk index and the climbing rate of each high-risk device when the total curtailable capacity is larger than the load loss amount, and determining a plurality of target shutdown devices according to the curtailable list and the active power of each high-risk device; When the total reducible capacity is smaller than or equal to the load loss amount, determining that all the high-risk devices are the target shutdown devices, calculating residual loss load according to the total reducible capacity and the load loss amount, and determining target shutdown devices according to the residual loss load, the risk index of each temporary device, the climbing rate and the active power; Wherein the temporary equipment is equipment other than the high risk equipment in the candidate shutdown equipment.
8. The artificial intelligence based power planning optimization method of claim 7, wherein determining a target shutdown device based on the residual loss load, the risk index for each temporary device, the ramp rate, and the active power comprises: calculating a plurality of matching degrees according to the active power and the residual loss load of each temporary device; When the matching degree is larger than zero and smaller than a preset matching degree threshold value, judging that the corresponding temporary equipment is the target shutdown equipment; And when the matching degree is not greater than zero and smaller than the preset matching degree threshold, determining a temporary list according to the risk index and the climbing rate of each temporary device, and determining a plurality of target shutdown devices according to the temporary list, the active power and the residual loss load.
9. The artificial intelligence based power planning optimization method of claim 8, wherein adjusting the preset deviation threshold or adjusting the preset exponent threshold based on the total power usage and the rotor speed for a preset adjustment period comprises: calculating an electricity consumption deviation fluctuation value according to the total electricity consumption and the historical total electricity consumption in the preset adjustment time; adjusting the preset deviation threshold according to a first comparison result of the electricity consumption deviation fluctuation value and the preset fluctuation threshold; Calculating the rotating speed change rate according to the rotating speed of the rotor in a preset adjustment time based on a second comparison result of the electricity consumption deviation fluctuation value and the preset fluctuation threshold value; and adjusting the preset index threshold according to the comparison result of the rotating speed change rate and the preset rotating speed change rate threshold.

Description

Power planning optimization method based on artificial intelligence Technical Field The invention relates to the technical field of data processing, in particular to an artificial intelligence-based power planning optimization method. Background The power system is faced with problems in this situation due to the large-scale downtime and stalling for a number of reasons. On the one hand, the rapid change of electricity demand makes the traditional power planning and scheduling method difficult to adapt, and the waste or the supply shortage of power resources can be caused, and on the other hand, the shutdown and the restarting of partial power generation equipment need to be carefully decided so as to avoid the impact on the stability of the power grid. In addition, how to optimize the operation of the power equipment and reduce the energy consumption and the environmental pollution while guaranteeing the basic power consumption is also a problem to be solved. The Chinese patent application publication number CN120387535A discloses an intelligent planning and optimizing method of a power system, which comprises the steps of S1, collecting operation state data in the power system, including electric parameters, power generation data, load data and charge and discharge states of energy storage equipment, S2, according to the load data and historical load data collected in the step S1, adopting an LSTM neural network to predict the load demand of the power system within a preset time range, S3, according to the predicted load demand, the operation state data, a preset optimizing target and a preset limiting condition, adopting a deep Q network to construct a power dispatching model, obtaining an optimal planning strategy, wherein the optimal planning strategy comprises an output strategy of a generator set, a charge and discharge strategy of the energy storage system and a load adjustment strategy, and S4, sending the optimal planning strategy to a dispatching center, and executing the optimal planning strategy by the dispatching center. Therefore, the intelligent planning and optimizing method for the electric power system has the following problems that based on the prediction of load demands, rapid changes of the power demands cannot be recognized in time, so that electric power resources are wasted or supplied insufficiently, multi-dimensional comprehensive evaluation of the running state of the equipment is lacking depending on load data and historical load data, and stability and adaptability of the electric power system under complex working conditions are difficult to guarantee when the power demands and the running state of the equipment change remarkably in a short time. Disclosure of Invention Therefore, the invention provides an artificial intelligence-based power planning optimization method, which is used for solving the problems of low shutdown decision accuracy and response lag caused by complex operation background and too-dependent model of a power system in the prior art through multidimensional parameter analysis and dynamic adjustment mechanisms. In order to achieve the above object, the present invention provides an artificial intelligence based power planning optimization method, comprising: Collecting the total electricity consumption of a power system in a responsible area of a power plant, the heat consumption rate, active power, rotor rotation speed, climbing rate and vibration frequency of a bearing of each device to be tested in the power plant in real time; Judging that an abnormal event occurs according to the total power consumption and a preset deviation threshold value; Based on the abnormal event, predicting and obtaining a load loss amount and a residual duration according to a preset artificial intelligent model and the total power consumption; judging a plurality of candidate shutdown devices according to the residual duration, the heat consumption rate and the vibration frequency; Determining a plurality of high risk devices according to the vibration frequency, the rotor rotating speed and a preset index threshold value of each candidate shutdown device; determining a plurality of target shutdown devices according to the active power, the climbing rate and the load loss of each high-risk device; Generating a power planning scheme according to all the target shutdown devices; And based on the power planning scheme, adjusting the preset deviation threshold or the preset index threshold according to the total power consumption and the rotor rotating speed in a preset adjustment time. Further, the process of determining that an abnormal event occurs according to the total power consumption and a preset deviation threshold value comprises the following steps: calculating electricity consumption deviation according to the total electricity consumption and the historical total electricity consumption; and judging that the electricity consumption requirement is reduced according