Concentrator intelligent fusion terminal based on multi-source fusion data regulation and control

Abstract

The invention relates to the technical field of data processing, in particular to a concentrator intelligent fusion terminal based on multi-source fusion data regulation and control, the terminal comprises a processor and a memory, and the processor executes a computer program of the memory to realize the following steps: for any equipment acquired by a concentrator, acquiring a data fusion moment, for any data fusion moment, obtaining a multi-dimensional electric energy data sequence; recording the multi-dimensional electric energy data at any data fusion moment as multi-dimensional target electric energy data, and obtaining the electric energy use degree of the electric energy data of each dimension according to the data difference in the multi-dimensional electric energy data sequence; acquiring a fusion weight of the electric energy data of each dimension according to data fluctuation characteristics in the multi-dimensional electric energy data sequence; according to the electric energy use degree and the fusion weight of the electric energy data of each dimension in the multi-dimensional target electric energy data, the fusion data of any data fusion moment is obtained, and the operation overhead is reduced while more accurate multi-source fusion data is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to an intelligent fusion terminal for a concentrator based on multi-source fusion data regulation. Background Art

[0002] With the large-scale access of new loads such as distributed photovoltaics and electric vehicle charging piles, the distribution network faces dual challenges of insufficient holographic perception ability and weak intelligent regulation ability. The multi-source data fusion technology can break through the limitations of a single data source and extract more complete and accurate information by integrating data from multiple types of devices such as smart meters, low-voltage circuit breakers, reactive power compensation devices, and electric vehicle charging piles. For example, the concentrator collects data from devices such as smart meters and sensors, and through multi-source data fusion regulation, realizes real-time monitoring and analysis of user electricity consumption behavior, which helps power companies with load forecasting, electricity bill settlement, anti-theft electricity, etc., and improves the intelligent level of power services.

[0003] Traditional multi-source data fusion methods usually adopt a weighted fusion algorithm with fixed weights to obtain multi-source fusion data. However, the data obtained by the concentrator is diverse, and the data sources mainly come from, for example, electricity consumption data of different residents, multiple sensor data, etc., and there is a possibility of dynamic increase, decrease, or change in the data sources. Therefore, traditional multi-source data fusion methods lack dynamic self-adaptability, resulting in unsatisfactory fusion results and multi-source fusion data that cannot accurately reflect the electricity consumption situation of users; at the same time, the large amount of data in the concentrator leads to a large computational load, increasing the operating overhead of the concentrator.

[0004] Therefore, how to adaptively obtain the dynamic weights of each data, obtain more accurate multi-source fusion data while adaptively adjusting the frequency of multi-source data fusion, and reduce the operating overhead has become an urgent problem to be solved. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide an intelligent fusion terminal for a concentrator based on multi-source fusion data regulation to solve the problem of how to adaptively obtain the dynamic weights of each data, obtain more accurate multi-source fusion data while adaptively adjusting the frequency of multi-source data fusion, and reduce the operating overhead.

[0006] An intelligent fusion terminal for a concentrator based on multi-source fusion data regulation is provided in an embodiment of the present invention, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the following method is implemented: For any device collected by the concentrator, obtain the data fusion frequency according to the preset power consumption frequency. According to the data fusion frequency, obtain at least two data fusion moments. For any data fusion moment, obtain the multi-dimensional power data of the any device at each moment to obtain the multi-dimensional power data sequence at the any data fusion moment. The multi-dimensional power data includes current data, voltage data, and power consumption data; Denote the multi-dimensional power data at the any data fusion moment as multi-dimensional target power data. According to the data differences of the multi-dimensional power data in the multi-dimensional power data sequence, obtain the power usage degree of each dimension of power data in the multi-dimensional target power data; According to the fluctuation characteristics of the multi-dimensional power data in the multi-dimensional power data sequence, obtain the power quality score of each dimension of power data in the multi-dimensional target power data. According to the power quality scores of each dimension of power data in the multi-dimensional target power data, obtain the fusion weight of each dimension of power data in the multi-dimensional target power data; According to the power usage degree and fusion weight of each dimension of power data in the multi-dimensional target power data, obtain the fusion data of the any device at the any data fusion moment, and obtain the fusion data of each device collected by the concentrator at each data fusion moment for the concentrator to perform regulation.

[0007] Preferably, the obtaining the power usage degree of each dimension of power data in the multi-dimensional target power data according to the data differences of the multi-dimensional power data in the multi-dimensional power data sequence includes: In the multi-dimensional power data sequence, obtain two multi-dimensional power data with a power consumption data difference of 0 and the moments corresponding to them being closest to the any data fusion moment. The data between the two multi-dimensional power data and the two multi-dimensional power data form a reference subsequence; For any dimension of power data in the multi-dimensional target power data, obtain the initial usage degree reference value of the any dimension of power data according to the fluctuation characteristics of the multi-dimensional power data in the reference subsequence; Obtain the absolute value of the difference between the any dimension of power data and the initial usage degree reference value of the any dimension of power data to obtain the usage difference. Obtain the addition result of the usage difference and the constant 1. According to the difference between the constant 1 and the reciprocal of the addition result, obtain the power usage degree of the any dimension of power data.

[0008] Preferably, the obtaining the initial usage degree reference value of the any dimension of power data according to the fluctuation characteristics of the multi-dimensional power data in the reference subsequence includes: If any of the dimensional power data belongs to current data, obtain the mean value of the current data in the reference subsequence as the initial usage degree reference value of the any-dimensional power data; If any of the dimensional power data belongs to voltage data, obtain the mean value of the voltage data in the reference subsequence as the initial usage degree reference value of the any-dimensional power data; If any of the dimensional power data belongs to power consumption data, set the initial usage degree reference value of the any-dimensional power data to 0.

[0009] Preferably, obtaining the power quality score of each dimensional power data in the multi-dimensional target power data according to the fluctuation characteristics of the multi-dimensional power data in the multi-dimensional power data sequence includes: For any dimensional power data in the multi-dimensional target power data, obtain the power data belonging to the same dimension as the any-dimensional power data in the multi-dimensional power data sequence, and construct a target sequence with a first preset length with the any-dimensional power data as the last data; Average the target sequence into at least two target subsequences with a second preset length, and the second preset length is less than the first preset length; According to the data fluctuation characteristics of the target sequence and the data fluctuation characteristics of each target subsequence, obtain the power quality score of the any-dimensional power data in the multi-dimensional target power data.

[0010] Preferably, obtaining the power quality score of the any-dimensional power data in the multi-dimensional target power data according to the data fluctuation characteristics of the target sequence and the data fluctuation characteristics of each target subsequence includes: If any of the dimensional power data belongs to current data or voltage data, for any target subsequence, obtain the variance of the target subsequence, calculate the difference between the constant 1 and the reciprocal of the variance, and obtain the fluctuation degree of the any target subsequence; Number the target subsequences in the target sequence according to time, obtain the sum result of the numbers of all target subsequences to get the total number value, and calculate the ratio of the number of the any target subsequence to the total number value to obtain the fluctuation weight of the fluctuation degree of the any target subsequence; Obtain the fluctuation degree and its weight of each target subsequence respectively, and perform weighted summation on the fluctuation degrees of all target subsequences to obtain the total fluctuation degree; Denote the degree of fluctuation of the target subsequence including the electric energy data of any one of the dimensions as the real-time fluctuation degree, perform weighted summation on the real-time fluctuation degree and the total fluctuation degree to obtain the fluctuation index of the electric energy data of any one of the dimensions, and calculate the difference between the constant 1 and the fluctuation index to obtain the power quality score of the electric energy data of any one of the dimensions in the multi-dimensional target electric energy data.

[0011] Preferably, the obtaining the power quality score of the electric energy data of any one of the dimensions in the multi-dimensional target electric energy data according to the data fluctuation characteristics of the target sequence and the data fluctuation characteristics of each target subsequence further includes: If the electric energy data of any one of the dimensions belongs to the electricity quantity data, fit the target sequence to obtain a target fitting curve, and obtain the fitting value of each electric energy data in the target sequence on the target fitting curve; For any electric energy data in the target sequence, obtain the absolute value of the difference between the any electric energy data and its fitting value to obtain the deviation degree of the any electric energy data, and obtain the average value of the reciprocals of the deviation degrees of each electric energy data in the target sequence to obtain the power quality usage index of the target sequence; Denote the target subsequence including the electric energy data of any one of the dimensions as the real-time subsequence, and obtain the power quality usage index of the real-time subsequence; Perform weighted summation on the power quality usage index of the target sequence and the power quality usage index of the real-time subsequence to obtain the power quality score of the electric energy data of any one of the dimensions in the multi-dimensional target electric energy data.

[0012] Preferably, the obtaining the fusion weight of the electric energy data of each dimension in the multi-dimensional target electric energy data according to the power quality score of the electric energy data of each dimension in the multi-dimensional target electric energy data includes: Obtain the cumulative value of the power quality scores of the electric energy data of each dimension in the multi-dimensional target electric energy data to obtain the total power quality score; Respectively obtain the ratio of the power quality score of the electric energy data of each dimension in the multi-dimensional target electric energy data to the total power quality score to obtain the fusion weight of the electric energy data of each dimension in the multi-dimensional target electric energy data.

[0013] Preferably, the obtaining the fusion data of any device at any data fusion moment according to the power usage degree and the fusion weight of the electric energy data of each dimension in the multi-dimensional target electric energy data includes: Taking the fusion weight of each - dimensional power data in the multi - dimensional target power data as the weight coefficient of the power usage degree of each - dimensional power data in the multi - dimensional target power data, perform a weighted sum of the power usage degrees of each - dimensional power data in the multi - dimensional target power data to obtain the fusion data of any device at any data fusion moment.

[0014] Preferably, the obtaining the data fusion frequency according to the preset power consumption frequency includes: Dividing the moments collected by the concentrator into at least two power consumption intervals according to the power consumption demand. For any power consumption interval, obtain the time length and average power consumption of the any power consumption interval; Obtain the reciprocal of the time length, denoted as the time index. Obtain the difference between the constant 1 and the reciprocal of the average power consumption to get the power consumption index. Obtain the mean value between the time index and the power consumption index to get the frequency weight. Obtain the product of the frequency weight and the preset power consumption frequency to get the data fusion frequency of the any power consumption interval.

[0015] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows: In the embodiments of the present invention, for any device collected by the concentrator, obtain the data fusion frequency according to the preset power consumption frequency. According to the data fusion frequency, obtain at least two data fusion moments. For any data fusion moment, obtain the multi - dimensional power data of the any device at each moment to obtain the multi - dimensional power data sequence at the any data fusion moment. The multi - dimensional power data includes current data, voltage data, and power consumption data. Denote the multi - dimensional power data at the any data fusion moment as multi - dimensional target power data. According to the data differences of the multi - dimensional power data in the multi - dimensional power data sequence, obtain the power usage degree of each - dimensional power data in the multi - dimensional target power data. According to the fluctuation characteristics of the multi - dimensional power data in the multi - dimensional power data sequence, obtain the power quality score of each - dimensional power data in the multi - dimensional target power data. According to the power quality score of each - dimensional power data in the multi - dimensional target power data, obtain the fusion weight of each - dimensional power data in the multi - dimensional target power data. According to the power usage degree and fusion weight of each - dimensional power data in the multi - dimensional target power data, obtain the fusion data of the any device at the any data fusion moment, and obtain the fusion data of each device collected by the concentrator at each data fusion moment for the concentrator to perform regulation. Among them, obtaining the data fusion frequency according to the preset power consumption frequency reduces the operation cost of the concentrator; by obtaining the power quality score, convert the power data of different dimensions into score data of the same form, and at the same time obtain the dynamic adaptive fusion weight according to the power quality score to obtain the fusion data, so that the fusion data can more accurately reflect the usage degree of the integrated power grid and the corresponding data status. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of a concentrator intelligent fusion method based on multi-source fusion data regulation provided in Embodiment 1 of the present invention. Specific embodiments

[0018] The following will describe in detail the embodiments of the present disclosure, and the examples of the embodiments are shown in the drawings. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present disclosure, and should not be construed as a limitation of the present disclosure.

[0019] It should be noted that the terms "first", "second", etc. in the specification of the present disclosure and the above drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0020] To illustrate the technical solutions of the present invention, the following will be described through specific embodiments.

[0021] The embodiment of the present invention provides a concentrator intelligent fusion terminal based on multi-source fusion data regulation, including a processor and a memory. The processor executes the computer program of the memory to implement a concentrator intelligent fusion method based on multi-source fusion data regulation, as Figure 1 shown. The method includes the following steps: Step S101, for any device collected by the concentrator, obtain the data fusion frequency according to the preset power consumption frequency. According to the data fusion frequency, obtain at least two data fusion times. For any data fusion time, obtain the multi-dimensional power data of the any device at each time to obtain the multi-dimensional power data sequence of the any data fusion time. The multi-dimensional power data includes current data, voltage data, and power consumption data.

[0022] With the large-scale access of new types of loads such as distributed photovoltaics and electric vehicle chargers, the distribution network faces the dual challenges of insufficient holographic perception ability and weak intelligent regulation ability. The multi-source data fusion technology can break through the limitations of a single data source and extract more complete and accurate information by integrating data from various devices such as smart meters, low-voltage circuit breakers, reactive power compensation devices, and electric vehicle chargers. For example, the concentrator collects data from devices such as smart meters and sensors, and through multi-source data fusion regulation, realizes the real-time monitoring and analysis of users' electricity consumption behaviors, which helps power companies with load forecasting, electricity bill settlement, anti-theft of electricity, etc., and improves the intelligent level of power services.

[0023] The scenario targeted by the embodiments of the present invention is a concentrator terminal with residential electricity consumption as the main data source. Traditional multi-source data fusion methods usually adopt a weighted fusion algorithm with fixed weights to obtain multi-source fusion data. However, the data types obtained by the concentrator are diverse, and the data sources mainly come from, for example, electricity consumption data of different residents, multiple sensor data, etc. There is a possibility of dynamic increase, decrease, or change in the data sources. Therefore, traditional multi-source data fusion methods lack dynamic self-adaptability, resulting in unsatisfactory fusion results and multi-source fusion data that cannot accurately reflect users' electricity consumption situations. At the same time, the large amount of data in the concentrator leads to a large computational load, increasing the operating overhead of the concentrator.

[0024] Therefore, in this embodiment, first, the data fusion frequency is obtained according to the preset electricity consumption frequency to reduce the operating overhead of the concentrator. Then, by obtaining the power quality score, the electrical energy data in different dimensions is converted into score data of the same form. At the same time, the dynamic adaptive fusion weight is obtained according to the power quality score, and finally, the fusion data is obtained, so that the fusion data can more accurately reflect the usage degree of the integrated power grid and the corresponding data status, and further enable the concentrator to perform more accurate regulation.

[0025] The core parameters in the power system are current, voltage, and electricity quantity. These three types of data can all represent the usage degree of the power grid to a certain extent. Therefore, in this embodiment, for any device collected by the concentrator, the current data, voltage data, and electricity quantity data of any device collected by the concentrator at each moment are obtained to form multi-dimensional electrical energy data at each moment.

[0026] The residential electricity consumption is theoretically calculated from voltage and current. However, in practice, there may be deviations between the electricity consumption and current / voltage. These deviations are mainly affected by various factors such as measurement errors, equipment characteristics, power grid fluctuations, and data acquisition and processing methods. For example, insufficient sampling frequency of the electricity meter may fail to capture rapidly changing current and voltage, resulting in calculation deviations of electricity consumption; electronic devices (such as variable-frequency air conditioners and LED lights) generate harmonic currents, making the electricity meter inaccurate; inductive loads (such as motors) cause current to lag behind voltage. If the power factor is not compensated by the electricity meter, the calculated electricity consumption will be too high; unstable power grid voltage (such as voltage drop during peak electricity consumption periods) affects the actual power, but the voltage meter usually calculates based on the rated voltage, leading to deviations; the time difference between the electricity meter and the concentrator may cause misalignment of electricity consumption data, etc. Therefore, the analysis of electricity consumption based on a single data point is not comprehensive and accurate enough. It is necessary to obtain fused data to more accurately reflect the degree of power grid usage and the corresponding data status.

[0027] Since obtaining fused data incurs resource consumption, if calculations are performed at every moment, it will lead to high operating overhead of the concentrator. Therefore, according to the actual situation of residential electricity consumption, the frequency of obtaining fused data can be adjusted to reduce the operating overhead.

[0028] Since there are peak and off-peak periods in residential electricity consumption, according to the electricity consumption demand and habits of residents, the moments collected by the concentrator are divided into different electricity consumption intervals, namely peak and off-peak periods. During the peak period, the frequency of obtaining fused data can be increased. During the off-peak period, the number of calculation nodes for the fusion task can be reduced, and fused data can be obtained in fixed inspection electricity and other scenarios to ensure data real-time while reducing the operating overhead.

[0029] Since the duration and electricity consumption of each electricity consumption interval are different, for any electricity consumption interval, the duration and average electricity consumption of any electricity consumption interval can be obtained. Based on the duration and average electricity consumption of any electricity consumption interval, and the preset electricity consumption frequency, the data fusion frequency can be obtained.

[0030] Among them, the method for obtaining the data fusion frequency based on the duration and average electricity consumption of any electricity consumption interval, and the preset electricity consumption frequency is as follows: Obtain the reciprocal of the duration, denoted as the time index. Obtain the difference between the constant 1 and the reciprocal of the average electricity consumption to get the electricity consumption index. Obtain the mean between the time index and the electricity consumption index to get the frequency weight. Obtain the product of the frequency weight and the preset electricity consumption frequency to get the data fusion frequency of any electricity consumption interval.

[0031] In an embodiment, taking the peak period as an example, the peak period is generally 4 hours, and the average electricity consumption is 10 degrees. Then the calculation formula for the data fusion frequency during the peak period is:f where f is the data fusion frequency during the peak electricity consumption period, 4 is the time length of the peak electricity consumption period, and 10 is the average electricity consumption during the peak electricity consumption period. is the preset electricity consumption frequency (i.e., the maximum frequency during the peak electricity consumption period), which needs to be set according to the actual situation and is not limited here. It can be set according to the specific implementation scenario.

[0032] Furthermore, according to the data fusion frequency, at least two data fusion moments for which data fusion is required are obtained. The main purpose of the present invention is to obtain fused data. For any data fusion moment, multi-dimensional power data of any device at each moment is obtained. The multi-dimensional power data at each moment between the any data fusion moment and its previous data fusion moment forms a multi-dimensional power data sequence for the any data fusion moment, which is used to analyze the fused data of any device at any data fusion moment. Among them, the last multi-dimensional power data in the multi-dimensional power data sequence belongs to the multi-dimensional power data collected at the any data fusion moment. In this embodiment, the acquisition frequency of the multi-dimensional power data is set to once per second, which is not limited here and can be set according to the specific implementation scenario.

[0033] Step S102: Denote the multi-dimensional power data at the any data fusion moment as multi-dimensional target power data, and obtain the electricity usage degree of each dimension of power data in the multi-dimensional target power data according to the data difference of the multi-dimensional power data in the multi-dimensional power data sequence.

[0034] When performing data fusion, since the data formats of current, voltage, and electricity quantity are inconsistent and cannot be directly fused, but these three types of data can all reflect the electricity usage degree. Therefore, the corresponding electricity usage degree can be obtained according to the characteristics of each type of data itself. Among them, the main manifestation of the current data during power grid use is that the current instantaneously increases (possibly exceeding the rated current), then returns to the normal value and remains stable, with possible slight fluctuations; the voltage behaves similarly, but the voltage is low during the peak electricity consumption period and high during the low electricity consumption period; the cumulative electricity quantity keeps increasing. Therefore, the method for obtaining the electricity usage degree of each dimension of power data in the multi-dimensional target power data according to the data difference of the multi-dimensional power data in the multi-dimensional power data sequence is as follows: (1) Obtain the voltage and current values when the residential electricity consumption is 0 as the reference values when the usage degree is 0.

[0035] Specifically, in the multi-dimensional power data sequence, obtain two multi-dimensional power data with a zero electricity quantity data difference and the moments corresponding to them being closest to the any data fusion moment. The data between the two multi-dimensional power data and the two multi-dimensional power data form a reference subsequence. For any dimensional electrical energy data in the multi-dimensional target electrical energy data, if the any-dimensional electrical energy data belongs to current data, obtain the average value of the current data in the reference subsequence as the initial usage degree reference value of the any-dimensional electrical energy data; If the any-dimensional electrical energy data belongs to voltage data, obtain the average value of the voltage data in the reference subsequence as the initial usage degree reference value of the any-dimensional electrical energy data; If the any-dimensional electrical energy data belongs to power consumption data, set the initial usage degree reference value of the any-dimensional electrical energy data to 0.

[0036] (2) Obtain the absolute value of the difference between the any-dimensional electrical energy data and the initial usage degree reference value of the any-dimensional electrical energy data to obtain a usage difference, obtain the sum result of the usage difference and the constant 1, and obtain the electrical energy usage degree of the any-dimensional electrical energy data according to the difference between the constant 1 and the reciprocal of the sum result.

[0037] In an embodiment, taking the voltage data in the multi-dimensional target electrical energy data as an example, the calculation formula for the electrical energy usage degree of the voltage data is:

[0038] Where, is the electrical energy usage degree of the voltage data; V is the voltage data in the multi-dimensional target electrical energy data; is the initial usage degree reference value of the voltage data in the multi-dimensional target electrical energy data; 1 is a constant; is the absolute value symbol.

[0039] It should be noted that the greater the difference between the voltage data in the multi-dimensional target electrical energy data and its initial usage degree reference value, the more electricity is consumed, and the greater the electrical energy usage degree of the voltage data.

[0040] Similarly, obtain the electrical energy usage degree of each dimensional electrical energy data in the multi-dimensional target electrical energy data.

[0041] Step S103, according to the fluctuation characteristics of the multi-dimensional electrical energy data in the multi-dimensional electrical energy data sequence, obtain the power quality score of each dimensional electrical energy data in the multi-dimensional target electrical energy data, and obtain the fusion weight of each dimensional electrical energy data in the multi-dimensional target electrical energy data according to the power quality score of each dimensional electrical energy data in the multi-dimensional target electrical energy data.

[0042] Due to the lack of dynamic self - adaptability in traditional multi - source data fusion methods, the obtained fusion results are not ideal, and the multi - source fusion data cannot accurately reflect the user's power consumption situation. Therefore, according to the fluctuation characteristics of multi - dimensional power data in the multi - dimensional power data sequence, the power quality score of each dimension of power data in the multi - dimensional target power data can be obtained to reflect the data quality of each power data. Furthermore, according to the power quality scores of each dimension of power data in the multi - dimensional target power data, the fusion weight of each dimension of power data in the multi - dimensional target power data can be obtained, so as to obtain the fusion data.

[0043] Since voltage and current data usually remain in a relatively stable state, their power quality scores mainly depend on the volatility of the data, while the power consumption data is a variable quantity, and its power quality score mainly depends on the trend stability of the data. Therefore, for any dimension of power data in the multi - dimensional target power data, power data belonging to the same dimension as the any - dimension power data can be obtained in the multi - dimensional power data sequence. Taking the any - dimension power data as the last data, a target sequence with a first preset length of 30 minutes (power data collected within 30 minutes, that is, including 1800 power data) is constructed; the target sequence is evenly divided into at least two target subsequences with a second preset length of 60 seconds (power data collected within 60 seconds, that is, including 60 power data). There is no limit here and it can be set according to the specific implementation scenario; according to the data fluctuation characteristics of the target sequence and the data fluctuation characteristics of each target subsequence, the power quality score of any dimension of power data in the multi - dimensional target power data is obtained.

[0044] If any dimension of power data belongs to current data or voltage data, the method for obtaining the power quality score of any dimension of power data is as follows: For any target subsequence, obtain the variance of the target subsequence, calculate the difference between the constant 1 and the reciprocal of the variance to obtain the fluctuation degree of the any - target subsequence; Number the target subsequences in the target sequence according to time, obtain the sum result of the numbers of all target subsequences to get the total number value, calculate the ratio of the number of the any - target subsequence to the total number value to obtain the fluctuation weight of the fluctuation degree of the any - target subsequence; Respectively obtain the fluctuation degree and its weight of each target subsequence, and perform weighted summation on the fluctuation degrees of all target subsequences to obtain the total fluctuation degree; Record the fluctuation degree of the target subsequence including the any - dimension power data as the real - time fluctuation degree, perform weighted summation on the real - time fluctuation degree and the total fluctuation degree to obtain the fluctuation index of the any - dimension power data, and calculate the difference between the constant 1 and the fluctuation index to obtain the power quality score of the any - dimension power data in the multi - dimensional target power data.

[0045] In one embodiment, taking the voltage data in the multi-dimensional target power data as an example, the calculation formula for the power quality score of the voltage data is:

[0046] Wherein, is the power quality score of the voltage data; is the variance of the last target subsequence in the target sequence (i.e., the target subsequence containing the voltage data in the multi-dimensional target power data); is the variance of the i-th target subsequence in the target sequence; M is the number of target subsequences in the target sequence; is the weight coefficient of the real-time fluctuation degree, is the weight coefficient of the total fluctuation degree. Since the fluctuation of the voltage data at the current time (any data fusion moment) is more important, in this embodiment, is set, Here, there is no limitation, and it can be set according to the specific implementation scenario.

[0047] It should be noted that, is the fluctuation degree of the i-th target subsequence in the target sequence, The larger, the more unstable the power data in the i-th target subsequence in the target sequence, that is, the stronger the fluctuation, and there may be interference or equipment quality problems in the power data, and the data quality is low, the larger, and then the smaller; is the fluctuation weight of the fluctuation degree of the i-th target subsequence in the target sequence. The larger i is, the closer the i-th target subsequence is to the voltage data in the multi-dimensional target power data, and the smaller the time decay, the larger, and then the smaller.

[0048] If any dimension of the power data belongs to the power quantity data, the method for obtaining the power quality score of any dimension of the power data is as follows: Fit the target sequence to obtain a target fitting curve, and respectively obtain the fitting value of each power data in the target sequence on the target fitting curve. Obtaining the fitting curve belongs to the prior art and will not be elaborated here; For any power data in the target sequence, obtain the absolute value of the difference between the any power data and its fitting value to obtain the deviation degree of the any power data, and obtain the average value of the reciprocals of the deviation degrees of each power data in the target sequence to obtain the power quality usage index of the target sequence; Denote the target subsequence including any dimension of the power data as the real-time subsequence, and obtain the power quality usage index of the real-time subsequence; Perform a weighted sum of the power quality usage metrics of the target sequence and the power quality usage metrics of the real-time subsequence to obtain the power quality score of the power data in any dimension of the multi-dimensional target power data.

[0049] In one embodiment, the calculation formula for the power quality score of power consumption data is:

[0050] Where, is the power quality score of the power consumption data; is the j-th power consumption data in the real-time subsequence; is the fitted value of the j-th power consumption data in the real-time subsequence; N is the number of power consumption data in the real-time subsequence; is the k-th power consumption data in the target sequence; is the fitted value of the k-th power consumption data in the target sequence; T is the number of power consumption data in the target sequence; is the weight coefficient of the power quality usage metric of the real-time subsequence, is the weight coefficient of the power quality usage metric of the target sequence. Since the degree of change deviation of the power consumption data at the current time (any data fusion moment) is more important, in this embodiment, , , which is not limited here and can be set according to the specific implementation scenario; is the absolute value symbol.

[0051] It should be noted that, is the power quality usage metric of the target sequence, indicating the quality of the power consumption during the time corresponding to the target sequence. The larger it is, the greater the deviation between the power consumption data in the target sequence and its fitted value. The smaller it is, and then The smaller it is.

[0052] Furthermore, the method for obtaining the fusion weight of the power data in each dimension of the multi-dimensional target power data according to the power quality score of the power data in each dimension of the multi-dimensional target power data is as follows: Obtain the cumulative value of the power quality scores of the power data in each dimension of the multi-dimensional target power data to obtain the total power quality score; Respectively obtain the ratio of the power quality score of the power data in each dimension of the multi-dimensional target power data to the total power quality score to obtain the fusion weight of the power data in each dimension of the multi-dimensional target power data.

[0053] In one embodiment, taking the power data in the h-th dimension of the multi-dimensional target power data as an example, the calculation formula for the fusion weight of the power data in the h-th dimension of the multi-dimensional target power data is:

[0054] Among them, is the fusion weight of the power data in the h-th dimension of the multi-dimensional target power data; is the power quality score of the power data in the h-th dimension of the multi-dimensional target power data; 3 is the total number of dimensions in the multi-dimensional target power data.

[0055] It should be noted that the larger, the better the data quality of the power data in the h-th dimension of the multi-dimensional target power data, the larger it will be.

[0056] Similarly, the fusion weight of the power data in each dimension of the multi-dimensional target power data is obtained.

[0057] Step S104, according to the power usage degree and fusion weight of the power data in each dimension of the multi-dimensional target power data, obtain the fusion data of any device at any data fusion moment, and obtain the fusion data of each device collected by the concentrator at each data fusion moment for the concentrator to perform regulation.

[0058] In step S103, the fusion weight of the power data in each dimension of the multi-dimensional target power data is obtained, and in step S102, the power usage degree of the power data in each dimension of the multi-dimensional target power data is obtained. Further, the fusion data corresponding to the multi-dimensional target power data can be obtained according to the power usage degree and fusion weight of the power data in each dimension of the multi-dimensional target power data.

[0059] Among them, the method for obtaining the fusion data corresponding to the multi-dimensional target power data according to the power usage degree and fusion weight of the power data in each dimension of the multi-dimensional target power data is as follows: Take the fusion weight of the power data in each dimension of the multi-dimensional target power data as the weight coefficient of the power usage degree of the power data in each dimension of the multi-dimensional target power data, and perform weighted summation on the power usage degree of the power data in each dimension of the multi-dimensional target power data to obtain the fusion data corresponding to the multi-dimensional target power data.

[0060] In an embodiment, the calculation formula for the fusion data corresponding to the multi-dimensional target power data is:

[0061] Among them, is the fusion data corresponding to the multi-dimensional target power data; is the fusion weight of the power data in the h-th dimension of the multi-dimensional target power data; is the degree of electricity consumption of the electricity data in the h-th dimension of the multi-dimensional target electricity data; 3 is the total number of dimensions in the multi-dimensional target electricity data.

[0062] Similarly, obtain the fusion data of each device collected by the concentrator at each data fusion moment for the concentrator to perform regulation, such as load forecasting and electricity bill settlement by power companies; optimize the dispatching of distributed energy; perform real-time detection and fault warning of device status, power dispatching and other behaviors.

[0063] Since the fusion data can more accurately reflect the degree of electricity consumption and the corresponding data status, that is, the fusion data is closer to the real data. After obtaining the fusion data, if you want to view the real data of each dimension, then use the fusion data as the degree of electricity consumption of each dimension, and perform the inverse operation on the calculation formula of the degree of electricity consumption to obtain the real data of each dimension. The main purpose of the present invention is how to adaptively obtain the dynamic weights of each data to obtain more accurate fusion data. The concentrator uses the fusion data for regulation, and the formula inverse operation belongs to the prior art and will not be elaborated here.

[0064] In summary, in the embodiment of the present invention, for any device collected by the concentrator, obtain the data fusion frequency according to the preset power consumption frequency, and according to the data fusion frequency, obtain at least two data fusion moments. For any data fusion moment, obtain the multi-dimensional electricity data of the any device at each moment to obtain the multi-dimensional electricity data sequence at the any data fusion moment. The multi-dimensional electricity data includes current data, voltage data and power consumption data; record the multi-dimensional electricity data at the any data fusion moment as multi-dimensional target electricity data, and obtain the degree of electricity consumption of the electricity data in each dimension of the multi-dimensional target electricity data according to the data difference of the multi-dimensional electricity data in the multi-dimensional electricity data sequence; obtain the power quality score of the electricity data in each dimension of the multi-dimensional target electricity data according to the fluctuation characteristics of the multi-dimensional electricity data in the multi-dimensional electricity data sequence, and obtain the fusion weight of the electricity data in each dimension of the multi-dimensional target electricity data according to the power quality score of the electricity data in each dimension of the multi-dimensional target electricity data; obtain the fusion data of the any device at the any data fusion moment according to the degree of electricity consumption and the fusion weight of the electricity data in each dimension of the multi-dimensional target electricity data, and obtain the fusion data of each device collected by the concentrator at each data fusion moment for the concentrator to perform regulation. Among them, obtaining the data fusion frequency according to the preset power consumption frequency reduces the operation overhead of the concentrator; by obtaining the power quality score, the electricity data of different dimensions is converted into score data of the same form, and at the same time, the dynamic adaptive fusion weight is obtained according to the power quality score to obtain the fusion data, so that the fusion data can more accurately reflect the degree of use of the fusion power grid and the corresponding data status.

[0065] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; 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 various embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A concentrator intelligent fusion terminal based on multi-source fusion data regulation, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, the following method is implemented: For any device collected by the concentrator, obtain the data fusion frequency according to the preset power consumption frequency. According to the data fusion frequency, obtain at least two data fusion moments. For any data fusion moment, obtain the multi-dimensional power energy data of the any device at each moment, and obtain the multi-dimensional power energy data sequence at the any data fusion moment. The multi-dimensional power energy data includes current data, voltage data, and power consumption data; Denote the multi-dimensional power energy data at the any data fusion moment as multi-dimensional target power energy data. According to the data differences of the multi-dimensional power energy data in the multi-dimensional power energy data sequence, obtain the power energy usage degree of each dimension of power energy data in the multi-dimensional target power energy data; According to the fluctuation characteristics of the multi-dimensional power energy data in the multi-dimensional power energy data sequence, obtain the power quality score of each dimension of power energy data in the multi-dimensional target power energy data. According to the power quality scores of each dimension of power energy data in the multi-dimensional target power energy data, obtain the fusion weight of each dimension of power energy data in the multi-dimensional target power energy data; According to the power energy usage degree and fusion weight of each dimension of power energy data in the multi-dimensional target power energy data, obtain the fusion data of the any device at the any data fusion moment, and obtain the fusion data of each device collected by the concentrator at each data fusion moment for the concentrator to perform regulation.

2. The intelligent fusion terminal of a concentrator based on multi-source fusion data regulation according to claim 1, wherein The obtaining the power energy usage degree of each dimension of power energy data in the multi-dimensional target power energy data according to the data differences of the multi-dimensional power energy data in the multi-dimensional power energy data sequence includes: In the multi-dimensional power energy data sequence, obtain two multi-dimensional power energy data with a power consumption data difference of 0 and the corresponding moments closest to the any data fusion moment. The data between the two multi-dimensional power energy data and the two multi-dimensional power energy data form a reference subsequence; For any dimension of power energy data in the multi-dimensional target power energy data, obtain the initial usage degree reference value of the any dimension of power energy data according to the fluctuation characteristics of the multi-dimensional power energy data in the reference subsequence; Obtain the absolute value of the difference between the any dimension of power energy data and the initial usage degree reference value of the any dimension of power energy data to obtain the usage difference. Obtain the addition result of the usage difference and the constant 1. According to the difference between the constant 1 and the reciprocal of the addition result, obtain the power energy usage degree of the any dimension of power energy data.

3. The intelligent fusion terminal of the concentrator based on multi-source fusion data regulation according to claim 2, wherein, The obtaining the initial usage degree reference value of the any dimension of power energy data according to the fluctuation characteristics of the multi-dimensional power energy data in the reference subsequence includes: If the any dimension of power energy data belongs to current data, obtain the average value of the current data in the reference subsequence as the initial usage degree reference value of the any dimension of power energy data; If the any dimension of power energy data belongs to voltage data, obtain the average value of the voltage data in the reference subsequence as the initial usage degree reference value of the any dimension of power energy data; If the any dimension of power energy data belongs to power consumption data, set the initial usage degree reference value of the any dimension of power energy data to 0.

4. The intelligent fusion terminal of a concentrator based on multi-source fusion data regulation according to claim 1, characterized in that Obtaining the power quality score of each dimension of electrical energy data in the multi-dimensional target electrical energy data according to the fluctuation characteristics of the multi-dimensional electrical energy data in the multi-dimensional electrical energy data sequence includes: For any dimension of electrical energy data in the multi-dimensional target electrical energy data, obtain the electrical energy data belonging to the same dimension as the any dimension of electrical energy data in the multi-dimensional electrical energy data sequence, and construct a target sequence with a first preset length with the any dimension of electrical energy data as the last data; Average divide the target sequence into at least two target subsequences with a second preset length, and the second preset length is less than the first preset length; According to the data fluctuation characteristics of the target sequence and the data fluctuation characteristics of each target subsequence, obtain the power quality score of the any dimension of electrical energy data in the multi-dimensional target electrical energy data.

5. The intelligent fusion terminal of the concentrator based on multi-source fusion data regulation according to claim 4, characterized in that, The obtaining the power quality score of the any dimension of electrical energy data in the multi-dimensional target electrical energy data according to the data fluctuation characteristics of the target sequence and the data fluctuation characteristics of each target subsequence includes: If the any dimension of electrical energy data belongs to current data or voltage data, then for any target subsequence, obtain the variance of the target subsequence, calculate the difference between the constant 1 and the reciprocal of the variance, and obtain the fluctuation degree of the any target subsequence; Number the target subsequences in the target sequence according to time, obtain the sum result of the numbers of all target subsequences to get the total number value, and calculate the ratio of the number of the any target subsequence to the total number value to obtain the fluctuation weight of the fluctuation degree of the any target subsequence; Respectively obtain the fluctuation degree and its weight of each target subsequence, and perform weighted summation on the fluctuation degrees of all target subsequences to obtain the total fluctuation degree; Record the fluctuation degree of the target subsequence including the any dimension of electrical energy data as the real-time fluctuation degree, perform weighted summation on the real-time fluctuation degree and the total fluctuation degree to obtain the fluctuation index of the any dimension of electrical energy data, and calculate the difference between the constant 1 and the fluctuation index to obtain the power quality score of the any dimension of electrical energy data in the multi-dimensional target electrical energy data.

6. The intelligent fusion terminal of the concentrator based on multi-source fusion data regulation according to claim 5, wherein, The obtaining the power quality score of the any dimension of electrical energy data in the multi-dimensional target electrical energy data according to the data fluctuation characteristics of the target sequence and the data fluctuation characteristics of each target subsequence further includes: If the any dimension of electrical energy data belongs to electricity quantity data, then fit the target sequence to obtain a target fitting curve, and respectively obtain the fitting value of each electrical energy data in the target sequence on the target fitting curve; For any electrical energy data in the target sequence, obtain the absolute value of the difference between the any electrical energy data and its fitting value to obtain the deviation degree of the any electrical energy data, and obtain the average value of the reciprocals of the deviation degrees of each electrical energy data in the target sequence to obtain the power quality usage index of the target sequence; Record the target subsequence including the any dimension of electrical energy data as the real-time subsequence, and obtain the power quality usage index of the real-time subsequence; The power quality usage index of the target sequence and the power quality usage index of the real-time subsequence are weighted and summed to obtain the power quality score of the power data of any dimension in the multi-dimensional target power data.

7. The intelligent fusion terminal of the concentrator based on multi-source fusion data regulation according to claim 1, characterized in that, The obtaining of the fusion weight of the power data of each dimension in the multi-dimensional target power data according to the power quality score of the power data of each dimension in the multi-dimensional target power data includes: Obtaining the accumulated value of the power quality scores of the power data of each dimension in the multi-dimensional target power data to obtain the total power quality score; Respectively obtaining the ratio of the power quality score of the power data of each dimension in the multi-dimensional target power data to the total power quality score to obtain the fusion weight of the power data of each dimension in the multi-dimensional target power data.

8. The intelligent fusion terminal of the concentrator based on multi-source fusion data regulation according to claim 1, wherein, The obtaining of the fusion data of any device at any data fusion moment according to the power usage degree and the fusion weight of the power data of each dimension in the multi-dimensional target power data includes: Taking the fusion weight of the power data of each dimension in the multi-dimensional target power data as the weight coefficient of the power usage degree of the power data of each dimension in the multi-dimensional target power data, and performing weighted summation on the power usage degree of the power data of each dimension in the multi-dimensional target power data to obtain the fusion data of any device at any data fusion moment.

9. The intelligent fusion terminal of the concentrator based on multi-source fusion data regulation according to claim 8, wherein The obtaining of the data fusion frequency according to the preset power consumption frequency includes: Dividing the moments collected by the concentrator into at least two power consumption intervals according to the power consumption demand. For any power consumption interval, obtaining the time length and the average power consumption of the any power consumption interval; Obtaining the reciprocal of the time length, denoted as the time index, obtaining the difference between the constant 1 and the reciprocal of the average power consumption to obtain the power consumption index, obtaining the mean value between the time index and the power consumption index to obtain the frequency weight, and obtaining the product of the frequency weight and the preset power consumption frequency to obtain the data fusion frequency of the any power consumption interval.

Images