Distributed energy and load similarity matching method and device based on time sequence characteristics

Abstract

The invention relates to a time sequence characteristic-based distributed energy and load similarity matching method and device. The method comprises the following steps: collecting distributed energy current information and load current information of each switch in the power distribution network through a feeder terminal unit in the power distribution network; determining a distributed energy time sequence according to the current data of the distributed energy at different time points, and determining a load time sequence according to the current data of the electrical load at different time points; performing variation trend analysis on the distributed energy time sequence and the load time sequence to determine trend similarity, and performing sequence shape analysis on the distributed energy time sequence and the load time sequence to determine shape similarity; and according to the trend similarity and the shape similarity, determining a similarity matching result of the distributed energy and the electrical load. By adopting the method, the similarity matching accuracy of the distributed energy and the load can be improved.

Description

Technical Field

[0001] The present application relates to the field of smart grid technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for matching distributed energy and load similarity based on timing characteristics. Background Art

[0002] With the increasing global energy shortage and climate change problems, how to use energy for power transmission more efficiently and environmentally friendly has become a core issue in the energy field. At present, using clean energy to generate electricity and realizing distributed power supply close to the user end has gradually become an important direction to solve this problem. However, the large-scale access of distributed power sources (such as photovoltaic, wind power and other clean energy) has posed new challenges to the safe operation and efficient management of distribution networks. In this context, the distributed energy and load similarity matching technology came into being, aiming to improve the ability of distribution networks to accept and utilize the power generated by distributed power sources, more reasonably balance the characteristics of the power supply side and the load side of the distribution network, and improve the safety and reliability of power supply. However, the current distributed energy and load similarity matching methods often rely on single, static load characteristics for matching (such as load size), resulting in low accuracy in the similarity matching of distributed energy and load. Summary of the invention

[0003] Based on this, it is necessary to provide a distributed energy and load similarity matching method, device, computer equipment, computer-readable storage medium and computer program product based on timing characteristics, which can improve the accuracy of similarity matching between distributed energy and load, in order to address the above technical problems.

[0004] In a first aspect, the present application provides a method for matching distributed energy and load similarity based on time series characteristics, including:

[0005] Collecting distributed energy current information and load current information of each switch in the distribution network through a feeder terminal unit in the distribution network; the distributed energy current information includes current data of distributed energy at different time points, and the load current information includes current data at different time points according to the power load;

[0006] Determine the distributed energy time series according to the current data of the distributed energy at different time points, and determine the load time series according to the current data of the power load at different time points;

[0007] Performing a change trend analysis on the distributed energy time series and the load time series to determine trend similarity, and performing a sequence shape analysis on the distributed energy time series and the load time series to determine shape similarity;

[0008] A similarity matching result between the distributed energy source and the power load is determined according to the trend similarity and the shape similarity.

[0009] In one embodiment, the distributed energy time series is expressed as: , is the power data determined according to the current data of the distributed energy at time point i; the load time series is expressed as: , The power data is determined based on the current data of the power load at time point j; the sequence shape analysis of the distributed energy time series and the load time series to determine the shape similarity includes:

[0010] According to the power difference between the distributed energy time series and the load time series at corresponding time points, determine The distance matrix of represents the power difference between the i-th point of the distributed energy time series and the j-th point of the load time series;

[0011] Determining the shape similarity according to the distance matrix;

[0012] Among them, the elements of the distance matrix It is expressed as:

[0013] .

[0014] In one embodiment, determining the shape similarity according to the distance matrix includes:

[0015] Finding an optimal path from the starting point to the end point of the distance matrix so that the cumulative distance of the optimal path is minimized; the starting point is the element position at the upper left corner of the distance matrix, and the end point is the element position at the lower right corner of the distance matrix;

[0016] determining the shape similarity according to the cumulative distance of the optimal path;

[0017] The cumulative distance of the optimal path is expressed as:

[0018] ;

[0019] The DTW is the cumulative distance of the optimal path. is the element position contained in the optimal path, The element position in the distance matrix is , k is the length of the optimal path.

[0020] In one embodiment, the finding of the optimal path from the starting point to the end point of the distance matrix includes:

[0021] Construct a cumulative distance matrix;

[0022] By using the cumulative distance matrix, the minimum cumulative distance from the starting point of the distance matrix to any element position of the distance matrix is ​​calculated until any element position reaches the end point of the distance matrix, thereby obtaining the cumulative distance of the optimal path;

[0023] Determine the optimal path from the starting point to the end point of the distance matrix based on the corresponding element positions of the cumulative distance of the optimal path in the distance matrix;

[0024] Wherein, the cumulative distance matrix is ​​expressed as:

[0025] ;

[0026] Said Represents the distance matrix from the starting point to the current element position of the distance matrix The minimum cumulative distance of The smaller it is, the higher the trend similarity between the distributed energy time series and the load time series represented by the trend similarity is.

[0027] In one embodiment, determining the distributed energy time series according to the current data of the distributed energy at different time points, and determining the load time series according to the current data of the power load at different time points, includes:

[0028] According to the current data of the distributed energy at different time points, the distributed energy generation power corresponding to multiple time periods in a scheduling cycle is determined, and according to the distributed energy generation power corresponding to the multiple time periods, the distributed energy time series is determined; wherein the distributed energy time series is expressed as: , the distributed energy time series is the distributed energy generation power in time period i; It is expressed as: , is the power generation of wind farm j in time period i, is the number of wind farms, is the power generation of photovoltaic power station k in time period i, is the number of photovoltaic power plants;

[0029] According to the current data of the power load at different time points, the load power corresponding to multiple time periods in one scheduling cycle is determined, and according to the load power corresponding to the multiple time periods, the load time series is determined; wherein the load time series is expressed as: , the load time series is the load power consumption in time period i.

[0030] In one embodiment, the performing change trend analysis on the distributed energy time series and the load time series to determine trend similarity includes:

[0031] Determine a similarity index between the distributed energy and the power load according to the covariance of the distributed energy generation power and the load power, the variance of the distributed energy generation power and the variance of the load power;

[0032] Determining the trend similarity according to the similarity index;

[0033] Wherein, the similarity index is expressed as:

[0034] ;

[0035] Said is the similarity index, is the covariance of the distributed energy generation power and the load power, is the variance of the distributed energy generation power, is the variance of the load power consumption.

[0036] In a second aspect, the present application also provides a distributed energy and load similarity matching device based on time series characteristics, comprising:

[0037] An acquisition module is used to collect distributed energy current information and load current information of each switch in the distribution network through a feeder terminal unit in the distribution network; the distributed energy current information includes current data of distributed energy at different time points, and the load current information includes current data at different time points according to the power load;

[0038] A sequence determination module, used to determine the distributed energy time sequence according to the current data of the distributed energy at different time points, and to determine the load time sequence according to the current data of the power load at different time points;

[0039] A similarity determination module is used to perform a change trend analysis on the distributed energy time series and the load time series to determine trend similarity, and to perform a sequence shape analysis on the distributed energy time series and the load time series to determine shape similarity;

[0040] A matching module is used to determine a similarity matching result between the distributed energy and the power load according to the trend similarity and the shape similarity.

[0041] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0043] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0044] The above-mentioned distributed energy and load similarity matching method, device, computer equipment, computer-readable storage medium and computer program product based on time series characteristics collect distributed energy current information and load current information of each switch in the distribution network through the feeder terminal unit in the distribution network; the distributed energy current information includes the current data of the distributed energy at different time points, and the load current information includes the current data according to the power load at different time points; the distributed energy time series is determined according to the current data of the distributed energy at different time points, and the load time series is determined according to the current data of the power load at different time points; the distributed energy time series and the load time series are analyzed for change trends to determine trend similarity, and the distributed energy time series and the load time series are analyzed for sequence shape to determine shape similarity; based on the trend similarity and shape similarity, the similarity matching result between the distributed energy and the power load is determined. By acquiring the current data of distributed energy and loads at different time points and constructing a time series, it is possible to consider the dynamic changes of distributed energy generation and load power consumption in the time dimension. In addition, by comprehensively considering the changing trend characteristics and shape characteristics of the time series, a multi-dimensional evaluation of the similarity between distributed energy and loads is achieved, thereby improving the accuracy of the similarity matching between distributed energy and loads, thereby improving the ability of the distribution network to accept and utilize the electricity generated by distributed power sources. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is an application environment diagram of a method for matching distributed energy and load similarity based on time series characteristics in one embodiment;

[0047] Figure 2 A schematic diagram of a flow chart of a method for matching distributed energy and load similarity based on time series characteristics in one embodiment;

[0048] Figure 3 It is a structural block diagram of a distributed energy source and load similarity matching device based on time sequence characteristics in one embodiment;

[0049] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] The distributed energy and load similarity matching method based on time series characteristics provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown.

[0052] Among them, the distribution network control system 102 is the command and dispatch center of the distribution network 104, responsible for monitoring, data analysis, fault detection, load dispatch and distributed energy management of the distribution network 104. The distribution network control system 102 is connected to the distribution network 104, monitors the operating status of the entire distribution network 104, and obtains real-time data of the distribution network 104. Specifically, the distribution network control system 102 is connected to the feeder terminal unit 106 and each switch 108 in the distribution network 104. The distribution network control system 102 can issue control instructions to the feeder terminal unit 106, and receive current information and switch status information collected by the feeder terminal unit 106. The distribution network control system 102 can achieve grid fault isolation and recovery by remotely controlling the on and off states of the switches 108.

[0053] The distribution network 104 is a physical infrastructure for the transmission and distribution of electric energy, including substations, transmission lines, switchgear, etc. The distribution network 104 includes a feeder terminal unit 106 and switches 108. The feeder terminal unit 106 is used to be distributed on the distribution line for data collection and status monitoring; each switch 108 is used to control the on and off of the current to ensure the safe operation of the distribution network 104. For example, the switch 108 can control the access and removal of the distributed energy 110, and can also control the power supply switch of the power load 112. The distribution network 104 can be connected to the distributed energy 110, and the distributed energy 110 is connected to the distribution network 104 to provide electricity to users; the distribution network 104 can be connected to the power load 112, and the user's electrical equipment obtains electricity from the distribution network 104.

[0054] Distributed energy 110 may include photovoltaic, wind power and other new energy generation devices to provide power for distribution network 104. Power load 112 may include power equipment on the user side, including industrial, commercial, residential and other loads. Power load 112 is connected to distribution network 104 and obtains power from distribution network 104.

[0055] The distribution network control system 102 collects distributed energy current information and load current information of each switch 108 in the distribution network 104 through the feeder terminal unit 106 in the distribution network 104; the distributed energy current information includes current data of the distributed energy 110 at different time points, and the load current information includes current data of the power load 112 at different time points; the distributed energy time series is determined according to the current data of the distributed energy 110 at different time points, and the load time series is determined according to the current data of the power load 112 at different time points; the distributed energy time series and the load time series are analyzed for change trends to determine trend similarity, and the distributed energy time series and the load time series are analyzed for sequence shape to determine shape similarity; based on the trend similarity and shape similarity, the similarity matching result between the distributed energy 110 and the power load 112 is determined.

[0056] In an exemplary embodiment, Figure 2 As shown in the figure, a method for matching distributed energy and load similarity based on time series characteristics is provided. Figure 1 The distribution network control system 102 in FIG. 1 is used as an example for explanation, including:

[0057] Step S202: collecting distributed energy current information and load current information of each switch in the distribution network through the feeder terminal unit in the distribution network.

[0058] The distributed energy current information includes the current data of the distributed energy at different time points, and the load current information includes the current data of the power load at different time points.

[0059] Among them, the feeder terminal unit (FTU) is responsible for collecting current information of each switch in the distribution network. The feeder terminal unit is a device installed on the distribution line with data collection and monitoring functions. It can monitor the current data of distributed energy and loads in the distribution network in real time.

[0060] Among them, the distributed energy current information includes the current data of distributed energy (such as photovoltaic, wind power, etc.) at different time points, reflecting the changes in the output current of distributed energy at different times.

[0061] The load current information includes the current data of the power load at different time points, which reflects the power consumption situation on the user side and the changes in load demand at different times.

[0062] Distributed energy current information and load current information are time-series, which provides a basis for subsequent analysis of the dynamic characteristics of distributed energy and loads.

[0063] Step S204, determining a distributed energy time series according to the current data of the distributed energy at different time points, and determining a load time series according to the current data of the power load at different time points.

[0064] Optionally, the distributed energy time series may include the current data of the distributed energy at each time point arranged in time sequence; the load time series may include the current data of the power load at each time point arranged in time sequence. Alternatively, the distributed energy time series may include the power data of the distributed energy at each time point arranged in time sequence, and the load time series may include the power data of the power load at each time point arranged in time sequence.

[0065] In the specific implementation, the current data at different time points in the distributed energy time series or load time series can be connected into a continuous curve, which is equivalent to the time point as the horizontal axis and the current data as the vertical axis, which can intuitively reflect the trend of current change over time. Therefore, the distributed energy time series and the load time series can be regarded as a curve respectively.

[0066] Step S206, performing a change trend analysis on the distributed energy time series and the load time series to determine trend similarity, and performing a sequence shape analysis on the distributed energy time series and the load time series to determine shape similarity.

[0067] The change trend analysis may include analyzing the increase and decrease trends of the distributed energy time series and the load time series on the time axis. For example, assuming that the distributed energy time series and the load time series include current data at each time point, the distributed energy time series and the load time series are analyzed for change trends to determine trend similarity, which may be to compare the consistency of the current change direction between the two, for example, to compare whether they rise or fall at the same time in the same time period to obtain trend similarity, so as to determine whether the change patterns of the two in power supply and power demand are consistent.

[0068] Among them, the sequence shape analysis may include analyzing the similarity between the distributed energy time series and the load time series in the overall fluctuation form, including the amplitude, frequency and shape of the fluctuation. Exemplarily, assuming that the distributed energy time series and the load time series include current data at each time point, the distributed energy time series and the load time series are subjected to sequence shape analysis to determine the shape similarity, which may be to determine whether the two are consistent in the overall current change form, such as whether the positions of the fluctuation peaks and valleys and the amplitude of the fluctuations are similar, so as to obtain the shape similarity.

[0069] Step S208: Determine the similarity matching result between the distributed energy and the power load according to the trend similarity and the shape similarity.

[0070] Among them, trend similarity can be used to reflect whether the increase and decrease trends of distributed energy time series and load time series in the time dimension are consistent; shape similarity can be used to reflect the similarity between distributed energy time series and load time series in the overall fluctuation shape.

[0071] As an example, based on trend similarity and shape similarity, the similarity matching result between distributed energy and power load can be determined by setting weights or thresholds, and determining the evaluation value of trend similarity and the evaluation value of shape similarity, wherein the higher the evaluation value, the higher the similarity, and then weighted calculation is performed on the evaluation values ​​corresponding to the trend similarity and shape similarity, respectively, to obtain a comprehensive similarity score to determine the similarity matching result. For example, if the comprehensive similarity score is greater than a certain threshold, it can be determined that the similarity matching degree between distributed energy and power load is high; if the comprehensive similarity score is less than a certain threshold, it can be determined that the similarity matching degree between distributed energy and power load is low.

[0072] As another example, the similarity matching result between distributed energy and power load is determined based on trend similarity and shape similarity. When the trend similarity is high and the shape similarity is also high, the similarity matching result between distributed energy and power load is determined to be high in similarity matching degree.

[0073] In the above-mentioned distributed energy and load similarity matching method based on time series characteristics, the distributed energy current information and load current information of each switch in the distribution network are collected through the feeder terminal unit in the distribution network; the distributed energy current information includes the current data of the distributed energy at different time points, and the load current information includes the current data according to the power load at different time points; the distributed energy time series is determined according to the current data of the distributed energy at different time points, and the load time series is determined according to the current data of the power load at different time points; the distributed energy time series and the load time series are analyzed for change trends to determine trend similarity, and the distributed energy time series and the load time series are analyzed for sequence shape to determine shape similarity; based on the trend similarity and shape similarity, the similarity matching result of the distributed energy and the power load is determined. By acquiring the current data of distributed energy and loads at different time points and constructing a time series, it is possible to consider the dynamic changes of distributed energy generation and load power consumption in the time dimension. In addition, by comprehensively considering the changing trend characteristics and shape characteristics of the time series, a multi-dimensional evaluation of the similarity between distributed energy and loads is achieved, thereby improving the accuracy of the similarity matching between distributed energy and loads, thereby improving the ability of the distribution network to accept and utilize the electricity generated by distributed power sources.

[0074] In another embodiment, the distributed energy time series is represented as: , is the power data determined based on the current data of distributed energy at time point i; the load time series is expressed as: , The power data is determined based on the current data of the power load at time point j; the distributed energy time series and the load time series are analyzed for sequence shape to determine the shape similarity, including: determining the power difference between the distributed energy time series and the load time series at the corresponding time points The distance matrix of represents the power difference between the i-th point of the distributed energy time series and the j-th point of the load time series; according to the distance matrix, the shape similarity is determined; among which, the elements of the distance matrix It is expressed as:

[0075] .

[0076] In specific implementation, Dynamic Time Warping (DTW) is a method for comparing the similarity of two time series. Dynamic Time Warping uses dynamic programming to find the best matching path between two sequences and calculates the cumulative distance between them. In DTW, the smaller the cumulative distance, the more similar the two sequences are in shape. The cumulative distance is the accumulation of the local distances between all corresponding points on the matching path of the two time series. If the shapes of the two sequences are similar, then during the matching process, the local distance between each corresponding point is small, so the total accumulated distance is also small. Therefore, the smaller the cumulative distance, the more similarities the two time series have in morphology, that is, the overall shape is closer.

[0077] In the specific implementation, the shape similarity of the distributed energy time series and the load time series can be calculated through the distance matrix. For example, methods such as dynamic time warping (DTW) can be used to find the optimal matching path between the two sequences on the distance matrix, and the shape similarity can be measured based on the cumulative distance of the path. The smaller the cumulative distance, the higher the similarity in shape between the two sequences.

[0078] The technical solution of this embodiment constructs a distance matrix between the distributed energy time series and the load time series, and evaluates their shape similarity based on power difference, providing a quantitative basis for subsequent similarity matching. This method can effectively improve the accuracy and applicability of matching, and is suitable for the dynamic matching needs of distributed energy and load.

[0079] In another embodiment, determining shape similarity according to a distance matrix includes: finding an optimal path from a starting point to an end point of the distance matrix so that the cumulative distance of the optimal path is minimized; the starting point is the element position at the upper left corner of the distance matrix, and the end point is the element position at the lower right corner of the distance matrix; determining shape similarity according to the cumulative distance of the optimal path; wherein the cumulative distance of the optimal path is expressed as:

[0080] ;

[0081] DTW is the cumulative distance of the optimal path, is the element position contained in the optimal path, The position of the element in the distance matrix is The corresponding element is , and k is the length of the optimal path.

[0082] In a specific implementation, the shape similarity between the distributed energy time series and the load time series can be determined based on a dynamic time warping method of a distance matrix.

[0083] Among them, the starting point of the distance matrix is ​​the upper left corner element position of the distance matrix, which represents the power difference between the first point of the distributed energy time series and the first point of the load time series.

[0084] Among them, the end point of the distance matrix is ​​the position of the lower right corner element of the distance matrix, which represents the power difference between the last point of the distributed energy time series and the last point of the load time series.

[0085] in, is the distance matrix element corresponding to each position on the path, that is, the power difference between the distributed energy time series and the load time series at that point.

[0086] In the distance matrix, there are many possible paths from the starting point to the end point. The optimal path refers to the path with the smallest cumulative distance among all the paths. The shape similarity of the distributed energy time series and the load time series is measured by calculating the cumulative distance of the optimal path. The smaller the cumulative distance, the higher the shape similarity of the two time series.

[0087] The technical solution of this embodiment uses the dynamic time warping (DTW) method to find the optimal matching path between two time series on the distance matrix, and measures their shape similarity by cumulative distance. This method can flexibly adapt to the fluctuation characteristics of time series and provide accurate and reliable similarity results for the matching analysis of distributed energy and loads.

[0088] In another embodiment, finding the optimal path from the starting point to the end point of the distance matrix includes: constructing a cumulative distance matrix; calculating the minimum cumulative distance from the starting point of the distance matrix to any element position of the distance matrix through the cumulative distance matrix, until any element position reaches the end point of the distance matrix, and obtaining the cumulative distance of the optimal path; determining the optimal path from the starting point to the end point of the distance matrix based on each element position corresponding to the cumulative distance of the optimal path in the distance matrix; wherein the cumulative distance matrix is ​​expressed as:

[0089] ;

[0090] Represents the distance from the starting point of the distance matrix to the current element position of the distance matrix The minimum cumulative distance of The smaller it is, the higher the trend similarity between the distributed energy time series and the load time series represented by the trend similarity is.

[0091] In the specific implementation, the optimal path from the starting point to the end point of the distance matrix can be found by constructing and calculating the cumulative distance matrix, and the trend similarity can be determined by the cumulative distance of the path. The cumulative distance matrix is ​​calculated by dynamic programming based on the distance matrix, and each element Represents the distance from the starting point (upper left corner) to the current element position in the distance matrix The minimum cumulative distance.

[0092] in, Indicates that the path with the smallest cumulative distance is selected in the three directions (upper left corner, above, and left) of a certain location. Find a path from the starting point (upper left corner) to the end point (lower right corner) of the cumulative distance matrix that minimizes the cumulative distance. This path is the optimal path.

[0093] The technical solution of this embodiment determines the trend similarity of the distributed energy time series and the load time series by constructing a cumulative distance matrix and calculating the optimal path from the starting point to the end point. The smallest cumulative distance indicates that the two are closer in increase and decrease mode, which helps to optimize the matching analysis of distributed energy and load in the distribution network.

[0094] In another embodiment, the distributed energy time series is determined according to the current data of the distributed energy at different time points, and the load time series is determined according to the current data of the power load at different time points, including: determining the distributed energy generation power corresponding to multiple time periods in a scheduling cycle according to the current data of the distributed energy at different time points, and determining the distributed energy time series according to the distributed energy generation power corresponding to the multiple time periods; wherein the distributed energy time series is expressed as: , in the distributed energy time series is the distributed energy generation power in time period i; It is expressed as: , is the power generation of wind farm j in time period i, is the number of wind farms, is the power generation of photovoltaic power station k in time period i, is the number of photovoltaic power stations; according to the current data of the power load at different time points, the load power corresponding to multiple time periods in a scheduling cycle is determined, and according to the load power corresponding to multiple time periods, the load time series is determined; wherein the load time series is expressed as: , in the load time series is the load power consumption in time period i.

[0095] In a specific implementation, the method for determining the distributed energy time series may include obtaining the current data of the distributed energy at different time points, and calculating the distributed energy power generation according to the voltage data at each time point; converting the current data into power generation, dividing it into multiple time periods according to the scheduling cycle, and calculating the corresponding distributed energy power generation for each time period. In addition, for distributed energy, the power generation of wind farms and photovoltaic power stations is calculated and the total power generation for each time period is obtained as the distributed energy power generation corresponding to each time period to determine the distributed energy time series.

[0096] In a specific implementation, the method for determining the load time series may include obtaining current data of the power load at different time points, and calculating the load power consumption based on the voltage data at each time point; converting the load current data into power consumption, dividing it into multiple time periods according to the scheduling cycle, and calculating the corresponding load power consumption in each time period.

[0097] The technical solution of this embodiment collects the current data of distributed energy and load, converts it into the corresponding power generation and power consumption, and constructs a time series to dynamically analyze the matching of power supply and power consumption. This method helps to optimize the grid dispatch, improve the new energy consumption capacity, and ensure the stability and reliability of the grid power supply. Through matching analysis, the consumption capacity of distributed energy such as wind power and photovoltaic power is optimized, and the utilization rate of new energy is improved.

[0098] In some embodiments, the distributed energy time series and the load time series are analyzed for change trends to determine trend similarity, including: determining a similarity index between the distributed energy and the power load according to the covariance of the distributed energy generation power and the load power, the variance of the distributed energy generation power and the variance of the load power; determining trend similarity according to the similarity index; wherein the similarity index is expressed as:

[0099] ;

[0100] is the similarity index, is the covariance of distributed energy generation power and load power consumption, is the variance of distributed energy generation power, is the variance of load power consumption.

[0101] Among them, the similarity index is a statistical index used to measure the strength and direction of the linear relationship between two sets of data. It can reflect the consistency of the change trend of the two time series, that is, the similarity of their increase and decrease patterns. The similarity index evaluates whether their trends are consistent by measuring the relative change direction of the two sets of data at each time point. If the fluctuations of the two time series show similar rising and falling patterns in time, their similarity index will be close to 1. The closer the similarity index is to 1, the higher the trend similarity. Even if the values ​​of the two sets of data are different, as long as the patterns and directions of their changes on the time axis are similar, the similarity index can capture this consistency. In addition, the similarity index standardizes the data, eliminates the influence of the value size and unit, and only focuses on the change trend of the data. In summary, trend similarity can be measured by the similarity index of distributed energy generation power and load power consumption.

[0102] The technical solution of this embodiment measures the trend similarity of distributed energy generation power and load power consumption in the time dimension by calculating the similarity index of the two, which can help the distribution network to perform intelligent scheduling and optimize supply and demand matching, thereby improving the stability of the power grid and its ability to absorb new energy.

[0103] In other embodiments, after determining the similarity matching results between distributed energy and power loads according to trend similarity and shape similarity, the method further includes: determining the weight coefficient of each power load according to the similarity matching results between distributed energy and power loads; and determining the load recovery priority of each power load according to the weight coefficient. The higher the similarity matching degree represented by the similarity matching result, the greater the weight coefficient; the greater the weight coefficient, the higher the load recovery priority.

[0104] In the distribution network, islanding means dividing the power grid into several areas (i.e. islands) that can operate independently in an emergency to improve power supply reliability. In any divided island, the power load with a higher similarity to the distributed power source can be restored first based on the similarity matching results.

[0105] When the distributed power source is far away from the important power load, we cannot blindly pursue the recovery of the important power load, but should introduce a weight coefficient to give different priorities to each level of power load. The weight coefficient can be determined according to the similarity matching results. Different weight coefficients can be set for the power loads in the same island to further refine the optimization goal, the goal is to maximize the recovery ability of the power load. The objective function can be expressed as:

[0106] ;

[0107] Where n is the number of islands into which the distribution network is divided; m is the number of power load nodes in the island numbered i; is the active load of the power load node numbered j in island i; is the weight coefficient of the power load numbered j in island i.

[0108] At the same time, the number of operating circuit breakers is optimized through the objective function to simplify the process and improve efficiency. The objective function can be expressed as:

[0109] ;

[0110] Where n is the number of isolated islands; The number of circuit breakers that need to be operated to disconnect the island numbered i from the system. This objective function is used to optimize the number of operated circuit breakers.

[0111] Distributed power sources with close electrical distance can operate together to supply power to the loads in the same island, while power sources with long distance should be divided into independent islands. The objective function can be expressed as:

[0112] ;

[0113] Where, b is the number of branches in the distribution network; is the breaking coefficient of branch i, which is 1 for closing and 0 for opening; is the resistance of branch i; is the active power flowing through the end of branch i; is the reactive power flowing through the end of branch i; is the voltage at the end of branch i. This objective function is used to minimize the power loss of the power grid.

[0114] In the technical solution of this embodiment, the similarity matching result can be used as an important basis for the load recovery strategy in the isolated island, helping to improve the reliability and efficiency of the distribution network operation.

[0115] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0116] Based on the same inventive concept, the embodiment of the present application also provides a distributed energy and load similarity matching device based on timing characteristics for implementing the above-mentioned distributed energy and load similarity matching method based on timing characteristics. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the distributed energy and load similarity matching device based on timing characteristics provided below can refer to the limitations of the distributed energy and load similarity matching method based on timing characteristics in the above text, and will not be repeated here.

[0117] In an exemplary embodiment, Figure 3 As shown, a distributed energy and load similarity matching device based on time sequence characteristics is provided, comprising:

[0118] The acquisition module 310 is used to collect the distributed energy current information and load current information of each switch in the distribution network through the feeder terminal unit in the distribution network; the distributed energy current information includes the current data of the distributed energy at different time points, and the load current information includes the current data at different time points according to the power load.

[0119] The sequence determination module 320 is used to determine the distributed energy time sequence according to the current data of the distributed energy at different time points, and to determine the load time sequence according to the current data of the power load at different time points.

[0120] The similarity determination module 330 is used to perform a change trend analysis on the distributed energy time series and the load time series to determine trend similarity, and to perform a sequence shape analysis on the distributed energy time series and the load time series to determine shape similarity.

[0121] The matching module 340 is used to determine the similarity matching result between the distributed energy and the power load according to the trend similarity and the shape similarity.

[0122] In one embodiment, the distributed energy time series is expressed as: , is the power data determined according to the current data of the distributed energy at time point i; the load time series is expressed as: , is the power data determined according to the current data of the power load at time point i; the similarity determination module 330 is specifically used to determine the power difference between the distributed energy time series and the load time series at corresponding time points. The distance matrix of represents the power difference between the i-th point of the distributed energy time series and the j-th point of the load time series; according to the distance matrix, the shape similarity is determined; wherein the elements of the distance matrix It is expressed as: .

[0123] In one embodiment, the similarity determination module 330 is specifically used to find the optimal path from the starting point to the end point of the distance matrix so that the cumulative distance of the optimal path is minimized; the starting point is the element position at the upper left corner of the distance matrix, and the end point is the element position at the lower right corner of the distance matrix; the shape similarity is determined according to the cumulative distance of the optimal path; wherein the cumulative distance of the optimal path is expressed as: ; The DTW is the cumulative distance of the optimal path, the is the element position contained in the optimal path, The element position in the distance matrix is , k is the length of the optimal path.

[0124] In one embodiment, the similarity determination module 330 is specifically used to construct a cumulative distance matrix; through the cumulative distance matrix, the minimum cumulative distance from the starting point of the distance matrix to any element position of the distance matrix is ​​calculated until the any element position reaches the end point of the distance matrix, and the cumulative distance of the optimal path is obtained; based on the corresponding element positions of the cumulative distance of the optimal path in the distance matrix, the optimal path from the starting point to the end point of the distance matrix is ​​determined; wherein the cumulative distance matrix is ​​expressed as: ; Represents the distance matrix from the starting point to the current element position of the distance matrix The minimum cumulative distance of The smaller it is, the higher the trend similarity between the distributed energy time series and the load time series represented by the trend similarity is.

[0125] In one embodiment, the sequence determination module 320 is specifically used to determine the distributed energy generation power corresponding to multiple time periods in a scheduling cycle according to the current data of the distributed energy at different time points, and determine the distributed energy time series according to the distributed energy generation power corresponding to the multiple time periods; wherein the distributed energy time series is expressed as: , the distributed energy time series is the distributed energy generation power in time period i; It is expressed as: , is the power generation of wind farm j in time period i, is the number of wind farms, is the power generation of photovoltaic power station k in time period i, is the number of photovoltaic power stations; according to the current data of the power load at different time points, the load power corresponding to multiple time periods in one scheduling cycle is determined, and according to the load power corresponding to the multiple time periods, the load time series is determined; wherein the load time series is expressed as: , the load time series is the load power consumption in time period i.

[0126] In one embodiment, the similarity determination module 330 is specifically used to determine the similarity index between the distributed energy and the power load according to the covariance of the distributed energy generation power and the load power, the variance of the distributed energy generation power and the variance of the load power; determine the trend similarity according to the similarity index; wherein the similarity index is expressed as:

[0127] ;

[0128] Said is the similarity index, is the covariance of the distributed energy generation power and the load power, is the variance of the distributed energy generation power, is the variance of the load power consumption.

[0129] Each module in the above-mentioned distributed energy and load similarity matching device based on timing characteristics can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0130] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a distributed energy and load similarity matching method based on timing characteristics is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0131] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0132] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0133] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0134] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0135] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0136] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0137] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0138] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for matching distributed energy and load similarity based on time series characteristics, characterized in that: The method comprises: Collecting distributed energy current information and load current information of each switch in the distribution network through a feeder terminal unit in the distribution network; the distributed energy current information includes current data of distributed energy at different time points, and the load current information includes current data at different time points according to the power load; Determine the distributed energy time series according to the current data of the distributed energy at different time points, and determine the load time series according to the current data of the power load at different time points; Performing a change trend analysis on the distributed energy time series and the load time series to determine trend similarity, and performing a sequence shape analysis on the distributed energy time series and the load time series to determine shape similarity; A similarity matching result between the distributed energy source and the power load is determined according to the trend similarity and the shape similarity.

2. The method according to claim 1, characterized in that: The distributed energy time series is expressed as: , is the power data determined according to the current data of the distributed energy at time point i; the load time series is expressed as: , is power data determined according to the current data of the power load at time point j; The performing sequence shape analysis on the distributed energy time series and the load time series to determine shape similarity includes: According to the power difference between the distributed energy time series and the load time series at corresponding time points, determine The distance matrix of represents the power difference between the i-th point of the distributed energy time series and the j-th point of the load time series; Determining the shape similarity according to the distance matrix; Among them, the elements of the distance matrix It is expressed as: 。 3. The method according to claim 2, characterized in that Determining the shape similarity according to the distance matrix includes: Finding an optimal path from the starting point to the end point of the distance matrix so that the cumulative distance of the optimal path is minimized; the starting point is the element position at the upper left corner of the distance matrix, and the end point is the element position at the lower right corner of the distance matrix; Determining the shape similarity according to the cumulative distance of the optimal path; The cumulative distance of the optimal path is expressed as: ； The DTW is the cumulative distance of the optimal path. is the element position contained in the optimal path, The element position in the distance matrix is , k is the length of the optimal path.

4. The method according to claim 3, characterized in that The step of finding the optimal path from the starting point to the end point of the distance matrix comprises: Construct a cumulative distance matrix; By using the cumulative distance matrix, the minimum cumulative distance from the starting point of the distance matrix to any element position of the distance matrix is ​​calculated until any element position reaches the end point of the distance matrix, thereby obtaining the cumulative distance of the optimal path; Determine the optimal path from the starting point to the end point of the distance matrix based on the positions of the elements corresponding to the cumulative distances of the optimal path in the distance matrix; Wherein, the cumulative distance matrix is ​​expressed as: ； Said Represents the distance matrix from the starting point to the current element position of the distance matrix The minimum cumulative distance of The smaller it is, the higher the trend similarity between the distributed energy time series and the load time series represented by the trend similarity is.

5. The method according to claim 1, characterized in that The step of determining the distributed energy time series according to the current data of the distributed energy at different time points, and determining the load time series according to the current data of the power load at different time points, comprises: According to the current data of the distributed energy at different time points, the distributed energy generation power corresponding to multiple time periods in a scheduling cycle is determined, and according to the distributed energy generation power corresponding to the multiple time periods, the distributed energy time series is determined; wherein the distributed energy time series is expressed as: , the distributed energy time series is the distributed energy generation power in time period i; It is expressed as: , is the power generation of wind farm j in time period i, is the number of wind farms, is the power generation of photovoltaic power station k in time period i, is the number of photovoltaic power plants; According to the current data of the power load at different time points, the load power corresponding to multiple time periods in one scheduling cycle is determined, and according to the load power corresponding to the multiple time periods, the load time series is determined; wherein the load time series is expressed as: , the load time series is the load power consumption in time period i.

6. The method according to claim 5, characterized in that The performing change trend analysis on the distributed energy time series and the load time series to determine trend similarity includes: Determine a similarity index between the distributed energy and the power load according to the covariance of the distributed energy generation power and the load power, the variance of the distributed energy generation power and the variance of the load power; Determining the trend similarity according to the similarity index; Wherein, the similarity index is expressed as: ； Said is the similarity index, is the covariance of the distributed energy generation power and the load power, is the variance of the distributed energy generation power, is the variance of the load power consumption.

7. A distributed energy and load similarity matching device based on time series characteristics, characterized in that: The device comprises: An acquisition module is used to collect distributed energy current information and load current information of each switch in the distribution network through a feeder terminal unit in the distribution network; the distributed energy current information includes current data of distributed energy at different time points, and the load current information includes current data at different time points according to the power load; A sequence determination module, used to determine the distributed energy time sequence according to the current data of the distributed energy at different time points, and to determine the load time sequence according to the current data of the power load at different time points; A similarity determination module is used to perform a change trend analysis on the distributed energy time series and the load time series to determine trend similarity, and to perform a sequence shape analysis on the distributed energy time series and the load time series to determine shape similarity; A matching module is used to determine a similarity matching result between the distributed energy and the power load according to the trend similarity and the shape similarity.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images