Power terminal equipment energy efficiency optimization method and device for smart power grid

Abstract

The invention discloses a power terminal equipment energy efficiency optimization method and device for an intelligent power grid, and relates to the technical field of power, and the method comprises the steps: obtaining a power terminal distribution network which comprises a plurality of power terminals and the layout positions of the power terminals in a target power grid; the method comprises the following steps: extracting operation data of a plurality of power terminals in a preset monitoring window to form a plurality of monitoring operation data sets, and performing centralized value analysis on the monitoring operation data sets to generate a plurality of explicit operation centralized value sets; the method comprises the following steps: extracting long-time-sequence operation data of a plurality of power terminals, performing segmented iterative analysis, and determining a plurality of implicit operation factors; and performing neighbor terminal sampling based on the power terminal distribution network and the layout position thereof, and performing correlation analysis by combining a sampling result and the implicit operation factor to obtain a plurality of energy efficiency optimization background factors. And the energy efficiency optimization background factors and the explicit operation centralized value set are used to carry out energy efficiency optimization on the plurality of power terminals, so that the technical effects of improving the equipment collaboration and the working condition adaptability and improving the energy efficiency performance are achieved.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method and device for optimizing energy efficiency of electric power terminal equipment for a smart grid. Background Art

[0002] In smart grid technology, intelligent management of power terminal equipment is the key to improving the efficiency of power grid operation. In the existing technology, when optimizing the energy efficiency of power terminal equipment, the operating conditions of each terminal equipment in the current or short term are often analyzed based on the static characteristics and single working conditions of the equipment, and energy efficiency is optimized based on the analysis results. There are technical problems such as low equipment coordination level, poor working condition adaptability and poor energy efficiency performance. Summary of the invention

[0003] The present invention provides a method and device for optimizing the energy efficiency of power terminal equipment for smart grids, so as to solve the technical problems in the prior art of low equipment coordination level, poor adaptability to working conditions and poor energy efficiency performance, and achieve the technical effect of improving equipment coordination and adaptability to working conditions and improving energy efficiency performance.

[0004] In a first aspect, the present invention provides a method for optimizing energy efficiency of power terminal equipment for a smart grid, wherein the method comprises: A power terminal distribution network of a target power grid is obtained, wherein the power terminal distribution network includes K power terminals and K terminal deployment locations, and K is an integer greater than or equal to 1.

[0005] Based on the integrated sensor array deployed on each power terminal, the operating data of the K power terminals in the preset monitoring window are extracted to obtain K monitoring operation data sets, wherein each monitoring operation data set includes all operating data of an operating indicator within the preset monitoring window.

[0006] Performing concentrated value analysis on the K monitoring operation data sets to obtain K explicit operation concentrated value sets.

[0007] The K power terminals are traversed to extract long-term operation data to obtain K long-term operation data sets.

[0008] Based on the K long time series operation data sets, data segmentation iterative analysis is performed to determine K implicit operation factors.

[0009] Based on the power terminal distribution network and the K terminal layout locations, neighboring terminal sampling is performed on the K power terminals, and correlation analysis is performed based on the sampling results and the K implicit operating factors to determine K energy efficiency optimization background factors.

[0010] Energy efficiency optimization of the K power terminals is performed according to the K energy efficiency optimization background factors and the K explicit operation concentrated value sets to obtain K energy efficiency optimization schemes.

[0011] In a second aspect, the present invention further provides an energy efficiency optimization device for power terminal equipment used in a smart grid, wherein the device comprises: A distribution network acquisition module, wherein the distribution network acquisition module is used to acquire the power terminal distribution network of the target power grid, wherein the power terminal distribution network includes K power terminals and K terminal layout locations, and K is an integer greater than or equal to 1.

[0012] An operation data extraction module is used to extract the operation data of the K power terminals in a preset monitoring window based on an integrated sensor array arranged on each power terminal, and obtain K monitoring operation data sets, wherein each monitoring operation data set includes all operation data of an operation indicator within the preset monitoring window.

[0013] A concentrated value analysis module is used to perform concentrated value analysis on the K monitoring operation data sets to obtain K explicit operation concentrated value sets.

[0014] A long time series extraction module is used to traverse the K power terminals to extract long time series operation data and obtain K long time series operation data sets.

[0015] The segmented iterative analysis module is used to perform segmented iterative analysis on the K long time series operation data sets to determine K implicit operation factors.

[0016] The background factor positioning module is used to perform neighboring terminal sampling on the K power terminals based on the power terminal distribution network and the K terminal layout locations, and perform correlation analysis based on the sampling results and the K implicit operating factors to determine K energy efficiency optimization background factors.

[0017] An optimization decision module, wherein the optimization decision module is used to optimize the energy efficiency of the K power terminals according to the K energy efficiency optimization background factors and the K explicit operation concentrated value sets, and obtain K energy efficiency optimization solutions.

[0018] The present invention discloses a method and device for optimizing energy efficiency of power terminal equipment for smart grids, comprising: obtaining distribution network information of power terminals in a target power grid, wherein the power terminal distribution network is composed of K power terminals and their corresponding layout positions, and K is an integer not less than 1; based on an integrated array of sensors installed on each power terminal, extracting operation data of each power terminal within a specified monitoring window to obtain K monitoring operation data sets, wherein each set contains all operation indicator data within the monitoring window; performing centralized value analysis on the K monitoring operation data sets to generate K explicit operation centralized value sets Combine; traverse the K power terminals one by one, extract their long-term operation data, and obtain K long-term operation data sets; use the K long-term operation data sets to perform data segmentation and iterative analysis, and identify K implicit operation factors; combine the distribution network of the power terminals and their layout locations, implement neighbor terminal sampling, and perform correlation analysis based on the sampling results and the K implicit operation factors to determine K background factors for energy efficiency optimization; finally, according to the K energy efficiency optimization background factors and the K explicit operation concentrated value sets, perform energy efficiency optimization for the K power terminals, and output K corresponding energy efficiency optimization schemes. The energy efficiency optimization method and device for power terminal equipment used in smart grids disclosed in the present invention solve the technical problems of low equipment coordination level, poor working condition adaptability and energy efficiency performance, and achieve the technical effect of improving equipment coordination and working condition adaptability and improving energy efficiency performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of the method for optimizing energy efficiency of electric power terminal equipment in smart grid according to the present invention.

[0020] Figure 2 It is a structural schematic diagram of the energy efficiency optimization device of power terminal equipment used in smart grid of the present invention.

[0021] Explanation of the reference numerals: distribution network acquisition module 11, operation data extraction module 12, concentration value analysis module 13, long time series extraction module 14, segmented iterative analysis module 15, background factor positioning module 16, optimization decision module 17. DETAILED DESCRIPTION

[0022] The technical solution provided in the embodiments of the present invention is to solve the technical problems of low equipment coordination level, poor working condition adaptability and poor energy efficiency performance in the prior art. The overall idea adopted is as follows: First, the power terminal distribution network of the target power grid is obtained, wherein the power terminal distribution network includes multiple power terminals and multiple terminal layout positions, which are mostly integers greater than or equal to 1; then, based on the sensor integrated array deployed on each power terminal, the operation data of the multiple power terminals in the preset monitoring window are extracted to obtain multiple monitoring operation data sets, wherein each monitoring operation data set contains all the operation data of an operation indicator in the preset monitoring window; then, the multiple monitoring operation data sets are analyzed for centralized values ​​to obtain multiple explicit operation centralized value sets; then, multiple power terminals are traversed to extract long-term operation data to obtain multiple long-term operation data sets; further, data segmented iterative analysis is performed based on the multiple long-term operation data sets to determine multiple implicit operation factors; then, based on the power terminal distribution network and the multiple terminal layout positions, neighboring terminal sampling is performed on the multiple power terminals, and correlation analysis is performed based on the sampling results and the multiple implicit operation factors to determine multiple energy efficiency optimization background factors; finally, based on the multiple energy efficiency optimization background factors and the multiple explicit operation centralized value sets, energy efficiency optimization is performed on the multiple power terminals to obtain multiple energy efficiency optimization schemes.

[0023] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0024] Embodiment 1 Figure 1 The present invention is a flow chart of a method for optimizing energy efficiency of power terminal equipment in a smart grid, wherein the method comprises: A power terminal distribution network of a target power grid is obtained, wherein the power terminal distribution network includes K power terminals and K terminal deployment locations, and K is an integer greater than or equal to 1.

[0025] Specifically, the power terminal distribution network is used to describe the specific distribution of power terminal devices in the target power grid. Among them, the power terminal is the basic node in the target power grid, including various power equipment (such as transformers, circuit breakers, power metering devices, smart meters, load nodes, etc.). The terminal layout location indicates the specific location of each power terminal, including the physical location, geographical coordinates and connection relationship of each power terminal in the power grid topology.

[0026] Optionally, the terminal deployment location is also associated with information such as the altitude of the terminal device, the installation location type (such as indoors or outdoors), etc.

[0027] Exemplarily, to obtain the power terminal distribution network of the target power grid, first, obtain the unique identifier of each power terminal (such as terminal ID, equipment number, etc.), and the terminal identification data can come from the equipment management system of the power grid (such as SCADA system, EMS system) or the tag information of the field equipment. Then, through field survey, GIS system or power grid management system (such as DMS system), collect the layout location of each power terminal, including its geographic coordinates (such as GPS coordinates) and topological location (such as node number in the power grid topology). Then, determine the connection relationship between each power terminal through the power grid topology map or the network topology management system of the power dispatching center.

[0028] Optionally, the power terminal distribution network of the target power grid is represented by a graph structure. First, each power terminal is used as a node to form a node set. The attributes of each node include: unique identifier, layout location, device type, device status, etc. Then, according to the power connection attributes (such as voltage level, transmission power, fault status, etc.), the connection relationship between nodes is defined to form an edge set. Finally, the node set and the edge set are combined to construct the power terminal distribution network of the target power grid. The power terminal distribution network constructed by the above steps realizes a graphical display of the target power grid and effectively describes the distribution of power terminals in the power grid.

[0029] Based on the integrated sensor array deployed on each power terminal, the operating data of the K power terminals in the preset monitoring window are extracted to obtain K monitoring operation data sets, wherein each monitoring operation data set includes all operating data of an operating indicator within the preset monitoring window.

[0030] Specifically, K monitoring operation data sets correspond to K operation indicators, such as voltage, current, reactive power, harmonics, etc., and each monitoring operation data set contains data sets corresponding to at most K power terminals. In other words, each monitoring operation data set contains all operation data of power terminals with corresponding operation indicator monitoring needs within a preset monitoring window.

[0031] Specifically, the preset monitoring window is the operation data monitoring and collection range defined based on the target power grid optimization computing power, including the collection time period of the operation data and the sampling frequency of the data. Optionally, the preset monitoring window is represented by the monitoring start time and end time, and the window size setting of the monitoring window is adjusted according to the actual application scenario. For example, a short-term monitoring window (such as 1 second, 10 seconds, 1 minute, etc.) is used to identify short-term state fluctuations of the power terminal (such as instantaneous overload, short-term power fluctuations).

[0032] The above steps conduct multi-dimensional monitoring of power terminals based on sensor integrated arrays, which can form a detailed monitoring operation data set, thereby providing strong data support for the status analysis and evaluation of power terminals.

[0033] In some embodiments, the sensor integrated array includes a voltage sensor, a current sensor, a power sensor, a temperature sensor, and a vibration sensor.

[0034] Specifically, the voltage sensor is used to measure the real-time voltage value of the power terminal to evaluate whether the power terminal is operating within the rated voltage range and identify voltage fluctuations, undervoltage or overvoltage. The current sensor is used to monitor the current output or input value of the power terminal, which can reflect the load status of the power terminal and help identify overload, short circuit and abnormal current fluctuations. The power sensor is used to monitor the power output of the power terminal, including active power and reactive power, and then reflect the energy efficiency level, load capacity and power factor changes of the power equipment. The temperature sensor is used to detect the surface temperature or internal temperature of the power terminal equipment, which helps to identify whether the power equipment is overheated, poorly dissipated or has abnormal ambient temperature, and assists in the energy efficiency level assessment. The vibration sensor monitors the vibration or mechanical failure that may exist in the power terminal equipment during operation (such as loose transformer core, abnormal vibration of circuit breaker, etc.), so as to obtain the health status of the mechanical structure of the power equipment.

[0035] Performing concentrated value analysis on the K monitoring operation data sets to obtain K explicit operation concentrated value sets.

[0036] Specifically, the centralized value analysis of K monitoring operation data sets identifies the centralized value points of each power terminal in the monitoring data set, obtains the explicit operation centralized value set of each set, and then determines the main operation state of each power terminal in a certain time window. This helps to identify the overall trend and characteristics of the target power grid operation state and provide strong support for optimization and decision-making.

[0037] In some embodiments, performing concentrated value analysis on the K monitoring operation data sets to obtain K explicit operation concentrated value sets includes: Extract the first monitoring operation data set from the K monitoring operation data sets, and calculate the mean of the first monitoring operation data set to obtain the first monitoring operation mean. Take the first monitoring operation mean as the search center, search in the first monitoring operation data set according to the preset concentrated bandwidth, and determine the first search monitoring operation data. Calculate the concentration density of the first monitoring operation mean and the first search monitoring operation data respectively, and when the concentration density of the first search monitoring operation data is greater than or equal to the concentration density of the first monitoring operation mean, obtain the first search direction. Update the first search monitoring operation data to the search center, search in the first monitoring operation data set based on the first search direction and according to the preset concentrated bandwidth until the concentration density difference between two adjacent searches is less than or equal to the preset concentration density difference, stop the search, and use the search center corresponding to the maximum concentration density during the search process as the target search center, and use the first monitoring operation data corresponding to the target search center as the first explicit operation concentrated value set. Perform concentrated value analysis on the K monitoring operation data sets according to the preset concentrated bandwidth to obtain the K explicit operation concentrated value sets.

[0038] In some implementations, the first search direction is a direction of the first search monitoring operation data relative to the first monitoring operation mean.

[0039] Specifically, first, from the monitoring data sets of K power terminals, select the data set of each power terminal in turn, and calculate the initial mean of the selected data set as the initial center point of the search. Then, with the initial mean as the search center, a neighborhood search is performed in the data set according to the preset concentrated bandwidth. Among them, the concentrated bandwidth is used to define the neighborhood range (i.e., the search radius) of the data points in the search process. In other words, the concentrated bandwidth determines the size of the search area. The search result is a set of data points of all concentrated bandwidths, which is recorded as the first search monitoring operation data set. Next, the initial mean and the concentration density of the first search monitoring operation data set are calculated respectively, wherein the concentration density represents the density of the data points in the search area, which is calculated by the number of data points in the neighborhood and is used to determine whether it is necessary to continue the search for the concentrated value. Then, the density change is determined. If the concentration density of the first search monitoring operation data set is greater than or equal to the concentration density of the first monitoring operation mean, the direction of the first search monitoring operation data relative to the first monitoring operation mean is determined to be the first search direction, and the mean of the first search monitoring operation data set is set as the new search center. Then, the neighborhood search process is repeated until the search center no longer changes significantly or the change in the concentration density is lower than the preset threshold (i.e., the search center tends to be stable), and the search center corresponding to the maximum concentration density in the search process is taken as the target search center, and the set of data points corresponding to the target search center is regarded as the first explicit running concentration value set.

[0040] Optionally, a kernel density estimation method is used to calculate the concentration density to smooth the noise data points and improve the robustness of the concentration value recognition. The kernel function includes Gaussian kernel, triangular kernel, Epanechnikov kernel, etc.

[0041] Optionally, during the search process, the concentration bandwidth is dynamically adjusted according to the distribution of the current search results to avoid over- or under-searching. For example, when the concentration density of the search direction increases slowly, the bandwidth can be appropriately increased to speed up the convergence.

[0042] The above-mentioned concentrated value analysis steps provide important data support for the status assessment and risk identification of power terminals. Combining kernel density estimation with bandwidth adaptive adjustment strategy can improve the efficiency and accuracy of analysis and ensure more stable and reliable analysis results.

[0043] The K power terminals are traversed to extract long-term operation data to obtain K long-term operation data sets.

[0044] Specifically, long-term operation data of K power terminals are obtained through long-term monitoring windows (such as 1 hour, 1 day, 1 week, etc.) to analyze the long-term operation trend and health status of the power terminals (such as long-term temperature rise and cumulative changes in mechanical vibration). Among them, long-term operation data has a relatively low collection frequency and a relatively long monitoring window to avoid processing and analysis difficulties caused by excessive data volume.

[0045] Based on the K long time series operation data sets, data segmentation iterative analysis is performed to determine K implicit operation factors.

[0046] In some embodiments, performing segmented iterative analysis based on the K long-time series operation data sets to determine K implicit operation factors includes: According to the time length of the preset monitoring window, the K long time series operation data sets are segmented in a direction away from the preset monitoring window to obtain K long time series segmented operation data clusters. The fluctuation variances of the K long time series segmented operation data clusters are calculated respectively to obtain K segmented fluctuation variance clusters. The K segmented fluctuation variance clusters are weighted calculated according to a preset weight allocation scheme to obtain the K implicit operation factors.

[0047] Specifically, the preset monitoring window is the short-term monitoring window for obtaining the K monitoring operation data sets mentioned above. The preset monitoring window is the time range for data segmentation and serves as the reference point for segmented iterative analysis. When segmenting the long time series data set according to the time length of the preset monitoring window, the data is sequentially segmented in the direction away from the preset monitoring window to form multiple long time series segmented data clusters. In other words, the segmentation direction is from new to old to form K long time series segmented data cluster sets, each of which is a subset of data within a time period.

[0048] Specifically, the fluctuation variance is used to quantify the fluctuation characteristics of each segmented data cluster within the time period to identify the degree of fluctuation and stability of the data. Exemplarily, the fluctuation variance of each segmented data cluster in K long-time segmented operation data clusters is calculated in turn to form K segmented fluctuation variance clusters.

[0049] Specifically, implicit operating factors refer to comprehensive characteristic indicators extracted from long time series data after segmented fluctuation variance analysis and weight allocation. They are used to reflect the potential state or trend of power terminals during long-term operation, and represent characteristic patterns that are not easily detected in the data (such as long-term fluctuation trends, abnormal frequent areas, load aging characteristics, etc.).

[0050] Specifically, a weighted calculation is performed on the segmented fluctuation variance cluster of each power terminal to obtain the implicit operation factor of each power terminal. Preferably, a lower weight is assigned to the segmented fluctuation variance of the time period far away from the current preset monitoring window to reflect the importance of the recent status.

[0051] The above method steps can effectively identify the long-term fluctuation pattern of the power terminal and reveal its implicit operating status through segmented iterative analysis of long time series data, which is helpful for subsequent optimization analysis and decision-making.

[0052] Based on the power terminal distribution network and the K terminal layout locations, neighboring terminal sampling is performed on the K power terminals, and correlation analysis is performed based on the sampling results and the K implicit operating factors to determine K energy efficiency optimization background factors.

[0053] Specifically, the operating status and energy efficiency level of each power terminal are not only affected by itself, but also by its topological position in the power grid, surrounding power terminals and the overall characteristics of the system. Therefore, the power terminal distribution network and its layout location are sampled by neighboring terminals, and combined with the correlation analysis of implicit operating factors to identify the energy efficiency optimization background factors of the power terminal, thereby providing an important reference for subsequent energy efficiency optimization and scheduling strategies. Among them, the energy efficiency optimization background factors represent the systematic factors that affect the energy efficiency level of the power terminal (such as the indicator parameters of the power terminal itself or the associated power terminal), which are jointly determined by the topological position of the power terminal, environmental factors and the correlation characteristics of its implicit operating factors.

[0054] In some embodiments, neighboring terminal sampling is performed on the K power terminals based on the power terminal distribution network and the K terminal layout locations, and association analysis is performed based on the sampling results and the K implicit operation factors to determine K energy efficiency optimization background factors, including: Based on the power terminal distribution network and the K terminal layout locations, the K power terminals are sampled as first-order neighbor terminals to obtain K first-order neighbor terminal sets. Based on the K first-order neighbor terminal sets and the K terminal layout locations, second-order neighbor terminal sampling is performed in the power terminal distribution network to obtain K second-order neighbor terminal sets. Using the K first-order neighbor terminal sets and the K second-order neighbor terminal sets as indexes, the K implicit operating factors are matched to obtain K first-order neighbor implicit operating factor sets and K second-order neighbor implicit operating factor sets. According to the distance to the K power terminals, the K first-order neighbor implicit operating factor sets, the K second-order neighbor implicit operating factor sets and the K implicit operating factors are subjected to association weighted analysis to obtain the K energy efficiency optimization background factors.

[0055] Specifically, first, the neighboring nodes of each power terminal are sampled to identify the spatial correlation characteristics of each power terminal in the power grid to determine its environmental impact range in the power grid and its potential energy efficiency influencing factors. Among them, neighboring nodes refer to other power terminal nodes with a shorter path distance to the target power terminal in the power distribution network. Neighboring nodes can be determined according to physical distance (such as geographic coordinates) or topological distance (such as the shortest path between nodes). Exemplarily, when performing neighbor sampling, the sampling influence range is defined according to a specific sampling strategy (such as setting a distance threshold or a hierarchical threshold).

[0056] Optionally, in the power terminal distribution network, neighbor sampling is performed on each power terminal node. First, each power terminal is traversed to set the current sampling center; then, an adjacent node search algorithm (such as breadth-first search, depth-first search) is used to traverse the first-order neighbor nodes in the network to form K first-order neighbor terminal sets. Then, based on the determined K first-order neighbor terminal sets, each first-order neighbor terminal is used as a sampling center to obtain multiple first-order neighbor nodes of each first-order neighbor terminal, and the output is K second-order neighbor terminal sets.

[0057] Optionally, for each first-order neighbor node and each first-order neighbor node's first-order neighbor node, its attribute data (such as operating status, location attribute, implicit operating factor, etc.) is recorded.

[0058] Furthermore, after completing the sampling of neighboring terminals, a correlation analysis is performed based on the operating status of neighboring nodes and their implicit factors to identify background factors that affect the energy efficiency of power terminals. Exemplarily, a correlation analysis is performed on the implicit operating factors of each power terminal and the implicit factors of its neighboring nodes to obtain the correlation of the implicit factors in spatial distribution and form a correlation matrix of the implicit factors. The correlation matrix of implicit factors characterizes the correlation strength of each power terminal in the energy efficiency impact dimension, that is, it describes the mutual energy efficiency impact relationship between power terminals. Among them, the correlation analysis methods include Pearson correlation coefficient analysis, grey correlation analysis, etc.

[0059] Furthermore, based on the correlation matrix of implicit factors and the operating characteristics of its neighboring terminals, the energy efficiency optimization background factor of each power terminal is constructed. The energy efficiency optimization background factor is a quantitative model of various factors affecting the energy efficiency of the power terminal. In other words, the K energy efficiency optimization background factors define how to quantitatively calculate the energy efficiency levels of K power terminals, so as to accurately identify the energy efficiency level of each power terminal and provide data support for subsequent optimization strategies.

[0060] In some implementations, the first-order neighbor terminal is a terminal that is on the same line and adjacent to the power terminal in the power terminal distribution network. The second-order neighbor terminal is a terminal that is on the same line and adjacent to the first-order neighbor terminal in the power terminal distribution network.

[0061] Specifically, the first-order neighbor terminal refers to the power terminal that is on the same line and adjacent to the target power terminal in the power terminal distribution network. These terminals have the most direct power connection relationship with the target terminal, usually in adjacent geographical locations or on the same physical line, that is, the power transmission path is the shortest, and they may directly share the same power grid branch, so their operating status and fluctuation characteristics have a greater impact on the energy efficiency of the target terminal.

[0062] Specifically, a second-order neighbor terminal refers to a power terminal that is on the same line and adjacent to a first-order neighbor terminal in a power terminal distribution network. In other words, a second-order neighbor terminal is usually indirectly connected to a target terminal, but is still affected by the same line or branch. The impact of a second-order neighbor terminal on the energy efficiency of a target terminal is slightly weaker than that of a first-order neighbor, but because it is on the same line, the abnormal state of a second-order neighbor terminal may still be transmitted to the target terminal through line fluctuations or load changes.

[0063] The acquisition of neighboring terminals based on different levels can more accurately quantify the energy efficiency influencing factors of the target terminal, thereby providing more accurate input data for the construction of energy efficiency optimization background factors and improving the model accuracy of energy efficiency optimization background factors.

[0064] Energy efficiency optimization of the K power terminals is performed according to the K energy efficiency optimization background factors and the K explicit operation concentrated value sets to obtain K energy efficiency optimization schemes.

[0065] Optionally, the objective function of energy efficiency optimization is defined by K energy efficiency optimization background factors, and the parameter selection space of energy efficiency optimization is determined according to the K explicit operation concentrated value sets, and the energy efficiency of K power terminals is optimized by combining optimization algorithms (such as genetic algorithm, particle swarm optimization, echo algorithm, etc.). By taking the background factors as the objective function, the main factors affecting the energy efficiency of power terminals can be more accurately identified, and then a more targeted optimization plan can be formulated.

[0066] Optionally, K energy efficiency optimization background factors are combined through a weighted fusion strategy to form the above objective function, wherein the fusion weight of each energy efficiency optimization background factor is determined based on the importance of the corresponding power terminal, thereby ensuring that the optimization objective function can reasonably reflect the energy efficiency level and priority of the power terminal under different operating conditions. The importance of the power terminal is defined by factors such as the corresponding grid topology position, load level, redundancy and standby, and historical operating performance.

[0067] In summary, the method for optimizing energy efficiency of power terminal equipment for smart grid provided by the present invention has the following technical effects: The distribution network information of the power terminals in the target power grid is obtained, wherein the power terminal distribution network is composed of K power terminals and their corresponding layout positions, and K is an integer not less than 1; based on the sensor integrated array installed on each power terminal, the operation data of each power terminal in the specified monitoring window is extracted to obtain K monitoring operation data sets, wherein each set contains all the operation indicator data in the monitoring window; the K monitoring operation data sets are subjected to concentrated value analysis to generate K explicit operation concentrated value sets; the K power terminals are traversed one by one, their long-time series operation data are extracted, and K long-time series operation data sets are obtained; data segmentation and iterative analysis are performed using the K long-time series operation data sets to identify K implicit operation factors; in combination with the distribution network of the power terminals and their layout positions, neighbor terminal sampling is implemented, and correlation analysis is performed based on the sampling results and the K implicit operation factors to determine K background factors for energy efficiency optimization; finally, based on the K energy efficiency optimization background factors and the K explicit operation concentrated value sets, energy efficiency optimization of the K power terminals is performed, and K corresponding energy efficiency optimization schemes are output. This will achieve the technical effect of improving equipment coordination and adaptability to working conditions and improving energy efficiency performance.

[0068] Embodiment 2 Figure 2 Schematic diagram of the structure of the power terminal equipment energy efficiency optimization device for smart grid of the present invention. For example, Figure 1 The flow chart of the method for optimizing the energy efficiency of power terminal equipment in the smart grid of the present invention can be shown as follows: Figure 2 The structure shown is implemented.

[0069] Based on the same concept as the method for optimizing energy efficiency of power terminal equipment for smart grid in the above embodiment, the present invention also provides a device for optimizing energy efficiency of power terminal equipment for smart grid, including: The distribution network acquisition module 11 is used to acquire the power terminal distribution network of the target power grid, wherein the power terminal distribution network includes K power terminals and K terminal deployment locations, and K is an integer greater than or equal to 1.

[0070] The operation data extraction module 12 is used to extract the operation data of the K power terminals in the preset monitoring window based on the sensor integrated array deployed on each power terminal, and obtain K monitoring operation data sets, wherein each monitoring operation data set includes all the operation data of an operation indicator within the preset monitoring window.

[0071] The concentrated value analysis module 13 is used to perform concentrated value analysis on the K monitoring operation data sets to obtain K explicit operation concentrated value sets.

[0072] The long time series extraction module 14 is used to traverse the K power terminals to extract long time series operation data and obtain K long time series operation data sets.

[0073] The segmented iterative analysis module 15 is used to perform segmented iterative analysis on the K long time series operation data sets to determine K implicit operation factors.

[0074] The background factor positioning module 16 is used to perform neighboring terminal sampling on the K power terminals based on the power terminal distribution network and the K terminal layout locations, and perform correlation analysis based on the sampling results and the K implicit operating factors to determine K energy efficiency optimization background factors.

[0075] The optimization decision module 17 is used to optimize the energy efficiency of the K power terminals according to the K energy efficiency optimization background factors and the K explicit operation concentrated value sets to obtain K energy efficiency optimization solutions.

[0076] The sensor integrated array in the operation data extraction module 12 includes a voltage sensor, a current sensor, a power sensor, a temperature sensor and a vibration sensor.

[0077] In some embodiments, the centralized value analysis module 13 includes The mean calculation unit is used to extract a first monitoring operation data set from the K monitoring operation data sets, and calculate the mean of the first monitoring operation data set to obtain a first monitoring operation mean.

[0078] The concentration density search unit is used to take the first monitoring operation mean as the search center, search in the first monitoring operation data set according to a preset concentration bandwidth, and determine the first search monitoring operation data.

[0079] A concentration density comparison and direction determination unit is used to calculate the concentration density of the first monitoring operation mean and the first search monitoring operation data respectively, and when the concentration density of the first search monitoring operation data is greater than or equal to the concentration density of the first monitoring operation mean, a first search direction is obtained.

[0080] A search update unit is used to update the first search monitoring operation data to a search center, search in the first monitoring operation data set based on the first search direction and according to a preset concentration bandwidth until the concentration density difference between two adjacent searches is less than or equal to a preset concentration density difference, stop the search, and use the search center corresponding to the maximum concentration density during the search process as the target search center, and use the first monitoring operation data corresponding to the target search center as the first explicit operation concentration value set.

[0081] The traversal search unit is used to perform concentrated value analysis on the K monitoring operation data sets according to a preset concentrated bandwidth to obtain the K explicit operation concentrated value sets.

[0082] In some embodiments, the first search direction in the concentration value analysis module 13 is a direction of the first search monitoring operation data relative to the first monitoring operation mean.

[0083] In some implementations, the segmented iterative analysis module 15 includes The long time series data segmentation unit is used to segment the K long time series operation data sets in a direction away from the preset monitoring window according to the time length of the preset monitoring window to obtain K long time series segmented operation data clusters.

[0084] The volatility variance calculation unit is used to calculate the volatility variances of the K long-time series segmented operation data clusters respectively to obtain K segmented volatility variance clusters.

[0085] The implicit operating factor determination unit is used to perform weighted calculation on the K segmented volatility variance clusters according to a preset weight allocation scheme to obtain the K implicit operating factors.

[0086] In some embodiments, the background factor location module 16 includes: The first-order neighbor terminal sampling unit is used to perform first-order neighbor terminal sampling on the K power terminals based on the power terminal distribution network and the K terminal layout positions to obtain K first-order neighbor terminal sets.

[0087] The second-order neighbor terminal sampling unit is used to perform second-order neighbor terminal sampling in the power terminal distribution network based on the K first-order neighbor terminal sets and the K terminal layout positions to obtain K second-order neighbor terminal sets.

[0088] The implicit operation factor matching unit is used to match the K implicit operation factors with the K first-order neighbor terminal sets and the K second-order neighbor terminal sets as indexes to obtain K first-order neighbor implicit operation factor sets and K second-order neighbor implicit operation factor sets.

[0089] The association weighted analysis unit is used to perform association weighted analysis on the K first-order neighbor implicit operating factor sets, the K second-order neighbor implicit operating factor sets and the K implicit operating factors according to the distances to the K power terminals, so as to obtain the K energy efficiency optimization background factors.

[0090] In some implementations, the first-order neighbor terminal in the background factor positioning module 16 is a terminal that is on the same line and adjacent to the power terminal in the power terminal distribution network. The second-order neighbor terminal is a terminal that is on the same line and adjacent to the first-order neighbor terminal in the power terminal distribution network.

[0091] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to the energy efficiency optimization device for power terminal equipment for smart grids described in embodiment two. For the sake of brevity of the specification, they will not be further elaborated here.

[0092] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for optimizing energy efficiency of power terminal equipment for smart grid, characterized in that: The method comprises: Acquire a power terminal distribution network of a target power grid, wherein the power terminal distribution network includes K power terminals and K terminal layout locations, where K is an integer greater than or equal to 1; Based on the sensor integrated array arranged on each power terminal, extract the operating data of the K power terminals in the preset monitoring window to obtain K monitoring operating data sets, wherein each monitoring operating data set includes all operating data of an operating indicator in the preset monitoring window; Performing concentrated value analysis on the K monitoring operation data sets to obtain K explicit operation concentrated value sets; Traversing the K power terminals to extract long-term operation data, and obtaining K long-term operation data sets; Performing segmented iterative analysis on the K long-time series operation data sets to determine K implicit operation factors; Based on the power terminal distribution network and the K terminal layout locations, neighboring terminal sampling is performed on the K power terminals, and association analysis is performed based on the sampling results and the K implicit operation factors to determine K energy efficiency optimization background factors; Energy efficiency optimization of the K power terminals is performed according to the K energy efficiency optimization background factors and the K explicit operation concentrated value sets to obtain K energy efficiency optimization schemes.

2. The method according to claim 1, characterized in that The sensor integrated array includes a voltage sensor, a current sensor, a power sensor, a temperature sensor and a vibration sensor.

3. The method according to claim 1, characterized in that Performing concentrated value analysis on the K monitoring operation data sets to obtain K explicit operation concentrated value sets, including: Extracting a first monitoring operation data set from the K monitoring operation data sets, and calculating a mean of the first monitoring operation data set to obtain a first monitoring operation mean; Taking the first monitoring operation mean as the search center, searching in the first monitoring operation data set according to a preset concentrated bandwidth to determine first search monitoring operation data; respectively calculating the concentration density of the first monitoring operation mean and the first search monitoring operation data, and obtaining a first search direction when the concentration density of the first search monitoring operation data is greater than or equal to the concentration density of the first monitoring operation mean; Update the first search monitoring operation data to a search center, search in the first monitoring operation data set based on the first search direction and according to a preset concentration bandwidth until the concentration density difference between two adjacent searches is less than or equal to the preset concentration density difference, stop searching, and use the search center corresponding to the maximum concentration density during the search process as the target search center, and use the first monitoring operation data corresponding to the target search center as the first explicit operation concentration value set; The K monitoring operation data sets are subjected to centralized value analysis according to a preset centralized bandwidth to obtain the K explicit operation centralized value sets.

4. The method according to claim 3, characterized in that The first search direction is a direction of the first search monitoring operation data relative to the first monitoring operation mean.

5. The method according to claim 1, characterized in that Based on the K long time series operation data sets, data segmentation iterative analysis is performed to determine K implicit operation factors, including: According to the time length of the preset monitoring window, the K long time series operation data sets are segmented in a direction away from the preset monitoring window to obtain K long time series segmented operation data clusters; Calculating the fluctuation variances of the K long-time series segmented operation data clusters respectively to obtain K segmented fluctuation variance clusters; The K segmented volatility variance clusters are weightedly calculated according to a preset weight allocation scheme to obtain the K implicit operating factors.

6. The method according to claim 1, characterized in that Based on the power terminal distribution network and the K terminal layout locations, neighboring terminal sampling is performed on the K power terminals, and association analysis is performed based on the sampling results and the K implicit operation factors to determine K energy efficiency optimization background factors, including: Based on the power terminal distribution network and the K terminal layout locations, the K power terminals are sampled as first-order neighbor terminals to obtain K first-order neighbor terminal sets; Based on the K first-order neighbor terminal sets and the K terminal layout locations, second-order neighbor terminal sampling is performed in the power terminal distribution network to obtain K second-order neighbor terminal sets; Using the K first-order neighbor terminal sets and the K second-order neighbor terminal sets as indexes, matching the K implicit operating factors to obtain K first-order neighbor implicit operating factor sets and K second-order neighbor implicit operating factor sets; According to the distances to the K power terminals, an associated weighted analysis is performed on the K first-order neighbor implicit operating factor sets, the K second-order neighbor implicit operating factor sets and the K implicit operating factors to obtain the K energy efficiency optimization background factors.

7. The method according to claim 6, characterized in that include: The first-order neighbor terminal is a terminal that is on the same line and adjacent to the power terminal in the power terminal distribution network; The second-order neighbor terminal is a terminal that is located on the same line and adjacent to the first-order neighbor terminal in the power terminal distribution network.

8. An energy efficiency optimization device for power terminal equipment used in smart grid, characterized in that: The device is used to execute the method for optimizing energy efficiency of power terminal equipment for smart grid according to any one of claims 1 to 7, and the device comprises: A distribution network acquisition module, the distribution network acquisition module is used to acquire a power terminal distribution network of a target power grid, wherein the power terminal distribution network includes K power terminals and K terminal layout locations, where K is an integer greater than or equal to 1; An operation data extraction module, the operation data extraction module is used to extract the operation data of the K power terminals in a preset monitoring window based on the sensor integrated array arranged on each power terminal, and obtain K monitoring operation data sets, wherein each monitoring operation data set includes all operation data of an operation indicator in the preset monitoring window; A concentrated value analysis module, the concentrated value analysis module is used to perform concentrated value analysis on the K monitoring operation data sets to obtain K explicit operation concentrated value sets; A long time series extraction module, the long time series extraction module is used to traverse the K power terminals to extract long time series operation data and obtain K long time series operation data sets; A segmented iterative analysis module, the segmented iterative analysis module is used to perform segmented iterative analysis of data based on the K long time series operation data sets to determine K implicit operation factors; A background factor positioning module, the background factor positioning module is used to perform neighbor terminal sampling on the K power terminals based on the power terminal distribution network and the K terminal layout locations, and perform association analysis based on the sampling results and the K implicit operation factors to determine K energy efficiency optimization background factors; An optimization decision module, wherein the optimization decision module is used to optimize the energy efficiency of the K power terminals according to the K energy efficiency optimization background factors and the K explicit operation concentrated value sets, and obtain K energy efficiency optimization solutions.

Images