A method and system for predicting power supply quality

Abstract

The present invention discloses a method and system for predicting the quality of power supply, which relates to the technical field of power supply management. Specifically, it discloses associating the respective expression states of an electricity demand expression model, a power supply characteristic expression model, and a power generation characteristic expression model of a power generation station to form a reference expression state group. The intercepted expression state sections are respectively denoted as a first comparison expression state section and a second comparison expression state section, and their combination is denoted as a reference usage expression state section group. Based on the coincidence of the real-time expression state group and the reference usage expression state section group, the called reference expression state group 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 solution, the present invention realizes the accurate prediction and evaluation of the power supply quality, providing a strong guarantee for the stable operation and optimized management of the power system.

Description

Technical Field

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

[0002] In the power industry, the stability and reliability of power supply quality are crucial for ensuring the normal operation of the social economy. However, with the continuous growth of power demand and the increasing complexity of the power system, traditional power supply management methods have been difficult to meet the requirements of the efficient and safe operation of modern power networks. Therefore, it is particularly important to develop a method and system that can accurately predict power supply quality. Summary of the Invention

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

[0004] To achieve the above purpose, the present invention adopts the following technical solutions:

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

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

[0007] Analyzing the historical power generation characteristics of the power stations in the area where the power supply block is located, and generating a power station power generation characteristic expression model;

[0008] According to the corresponding manner of equivalent time periods, associating the respective expression states of the power consumption 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 power consumption demand expression model is denoted as the reference power consumption demand expression state, the expression state corresponding to the power supply characteristic expression model is denoted as the reference power supply characteristic expression state, and the expression state corresponding to the power station power generation characteristic expression model is denoted as the reference power generation characteristic expression state;

[0009] Determining the truncation nodes of the expression state sections in the reference power consumption demand expression state and the reference power generation characteristic expression state, respectively denoting the truncated expression state sections as the first comparison expression state section and the second comparison expression state section, and denoting the combination of the two as the reference power expression state section group;

[0010] Obtain the real-time electricity consumption demand and real-time power generation characteristics corresponding to the power supply section, and use the electricity demand expression model and the power generation characteristics expression model of the power station for expression to obtain the real-time electricity consumption demand expression state and the real-time power generation characteristics expression state, and record the combination of the two as the real-time expression state group. Based on the coincidence between the real-time expression state group and the reference electricity consumption expression state section group, determine the called reference expression state group, and based on the reference power supply characteristics expression state in the reference expression state group, determine the power supply quality of the power supply block to be analyzed.

[0011] In some embodiments disclosed by the present invention, the method for constructing the electricity consumption demand expression model and the power supply characteristics expression model includes:

[0012] Construct a position expression layer for the power supply block, and based on the positions of the important electricity consumption nodes in the power supply block, set electricity mapping points at the corresponding positions in the position expression layer, and each electricity mapping point is configured with a parameter intensity expression module, where the parameter intensity expression module performs expression changes according to the magnitude of the parameter corresponding to the electricity mapping point;

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

[0014] Based on the electricity consumption demand parameter sequence and the power supply parameter sequence, dynamically adjust the parameter intensity expression module to obtain the electricity consumption demand expression model and the power supply characteristics expression model respectively.

[0015] In some embodiments disclosed by the present invention, the method for determining the truncation node of the expression state section in the reference electricity consumption demand expression state and the reference power generation characteristics expression state includes:

[0016] Gradually shift the truncation node of the expression state section in the manner of time progression, and analyze the section volatility corresponding to the expression state section in real time, and based on the analysis result, determine the section volatility parameter corresponding to the expression state section;

[0017] If the section volatility parameter is greater than or equal to the preset value, then take the node corresponding to the expression state section at this time as the truncation node.

[0018] In some embodiments disclosed by the present invention, the method for calculating the section volatility parameter includes:

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

[0020] Based on the expression state difference characteristics corresponding to all adjacent time nodes, determine the section volatility parameter;

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

[0022]

[0023] Among them, Q is the section fluctuation parameter, and 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 section, and T is the number of all time nodes in the expression state section;

[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 a preset first adjustment coefficient. If the parameter difference value of the i-th electricity consumption mapping point is negative, then δ(i) outputs a preset second adjustment coefficient, and b is the difference characteristic adjustment constant.

[0026] In some embodiments disclosed by the present invention, the method for determining the called reference expression state group includes:

[0027] Perform feature dimensionality reduction on the real-time electricity consumption demand expression state and the real-time power generation characteristic expression state in the real-time expression state group, and based on the dimensionality reduction result, set labels for the expression state intervals on the real-time electricity consumption demand expression state and the real-time power generation characteristic expression state;

[0028] Perform feature dimensionality reduction on the first comparison expression state section and the second comparison expression state section in the reference electricity consumption expression section group, and based on the dimensionality reduction result, set labels for the first comparison expression section and the second comparison expression state section;

[0029] Based on the conformity of the labels, determine the expression state interval to which the first comparison expression state section belongs on the real-time electricity consumption demand expression state, and determine the expression state interval to which the second comparison expression state section belongs on the real-time power generation characteristic expression state;

[0030] Gradually advance the first comparison expression state section on the expression state interval of the real-time electricity consumption demand expression state, and at the same time gradually advance the second comparison expression state section on the expression state interval of the real-time power generation characteristic expression state until the matching state between the first comparison expression state section and the real-time electricity consumption demand expression state reaches a preset standard, and the matching state between the second comparison expression state section and the real-time power generation characteristic expression state reaches a preset standard.

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

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

[0034] In some embodiments disclosed in the present invention, the ways for the parameter intensity expression module to perform expression changes include:

[0035] The parameter intensity expression module is a circular change component, and adjusts the area of the circular change component according to the parameter changes corresponding to the electricity consumption mapping points.

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

[0037] Analyze the historical power generation characteristics, determine the power generation power at different time nodes, and construct a power generation power curve with time as the horizontal axis and power generation power as the vertical axis.

[0038] In some embodiments disclosed in the present invention, the method for forming a reference expression state group includes:

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

[0040] Among them, the interception method includes intercepting the expression state corresponding to the intercepted time section, and the number of interceptions is at least guaranteed to completely cover the time range corresponding to the overall expression state by all the intercepted time sections.

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

[0042] The first module is used to delimit the power supply block to be analyzed to obtain the power supply block to be analyzed, analyze the historical electricity demand of the power supply block to be analyzed, and generate an electricity 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, analyze the historical power generation characteristics of the power generation stations in the area where the power supply block is located, and generate a power generation station power generation characteristic expression model;

[0043] The second module associates the respective expression states of the electricity demand expression model, the power supply characteristic expression model, and the power generation station power generation characteristic expression model in a manner corresponding to equivalent time periods to form a reference expression state group. Among them, the expression state corresponding to the electricity demand expression model is denoted as the reference electricity demand expression state, the expression state corresponding to the power supply characteristic expression model is denoted as the reference power supply characteristic expression state, and the expression state corresponding to the power generation station power generation characteristic expression model is denoted as the reference power generation characteristic expression state;

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

[0045] The fourth module is used to obtain the real-time electricity demand and the real-time power generation characteristics corresponding to the power supply segment, and use the electricity demand expression model and the power generation station power generation characteristic expression model for expression to obtain the real-time electricity demand expression state and the real-time power generation characteristic expression state, and denote the combination of the two as the real-time expression state group. Based on the consistency between the real-time expression state group and the reference usage expression state segment group, the called reference expression state group 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.

[0046] The present invention discloses a method and system for predicting power supply quality, which relates to the technical field of power supply management. Specifically, it discloses associating the respective expression states of the electricity demand expression model, the power supply characteristic expression model, and the power generation station power generation characteristic expression model to form a reference expression state group, respectively denoting the truncated expression state segments as the first comparison expression state segment and the second comparison expression state segment, and denoting the combination of the two as the reference usage expression state segment group. Based on the consistency between the real-time expression state group and the reference usage expression state segment group, the called reference expression state group 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 solutions, the present invention realizes the accurate prediction and evaluation of power supply quality, providing a strong guarantee for the stable operation and optimal management of the power system. Description of the Drawings

[0047] Figure 1 It is a method step diagram of a method for predicting power supply quality disclosed in an embodiment of the present invention. Detailed Embodiment

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

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

[0050] To achieve the above object, the present invention adopts the following technical solutions:

[0051] Refer to Figure 1 , a method for predicting the quality of power supply, including:

[0052] Step S100, demarcate the power supply block to be analyzed to obtain the power supply block to be analyzed, analyze the historical power consumption demand of the power supply block to be analyzed, and generate a power consumption demand expression model, and 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, demarcating a specific power supply block is to make the analysis more targeted and accurate; then, deeply analyze the historical power consumption demand of these blocks, aiming to find out the characteristics such as periodicity and trend of the power consumption demand, and generate a power consumption demand expression model accordingly; at the same time, the analysis of the power supply characteristics is similar, aiming to understand factors such as stability and reliability in the power supply process, and construct a power supply characteristic expression model; these models can reflect the power consumption and power supply characteristics of the power supply block, laying a foundation for subsequent prediction.

[0054] In some embodiments disclosed by the present invention, the methods for constructing the power consumption demand expression model and the power supply characteristic expression model include:

[0055] Step S101, construct a location expression layer for the power supply block, and based on the locations of important power consumption nodes within the power supply block, set power consumption mapping points at the corresponding locations of the location expression layer, and each power consumption mapping point is configured with a parameter intensity expression module, where the parameter intensity expression module performs expression changes according to the magnitude of the parameter corresponding to the power consumption mapping point.

[0056] Step S102, analyze the historical power consumption demand and historical power supply characteristics, determine the power consumption demand parameters and power supply parameters of different power consumption mapping points at different time nodes, and sort the power consumption demand parameters and power supply parameters belonging to the same power consumption mapping point based on the chronological order before and after to obtain a power consumption demand parameter sequence and a power supply parameter sequence.

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

[0058] Step S200, analyze the historical power generation characteristics of power stations in the area where the power supply block is located, and generate a power station power generation characteristic expression model.

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

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

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

[0062] Step S300, in the corresponding manner of equivalent time periods, associate the respective expression states of the power consumption 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, where the expression state corresponding to the power consumption demand expression model is denoted as the reference power consumption demand expression state, the expression state corresponding to the power supply characteristic expression model is denoted as the reference power supply characteristic expression state, and the expression state corresponding to the power station power generation characteristic expression model is denoted as the reference power generation characteristic expression state.

[0063] The core of this step lies in data association and integration; by associating the power consumption demand expression model, the power supply characteristic expression model, and the power station power generation characteristic expression model according to equivalent time periods, a comprehensive reference expression state group can be formed; this association enables different models to be aligned in the time dimension, thus more accurately analyzing the mutual relationships and influences between them. This integration method provides more comprehensive data support for subsequent predictions.

[0064] In some embodiments disclosed in the present invention, the method for forming a reference expression state group includes:

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

[0066] Among them, the interception method includes intercepting the expression states corresponding to the intercepted time periods, and the number of interceptions should at least ensure that all intercepted time periods can completely cover the time range corresponding to the overall expression state.

[0067] Step S400: Determine the truncation nodes for the expression segments in the reference power consumption demand expression state and the reference power generation characteristic expression state, respectively record the truncated expression segments as the first comparison expression segment and the second comparison expression segment, and record the combination of the two as the reference power consumption expression segment group.

[0068] In this step, the key is to determine the truncation nodes and extract the key expression segments; the selection of the truncation nodes is usually based on the results of data analysis, such as the peak power consumption or the key turning points of the power station operation status; by truncating these key expression segments, the change rules and influencing factors of the power supply quality can be analyzed more accurately.

[0069] In some embodiments disclosed by the present invention, the method for determining the truncation nodes for the expression segments in the reference power consumption demand expression state and the reference power generation characteristic expression state includes:

[0070] Step S401: Gradually shift the truncation nodes of the expression segment according to the progress of time, and analyze the segment volatility corresponding to the expression segment in real time, and determine the segment volatility parameter corresponding to the expression segment based on the analysis results.

[0071] Step S403: If the segment volatility parameter is greater than or equal to the preset value, then use the node corresponding to the expression segment at this time as the truncation node.

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

[0073] Step S4011: Calculate the expression state difference characteristics corresponding to the expression segment at adjacent time nodes.

[0074] Step S4012: Determine the segment volatility parameter based on the expression state difference characteristics corresponding to all adjacent time nodes.

[0075] Among them, the expression for calculating the segment volatility parameter is:

[0076]

[0077] Among them, Q is the segment volatility 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 segment, and T is the number of all time nodes in the expression 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, δ(i) outputs a preset first adjustment coefficient; if the parameter difference value of the i-th electricity consumption mapping point is negative, δ(i) outputs a preset second adjustment coefficient, and b is the difference feature adjustment constant.

[0080] Step S500: Obtain the real-time electricity consumption demand and real-time power generation characteristics corresponding to the power supply section, and use the electricity demand expression model and the power generation station power generation characteristic expression model for expression to obtain the real-time electricity consumption 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. Based on the consistency between the real-time expression state group and the reference electricity consumption 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 link of the prediction method. First, obtain real-time electricity consumption demand and power generation characteristic data, and use the previously constructed model for expression 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 section group, the historical pattern 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, determine the power supply quality of the power supply block to be analyzed according to 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 by the present invention, the method for determining the called reference expression state group includes:

[0083] Step S501: Perform feature dimensionality reduction on the real-time electricity consumption demand expression state and the real-time power generation characteristic expression state in the real-time expression state group, and based on the dimensionality reduction result, set labels for the expression state intervals on the real-time electricity consumption demand expression state and the real-time power generation characteristic expression state.

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

[0085] Step S502: Perform feature dimensionality reduction on the first comparison expression state section and the second comparison expression state section in the reference electricity consumption expression section group, and based on the dimensionality reduction result, set labels for the first comparison expression section and the second comparison expression state section.

[0086] Step S502 is similar to Step S501, but the objects are changed to the first comparison expression state section and the second comparison expression state section in the reference expression section group. Similarly, feature dimensionality reduction is performed on these sections to reduce the dimensionality and complexity of the data. Then, labels are set for the dimensionality-reduced comparison expression state sections, and these labels will be used in subsequent comparison and identification processes.

[0087] In Step S503, based on the consistency of the labels, the expression state interval to which the first comparison expression state section belongs is determined on the real-time power consumption demand expression state, and the expression state interval to which the second comparison expression state section belongs is determined on the real-time power generation feature expression state.

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

[0089] In Step S504, the first comparison expression state section is gradually advanced on the expression state interval of the real-time power consumption demand expression state, and at the same time, the second comparison expression state section is gradually advanced on the expression state interval of the real-time power generation feature expression state until the matching state between the first comparison expression state section and the real-time power consumption demand expression state reaches a preset standard, and the matching state between the second comparison expression state section and the real-time power generation feature expression state reaches a preset standard.

[0090] In this step, on the determined expression state intervals of the real-time power consumption demand expression state and the real-time power generation feature expression state, the first comparison expression state section and the second comparison expression state section are gradually advanced. By continuously comparing and adjusting the positions of these sections, an attempt is made to find the comparison expression state section that best matches the real-time expression state. When the matching state between the first comparison expression state section and the real-time power consumption demand expression state and the matching state between the second comparison expression state section and the real-time power generation feature expression state both reach the preset standards, it is considered that the best match has been found. The purpose of this step is to ensure that the found reference expression group has a high degree of similarity to the real-time expression state, thereby improving the accuracy of prediction and analysis.

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

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

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

[0094] In some embodiments disclosed by the present invention, the manner in which the parameter intensity expression module performs expression changes includes: the parameter intensity expression module is a circular change component, and adjusts the area of the circular change component according to the parameter changes corresponding to the power consumption mapping points.

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

[0096] A first module, configured to delimit the power supply block to be analyzed to obtain the power supply block to be analyzed, analyze the historical power consumption demand of the power supply block to be analyzed, and generate a power consumption 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, analyze the historical power generation characteristics of the power stations in the area where the power supply block is located, and generate a power station power generation characteristic expression model;

[0097] A second module, which associates the respective expression states of the power consumption demand expression model, the power supply characteristic expression model, and the power station power generation characteristic expression model in the corresponding manner of equivalent time sections to form a reference expression state group, where the expression state corresponding to the power consumption demand expression model is denoted as the reference power consumption demand expression state, the expression state corresponding to the power supply characteristic expression model is denoted as the reference power supply characteristic expression state, and the expression state corresponding to the power station power generation characteristic expression model is denoted as the reference power generation characteristic expression state;

[0098] A third module, configured to determine the intercept nodes of the expression state sections in the reference power consumption demand expression state and the reference power generation characteristic expression state, respectively denote the intercepted expression state sections as the first comparison expression state section and the second comparison expression state section, and denote the combination of the two as the reference usage expression state section group;

[0099] A fourth module, configured to obtain the real-time power consumption demand and the real-time power generation characteristics corresponding to the power supply section, perform expression using the power consumption demand expression model and the power station power generation characteristic expression model to obtain the real-time power consumption demand expression state and the real-time power generation characteristic expression state, and denote the combination of the two as the real-time expression state group, and determine the called reference expression state group based on the conformity between the real-time expression state group and the reference usage expression state section group, and determine the power supply quality of the power supply block to be analyzed based on the reference power supply characteristic expression state in the reference expression state group.

[0100] The present invention discloses a method and system for predicting the quality of power supply, which relates to the technical field of power supply management. Specifically, it discloses that the respective expression states of the power consumption demand expression model, the power supply characteristic expression model, and the power generation characteristic expression model of the power generation station are associated to form a reference expression state group. The intercepted expression state sections are respectively denoted as the first comparison expression state section and the second comparison expression state section, and their combination is denoted as the reference power consumption expression state section group. Based on the coincidence of the real-time expression state group and the reference power consumption expression state section group, the called reference expression state group 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 solutions, the present invention realizes the accurate prediction and evaluation of the power supply quality, and provides a strong guarantee for the stable operation and optimized management of the power system.

[0101] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solutions and inventive concepts of the present invention, makes equivalent substitutions or changes, and all should be covered within the protection scope of the present invention.

Claims

1. A power supply quality prediction method, characterized in that, Including: Demarcate the power supply block to be analyzed to obtain the power supply block to be analyzed, analyze the historical electricity consumption demand of the power supply block to be analyzed, generate an electricity consumption 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; Analyze the historical power generation characteristics of the power generation stations in the area where the power supply block is located, and generate a power generation station power generation characteristic expression model; In the corresponding manner of equivalent time periods, associate the respective expression states of the electricity consumption demand expression model, the power supply characteristic expression model, and the power generation station power generation characteristic expression model to form a reference expression state group. Among them, the expression state corresponding to the electricity consumption demand expression model is denoted as the reference electricity consumption demand expression state, the expression state corresponding to the power supply characteristic expression model is denoted as the reference power supply characteristic expression state, and the expression state corresponding to the power generation station power generation characteristic expression model is denoted as the reference power generation characteristic expression state; Determine the truncation nodes of the expression state sections in the reference electricity consumption demand expression state and the reference power generation characteristic expression state, respectively denote the truncated expression state sections as the first comparison expression state section and the second comparison expression state section, and denote the combination of the two as the reference usage expression state section group; Obtain the real-time electricity consumption demand and real-time power generation characteristics corresponding to the power supply section, and use the electricity demand expression model and the power generation station power generation characteristic expression model for expression to obtain the real-time electricity consumption demand expression state and the real-time power generation characteristic expression state, and denote the combination of the two as the real-time expression state group. Based on the coincidence of the real-time expression state group and the reference usage 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; The methods for constructing the electricity consumption demand expression model and the power supply characteristic expression model include: Construct a position expression layer for the power supply block, and based on the positions of the important electricity consumption nodes in the power supply block, set electricity mapping points at the corresponding positions in the position expression layer. Each electricity mapping point is configured with a parameter intensity expression module, where the parameter intensity expression module performs expression changes according to the magnitude of the parameter corresponding to the electricity mapping point; Analyze the historical electricity consumption demand and historical power supply characteristics, determine the electricity consumption demand parameters and power supply parameters of different electricity mapping points at different time nodes, and based on the chronological order, sort the electricity consumption demand parameters and power supply parameters belonging to the same electricity mapping point to obtain an electricity consumption demand parameter sequence and a power supply parameter sequence; Based on the electricity consumption demand parameter sequence and the power supply parameter sequence, dynamically adjust the parameter intensity expression module to obtain the electricity consumption demand expression model and the power supply characteristic expression model respectively; The methods for determining the truncation nodes of the expression state sections in the reference electricity consumption demand expression state and the reference power generation characteristic expression state include: Gradually shift the truncation nodes of the expression state sections in the manner of time progression, and analyze the section volatility corresponding to the expression state sections in real time. Based on the analysis results, determine the section fluctuation parameters corresponding to the expression state sections; If the section fluctuation parameter is greater than or equal to the preset value, the node corresponding to the expression state section at this time is the intercepted node.

2. The power supply quality prediction method according to claim 1, characterized in that, The method for calculating the section fluctuation parameter includes: Calculating the expression state difference features corresponding to the expression state section at adjacent time nodes; Based on the expression state difference features corresponding to all adjacent time nodes, determining the section fluctuation parameter; Among them, the expression for calculating the section fluctuation parameter is: Among them, Q is the section fluctuation parameter, and 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 section, and T is the number of all time nodes in the expression state section; where 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, δ(i) outputs a preset first adjustment coefficient. If the parameter difference value of the i-th electricity consumption mapping point is negative, δ(i) outputs a preset second adjustment coefficient, and b is the difference feature adjustment constant.

3. A power supply quality prediction method according to claim 1, characterized in that, The method for determining the called reference expression state group includes: Performing feature dimensionality reduction on the real-time electricity demand expression state and the real-time power generation feature expression state in the real-time expression state group, and based on the dimensionality reduction result, setting labels for the expression state intervals on the real-time electricity demand expression state and the real-time power generation feature expression state; Performing feature dimensionality reduction on the first comparison expression state section and the second comparison expression state section in the reference electricity consumption expression section group, and based on the dimensionality reduction result, setting labels for the first comparison expression section and the second comparison expression state section; Based on the consistency of the labels, determining the expression state interval to which the first comparison expression state section belongs on the real-time electricity demand expression state, and determining the expression state interval to which the second comparison expression state section belongs on the real-time power generation feature expression state; Gradually advancing the first comparison expression state section on the expression state interval of the real-time electricity demand expression state, and at the same time gradually advancing the second comparison expression state section on the expression state interval of the real-time power generation feature expression state until the matching state between the first comparison expression state section and the real-time electricity demand expression state reaches the preset standard, and the matching state between the second comparison expression state section and the real-time power generation feature expression state reaches the preset standard.

4. A power supply quality prediction method according to claim 3, wherein The expression state interval of the real-time electricity demand expression state and the label of the first comparison expression state section include the average electricity demand parameters at different time nodes; The expression state interval of the real-time power generation feature expression state and the label of the second comparison expression state section include the average power generation power parameters at different time nodes.

5. A power supply quality prediction method according to claim 1, characterized in that, The way the parameter intensity expression module performs expression changes includes: The parameter intensity expression module is a circular change component, and adjusts the area of the circular change component according to the parameter change corresponding to the electricity consumption mapping point.

6. A power supply quality prediction method according to claim 1, characterized in that The method for generating a power generation station power generation feature expression model includes: Analyzing the historical power generation features, determining the power generation power at different time nodes, and constructing a power generation power curve with time as the horizontal axis and power generation power as the vertical axis.

7. A power supply quality prediction method according to claim 1, characterized in that, The method for forming a reference expression state group includes: Performing several random expression state interceptions on the electricity demand expression model, the power supply feature expression model, and the power generation station power generation feature expression model; Among them, the interception method includes intercepting the expression state corresponding to the intercepted time section, and the number of interceptions is at least guaranteed to completely cover the time range corresponding to the overall expression state by all intercepted time sections.

8. A power supply quality prediction system, characterized in that, A power supply quality prediction method for executing any one of claims 1-7 includes: The first module is used to delimit the power supply block to be analyzed, obtain the power supply block to be analyzed, analyze the historical electricity consumption demand of the power supply block to be analyzed, and generate an electricity consumption 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, analyze the historical power generation characteristics of the power stations in the area where the power supply block is located, and generate a power station power generation characteristic expression model; The second module associates the respective expression states of the electricity consumption demand expression model, the power supply characteristic expression model, and the power station power generation characteristic expression model in a corresponding manner according to the equivalent time periods to form a reference expression state group. Among them, the expression state corresponding to the electricity consumption demand expression model is denoted as the reference electricity consumption demand expression state, the expression state corresponding to the power supply characteristic expression model is denoted as the reference power supply characteristic expression state, and the expression state corresponding to the power station power generation characteristic expression model is denoted as the reference power generation characteristic expression state; The third module is used to determine the interception nodes of the expression state sections in the reference electricity consumption demand expression state and the reference power generation characteristic expression state, respectively denote the intercepted expression state sections as the first comparison expression state section and the second comparison expression state section, and denote the combination of the two as the reference usage expression state section group; The fourth module is used to obtain the real-time electricity consumption demand and real-time power generation characteristics corresponding to the power supply section, and use the electricity demand expression model and the power station power generation characteristic expression model for expression to obtain the real-time electricity consumption demand expression state and the real-time power generation characteristic expression state, and denote the combination of the two as the real-time expression state group. Based on the consistency between the real-time expression state group and the reference usage 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.

Images