CN-122001025-A - Novel power system dispatching optimization method integrating renewable energy sources

CN122001025ACN 122001025 ACN122001025 ACN 122001025ACN-122001025-A

Abstract

The invention relates to the technical field of power supply or distribution circuit devices or systems and electric energy storage systems, in particular to a novel power system dispatching optimization method integrating renewable energy sources. The method solves the technical problem that the prediction accuracy and reliability of the existing method are difficult to meet the actual requirements of fine scheduling of the power grid. The method comprises the steps of determining a first target value among various environmental data based on first data of a first time point, wherein the first target value is used for representing relevance among the various environmental data, determining a second target value among the various environmental data based on the first target value, a fluctuation variable of a first environment monitoring value at a second time point and a power variable of first power generation power at a second time point, wherein the second time point is a time point when the first power generation power fluctuates, and determining predicted power generation power of a target time point based on the first data, the second target value and a second environment predicted value of the target time point.

Inventors

WANG ZHAOPING
ZHANG ZHIFANG
WANG JUN
BAO YONGGUI
LI MEI

Assignees

西安云领大数据科技有限公司

Dates

Publication Date: 20260508
Application Date: 20260327

Claims (10)

1. A novel power system scheduling optimization method integrating renewable energy sources, characterized in that the method comprises the following steps: The method comprises the steps of determining a first target value among various environmental data based on first data of a first time point, wherein the first time point is any historical observation time point, and the first data at least comprises one of a first environmental monitoring value, a first environmental prediction value and a first power generation of the renewable energy source at the first time point, wherein the first target value is used for representing the relevance among the various environmental data; Determining a second target value among the plurality of environmental data based on the first target value, a fluctuation variable of the first environmental monitoring value at a second time point and a power variable of the first power generation at a second time point, wherein the second time point is a time point when the first power generation fluctuates; And determining the predicted power generation power of a target time point based on the first data, the second target value and a second environment predicted value of the target time point, wherein the target time point is any time point of the power generation power to be predicted, and the predicted power generation power is used for power system scheduling optimization.
2. A novel power system dispatch optimization method for integrating renewable energy sources according to claim 1, further comprising: Generating a first predicted power generation sequence based on the predicted power generation at the plurality of target time points; The predicted generated power is modified based on a similarity of the first predicted generated power sequence to a second predicted generated power sequence of the plurality of first time points.
3. A novel power system dispatch optimization method for integrated renewable energy according to claim 2, wherein the determining a first target value between a plurality of environmental data based on first data at a first point in time comprises: determining any two kinds of target environmental data in the plurality of environmental data; And determining a first target value between the two target environment data based on the proximity of the change ratio of the first environment monitoring values of the two target environment data at a plurality of first time points, wherein the proximity of the change ratio is in direct proportion to the first target value between the two target environment data.
4. A novel power system schedule optimization method for integrating renewable energy according to claim 3, wherein said determining a second target value between said plurality of environmental data based on said first target value, a fluctuation variable of said first environmental monitoring value at a second point in time, and a power variable of said first power generation at a second point in time comprises: Determining a second environmental monitoring value for each environmental data of the plurality of environmental data at the second point in time; Determining an impact weight of the plurality of environmental data at the second point in time based on a fluctuation variable between the first environmental monitoring value and the second environmental monitoring value; A second target value between the plurality of environmental data is determined based on the influence weight of the plurality of environmental data at the second time point, and the fluctuation variable of the first environmental monitoring value at the second time point and the power variable of the first power generation at the second time point.
5. The method of claim 4, wherein determining the predicted generated power at the target point in time based on the first data, the second target value, and a second environmental predicted value at the target point in time comprises: Determining a plurality of prediction weights of the predicted power generation at a plurality of first time points occupying the target time points based on the first data and the second target value; A predicted generated power of the target point in time is determined based on the plurality of predicted weights and the first generated powers of the plurality of first points in time.
6. The method for optimizing power system scheduling for integrated renewable energy according to claim 5, wherein determining a plurality of predicted weights of the predicted generated power of the target time point from a plurality of first time points based on the first data and the second target value comprises: determining a negative correlation mapping value of each environmental data difference in the plurality of environmental data at the first point in time based on the first environmental prediction value and the second environmental prediction value; and determining a plurality of prediction weights of the predicted power generation at the target time points at a plurality of first time points based on the negative correlation mapping value and the second target value.
7. The method of claim 6, wherein the modifying the predicted generated power based on the similarity of the first predicted generated power sequence to a second predicted generated power sequence at a plurality of first time points comprises: determining a similarity between the first predicted generated power sequence and a second predicted generated power sequence of the plurality of first time points; Determining a correction weight for each first point in time based on a similarity between the first predicted generated power sequence and each second predicted generated power sequence of the plurality of first points in time; And correcting the predicted power generation based on the correction weight and the difference value between the predicted power generation and the actual power generation at each first time point.
8. The method of claim 7, wherein determining the similarity between the first predicted generated power sequence and a second predicted generated power sequence at a plurality of first points in time comprises: and calculating the similarity between the first predicted generated power sequence and a second predicted generated power sequence of a plurality of first time points based on a preset dynamic time warping algorithm.
9. The method of optimizing power system scheduling for integrated renewable energy according to claim 8, further comprising: Determining a conventional energy demand generated power at the target point in time based on the predicted generated power of at least one of the renewable energy sources at the target point in time and the predicted power for the target region; And scheduling the power system based on the traditional energy demand generated power, and maintaining the supply and demand balance of the power generation side and the power utilization side.
10. The novel power system dispatching optimization method integrated with renewable energy sources according to claim 9 is characterized in that the renewable energy sources at least comprise one of solar energy, wind energy and water energy, and the environment data at least comprise one of illumination intensity, temperature, cloud layer thickness and air humidity of the solar energy, wind speed, air density and temperature of the wind energy, water flow rate of the water energy, water level difference and water temperature of the water energy.

Description

Novel power system dispatching optimization method integrating renewable energy sources Technical Field The invention relates to the technical field of power system dispatching, in particular to a novel power system dispatching optimization method integrating renewable energy sources. Background Along with the continuous promotion of global energy transformation, the permeability of renewable energy sources represented by solar energy and wind energy in an electric power system is continuously improved. Renewable energy power generation has the remarkable advantages of cleanness and low carbon, but the output is remarkably influenced by natural environment and meteorological conditions, and the renewable energy power generation has the characteristics of intermittence and volatility, which forms a great challenge for maintaining the real-time power balance and safe and stable operation of an electric power system. At present, power system scheduling depends on accurate prediction of renewable energy generated power to a great extent, and an existing prediction method generally builds a prediction model based on historical environment monitoring data and generated power data so as to estimate future generated power. However, under the high-proportion renewable energy source access background, wide-area cooperative fluctuation characteristics driven by a complex meteorological system exist, the existing prediction model cannot fully consider the inherent relevance among various environmental data, the composite influence of common change on the generated power cannot be accurately described, the prediction model directly takes the environmental prediction value with uncertainty as input, and a learning and correcting mechanism for the prediction deviation is lacking, so that the prediction accuracy and reliability of the existing method are difficult to meet the actual requirements of fine scheduling of a power grid, and the overall operation efficiency and safety stability of the power system are further influenced. Disclosure of Invention In order to solve the technical problems that the prediction accuracy and reliability of the existing method are difficult to meet the actual requirements of fine scheduling of a power grid and further influence the overall operation efficiency and safety stability of a power system, the invention aims to provide a novel power system scheduling optimization method integrating renewable energy, and the adopted technical scheme is as follows: In a first aspect, the invention provides a novel power system scheduling optimization method integrating renewable energy, which comprises the steps of determining a first target value among various environmental data based on first data of a first time point, wherein the first time point is any historical observation time point, the first data at least comprises one of a first environment monitoring value of the renewable energy at the first time point and a first power generation power of the renewable energy at the first time point, the first target value is used for representing the relevance among the various environmental data, determining a second target value among the various environmental data based on the first target value, fluctuation variables of the first environment monitoring value at a second time point and power variables of the first power generation at the second time point, the second time point is the time point when the first power generation power fluctuates, the second target value is used for representing the influence degree of the various environmental data on the power generation power, the target time point is determined based on the first data, the second target value and the second environment predicted value of the target time point, and the power generation power is any power generation power to be predicted, and the power generation power is predicted to be used for performing power system scheduling optimization. With reference to the first aspect, in a possible implementation manner, the method further includes generating a first predicted power generation sequence based on the predicted power generation at the plurality of target time points, and correcting the predicted power generation based on similarity between the first predicted power generation sequence and a second predicted power generation sequence at the plurality of first time points. With reference to the first aspect, in one possible implementation manner, the method specifically includes determining any two kinds of target environmental data in a plurality of environmental data, determining a first target value between the two kinds of target environmental data based on the proximity of a change ratio of a first environmental monitoring value of the two kinds of target environmental data at a plurality of first time points, and determining that the proximity of the change ratio is proportional to the first target value between the t