Power grid wind energy absorption optimization method and system based on multi-time scale demand response

Abstract

The invention provides a power grid wind energy consumption optimization method and system based on multi-time scale demand response. The method comprises the following steps: step 1, constructing a wind energy output prediction model based on meteorology; 2, analyzing power utilization rule attributes of the multi-class energy consumption terminals under multiple time scales; 3, carrying out correlation analysis on the wind energy output prediction model and the power utilization rule attributes of the multi-class energy consumption terminals under multiple time scales, and determining a dynamic demand response plan; and step 4, demand response resources are controlled according to the dynamic demand response plan to perform power grid wind energy scheduling absorption. The power grid consumption capability is effectively improved, and the intelligence and accuracy of power grid consumption control are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind energy consumption in power grids, and in particular to a method and system for optimizing wind energy consumption in power grids based on multi-time-scale demand response. Background Art

[0002] Currently, wind energy, as a clean and renewable energy source, is increasingly used in power grids. However, wind energy is characterized by uncertainty, which has brought inconvenience to the stable operation of the power grid and the effective absorption of wind energy.

[0003] Traditional grid wind energy dispatch methods struggle to fully adapt to the uncertainty of wind energy, resulting in some wind energy being abandoned and wasting energy. Furthermore, current demand response systems often lack multi-timescale considerations when dealing with wind energy absorption, making it impossible to fully and effectively coordinate wind energy fluctuations with demand response resources, significantly reducing the effectiveness of grid wind energy absorption.

[0004] Therefore, in order to overcome the above-mentioned defects, the present invention provides a method and system for optimizing wind energy consumption in a power grid based on multi-time-scale demand response. Summary of the Invention

[0005] The present invention provides a wind energy absorption optimization method and system for a power grid based on multi-time-scale demand response, which can effectively and accurately realize the prediction of electric energy by constructing a meteorological-based wind energy output prediction model. By analyzing the power consumption regularity attributes corresponding to multiple categories of energy-consuming terminals under multiple time scales, the power consumption patterns of different user-side energy-consuming equipment can be effectively mined, and load regulation potential analysis can be provided for demand response strategies. By correlating and analyzing the wind energy output prediction model with the power consumption regularity attributes of multiple categories of energy-consuming terminals under multiple time scales, a dynamic demand response plan can be accurately determined, and the demand response resources can be controlled according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid, thereby effectively improving the power grid absorption capacity and effectively improving the intelligence and accuracy of the power grid absorption control.

[0006] A method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response, comprising:

[0007] Step 1: Build a meteorological-based wind power output prediction model;

[0008] Step 2: Analyze the power consumption patterns of multiple energy-consuming terminals at multiple time scales;

[0009] Step 3: Correlate the wind power output forecast model with the power consumption patterns of multiple energy-consuming terminals at multiple time scales to determine a dynamic demand response plan.

[0010] Step 4: Control the demand response resources according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid.

[0011] Preferably, a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response comprises, in step 1, constructing a meteorological-based wind energy output prediction model, comprising:

[0012] S101: Collecting wind turbine power generation parameters under multi-source meteorological conditions;

[0013] S102: Analyze wind turbine power generation parameters under multi-source meteorological conditions and construct a characteristic transformation function;

[0014] S103: Constructing a meteorological-based wind energy output prediction model according to the characteristic transformation function.

[0015] Preferably, a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response, in step 2, analyzing the power consumption regularity attributes of multiple categories of energy-consuming terminals under multiple time scales, includes:

[0016] S201: Acquire all energy-consuming terminals, and classify the energy-consuming terminals according to their terminal categories to obtain energy-consuming terminal sets of each category;

[0017] S202: Reading scale dimensions of multiple time scales, and respectively reading power consumption parameters of each category of energy-consuming terminal sets in each scale dimension;

[0018] S203: Analyze the unit power consumption pattern of each energy-consuming terminal in each category in the corresponding scale dimension based on the power consumption parameters;

[0019] S204: Analyze the unit power consumption pattern of each energy consuming terminal in the corresponding scale dimension, collect the intersection of the unit power consumption patterns of each energy consuming terminal in the corresponding scale dimension, and use the intersection of the unit power consumption patterns as the sub-power consumption pattern of the corresponding scale dimension under the current category;

[0020] S205: Repeat steps S203-S204 to obtain the sub-power consumption pattern of each category of energy-consuming terminals in each scale dimension;

[0021] S206: Integrate the sub-power consumption patterns of each category of energy-consuming terminals in each scale dimension to obtain power consumption pattern attributes of multiple categories of energy-consuming terminals in multiple time scales.

[0022] In this embodiment, the electricity usage parameters include: electricity usage behavior, electricity usage amount, electricity usage duration, etc.

[0023] Preferably, a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response, S206: integrating the sub-power consumption patterns of each category of energy-consuming terminals in each scale dimension, including:

[0024] An electricity consumption pattern table is constructed with the terminal category as the horizontal axis and the scale dimension as the vertical axis, and the corresponding sub-electricity consumption patterns are mapped in the electricity consumption pattern table to obtain the electricity consumption pattern attributes of multiple categories of energy-consuming terminals under multiple time scales.

[0025] Preferably, a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response, in step 3, performs correlation analysis between the wind energy output prediction model and the power consumption regularity attributes of multiple categories of energy-consuming terminals under multiple time scales to determine a dynamic demand response plan, including:

[0026] Obtaining the power consumption regularity attributes of multiple categories of energy-consuming terminals at multiple time scales, and dividing the power consumption regularity attributes of the multiple categories of energy-consuming terminals based on the time scales;

[0027] Based on the division results, the power consumption regularity attributes of multiple categories of energy-consuming terminals at the same time scale are grouped to obtain a multi-category sample data group at the same time scale;

[0028] Based on the wind power output prediction model, the multi-category sample data set at the same time scale is analyzed to obtain the power consumption demand of different types of energy-consuming terminals at the same time scale. At the same time, based on the wind power output prediction model, the meteorological data at different time scales are analyzed to obtain the conversion amount of wind energy to electricity at different time scales.

[0029] A dynamic demand response plan is constructed based on the electricity consumption demand of different types of energy-consuming terminals and the conversion amount of wind energy to electrical energy on the same time scale.

[0030] Preferably, a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response is provided, which constructs a dynamic demand response plan based on the power consumption demand of different types of energy-consuming terminals and the conversion amount of wind energy to electric energy at the same time scale, including:

[0031] Summarize the electricity demand of different types of energy-consuming terminals at the same time scale, and match the summary results with the conversion amount of wind energy to electricity at the corresponding time scale;

[0032] When the matching result determines that the summary result does not match the amount of wind energy converted into electrical energy, a dynamic demand response is initiated based on the determination result;

[0033] Prioritize the dynamic demand response schemes based on the activation results, and determine the logical switching points of different dynamic demand response schemes and the dynamic demand response execution amounts under different dynamic demand response schemes based on the priority configuration results and the judgment results;

[0034] A dynamic demand response plan is obtained based on the logic switching point and the dynamic demand response execution amount.

[0035] Preferably, a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response obtains a dynamic demand response plan based on a logic switching point and a dynamic demand response execution amount, including:

[0036] Based on the wind power output forecast model, the target meteorological data at the current moment is analyzed to obtain the real-time power output. At the same time, the real-time power demand is determined based on the power consumption pattern attributes at the current moment.

[0037] parsing the real-time power output and power demand based on the dynamic demand response plan, and re-parsing the parsed results based on the priority configuration of the dynamic demand response plan, wherein the dynamic demand response plan includes power coordination and interrupted loads, and the power coordination has a higher priority than the interrupted loads;

[0038] Based on the re-analysis results, the power demand dispatch amount for different types of energy-consuming terminals under the power coordinated response plan is determined, and when the power demand dispatch amount meets the preset operating requirements, dynamic demand response is performed based on the power coordinated response plan;

[0039] At the same time, when the power demand dispatching amount does not meet the preset operation requirements, the interruption load response plan is activated;

[0040] Determine the optimal amount of power coordination based on the startup results, and determine the current maximum load available based on the optimal amount, real-time power output, and the operating status of different types of energy-consuming terminals;

[0041] Based on the maximum available load, the interruption load amount for different types of energy consumption terminals is determined, and the interruption load amount is used to generate an interruption guidance report and sent to the management terminal of different types of energy consumption interruptions for interruption load guidance, thereby completing dynamic demand response.

[0042] Preferably, a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response, in step 4, controlling demand response resources according to a dynamic demand response plan to dispatch and consume wind energy in the power grid, includes:

[0043] Read the dynamic demand response plan, determine the consumption target in the dynamic demand response plan, and divide the dynamic demand response according to the consumption target;

[0044] Determine the sub-response demand plan corresponding to each absorption target based on the division results;

[0045] Obtain the execution parameters of the sub-response demand plan and the scheduling relationship between each absorption target;

[0046] The grid wind energy is dispatched and absorbed according to the dispatch relationship between the execution parameters of the sub-response demand plan and each absorption target.

[0047] A wind energy consumption optimization system for a power grid based on multi-time-scale demand response, comprising:

[0048] Model building module, used to build a meteorological-based wind power output prediction model;

[0049] The power consumption regularity attribute determination module is used to analyze the power consumption regularity attributes of multiple categories of energy-consuming terminals at multiple time scales;

[0050] The correlation analysis module is used to correlate the wind power output forecast model with the power consumption characteristics of multiple energy-consuming terminals at multiple time scales to determine the dynamic demand response plan;

[0051] The dispatching and absorbing module is used to control the demand response resources according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid.

[0052] Preferably, a wind energy consumption optimization system for a power grid based on multi-time-scale demand response, the model building module includes:

[0053] Data acquisition unit, used to collect power generation parameters of wind turbines under multi-source meteorological conditions;

[0054] A function construction unit is used to analyze wind turbine power generation parameters under multi-source meteorological conditions and construct a characteristic transformation function;

[0055] The model building unit is used to build a meteorological-based wind energy output prediction model according to the characteristic transformation function.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] By constructing a meteorological-based wind power output prediction model, electric energy can be predicted effectively and accurately. By analyzing the power consumption patterns of various energy-consuming terminals at multiple time scales, the power consumption patterns of different user-side energy-consuming devices can be effectively explored, providing load regulation potential analysis for demand response strategies. By correlating the wind power output prediction model with the power consumption patterns of various energy-consuming terminals at multiple time scales, the dynamic demand response plan can be accurately determined, and the demand response resources can be controlled according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid, thereby effectively improving the grid's absorption capacity and the intelligence and accuracy of the grid's absorption control.

[0058] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0059] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0061] Figure 1 This is a flow chart of a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response in an embodiment of the present invention;

[0062] Figure 2 This is a flowchart of step 1 in a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response in an embodiment of the present invention;

[0063] Figure 3 This is a structural diagram of a power grid wind energy consumption optimization system based on multi-time scale demand response in an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0065] Example 1:

[0066] This embodiment provides a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response. Figure 1 As shown, including:

[0067] Step 1: Build a meteorological-based wind power output prediction model;

[0068] Step 2: Analyze the power consumption patterns of multiple energy-consuming terminals at multiple time scales;

[0069] Step 3: Correlate the wind power output forecast model with the power consumption patterns of multiple energy-consuming terminals at multiple time scales to determine a dynamic demand response plan.

[0070] Step 4: Control the demand response resources according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid.

[0071] In this embodiment, the wind power output model is used to achieve high-precision wind power generation prediction based on the impact of meteorological conditions on wind turbine parameters and power generation.

[0072] In this embodiment, the multiple categories of energy-consuming terminals are determined according to the terminal types of the energy-consuming terminals, including industrial, residential, commercial, agricultural, and the like.

[0073] In this embodiment, the multiple time scales are determined according to preset requirements and are composed of multiple different time dimensions, including: day-ahead, intraday, real-time, quarterly, monthly, and annual divisions.

[0074] In this embodiment, the wind energy output prediction model is correlated with the power consumption regularity attributes of multiple categories of energy-consuming terminals at multiple time scales and analyzed to determine the dynamic demand response plan, that is, the conversion amount of wind energy to electric energy under different meteorological data is analyzed through the wind energy output prediction model, and then the power consumption demand of different energy-consuming terminals at different time scales is obtained by analyzing the power consumption regularity attributes, and the conversion amount of wind energy to electric energy is matched with the power consumption demand, so as to achieve coordination of the power required by different categories of energy-consuming terminals or response to load interruption.

[0075] In this embodiment, the dynamic demand response plan is a plan or measure for coordinating electric energy according to the real-time power consumption status, including coordinating the electric energy required by different types of energy-consuming terminals or responding to load interruption.

[0076] In this embodiment, the power usage regularity attribute represents the fluctuation of the power consumption of the energy consuming terminal under the influence of factors such as time, climate, and region.

[0077] The working principle and beneficial effects of the above technical solution are: by constructing a meteorological-based wind power output prediction model, the prediction of electric energy can be effectively and accurately realized; by analyzing the power consumption regularity attributes corresponding to multiple categories of energy-consuming terminals at multiple time scales, the power consumption patterns of different user-side energy-consuming equipment can be effectively mined, and load regulation potential analysis can be provided for demand response strategies; by correlating the wind power output prediction model with the power consumption regularity attributes of multiple categories of energy-consuming terminals at multiple time scales, the dynamic demand response plan can be accurately determined, and the demand response resources can be controlled according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid, thereby effectively improving the grid absorption capacity and effectively improving the intelligence and accuracy of the grid absorption control.

[0078] Example 2:

[0079] Based on Example 1, this embodiment provides a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response, such as Figure 2 As shown, in step 1, a meteorological-based wind power output prediction model is constructed, including:

[0080] S101: Collecting wind turbine power generation parameters under multi-source meteorological conditions;

[0081] S102: Analyze wind turbine power generation parameters under multi-source meteorological conditions and construct a characteristic transformation function;

[0082] S103: Constructing a meteorological-based wind energy output prediction model according to the characteristic transformation function.

[0083] Among them, the power generation parameters include wind turbine parameters and historical power generation data. The specific process includes: collecting wind turbine parameters and historical power generation data of wind turbines under multi-source meteorological conditions; analyzing the wind turbine parameters and historical power generation data under multi-source meteorological conditions, and determining the parameter transformation characteristics of wind turbine parameters under different meteorological conditions and the power generation transformation characteristics of historical power generation data; taking meteorological conditions as the first independent variable, taking the parameter transformation characteristics of wind turbine parameters as the first dependent variable, and at the same time, taking the power generation transformation characteristics as the second dependent variable; constructing a meteorological-wind turbine parameter transformation function based on the first independent variable and the first dependent variable. Among them, Where f(x) represents the weather-to-power conversion function; β0 represents the baseline wind turbine parameter when it does not change with weather conditions; i represents the ordinal value of the weather condition; n represents the total number of weather conditions; δ i represents the influence coefficient of the wind turbine parameters under the i-th meteorological condition; x i represents the meteorological characteristic value corresponding to the i-th meteorological condition (i.e., the first independent variable); a meteorological-power generation transformation function is constructed based on the first independent variable and the second dependent variable; wherein, Where G(x) represents the weather-power conversion function; α0 represents the reference power when it does not change with the weather; ρ i represents the influence coefficient of the i-th meteorological condition on the power generation; obtain the baseline meteorological conditions (wherein, the baseline meteorological conditions are set in advance and are the operating conditions of the wind turbine under normal climate, the purpose of which is to eliminate the influence of meteorological conditions on the wind turbine parameters), and simulate the different parameter change characteristics of the wind turbine parameters under the baseline meteorological conditions, and use the simulated different parameter change characteristics as the second independent variable. At the same time, according to the simulation results, the power generation conversion characteristics under different parameter change characteristics are collected, and the power generation conversion characteristics collected based on the simulation results are used as the third dependent variable; construct the wind turbine parameter-power generation conversion function based on the second independent variable and the third dependent variable, wherein, h(z) represents the wind turbine parameter-power generation conversion function; ε0 represents the baseline power generation under baseline meteorological conditions when it does not change with wind turbine parameters; j represents the ordinal value of the wind turbine parameter; m represents the total number of wind turbine parameters; ξ j represents the influence coefficient of the j-th wind turbine parameter on power generation; z jRepresents the change characteristic value of the j-th wind turbine parameter under the baseline meteorological conditions (i.e., the second independent variable); according to the wind turbine parameter-power generation conversion function, the meteorological-wind turbine parameter conversion function and the meteorological-power generation conversion function are fitted and trained to construct a meteorological-based wind power output prediction model P(x)=G(x)*ω1+h(f(x))ω2; wherein ω1 and ω2 represent weighting coefficients, and ω1+ω2=1; the wind power output prediction model is simulated and run in a computer, and verification data is input for simulation verification. When the verification result meets the preset standard (the preset standard is set in advance and used as the inspection standard for judging whether the simulation is qualified, For example, the wind energy output model can be simulated and run in a computer to determine the output result value. The preset standard is the actual wind energy output value. When the output result value meets the actual wind energy output value, it is judged to meet the inspection standard; otherwise, it is judged to not meet the inspection standard. Then, a digital twin model based on the wind energy output prediction model is constructed, and the current meteorological data and the corresponding wind turbine parameters are monitored in real time according to the digital twin model, and the predicted value of the wind energy output is output; when the verification result does not meet the preset standard, the degree of difference between the verification result and the preset standard is determined, and the wind energy output prediction model is optimized according to the degree of difference until it meets the preset standard.

[0084] The working principle and beneficial effects of the above technical solution are: by collecting the power generation parameters of the wind turbine under multi-source meteorological conditions and conducting effective analysis, it is conducive to the determination of the wind turbine parameter-power generation transformation function, the meteorological-wind turbine parameter transformation function, and the meteorological-power generation transformation function, so as to effectively fit the meteorological-wind turbine parameter transformation function and the meteorological-power generation transformation function according to the wind turbine parameter-power generation transformation function, and complete the construction of the wind power output prediction model, which greatly guarantees the effectiveness and accuracy of the constructed model. The accuracy of the wind power output prediction model can be effectively guaranteed through simulation verification, and then when the verification results meet the preset standards, by constructing a digital twin model, the simulation of real-time data is realized, which is conducive to ensuring the accuracy and effectiveness of the model in wind power processing prediction.

[0085] Example 3:

[0086] Based on Example 1, this embodiment provides a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response. In step 2, the power consumption regularity attributes of multiple types of energy-consuming terminals at multiple time scales are analyzed, including:

[0087] S201: Acquire all energy-consuming terminals, and classify the energy-consuming terminals according to their terminal categories to obtain energy-consuming terminal sets of each category;

[0088] S202: Reading scale dimensions of multiple time scales, and respectively reading power consumption parameters of each category of energy-consuming terminal sets in each scale dimension;

[0089] S203: Analyze the unit power consumption pattern of each energy-consuming terminal in each category in the corresponding scale dimension based on the power consumption parameters;

[0090] S204: Analyze the unit power consumption pattern of each energy consuming terminal in the corresponding scale dimension, collect the intersection of the unit power consumption patterns of each energy consuming terminal in the corresponding scale dimension, and use the intersection of the unit power consumption patterns as the sub-power consumption pattern of the corresponding scale dimension under the current category;

[0091] S205: Repeat steps S203-S204 to obtain the sub-power consumption pattern of each category of energy-consuming terminals in each scale dimension;

[0092] S206: Integrate the sub-power consumption patterns of each category of energy-consuming terminals in each scale dimension to obtain power consumption pattern attributes of multiple categories of energy-consuming terminals in multiple time scales.

[0093] In this embodiment, electricity usage parameters include: electricity usage behavior, electricity consumption, electricity usage duration, etc., among which electricity usage behavior is a series of behavioral patterns and habits of energy-consuming terminals in using electricity in production, life, business and other activities, covering the acquisition, consumption, management and related decision-making processes of electricity.

[0094] In this embodiment, S20 integrates the sub-power consumption patterns of each category of energy-consuming terminals in each scale dimension, including: constructing a power consumption pattern table with the terminal category as the horizontal axis and the scale dimension as the vertical axis, and mapping the corresponding sub-power consumption patterns in the power consumption pattern table to obtain the power consumption pattern attributes of multiple categories of energy-consuming terminals in multiple time scales.

[0095] In this embodiment, the intersection of power consumption rules means that each energy consumption terminal generates a corresponding unit power consumption rule under the corresponding scale dimension, wherein similar rules among the unit power consumption rules of each energy consumption terminal under the corresponding scale dimension are used as the intersection of unit power consumption rules.

[0096] The beneficial effect of the above technical solution is: effectively realizing the determination of the power consumption regularity attributes of multiple types of energy-consuming terminals based on multiple time scales, laying the foundation for subsequent correlation analysis to determine the dynamic demand response plan, and ensuring the objectivity of the analysis.

[0097] Example 4:

[0098] Based on Example 1, this embodiment provides a method for optimizing wind energy consumption in a power grid based on multi-timescale demand response. In step 3, a correlation analysis is performed between the wind energy output prediction model and the power consumption regularity attributes of multiple types of energy-consuming terminals at multiple timescales to determine a dynamic demand response plan, including:

[0099] Obtaining the power consumption regularity attributes of multiple categories of energy-consuming terminals at multiple time scales, and dividing the power consumption regularity attributes of the multiple categories of energy-consuming terminals based on the time scales;

[0100] Based on the division results, the power consumption regularity attributes of multiple categories of energy-consuming terminals at the same time scale are grouped to obtain a multi-category sample data group at the same time scale;

[0101] Based on the wind power output prediction model, the multi-category sample data set at the same time scale is analyzed to obtain the power consumption demand of different types of energy-consuming terminals at the same time scale. At the same time, based on the wind power output prediction model, the meteorological data at different time scales are analyzed to obtain the conversion amount of wind energy to electricity at different time scales.

[0102] A dynamic demand response plan is constructed based on the electricity consumption demand of different types of energy-consuming terminals and the conversion amount of wind energy to electrical energy on the same time scale.

[0103] In this embodiment, the power consumption regularity attribute refers to power consumption fluctuations of various types of energy-consuming terminals at different times.

[0104] In this embodiment, classifying the power consumption regularity attributes of multiple categories of energy consuming terminals based on the time scale means classifying the power consumption regularity attributes of multiple categories of energy consuming terminals based on the time scale, that is, obtaining the power consumption of different categories of energy consuming terminals in different time periods.

[0105] In this embodiment, the multi-category sample data group refers to the result obtained by summarizing the power consumption regularity attributes of different categories of energy-consuming terminals in the same time scale.

[0106] In this embodiment, the conversion amount of wind energy to electric energy refers to the amount obtained by analyzing the magnitude of wind energy and the conversion coefficient of wind energy to electric energy.

[0107] The beneficial effects of the above technical solution are: by dividing the power consumption regular attributes of multiple categories of energy-consuming terminals according to the time scale, and analyzing the multiple categories of sample data groups at each time scale after division through the wind power output prediction model, the power consumption demand of different categories of energy-consuming terminals at different time scales is realized. At the same time, the conversion amount of wind energy to electric energy is determined, and the dynamic demand response plan is accurately and effectively determined according to the power consumption demand of different categories of energy-consuming terminals at the same time scale and the conversion amount of wind energy to electric energy, which provides a guarantee for improving the optimization of wind energy absorption in the power grid.

[0108] Example 5:

[0109] Based on Example 4, this embodiment provides a method for optimizing wind energy consumption in a power grid based on multi-timescale demand response. A dynamic demand response plan is constructed based on the power consumption demand of different types of energy-consuming terminals and the amount of wind energy converted to electric energy at the same timescale, including:

[0110] Summarize the electricity demand of different types of energy-consuming terminals at the same time scale, and match the summary results with the conversion amount of wind energy to electricity at the corresponding time scale;

[0111] When the matching result determines that the summary result does not match the amount of wind energy converted into electrical energy, a dynamic demand response is initiated based on the determination result;

[0112] Prioritize the dynamic demand response schemes based on the activation results, and determine the logical switching points of different dynamic demand response schemes and the dynamic demand response execution amounts under different dynamic demand response schemes based on the priority configuration results and the judgment results;

[0113] A dynamic demand response plan is obtained based on the logic switching point and the dynamic demand response execution amount.

[0114] In this embodiment, when the matching result determines that the summary result does not match the amount of conversion from wind energy to electric energy, it means that the amount of electricity required by the summary result is greater than the amount of conversion from wind energy to electric energy.

[0115] In this embodiment, priority configuration refers to configuring the priorities of two modes, namely, power coordination and load interruption for multiple types of energy-consuming terminals included in the dynamic demand response solution.

[0116] In this embodiment, the logical switching point refers to the condition for switching between different measures in the dynamic demand response solution to take effect.

[0117] In this embodiment, the dynamic demand response execution amount refers to the specific amount of electricity that needs to be scheduled or the specific amount of interrupted load under the dynamic demand response solution.

[0118] The beneficial effects of the above technical solution are: by analyzing the electricity consumption demand and the conversion amount of wind energy to electric energy of different categories of energy-consuming terminals under the same time scale, the starting conditions for dynamic demand response and the specific parameters for executing the dynamic demand response plan after startup are determined, and finally the dynamic demand response plan is accurately and effectively constructed, which provides convenience for the wind energy absorption of the power grid.

[0119] In this embodiment, a dynamic demand response plan is obtained based on the logic switching point and the dynamic demand response execution amount, including:

[0120] Based on the wind power output forecast model, the target meteorological data at the current moment is analyzed to obtain the real-time power output. At the same time, the real-time power demand is determined based on the power consumption pattern attributes at the current moment.

[0121] Based on the dynamic demand response plan, the real-time power output and real-time power demand are analyzed, and the analysis results are re-analyzed based on the priority configuration of the dynamic demand response scheme, wherein the dynamic demand response scheme includes power coordination and interruption load, and the priority of power coordination is higher than the priority of interruption load; based on the re-analysis result, the power demand scheduling amount for different categories of energy-consuming terminals under the power coordination response scheme is determined, and when the power demand scheduling amount meets the preset operating requirements, dynamic demand response is performed based on the power coordination response scheme; at the same time, when the power demand scheduling amount does not meet the preset operating requirements, the interruption load response scheme is started; based on the startup result, the optimal amount of power coordination is determined, and the current maximum available load is determined based on the optimal amount, real-time power output and the operating status of different categories of energy-consuming terminals; based on the maximum available load, the interruption load amount for different categories of energy-consuming terminals is determined, and an interruption guidance report is generated based on the interruption load amount and sent to the management terminal of different categories of energy-consuming interruptions for interruption load guidance, thereby completing the dynamic demand response.

[0122] As mentioned above, the real-time electric energy output refers to the amount of electric energy that can be generated after analyzing the real-time target meteorological data through the wind energy output prediction model.

[0123] As mentioned above, the real-time power demand refers to the current power demand of multiple categories of terminals determined based on the properties of power consumption patterns.

[0124] The above-mentioned power demand dispatching amount refers to the amount of power that needs to be dispatched to meet the operating needs of multiple categories of energy-consuming terminals under the power coordination plan.

[0125] As mentioned above, the preset operating requirements are set in advance, that is, the dispatchable electric energy meets the dispatching amount of electric energy demand.

[0126] As mentioned above, the optimal amount of power coordination refers to the maximum amount of power that can be used for power demand scheduling.

[0127] In the above, the current maximum available load refers to the load value that can be allowed to operate under the optimal amount of power coordination, real-time power output and the operating status of different types of energy-consuming terminals.

[0128] As mentioned above, the interruption load refers to the load parameter that needs to be interrupted.

[0129] The beneficial effects of the above technical solution are: by analyzing the real-time power output and real-time power demand, and combining it with a dynamic demand response plan, different response plans can be adopted in different situations to optimize the absorption of wind energy in the power grid, thereby effectively improving the grid's absorption capacity. At the same time, it effectively improves the intelligence and accuracy of the grid's absorption control.

[0130] Example 6:

[0131] Based on Example 1, this embodiment provides a method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response. In step 4, demand response resources are controlled according to a dynamic demand response plan to dispatch and consume wind energy in the power grid, including:

[0132] Read the dynamic demand response plan, determine the consumption target in the dynamic demand response plan, and divide the dynamic demand response according to the consumption target;

[0133] Determine the sub-response demand plan corresponding to each absorption target based on the division results;

[0134] Obtain the execution parameters of the sub-response demand plan and the scheduling relationship between each absorption target;

[0135] The grid wind energy is dispatched and absorbed according to the dispatch relationship between the execution parameters of the sub-response demand plan and each absorption target.

[0136] In this embodiment, the absorption target refers to absorbing a certain amount of wind energy within a specific time period, balancing wind energy access in different areas, etc.

[0137] In this embodiment, each sub-response demand plan is determined according to the absorption target.

[0138] In this embodiment, the execution parameters may be, for example, a load regulation capability range, the capacity of the energy storage device, and the charging and discharging efficiency.

[0139] In this embodiment, the scheduling relationship may be a problem in which each consumption target may affect each other. For example, at a certain moment, the wind energy consumption of a certain energy-consuming terminal may affect the power balance of other energy-consuming terminals.

[0140] The working principle and beneficial effects of the above technical solution are: by determining the sub-response demand plan corresponding to each absorption target, targeted wind energy absorption can be effectively achieved, thereby improving the efficiency of wind energy absorption; by determining the execution parameters of the sub-response parameter plan and the scheduling relationship between the absorption targets, the grid scheduling can be effectively optimized, thereby providing flexibility, effectiveness and accuracy in the grid wind energy scheduling and absorption.

[0141] Example 7:

[0142] This embodiment provides a wind energy consumption optimization system for a power grid based on multi-time scale demand response, such as Figure 3 As shown, including:

[0143] Model building module, used to build a meteorological-based wind power output prediction model;

[0144] The power consumption regularity attribute determination module is used to analyze the power consumption regularity attributes of multiple categories of energy-consuming terminals at multiple time scales;

[0145] The correlation analysis module is used to correlate the wind power output forecast model with the power consumption characteristics of multiple energy-consuming terminals at multiple time scales to determine the dynamic demand response plan;

[0146] The dispatching and absorbing module is used to control the demand response resources according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid.

[0147] The working principle and beneficial effects of the above technical solution are: by constructing a meteorological-based wind power output prediction model, the prediction of electric energy can be effectively and accurately realized; by analyzing the power consumption regularity attributes corresponding to multiple categories of energy-consuming terminals at multiple time scales, the power consumption patterns of different user-side energy-consuming equipment can be effectively mined, and load regulation potential analysis can be provided for demand response strategies; by correlating the wind power output prediction model with the power consumption regularity attributes of multiple categories of energy-consuming terminals at multiple time scales, the dynamic demand response plan can be accurately determined, and the demand response resources can be controlled according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid, thereby effectively improving the grid absorption capacity and effectively improving the intelligence and accuracy of the grid absorption control.

[0148] Example 8:

[0149] Based on Example 7, this embodiment provides a grid wind energy consumption optimization system based on multi-time-scale demand response, and the model building module includes:

[0150] Data acquisition unit, used to collect power generation parameters of wind turbines under multi-source meteorological conditions;

[0151] A function construction unit is used to analyze wind turbine power generation parameters under multi-source meteorological conditions and construct a characteristic transformation function;

[0152] The model building unit is used to build a meteorological-based wind energy output prediction model according to the characteristic transformation function.

[0153] Among them, the power generation parameters include wind turbine parameters and historical power generation data. The specific process includes: collecting wind turbine parameters and historical power generation data of wind turbines under multi-source meteorological conditions; analyzing wind turbine parameters and historical power generation data under multi-source meteorological conditions, and determining the parameter transformation characteristics of wind turbine parameters under different meteorological conditions and the power generation transformation characteristics of historical power generation data; taking meteorological conditions as the first independent variable, and the parameter transformation characteristics of wind turbine parameters as the first dependent variable, and at the same time, taking power generation transformation characteristics as the second dependent variable; constructing a meteorological-wind turbine parameter transformation function based on the first independent variable and the first dependent variable; constructing a meteorological-power generation transformation function based on the first independent variable and the second dependent variable; obtaining baseline meteorological conditions, and simulating different parameter change characteristics in wind turbine parameters under baseline period conditions, and taking the simulated different parameter change characteristics as the second independent variable, and at the same time, collecting different parameter change characteristics based on the simulation results. The power generation conversion characteristics under the characteristics are obtained, and the power generation conversion characteristics collected based on the simulation results are used as the third dependent variable; a wind turbine parameter-power generation conversion function is constructed according to the second independent variable and the third dependent variable; the meteorological-wind turbine parameter conversion function and the meteorological-power generation conversion function are fitted and trained according to the wind turbine parameter-power generation conversion function to construct a wind energy output prediction model based on meteorology; the wind energy output prediction model is simulated and run in a computer, and verification data is input for simulation verification. When the verification result meets the preset standard, a digital twin model based on the wind energy output prediction model is constructed, and the current meteorological data and the corresponding wind turbine parameters are monitored in real time according to the digital twin model, and the predicted value of the wind energy output is output; when the verification result does not meet the preset standard, the degree of difference between the verification result and the preset standard is determined, and the wind energy output prediction model is optimized according to the degree of difference until it meets the preset standard.

[0154] The working principle and beneficial effects of the above technical solution are: by collecting the power generation parameters of the wind turbine under multi-source meteorological conditions and conducting effective analysis, it is conducive to the determination of the wind turbine parameter-power generation transformation function, the meteorological-wind turbine parameter transformation function, and the meteorological-power generation transformation function, so as to effectively fit the meteorological-wind turbine parameter transformation function and the meteorological-power generation transformation function according to the wind turbine parameter-power generation transformation function, and complete the construction of the wind power output prediction model, which greatly guarantees the effectiveness and accuracy of the constructed model. The accuracy of the wind power output prediction model can be effectively guaranteed through simulation verification, and then when the verification results meet the preset standards, by constructing a digital twin model, the simulation of real-time data is realized, which is conducive to ensuring the accuracy and effectiveness of the model in wind power processing prediction.

[0155] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for optimizing wind energy consumption in power grids based on multi-time-scale demand response, characterized in that: include: Step 1: Build a meteorological-based wind power output prediction model; Step 2: Analyze the power consumption patterns of multiple energy-consuming terminals at multiple time scales; Step 3: Correlate the wind power output forecast model with the power consumption patterns of multiple energy-consuming terminals at multiple time scales to determine a dynamic demand response plan. Step 4: Control the demand response resources according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid.

2. The method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response according to claim 1, characterized in that: In step 1, a meteorological-based wind power output prediction model is constructed, including: S101: Collecting wind turbine power generation parameters under multi-source meteorological conditions; S102: Analyze wind turbine power generation parameters under multi-source meteorological conditions and construct a characteristic transformation function; S103: Constructing a meteorological-based wind energy output prediction model according to the characteristic transformation function.

3. The method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response according to claim 1, characterized in that: In step 2, the power consumption patterns of multiple energy-consuming terminals at multiple time scales are analyzed, including: S201: Acquire all energy-consuming terminals, and classify the energy-consuming terminals according to their terminal categories to obtain energy-consuming terminal sets of each category; S202: Reading scale dimensions of multiple time scales, and respectively reading power consumption parameters of each category of energy-consuming terminal sets in each scale dimension; S203: Analyze the unit power consumption pattern of each energy-consuming terminal in each category in the corresponding scale dimension based on the power consumption parameters; S204: Analyze the unit power consumption pattern of each energy consuming terminal in the corresponding scale dimension, collect the intersection of the unit power consumption patterns of each energy consuming terminal in the corresponding scale dimension, and use the intersection of the unit power consumption patterns as the sub-power consumption pattern of the corresponding scale dimension under the current category; S205: Repeat steps S203-S204 to obtain the sub-power consumption pattern of each category of energy-consuming terminals in each scale dimension; S206: Integrate the sub-power consumption patterns of each category of energy-consuming terminals in each scale dimension to obtain power consumption pattern attributes of multiple categories of energy-consuming terminals in multiple time scales.

4. The method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response according to claim 3, characterized in that: S206: Summarize the sub-power consumption patterns of each category of energy-consuming terminals in each scale dimension, including: An electricity consumption pattern table is constructed with the terminal category as the horizontal axis and the scale dimension as the vertical axis, and the corresponding sub-electricity consumption patterns are mapped in the electricity consumption pattern table to obtain the electricity consumption pattern attributes of multiple categories of energy-consuming terminals under multiple time scales.

5. The method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response according to claim 1, characterized in that: In step 3, the wind power output forecast model is correlated with the power consumption patterns of multiple energy-consuming terminals at multiple time scales to determine a dynamic demand response plan, including: Obtaining the power consumption regularity attributes of multiple categories of energy-consuming terminals at multiple time scales, and dividing the power consumption regularity attributes of the multiple categories of energy-consuming terminals based on the time scales; Based on the division results, the power consumption regularity attributes of multiple categories of energy-consuming terminals at the same time scale are grouped to obtain a multi-category sample data group at the same time scale; Based on the wind power output prediction model, the multi-category sample data set at the same time scale is analyzed to obtain the power consumption demand of different types of energy-consuming terminals at the same time scale. At the same time, based on the wind power output prediction model, the meteorological data at different time scales are analyzed to obtain the conversion amount of wind energy to electricity at different time scales. A dynamic demand response plan is constructed based on the electricity consumption demand of different types of energy-consuming terminals and the conversion amount of wind energy to electrical energy on the same time scale.

6. The method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response according to claim 5, characterized in that: A dynamic demand response plan is built based on the electricity demand of different types of energy-consuming terminals and the amount of wind energy converted to electricity on the same time scale, including: Summarize the electricity demand of different types of energy-consuming terminals at the same time scale, and match the summary results with the conversion amount of wind energy to electricity at the corresponding time scale; When the matching result determines that the summary result does not match the amount of wind energy converted into electrical energy, a dynamic demand response is initiated based on the determination result; Prioritize the dynamic demand response schemes based on the activation results, and determine the logical switching points of different dynamic demand response schemes and the dynamic demand response execution amounts under different dynamic demand response schemes based on the priority configuration results and the judgment results; A dynamic demand response plan is obtained based on the logic switching point and the dynamic demand response execution amount.

7. The method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response according to claim 6, characterized in that: A dynamic demand response plan is obtained based on the logical switching point and the dynamic demand response execution amount, including: Based on the wind power output forecast model, the target meteorological data at the current moment is analyzed to obtain the real-time power output. At the same time, the real-time power demand is determined based on the power consumption pattern attributes at the current moment. parsing the real-time power output and power demand based on the dynamic demand response plan, and re-parsing the parsed results based on the priority configuration of the dynamic demand response plan, wherein the dynamic demand response plan includes power coordination and interrupted loads, and the power coordination has a higher priority than the interrupted loads; Based on the re-analysis results, the power demand dispatch amount for different types of energy-consuming terminals under the power coordinated response plan is determined, and when the power demand dispatch amount meets the preset operating requirements, dynamic demand response is performed based on the power coordinated response plan; At the same time, when the power demand dispatching amount does not meet the preset operation requirements, the interruption load response plan is activated; Determine the optimal amount of power coordination based on the startup results, and determine the current maximum load available based on the optimal amount, real-time power output, and the operating status of different types of energy-consuming terminals; Based on the maximum available load, the interruption load amount for different types of energy consumption terminals is determined, and the interruption load amount is used to generate an interruption guidance report and sent to the management terminal of different types of energy consumption interruptions for interruption load guidance, thereby completing dynamic demand response.

8. The method for optimizing wind energy consumption in a power grid based on multi-time-scale demand response according to claim 1, characterized in that: In step 4, the demand response resources are controlled according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid, including: Read the dynamic demand response plan, determine the consumption target in the dynamic demand response plan, and divide the dynamic demand response according to the consumption target; Determine the sub-response demand plan corresponding to each absorption target based on the division results; Obtain the execution parameters of the sub-response demand plan and the scheduling relationship between each absorption target; The grid wind energy is dispatched and absorbed according to the dispatch relationship between the execution parameters of the sub-response demand plan and each absorption target.

9. A wind energy consumption optimization system for power grid based on multi-time scale demand response, characterized in that: include: Model building module, used to build a meteorological-based wind power output prediction model; The power consumption regularity attribute determination module is used to analyze the power consumption regularity attributes of multiple categories of energy-consuming terminals at multiple time scales; The correlation analysis module is used to correlate the wind power output forecast model with the power consumption characteristics of multiple energy-consuming terminals at multiple time scales to determine the dynamic demand response plan; The dispatching and absorbing module is used to control the demand response resources according to the dynamic demand response plan to dispatch and absorb wind energy in the power grid.

10. A wind energy consumption optimization system for a power grid based on multi-time-scale demand response according to claim 9, characterized in that: Model building modules, including: Data acquisition unit, used to collect power generation parameters of wind turbines under multi-source meteorological conditions; A function construction unit is used to analyze wind turbine power generation parameters under multi-source meteorological conditions and construct a characteristic transformation function; The model building unit is used to build a meteorological-based wind energy output prediction model according to the characteristic transformation function.

Images