Power supply quality prediction method and system

By constructing and correlating the expression model of electricity demand, power supply characteristics and power generation characteristics, the problem of difficult to accurately predict the quality of power supply in traditional power supply management is solved, and accurate prediction and evaluation of the quality of power supply is achieved, which is a stable power system Operation guarantee.

CN118982099AActive Publication Date: 2024-11-19HEBEI CHANGLI ELECTRIC TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410993509.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-19
Estimated Expiration
2044-07-24

AI Technical Summary

Technical Problem

Traditional power supply management methods are difficult to meet the efficient and safe operation needs of modern power networks, especially in terms of accurate prediction of power supply quality.

Method used

By analyzing the historical electricity demand and power supply characteristics of the power supply block, a power demand expression model and power supply characteristic expression model are constructed, and associated with the power generation characteristic expression model of the power station, forming a reference expression state group, combining real-time power consumption and power generation characteristic data, the reference expression state group is determined to predict the power supply quality.

Benefits of technology

Accurate prediction and evaluation of the quality of power supply is achieved, providing strong guarantees for the stable operation and optimization management of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982099A_ABST
    Figure CN118982099A_ABST
Patent Text Reader

Abstract

The invention discloses a power supply quality prediction method and system, relates to the technical field of power supply management, and particularly discloses a method for predicting power supply quality by associating expression states of a power demand expression model, a power supply characteristic expression model and a power generation characteristic expression model of a power station to form a reference expression state group. Recording the intercepted expression state sections as a first comparison expression state section and a second comparison expression state section respectively, recording the combination of the first comparison expression state section and the second comparison expression state section as a reference expression state section group, and determining a called reference expression state group based on the coincidence of the real-time expression state group and the reference expression state section group, and determining the power supply quality of the power supply block needing to be analyzed based on the reference power supply characteristic expression state in the reference expression state group. According to the technical scheme, accurate prediction and evaluation of the power supply quality are realized, and a powerful guarantee is provided for stable operation and optimal management of a power system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power supply management, and in particular to packaging equipment for crystal oscillator production. Background Art

[0002] In the power industry, the stability and reliability of power supply quality is crucial to ensure the normal operation of the social economy; however, with the continuous growth of power demand and the increasing complexity of the power system, the traditional power supply management method can no longer meet the efficient and safe operation requirements of modern power networks. Therefore, it is particularly important to develop a method and system that can accurately predict the power supply quality. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system capable of accurately predicting the quality of power supply.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] A method for predicting power supply quality, comprising:

[0006] Delineating the power supply blocks to be analyzed to obtain the power supply blocks to be analyzed, analyzing the historical power demand of the power supply blocks to be analyzed and generating a power demand expression model, analyzing the historical power supply characteristics of the power supply blocks to be analyzed and generating a power supply characteristic expression model;

[0007] Analyze the historical power generation characteristics of power plants in the area to which the power supply block belongs, and generate a power generation characteristic expression model for the power plants;

[0008] In accordance with the correspondence of equivalent time segments, the respective expression states of the power demand expression model, the power supply characteristic expression model and the power station generation characteristic expression model are associated to form a reference expression state group, wherein the expression state corresponding to the power demand expression model is recorded as the reference power demand expression state, the expression state corresponding to the power supply characteristic expression model is recorded as the reference power supply characteristic expression state, and the expression state corresponding to the power station generation characteristic expression model is recorded as the reference generation characteristic expression state;

[0009] Determine the interception nodes of the expression state segments in the reference power demand expression state and the reference power generation characteristic expression state, and record the intercepted expression state segments as the first comparison expression state segment and the second comparison expression state segment, and record the combination of the two as the reference power demand expression state segment group;

[0010] The real-time electricity demand and real-time power generation characteristics corresponding to the power supply section are obtained, and expressed using the electricity demand expression model and the power station power generation characteristic expression model to obtain the real-time electricity demand expression state and the real-time power generation characteristic expression state, and the combination of the two is recorded as a real-time expression state group, and based on the consistency of the real-time expression state group and the reference expression state section group, the reference expression state group to be called is determined, and based on the reference power supply characteristic expression state in the reference expression state group, the power supply quality of the power supply block to be analyzed is determined.

[0011] In some embodiments disclosed in the present invention, the method for constructing a power demand expression model and a power supply feature expression model includes:

[0012] A position expression layer is constructed for the power supply block, and based on the position of the important power consumption nodes in the power supply block, a power consumption mapping point is set at the corresponding position of the position expression layer, and a parameter strength expression module is configured for each power consumption mapping point, wherein the parameter strength expression module performs expression changes according to the size of the parameter corresponding to the power consumption mapping point;

[0013] Analyze the historical electricity demand and historical power supply characteristics, determine the electricity demand parameters and power supply parameters of different electricity mapping points at different time nodes, and sort the electricity demand parameters and power supply parameters of the same electricity mapping point based on the chronological order, and obtain the electricity demand parameter sequence and power supply parameter sequence;

[0014] Based on the electricity demand parameter sequence and the power supply parameter sequence, the parameter intensity expression module is dynamically adjusted to obtain the electricity demand expression model and the power supply characteristic expression model respectively.

[0015] In some embodiments disclosed in the present invention, a method for determining a cut-off node for an expression state segment in a reference power demand expression state and a reference power generation characteristic expression state includes:

[0016] The interception nodes of the expression state segment are gradually moved in a time-progress manner, and the segment volatility corresponding to the expression state segment is analyzed in real time, and based on the analysis results, the segment fluctuation parameter corresponding to the expression state segment is determined;

[0017] If the segment fluctuation parameter is greater than or equal to the preset value, the node corresponding to the current expression segment will be the interception node.

[0018] In some embodiments disclosed in the present invention, the method for calculating the segment fluctuation parameter includes:

[0019] Calculate the expression difference characteristics corresponding to the expression segments at adjacent time nodes;

[0020] Based on the expression difference characteristics corresponding to all adjacent time nodes, the segment fluctuation parameters are determined;

[0021] Among them, the expression for calculating the section fluctuation parameter is:

[0022]

[0023] Among them, Q is the section fluctuation parameter, q t is the expression state difference characteristic parameter corresponding to the t-th time node to the (t+1)-th time node in the expression state segment, and T is the number of all time nodes in the expression state segment;

[0024]

[0025] Among them, ΔS i is the parameter difference value of the i-th electricity consumption mapping point between the expression states corresponding to adjacent time nodes, δ(i) is the difference parameter coefficient adjustment function, if the parameter difference value of the i-th electricity consumption mapping point is positive, then δ(i) outputs the preset first adjustment coefficient, if the parameter difference value of the i-th electricity consumption mapping point is negative, then δ(i) outputs the preset second adjustment coefficient, and b is the difference feature adjustment constant.

[0026] In some embodiments disclosed in the present invention, a method for determining a reference expression profile group to be called includes:

[0027] Performing feature dimensionality reduction on the real-time power demand expression state and the real-time power generation characteristic expression state in the real-time expression state group, and setting labels for the expression state intervals on the real-time power demand expression state and the real-time power generation characteristic expression state based on the dimensionality reduction results;

[0028] Performing feature dimensionality reduction on the first compared expression segment and the second compared expression segment in the reference expression segment group, and setting labels for the first compared expression segment and the second compared expression segment based on the dimensionality reduction result;

[0029] Based on the consistency of the labels, determining the expression state interval to which the first comparison expression state segment belongs in the real-time power demand expression state, and determining the expression state interval to which the second comparison expression state segment belongs in the real-time power generation characteristic expression state;

[0030] The first comparison expression state segment is gradually advanced in the expression state interval of the real-time electricity demand expression state, and the second comparison expression state segment is gradually advanced in the expression state interval of the real-time power generation characteristic expression state, until the first comparison expression state segment and the real-time electricity demand expression state are consistent with each other, and the second comparison expression state segment and the real-time power generation characteristic expression state are consistent with each other, until the first comparison expression state segment and the real-time power generation characteristic expression state are consistent with each other, and the preset standard is reached.

[0031] In some embodiments disclosed in the present invention,

[0032] The expression state interval of the real-time power demand expression state and the label of the first comparison expression state segment include average power demand parameters at different time nodes;

[0033] The expression state interval of the real-time power generation characteristic expression state and the label of the second comparison expression state section include average power generation parameters at different time nodes.

[0034] In some embodiments disclosed in the present invention, the parameter intensity expression module performs expression changes in the following ways:

[0035] The parameter intensity expression module is a circular variation component, and the area of ​​the circular variation component is adjusted according to the parameter change corresponding to the electricity consumption mapping point.

[0036] In some embodiments disclosed in the present invention, a method for generating a power plant power generation characteristic expression model includes:

[0037] The historical power generation characteristics are analyzed to determine the power generation at different time nodes, and a power generation curve is constructed with time as the horizontal axis and power generation as the vertical axis.

[0038] In some embodiments disclosed herein, the method of forming a reference expression profile group includes:

[0039] Performing several random expression state interceptions on the electricity demand expression model, the power supply characteristic expression model and the power station generation characteristic expression model;

[0040] The interception method includes intercepting the expression state corresponding to the intercepted time segment, and the number of interceptions is at least enough to ensure that all the intercepted time segments can completely cover the time range corresponding to the overall expression state.

[0041] In some embodiments disclosed in the present invention, there is also disclosed a power supply quality prediction system, comprising:

[0042] The first module is used to delineate the power supply blocks to be analyzed, obtain the power supply blocks to be analyzed, analyze the historical power demand of the power supply blocks to be analyzed, and generate a power demand expression model, analyze the historical power supply characteristics of the power supply blocks to be analyzed, and generate a power supply characteristic expression model, analyze the historical power generation characteristics of the power stations in the area to which the power supply blocks belong, and generate a power generation characteristic expression model of the power stations;

[0043] The second module associates the respective expression states of the power demand expression model, the power supply characteristic expression model and the power station power generation characteristic expression model in a manner corresponding to equivalent time segments to form a reference expression state group, wherein the expression state corresponding to the power demand expression model is recorded as the reference power demand expression state, the expression state corresponding to the power supply characteristic expression model is recorded as the reference power supply characteristic expression state, and the expression state corresponding to the power station power generation characteristic expression model is recorded as the reference power generation characteristic expression state;

[0044] The third module is used to determine the interception nodes of the expression state segments in the reference power demand expression state and the reference power generation characteristic expression state, and record the intercepted expression state segments as the first comparison expression state segment and the second comparison expression state segment respectively, and record the combination of the two as the reference power demand expression state segment group;

[0045] The fourth module is used to obtain the real-time electricity demand and real-time power generation characteristics corresponding to the power supply section, and express them using the electricity demand expression model and the power station power generation characteristic expression model to obtain the real-time electricity demand expression state and the real-time power generation characteristic expression state, and record the combination of the two as the real-time expression state group, and based on the consistency of the real-time expression state group and the reference expression state section group, determine the called reference expression state group, and based on the reference power supply characteristic expression state in the reference expression state group, determine the power supply quality of the power supply block to be analyzed.

[0046] The present invention discloses a method and system for predicting the quality of electric power supply, and relates to the technical field of electric power supply management. Specifically, the present invention discloses associating the respective expression states of an electric power demand expression model, a power supply characteristic expression model, and a power station power generation characteristic expression model to form a reference expression state group, recording the intercepted expression state segments as a first comparison expression state segment and a second comparison expression state segment, and recording the combination of the two as a reference expression state segment group. Based on the consistency of the real-time expression state group and the reference expression state segment group, the reference expression state group to be called is determined, and based on the reference power supply characteristic expression state in the reference expression state group, the power supply quality of the power supply block to be analyzed is determined. Through the above technical scheme, the present invention realizes accurate prediction and evaluation of the quality of electric power supply, and provides a strong guarantee for the stable operation and optimized management of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A method step diagram of a method for predicting power supply quality disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0049] The purpose of the present invention is to provide a method and system capable of accurately predicting the quality of power supply.

[0050] In order to achieve the above object, the present invention adopts the following technical solutions:

[0051] See also Figure 1 , a method for predicting power supply quality, comprising:

[0052] Step S100, delineate the power supply block to be analyzed, obtain the power supply block to be analyzed, analyze the historical power demand of the power supply block to be analyzed, and generate a power demand expression model, analyze the historical power supply characteristics of the power supply block to be analyzed, and generate a power supply characteristic expression model.

[0053] In this step, specific power supply blocks are delineated to make the analysis more targeted and accurate; then, the historical electricity demand of these blocks is deeply analyzed to find out the periodicity, trend and other characteristics of electricity demand, and generate an electricity demand expression model based on this; at the same time, the analysis of power supply characteristics is similar, aiming to understand factors such as stability and reliability in the power supply process, and to construct a power supply characteristic expression model; these models can reflect the power consumption and power supply characteristics of the power supply blocks, laying the foundation for subsequent predictions.

[0054] In some embodiments disclosed in the present invention, the method for constructing a power demand expression model and a power supply feature expression model includes:

[0055] Step S101, construct a position expression layer for the power supply block, and based on the positions of important power consumption nodes in the power supply block, set power consumption mapping points at corresponding positions of the position expression layer, and configure a parameter strength expression module for each power consumption mapping point, wherein the parameter strength expression module performs expression changes according to the size of the parameter corresponding to the power consumption mapping point.

[0056] Step S102, analyze the historical electricity demand and historical power supply characteristics, determine the electricity demand parameters and power supply parameters of different electricity mapping points at different time nodes, and sort the electricity demand parameters and power supply parameters of the same electricity mapping point based on the causal relationship of time sorting to obtain the electricity demand parameter sequence and the power supply parameter sequence.

[0057] Step S103: Based on the power demand parameter sequence and the power supply parameter sequence, dynamically adjust the parameter intensity expression module to obtain a power demand expression model and a power supply characteristic expression model respectively.

[0058] Step S200 , analyzing the historical power generation characteristics of the power stations in the area to which the power supply block belongs, and generating a power generation characteristic expression model of the power stations.

[0059] In this step, it is crucial to analyze the historical power generation characteristics of the power stations in the area to which the power supply block belongs; the power generation capacity, stability and efficiency of the power station directly affect the quality of power supply; therefore, by analyzing historical data such as power generation, power generation efficiency, failure rate, etc., a power station power generation characteristic expression model can be constructed; this model helps to understand the working status and performance of the power station, and then predict its impact on the quality of power supply.

[0060] In some embodiments disclosed in the present invention, a method for generating a power plant power generation characteristic expression model includes:

[0061] Step S201 , analyzing the historical power generation characteristics, determining the power generation at different time nodes, and constructing a power generation curve with time as the horizontal axis and the power generation as the vertical axis.

[0062] Step S300, in a manner corresponding to equivalent time segments, associate the respective expression states of the electricity demand expression model, the power supply characteristic expression model and the power station power generation characteristic expression model to form a reference expression state group, wherein the expression state corresponding to the electricity demand expression model is recorded as the reference electricity demand expression state, the expression state corresponding to the power supply characteristic expression model is recorded as the reference power supply characteristic expression state, and the expression state corresponding to the power station power generation characteristic expression model is recorded as the reference power generation characteristic expression state.

[0063] The core of this step is data association and integration; by associating the power demand expression model, power supply characteristic expression model and power station power generation characteristic expression model according to the same time period, a comprehensive reference expression state group can be formed; this association enables different models to be aligned in the time dimension, so as to more accurately analyze their mutual relationship and influence. This integration method provides more comprehensive data support for subsequent predictions.

[0064] In some embodiments disclosed herein, the method of forming a reference expression profile group includes:

[0065] Step S301, performing several random expression state interceptions on the power demand expression model, the power supply characteristic expression model and the power station power generation characteristic expression model;

[0066] The interception method includes intercepting the expression state corresponding to the intercepted time segment, and the number of interceptions is at least enough to ensure that all the intercepted time segments can completely cover the time range corresponding to the overall expression state.

[0067] Step S400, determine the interception nodes of the expression state segments in the reference power demand expression state and the reference power generation characteristic expression state, and record the intercepted expression state segments as the first comparison expression state segment and the second comparison expression state segment respectively, and record the combination of the two as the reference expression state segment group.

[0068] In this step, the focus is on determining the interception nodes and extracting key expression segments; the selection of interception nodes is usually based on the results of data analysis, such as peak power consumption or key turning points in the operating status of power plants; by intercepting these key expression segments, the changing patterns and influencing factors of power supply quality can be analyzed more accurately.

[0069] In some embodiments disclosed in the present invention, a method for determining a cut-off node for an expression state segment in a reference power demand expression state and a reference power generation characteristic expression state includes:

[0070] Step S401, gradually move the interception nodes of the expression state segment in a time-progress manner, and analyze the segment volatility corresponding to the expression state segment in real time, and determine the segment fluctuation parameter corresponding to the expression state segment based on the analysis result.

[0071] Step S403: if the segment fluctuation parameter is greater than or equal to a preset value, the node corresponding to the current expression state segment is regarded as a cut node.

[0072] In some embodiments disclosed in the present invention, the method for calculating the segment fluctuation parameter includes:

[0073] Step S4011, calculating the expression difference characteristics corresponding to the expression segments at adjacent time nodes.

[0074] Step S4012, determining the segment fluctuation parameter based on the expression state difference characteristics corresponding to all adjacent time nodes.

[0075] Among them, the expression for calculating the section fluctuation parameter is:

[0076]

[0077] Among them, Q is the section fluctuation parameter, q t is the expression state difference characteristic parameter corresponding to the tth time node to the (t+1)th time node in the expression state segment, and T is the number of all time nodes in the expression state segment.

[0078]

[0079] Among them, ΔS iis the parameter difference value of the i-th electricity consumption mapping point between the expression states corresponding to adjacent time nodes, δ(i) is the difference parameter coefficient adjustment function, if the parameter difference value of the i-th electricity consumption mapping point is positive, then δ(i) outputs the preset first adjustment coefficient, if the parameter difference value of the i-th electricity consumption mapping point is negative, then δ(i) outputs the preset second adjustment coefficient, and b is the difference feature adjustment constant.

[0080] Step S500, obtain the real-time electricity demand and real-time power generation characteristics corresponding to the power supply section, and express them using the electricity demand expression model and the power station power generation characteristic expression model to obtain the real-time electricity demand expression state and the real-time power generation characteristic expression state, and record the combination of the two as a real-time expression state group, and based on the consistency of the real-time expression state group and the reference expression state section group, determine the called reference expression state group, and based on the reference power supply characteristic expression state in the reference expression state group, determine the power supply quality of the power supply block to be analyzed.

[0081] This step is the core of the prediction method. First, obtain the real-time electricity demand and power generation characteristic data, and use the previously constructed model to express them to obtain the real-time expression state group; then, by comparing the consistency between the real-time expression state group and the reference expression state segment group, the historical pattern that is most similar to the current situation can be found. Based on this pattern matching method, the current power supply quality can be accurately predicted. Finally, the power supply quality of the power supply block to be analyzed is determined based on the reference power supply characteristic expression state, providing a strong guarantee for the stable operation and optimized management of the power system.

[0082] In some embodiments disclosed in the present invention, a method for determining a reference expression profile group to be called includes:

[0083] Step S501 , performing feature dimensionality reduction on the real-time power demand expression state and the real-time power generation characteristic expression state in the real-time expression state group, and setting labels for the expression state intervals on the real-time power demand expression state and the real-time power generation characteristic expression state based on the dimensionality reduction results.

[0084] In step S501, first, feature dimension reduction is performed on the real-time power demand expression and the real-time power generation characteristic expression in the real-time expression group. Feature dimension reduction is a data preprocessing technology, which aims to reduce the dimension of the data while retaining the main features of the data. By reducing the dimension, the complexity of the data can be simplified and the efficiency of subsequent processing can be improved. After the dimension reduction, labels are set for each interval of the real-time power demand expression and the real-time power generation characteristic expression based on the result of the dimension reduction.

[0085] Step S502 , performing feature dimensionality reduction on the first compared expression segment and the second compared expression segment in the reference expression segment group, and setting labels for the first compared expression segment and the second compared expression segment based on the dimensionality reduction result.

[0086] Step S502 is similar to step S501, but the objects are replaced by the first comparison expression state segment and the second comparison expression state segment in the reference expression segment group. The feature dimension reduction is also performed on these segments to reduce the dimension and complexity of the data. Then, labels are set for the comparison expression state segments after dimension reduction, and these labels will be used in the subsequent comparison and recognition process.

[0087] Step S503, based on the consistency of the tags, determining the expression state interval to which the first comparison expression state segment belongs in the real-time power demand expression state, and determining the expression state interval to which the second comparison expression state segment belongs in the real-time power generation characteristic expression state.

[0088] In step S503, the labels set in the previous steps are used for comparison. Specifically, the consistency of the label of the real-time power demand expression state with the label of the first comparison expression state segment is compared, and the consistency of the label of the real-time power generation characteristic expression state with the label of the second comparison expression state segment is compared. By comparing the consistency of the labels, the expression state interval corresponding to the comparison expression state segment can be determined in the real-time power demand expression state and the real-time power generation characteristic expression state respectively. The purpose of this step is to find the comparison expression state segment that matches the real-time expression state, providing a basis for subsequent analysis and prediction.

[0089] Step S504, gradually advance the first comparison expression state segment in the expression state interval of the real-time electricity demand expression state, and at the same time gradually advance the second comparison expression state segment in the expression state interval of the real-time power generation characteristic expression state, until the first comparison expression state segment and the real-time electricity demand expression state are consistent with each other, and the second comparison expression state segment and the real-time power generation characteristic expression state are consistent with each other, until the first comparison expression state segment and the real-time power generation characteristic expression state are consistent with each other, and the second comparison expression state segment and the real-time power generation characteristic expression state are consistent with each other, and ...

[0090] In this step, the first comparison expression state segment and the second comparison expression state segment are gradually advanced on the expression state interval of the real-time power demand expression state and the real-time power generation characteristic expression state that have been determined. By constantly comparing and adjusting the positions of these segments, we try to find the comparison expression state segment that best matches the real-time expression state. When the matching state of the first comparison expression state segment with the real-time power demand expression state and the matching state of the second comparison expression state segment with the real-time power generation characteristic expression state both meet the preset standards, it is considered that the best match has been found. The purpose of this step is to ensure that the reference expression state group we find has a high degree of similarity with the real-time expression state, thereby improving the accuracy of prediction and analysis.

[0091] In some embodiments disclosed in the present invention,

[0092] The expression state interval of the real-time power demand expression state and the label of the first comparison expression state section include average power demand parameters at different time nodes.

[0093] The expression state interval of the real-time power generation characteristic expression state and the label of the second comparison expression state section include average power generation parameters at different time nodes.

[0094] In some embodiments disclosed in the present invention, the parameter intensity expression module expresses changes in the following manner: the parameter intensity expression module is a circular change component, and the area of ​​the circular change component is adjusted according to the parameter change corresponding to the power consumption mapping point.

[0095] In some embodiments disclosed in the present invention, there is also disclosed a power supply quality prediction system, comprising:

[0096] The first module is used to delineate the power supply blocks to be analyzed, obtain the power supply blocks to be analyzed, analyze the historical power demand of the power supply blocks to be analyzed, and generate a power demand expression model, analyze the historical power supply characteristics of the power supply blocks to be analyzed, and generate a power supply characteristic expression model, analyze the historical power generation characteristics of the power stations in the area to which the power supply blocks belong, and generate a power generation characteristic expression model of the power stations;

[0097] The second module associates the respective expression states of the power demand expression model, the power supply characteristic expression model and the power station power generation characteristic expression model in a manner corresponding to equivalent time segments to form a reference expression state group, wherein the expression state corresponding to the power demand expression model is recorded as the reference power demand expression state, the expression state corresponding to the power supply characteristic expression model is recorded as the reference power supply characteristic expression state, and the expression state corresponding to the power station power generation characteristic expression model is recorded as the reference power generation characteristic expression state;

[0098] The third module is used to determine the interception nodes of the expression state segments in the reference power demand expression state and the reference power generation characteristic expression state, and record the intercepted expression state segments as the first comparison expression state segment and the second comparison expression state segment respectively, and record the combination of the two as the reference power demand expression state segment group;

[0099] The fourth module is used to obtain the real-time electricity demand and real-time power generation characteristics corresponding to the power supply section, and express them using the electricity demand expression model and the power station power generation characteristic expression model to obtain the real-time electricity demand expression state and the real-time power generation characteristic expression state, and record the combination of the two as the real-time expression state group, and based on the consistency of the real-time expression state group and the reference expression state section group, determine the called reference expression state group, and based on the reference power supply characteristic expression state in the reference expression state group, determine the power supply quality of the power supply block to be analyzed.

[0100] The present invention discloses a method and system for predicting the quality of electric power supply, and relates to the technical field of electric power supply management. Specifically, the present invention discloses associating the respective expression states of an electric power demand expression model, a power supply characteristic expression model, and a power station power generation characteristic expression model to form a reference expression state group, recording the intercepted expression state segments as a first comparison expression state segment and a second comparison expression state segment, and recording the combination of the two as a reference expression state segment group. Based on the consistency of the real-time expression state group and the reference expression state segment group, the reference expression state group to be called is determined, and based on the reference power supply characteristic expression state in the reference expression state group, the power supply quality of the power supply block to be analyzed is determined. Through the above technical scheme, the present invention realizes accurate prediction and evaluation of the quality of electric power supply, and provides a strong guarantee for the stable operation and optimized management of the power system.

[0101] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for predicting power supply quality, characterized in that: include: Delineating the power supply blocks to be analyzed to obtain the power supply blocks to be analyzed, analyzing the historical power demand of the power supply blocks to be analyzed and generating a power demand expression model, analyzing the historical power supply characteristics of the power supply blocks to be analyzed and generating a power supply characteristic expression model; Analyze the historical power generation characteristics of power plants in the area to which the power supply block belongs, and generate a power generation characteristic expression model for the power plants; In accordance with the correspondence of equivalent time segments, the respective expression states of the power demand expression model, the power supply characteristic expression model and the power station generation characteristic expression model are associated to form a reference expression state group, wherein the expression state corresponding to the power demand expression model is recorded as the reference power demand expression state, the expression state corresponding to the power supply characteristic expression model is recorded as the reference power supply characteristic expression state, and the expression state corresponding to the power station generation characteristic expression model is recorded as the reference generation characteristic expression state; Determine the interception nodes of the expression state segments in the reference power demand expression state and the reference power generation characteristic expression state, and record the intercepted expression state segments as the first comparison expression state segment and the second comparison expression state segment, and record the combination of the two as the reference power demand expression state segment group; The real-time electricity demand and real-time power generation characteristics corresponding to the power supply section are obtained, and expressed using the electricity demand expression model and the power station power generation characteristic expression model to obtain the real-time electricity demand expression state and the real-time power generation characteristic expression state, and the combination of the two is recorded as a real-time expression state group, and based on the consistency of the real-time expression state group and the reference expression state section group, the reference expression state group to be called is determined, and based on the reference power supply characteristic expression state in the reference expression state group, the power supply quality of the power supply block to be analyzed is determined.

2. A method for predicting power supply quality according to claim 1, characterized in that: Methods for constructing a power demand expression model and a power supply characteristic expression model include: A position expression layer is constructed for the power supply block, and based on the position of the important power consumption nodes in the power supply block, a power consumption mapping point is set at the corresponding position of the position expression layer, and a parameter strength expression module is configured for each power consumption mapping point, wherein the parameter strength expression module performs expression changes according to the size of the parameter corresponding to the power consumption mapping point; Analyze the historical electricity demand and historical power supply characteristics, determine the electricity demand parameters and power supply parameters of different electricity mapping points at different time nodes, and sort the electricity demand parameters and power supply parameters of the same electricity mapping point based on the chronological order, and obtain the electricity demand parameter sequence and power supply parameter sequence; Based on the electricity demand parameter sequence and the power supply parameter sequence, the parameter intensity expression module is dynamically adjusted to obtain the electricity demand expression model and the power supply characteristic expression model respectively.

3. A method for predicting power supply quality according to claim 2, characterized in that: The method for determining the interception node of the expression state segment in the reference power demand expression state and the reference power generation characteristic expression state includes: The interception nodes of the expression state segment are gradually moved in a time-progress manner, and the segment volatility corresponding to the expression state segment is analyzed in real time, and based on the analysis results, the segment fluctuation parameter corresponding to the expression state segment is determined; If the segment fluctuation parameter is greater than or equal to the preset value, the node corresponding to the current expression segment will be the interception node.

4. A method for predicting power supply quality according to claim 3, characterized in that: The methods for calculating the segment fluctuation parameters include: Calculate the expression difference characteristics corresponding to the expression segments at adjacent time nodes; Based on the expression difference characteristics corresponding to all adjacent time nodes, the segment fluctuation parameters are determined; Among them, the expression for calculating the section fluctuation parameter is: Among them, Q is the section fluctuation parameter, q t is the expression state difference characteristic parameter corresponding to the t-th time node to the (t+1)-th time node in the expression state segment, and T is the number of all time nodes in the expression state segment; Among them, ΔS i is the parameter difference value of the i-th electricity consumption mapping point between the expression states corresponding to adjacent time nodes, δ(i) is the difference parameter coefficient adjustment function, if the parameter difference value of the i-th electricity consumption mapping point is positive, then δ(i) outputs the preset first adjustment coefficient, if the parameter difference value of the i-th electricity consumption mapping point is negative, then δ(i) outputs the preset second adjustment coefficient, and b is the difference feature adjustment constant.

5. A method for predicting power supply quality according to claim 2, characterized in that: Methods for determining the reference expression profile group to be called include: Performing feature dimensionality reduction on the real-time power demand expression state and the real-time power generation characteristic expression state in the real-time expression state group, and setting labels for the expression state intervals on the real-time power demand expression state and the real-time power generation characteristic expression state based on the dimensionality reduction results; Performing feature dimensionality reduction on the first compared expression segment and the second compared expression segment in the reference expression segment group, and setting labels for the first compared expression segment and the second compared expression segment based on the dimensionality reduction result; Based on the consistency of the labels, determining the expression state interval to which the first comparison expression state segment belongs in the real-time power demand expression state, and determining the expression state interval to which the second comparison expression state segment belongs in the real-time power generation characteristic expression state; The first comparison expression state segment is gradually advanced in the expression state interval of the real-time electricity demand expression state, and the second comparison expression state segment is gradually advanced in the expression state interval of the real-time power generation characteristic expression state, until the first comparison expression state segment and the real-time electricity demand expression state are consistent with each other, and the second comparison expression state segment and the real-time power generation characteristic expression state are consistent with each other, until the first comparison expression state segment and the real-time power generation characteristic expression state are consistent with each other, and the preset standard is reached.

6. A method for predicting power supply quality according to claim 5, characterized in that: The expression state interval of the real-time power demand expression state and the label of the first comparison expression state segment include average power demand parameters at different time nodes; The expression state interval of the real-time power generation characteristic expression state and the label of the second comparison expression state section include average power generation parameters at different time nodes.

7. A method for predicting power supply quality according to claim 1, characterized in that: The parameter intensity expression module expresses changes in the following ways: The parameter intensity expression module is a circular variation component, and the area of ​​the circular variation component is adjusted according to the parameter change corresponding to the electricity consumption mapping point.

8. A method for predicting power supply quality according to claim 1, characterized in that: The method for generating a power plant power generation characteristic expression model includes: The historical power generation characteristics are analyzed to determine the power generation at different time nodes, and a power generation curve is constructed with time as the horizontal axis and power generation as the vertical axis.

9. A method for predicting power supply quality according to claim 1, characterized in that: Methods for forming a reference expression profile group include: Performing several random expression state interceptions on the electricity demand expression model, the power supply characteristic expression model and the power station generation characteristic expression model; The interception method includes intercepting the expression state corresponding to the intercepted time segment, and the number of interceptions is at least enough to ensure that all the intercepted time segments can completely cover the time range corresponding to the overall expression state.

10. A power supply quality prediction system, characterized in that: include: The first module is used to delineate the power supply blocks to be analyzed, obtain the power supply blocks to be analyzed, analyze the historical power demand of the power supply blocks to be analyzed, and generate a power demand expression model, analyze the historical power supply characteristics of the power supply blocks to be analyzed, and generate a power supply characteristic expression model, analyze the historical power generation characteristics of the power stations in the area to which the power supply blocks belong, and generate a power generation characteristic expression model of the power stations; The second module associates the respective expression states of the power demand expression model, the power supply characteristic expression model and the power station power generation characteristic expression model in a manner corresponding to equivalent time segments to form a reference expression state group, wherein the expression state corresponding to the power demand expression model is recorded as the reference power demand expression state, the expression state corresponding to the power supply characteristic expression model is recorded as the reference power supply characteristic expression state, and the expression state corresponding to the power station power generation characteristic expression model is recorded as the reference power generation characteristic expression state; The third module is used to determine the interception nodes of the expression state segments in the reference power demand expression state and the reference power generation characteristic expression state, and record the intercepted expression state segments as the first comparison expression state segment and the second comparison expression state segment respectively, and record the combination of the two as the reference power demand expression state segment group; The fourth module is used to obtain the real-time electricity demand and real-time power generation characteristics corresponding to the power supply section, and express them using the electricity demand expression model and the power station power generation characteristic expression model to obtain the real-time electricity demand expression state and the real-time power generation characteristic expression state, and record the combination of the two as the real-time expression state group, and based on the consistency of the real-time expression state group and the reference expression state section group, determine the called reference expression state group, and based on the reference power supply characteristic expression state in the reference expression state group, determine the power supply quality of the power supply block to be analyzed.

Citation Information

Patent Citations

  • Electricity consumption information association model establishing method and system and intelligent electric meter

    CN115130510A

  • Power consumption management method and system based on AI technology

    CN116822851A

  • Power plant energy management method and system applied to city

    CN117421567A

  • Power supply station resource intelligent scheduling management method and system

    CN117634838A

  • Cooperative control method and system for source network load storage

    CN117895468A