A household photovoltaic power generation monitoring method and system

Abstract

The present invention relates to the technical field of household photovoltaic power generation, and specifically discloses a household photovoltaic power generation monitoring method and system, including: obtaining the area where the household photovoltaic is located, and determining the environmental photovoltaic coefficient of the photovoltaic area according to the area where the household photovoltaic is located; obtaining the user electricity consumption characteristics of the photovoltaic area, and determining the user electricity consumption coefficient according to the user electricity consumption characteristics; clustering each household photovoltaic according to the environmental photovoltaic coefficient and the user electricity consumption coefficient to obtain a photovoltaic partition; obtaining the clustering center of the photovoltaic partition, and setting the power generation risk level of the household photovoltaic according to the clustering center of the photovoltaic partition. The present invention can accurately detect the power generation risk level of household photovoltaics, effectively ensure the stable operation of household photovoltaic equipment, and reduce losses.

Description

Technical Field

[0001] The present application relates to the technical field of household photovoltaic power generation, and more specifically, to a household photovoltaic power generation monitoring method and system. Background Art

[0002] Household photovoltaic refers to placing photovoltaic panels on the rooftop or in the courtyard of a family house, using low-power or micro-inverters for commutation, and directly utilizing this new energy, or integrating excess electricity into the grid. However, the existing household photovoltaic power generation industry is in its infancy, with a low level of informatization. The individual size of household photovoltaics is small, the base number is large, and it is impossible to detect abnormalities in the power generation state in a timely manner, resulting in reduced operating efficiency of household photovoltaics. Summary of the invention

[0003] The present invention provides a household photovoltaic power generation monitoring method and system, which is used to solve the problem in the prior art that household photovoltaic power generation cannot be detected in time when the power generation state is abnormal, including:

[0004] Obtain the area where the household photovoltaic system is located, and determine the environmental photovoltaic coefficient of the photovoltaic area according to the area where the household photovoltaic system is located;

[0005] Obtain the electricity consumption characteristics of users in the photovoltaic area, and determine the user electricity consumption coefficient according to the user electricity consumption characteristics;

[0006] The photovoltaic power of each household is clustered according to the environmental photovoltaic coefficient and the user's electricity consumption coefficient to obtain the photovoltaic partition;

[0007] The cluster center of the photovoltaic partition is obtained, and the power generation hazard level of the household photovoltaic is set according to the cluster center of the photovoltaic partition.

[0008] Furthermore, the environmental photovoltaic coefficient of the photovoltaic area is determined according to the area where the household photovoltaic is located, including:

[0009] Obtain the light intensity value of the area where the household photovoltaic system is located, and draw a light intensity change curve according to the change of the light intensity value;

[0010] Filter out the peak point and valley point of the light intensity change curve, and calculate the variance of the remaining points in the light intensity change curve with the peak point and valley point;

[0011] Determine the peak period and valley period of the light intensity according to the variance of the remaining points in the light intensity change curve with the peak point and valley point, calculate the proportion of the peak period and valley period in the light intensity change curve, and obtain the period weight;

[0012] Calculate the average light intensity of the peak period and the valley period, perform weighted summation on the average light intensity of the peak period and the valley period to obtain the light intensity coefficient, and determine the environmental photovoltaic coefficient based on the light intensity coefficient;

[0013] Obtain the weather change data of the photovoltaic area, determine the weather fluctuation value according to the weather change data, and correct the environmental photovoltaic coefficient according to the weather fluctuation value.

[0014] Further, determine the peak period and valley period of the light intensity according to the variances between the remaining points in the light intensity change curve and the peak point and the valley point, including:

[0015] Obtain a preset variance threshold. When the variance between the remaining points in the light intensity change curve and the peak point is less than the preset variance threshold, set the remaining points in the light intensity change curve as peak period points;

[0016] When the variance between the remaining points in the light intensity change curve and the valley point is less than the preset variance threshold, set the remaining points in the light intensity change curve as valley period points;

[0017] Determine the peak period and valley period according to the peak period points and valley period points.

[0018] Further, determine the weather fluctuation value according to the weather change data, including:

[0019] Obtain the weather change data of the photovoltaic area within a preset period, and determine the number of occurrences of cloudy weather and rainy weather in the photovoltaic area within the preset period according to the weather change data;

[0020] Determine the weather weight according to the number of occurrences of cloudy weather and rainy weather, and perform weighted summation on the number of occurrences of cloudy weather and rainy weather in the photovoltaic area within the preset period based on the weather weight to obtain a weather impact factor;

[0021] Perform normalization processing on the weather impact factor to obtain the weather fluctuation value.

[0022] Further, determine the user electricity consumption coefficient according to the user electricity consumption characteristics, including:

[0023] Obtain the historical power generation data and historical power generation fault type data of each household's photovoltaic power generation, obtain a power generation fault data set, and perform data mining on the power generation fault data set based on the apriori association rule algorithm;

[0024] Obtain the parameter level interval and the fault type level interval, determine the fault parameter level and the corresponding fault type level of the mining result according to the parameter level interval and the fault type level interval, and calculate the sum of the fault parameter level and the fault type level corresponding to each power generation fault type to obtain a power generation fault factor;

[0025] Obtain the frequencies of various power generation fault types of household photovoltaic, set fault weights according to the frequencies of power generation fault types, and perform weighted summation on power generation fault factors according to the fault weights to obtain the user power consumption coefficient of household photovoltaic.

[0026] Further, perform data mining on the power generation fault data set based on the apriori association rule algorithm, including:

[0027] Discretize the power generation fault data set, generate candidate itemset C1 according to the discretized power generation fault data set, and calculate the support degree corresponding to each item in C1;

[0028] Set the minimum support degree threshold, screen out the item sets whose support degrees corresponding to each item in C1 are greater than the minimum support degree threshold to obtain frequent itemset L1;

[0029] Perform connection and pruning processing on L1 to obtain candidate itemset C2, calculate the support degree corresponding to each item in C2, screen out the item sets whose support degrees corresponding to each item in C2 are greater than the minimum support degree threshold to obtain frequent itemset L2;

[0030] Repeat the above operations until the maximum frequent itemset Lk is obtained, set the minimum confidence threshold, and determine the power generation fault association rules according to the confidence of each item in Lk.

[0031] Further, cluster each household photovoltaic according to the environmental photovoltaic coefficient and the user power consumption coefficient, including:

[0032] Obtain the environmental photovoltaic coefficient and the user power consumption coefficient of household photovoltaic, and establish a household photovoltaic data set according to the environmental photovoltaic coefficient and the user power consumption coefficient;

[0033] Randomly select k initial clustering centers, and calculate the Euclidean distances from the data in the household photovoltaic data set to the initial clustering centers;

[0034] Divide each household photovoltaic data into the corresponding partition according to the Euclidean distances from the data in the household photovoltaic data set to the initial clustering centers;

[0035] Update the clustering centers according to the average values of all household photovoltaic data in each partition, and perform repeated iteration according to the new clustering centers until the clustering centers no longer change to obtain k final clustering centers;

[0036] Divide the user photovoltaic data in the user photovoltaic data set into k partitions according to the Euclidean distances from the household photovoltaic data to the final clustering centers.

[0037] Further, set the power generation danger level of household photovoltaic according to the clustering centers of photovoltaic partitions, including:

[0038] Screen out the residential PV with the closest data to the clustering center according to the clustering center of each PV zone, obtain the power generation curve of the residential PV with the closest data to the clustering center, and obtain the standard curve;

[0039] Calculate the correlation between the power generation curves of the remaining users in the PV zone and the standard curve, obtain the power generation curve correlation, and determine the power generation risk level of the residential PV according to the power generation curve correlation.

[0040] Further, determining the power generation risk level of the residential PV according to the power generation curve correlation includes:

[0041] Obtain a preset correlation threshold, calculate the difference between the power generation curve correlation and the preset correlation threshold, and determine whether the difference between the power generation curve correlation and the preset correlation threshold is greater than a first preset threshold;

[0042] If the difference between the power generation curve correlation and the preset correlation threshold is greater than the first preset threshold, set the preset first fault level as the power generation risk level of the residential PV;

[0043] If the difference between the power generation curve correlation and the preset correlation threshold is less than or equal to the first preset threshold, determine whether the difference between the power generation curve correlation and the preset correlation threshold is greater than a second preset threshold;

[0044] If the difference between the power generation curve correlation and the preset correlation threshold is greater than the second preset threshold, set the preset second fault level as the power generation risk level of the residential PV;

[0045] If the difference between the power generation curve correlation and the preset correlation threshold is less than or equal to the second preset threshold, set the preset third fault level as the power generation risk level of the residential PV.

[0046] To achieve the above object, the present invention also provides a residential PV power generation monitoring system, including:

[0047] An environment module for obtaining the area where the residential PV is located and determining the environmental PV coefficient of the PV area according to the area where the residential PV is located;

[0048] A user module for obtaining the user power consumption characteristics of the PV area and determining the user power consumption coefficient according to the user power consumption characteristics;

[0049] A zoning module for clustering each residential PV according to the environmental PV coefficient and the user power consumption coefficient to obtain a PV zone;

[0050] A level module for obtaining the clustering center of the PV zone and setting the power generation risk level of the residential PV according to the clustering center of the PV zone.

[0051] The beneficial effects of the present invention are as follows:

[0052] By applying the above technical solution, the present invention comprehensively analyzes the environmental characteristics of household photovoltaic and the electricity consumption characteristics of users, partitions household photovoltaics with different environmental characteristics and user electricity consumption characteristics based on a clustering algorithm, sets the power generation risk level of household photovoltaics for the power generation of each partition, has high accuracy, helps household photovoltaic users to detect abnormalities in time, ensures the stable operation of household photovoltaic equipment, and reduces losses. Description of the Drawings

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0054] Figure 1 Shows the overall flowchart of a household photovoltaic power generation monitoring method proposed by an embodiment of the present invention;

[0055] Figure 2 Shows the structural schematic diagram of a household photovoltaic power generation monitoring system proposed by an embodiment of the present invention. Detailed Embodiments

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0057] The embodiments of the present application provide a household photovoltaic power generation monitoring method, as Figure 1 shown, including:

[0058] S101, obtaining the area where the household photovoltaic is located, and determining the environmental photovoltaic coefficient of the photovoltaic area according to the area where the household photovoltaic is located;

[0059] In some embodiments of the present application, determining the environmental photovoltaic coefficient of a photovoltaic region according to the region where the household photovoltaic is located includes: obtaining the light intensity value of the region where the household photovoltaic is located, and drawing a light intensity change curve according to the change situation of the light intensity value; screening out the peak points and valley points of the light intensity change curve, and calculating the variances between the remaining points in the light intensity change curve and the peak points and valley points; determining the peak period and valley period of the light intensity according to the variances between the remaining points in the light intensity change curve and the peak points and valley points, calculating the proportions of the peak period and valley period in the light intensity change curve to obtain the period weights; calculating the average light intensity values of the peak period and valley period, and performing weighted summation on the average light intensity values of the peak period and valley period to obtain the light intensity coefficient, and determining the environmental photovoltaic coefficient according to the light intensity coefficient; obtaining the weather change data of the photovoltaic region, determining the weather fluctuation value according to the weather change data, and correcting the environmental photovoltaic coefficient according to the weather fluctuation value.

[0060] In this embodiment, the light intensity change curve is divided into multiple peak periods and valley periods by the variances between the remaining points in the light intensity change curve and the peak points and valley points, and the average light intensity values of the peak period and valley period are calculated respectively. Since the power generation amount at the peak of the light intensity is much larger than that at the valley of the light intensity, the initial weights of the peak period and valley period are preset, where the preset peak period weight is greater than the preset valley period weight. By multiplying the proportions of the peak period and valley period in the light intensity change curve by the corresponding preset initial weights, the peak period weight and valley period weight are obtained, and the above average light intensity values are weighted and summed to obtain the light intensity coefficient.

[0061] In some embodiments of the present application, determining the peak period and valley period of the light intensity according to the variances between the remaining points in the light intensity change curve and the peak points and valley points includes: obtaining a preset variance threshold. When the variance between the remaining points in the light intensity change curve and the peak point is less than the preset variance threshold, the remaining points in the light intensity change curve are set as peak period points; when the variance between the remaining points in the light intensity change curve and the valley point is less than the preset variance threshold, the remaining points in the light intensity change curve are set as valley period points; determining the peak period and valley period according to the peak period points and valley period points.

[0062] In this embodiment, the continuous peak period points are connected to obtain the peak period, and the continuous valley period points are connected to obtain the valley period. If there are no cycle points of the same type on both sides of a certain cycle point, then this cycle point is removed.

[0063] In some embodiments of the present application, determining the weather fluctuation value according to the weather change data includes: obtaining the weather change data of the photovoltaic area within a preset period, and determining the number of occurrences of cloudy weather and rainy weather in the photovoltaic area within the preset period according to the weather change data; determining the weather weight according to the number of occurrences of cloudy weather and rainy weather, and performing weighted summation on the number of occurrences of cloudy weather and rainy weather in the photovoltaic area within the preset period based on the weather weight to obtain the weather influence factor; performing normalization processing on the weather influence factor to obtain the weather fluctuation value.

[0064] In this embodiment, the preset period is set to one month, and the initial rainy weather weight is set to be greater than the initial cloudy weather weight. The initial rainy weather weight and the initial cloudy weather weight are respectively corrected according to the number of occurrences of cloudy weather and rainy weather. The more the number of occurrences, the greater the corresponding weight correction value. The range of the weather influence factor is limited to [0, 1] through the normalization processing formula, so as to obtain the weather fluctuation value.

[0065] S102, obtaining the user electricity consumption characteristics of the photovoltaic area, and determining the user electricity consumption coefficient according to the user electricity consumption characteristics;

[0066] In some embodiments of the present application, determining the user electricity consumption coefficient according to the user electricity consumption characteristics includes: obtaining the historical power generation data and historical power generation fault type data of each household photovoltaic to obtain a power generation fault data set, and performing data mining on the power generation fault data set based on the apriori association rule algorithm; obtaining the parameter level interval and the fault type level interval, determining the fault parameter level and the corresponding fault type level of the mining result according to the parameter level interval and the fault type level interval, and calculating the sum of the fault parameter level and the fault type level corresponding to each power generation fault type to obtain the power generation fault factor; obtaining the frequency of each power generation fault type of the household photovoltaic, setting the fault weight according to the frequency of the power generation fault type, and performing weighted summation on the power generation fault factor according to the fault weight to obtain the user electricity consumption coefficient of the household photovoltaic.

[0067] In this embodiment, the historical power generation data includes power generation parameters such as the peak power, maximum power point voltage, and conversion efficiency of the household photovoltaic equipment. A power generation fault data set is established through the historical power generation data and the historical power generation fault type data. By presetting several parameter level intervals and fault type level intervals, the power generation data and the corresponding power generation fault type data in each strong association rule are classified, so as to calculate the power generation fault factor. The fault weight is determined by setting a fault frequency - fault weight mapping table, and then the user electricity consumption coefficient of the household photovoltaic is calculated.

[0068] In some embodiments of the present application, data mining is performed on the power generation failure dataset based on the Apriori association rule algorithm, including: discretizing the power generation failure dataset, generating candidate itemset C1 according to the discretized power generation failure dataset, and calculating the support degree corresponding to each item in C1; setting a minimum support degree threshold, screening out the itemset whose support degree corresponding to each item in C1 is greater than the minimum support degree threshold to obtain frequent itemset L1; performing connection and pruning processing on L1 to obtain candidate itemset C2, calculating the support degree corresponding to each item in C2, screening out the itemset whose support degree corresponding to each item in C2 is greater than the minimum support degree threshold to obtain frequent itemset L2; repeating the above operations until the maximum frequent itemset Lk is obtained, setting a minimum confidence threshold, and determining the power generation failure association rule according to the confidence of each item in Lk.

[0069] In this embodiment, data mining is performed on the power generation failure dataset when household photovoltaic has a failure based on the Apriori algorithm, the association relationship between the power generation data and the power generation failure type is mined, and the power generation failure factor is obtained.

[0070] S103, clustering each household photovoltaic according to the environmental photovoltaic coefficient and the user electricity consumption coefficient to obtain photovoltaic partitions;

[0071] In some embodiments of the present application, clustering each household photovoltaic according to the environmental photovoltaic coefficient and the user electricity consumption coefficient includes: obtaining the environmental photovoltaic coefficient and the user electricity consumption coefficient of the household photovoltaic, and establishing a household photovoltaic dataset according to the environmental photovoltaic coefficient and the user electricity consumption coefficient; randomly selecting k initial clustering centers, and calculating the Euclidean distance from the data in the household photovoltaic dataset to the initial clustering centers; dividing each household photovoltaic data into the corresponding partition according to the Euclidean distance from the data in the household photovoltaic dataset to the initial clustering centers; updating the clustering centers according to the average value of all household photovoltaic data in each partition, and performing repeated iteration according to the new clustering centers until the clustering centers no longer change to obtain k final clustering centers; dividing the household photovoltaic data in the user photovoltaic dataset into k partitions according to the Euclidean distance from the household photovoltaic data to the final clustering centers.

[0072] In this embodiment, the value of k is set to 3, a household photovoltaic dataset is established according to the environmental photovoltaic coefficient and the user electricity consumption coefficient, and the household photovoltaic is clustered based on the k-means clustering algorithm to obtain 3 photovoltaic partitions.

[0073] S104, obtaining the clustering centers of the photovoltaic partitions, and setting the power generation danger level of the household photovoltaic according to the clustering centers of the photovoltaic partitions.

[0074] In some embodiments of the present application, the power generation risk level of household photovoltaic is set according to the cluster center of photovoltaic partitions, including: screening out the household photovoltaic with the closest household photovoltaic data to the cluster center from each photovoltaic partition, obtaining the power generation curve of the household photovoltaic with the closest household photovoltaic data to the cluster center, and obtaining a standard curve; calculating the correlation degree between the power generation curves of the remaining users in the photovoltaic partition and the standard curve, obtaining the power generation curve correlation degree, and determining the power generation risk level of the household photovoltaic according to the power generation curve correlation degree.

[0075] In this embodiment, by calculating the distance between the household photovoltaic data of the household photovoltaic in the photovoltaic partition and the cluster center, the household photovoltaic closest to the cluster center in the photovoltaic partition is obtained, so as to establish a standard power generation curve, and the correlation degree between the remaining curves in the photovoltaic partition and the standard curve is calculated based on the Pearson correlation coefficient calculation formula to determine the power generation risk level.

[0076] In some embodiments of the present application, determining the power generation risk level of household photovoltaic according to the power generation curve correlation degree includes: obtaining a preset correlation degree threshold, calculating the difference between the power generation curve correlation degree and the preset correlation degree threshold, and determining whether the difference between the power generation curve correlation degree and the preset correlation degree threshold is greater than a first preset threshold; if the difference between the power generation curve correlation degree and the preset correlation degree threshold is greater than the first preset threshold, setting a preset first fault level as the power generation risk level of the household photovoltaic; if the difference between the power generation curve correlation degree and the preset correlation degree threshold is less than or equal to the first preset threshold, determining whether the difference between the power generation curve correlation degree and the preset correlation degree threshold is greater than a second preset threshold; if the difference between the power generation curve correlation degree and the preset correlation degree threshold is greater than the second preset threshold, setting a preset second fault level as the power generation risk level of the household photovoltaic; if the difference between the power generation curve correlation degree and the preset correlation degree threshold is less than or equal to the second preset threshold, setting a preset third fault level as the power generation risk level of the household photovoltaic.

[0077] In this embodiment, by presetting the correlation degree threshold, different power generation risk levels of household photovoltaic are obtained according to the difference between the power generation curve correlation degree and the preset correlation degree threshold. The greater the difference between the power generation curve correlation degree and the preset correlation degree threshold, the higher the power generation risk level.

[0078] Based on the same technical concept, such as Figure 2As shown in the figure, the present invention also provides a household photovoltaic power generation monitoring system, including: an environment module, configured to obtain the area where the household photovoltaic is located and determine the environmental photovoltaic coefficient of the photovoltaic area according to the area where the household photovoltaic is located; a user module, configured to obtain the user's electricity consumption characteristics in the photovoltaic area and determine the user's electricity consumption coefficient according to the user's electricity consumption characteristics; a zoning module, configured to cluster each household photovoltaic according to the environmental photovoltaic coefficient and the user's electricity consumption coefficient to obtain a photovoltaic zone; a grading module, configured to obtain the clustering center of the photovoltaic zone and set the power generation risk level of the household photovoltaic according to the clustering center of the photovoltaic zone.

[0079] By applying the above technical solutions, the present invention obtains the area where the household photovoltaic is located, determines the environmental photovoltaic coefficient of the photovoltaic area according to the area where the household photovoltaic is located; obtains the user's electricity consumption characteristics in the photovoltaic area, determines the user's electricity consumption coefficient according to the user's electricity consumption characteristics; clusters each household photovoltaic according to the environmental photovoltaic coefficient and the user's electricity consumption coefficient to obtain a photovoltaic zone; obtains the clustering center of the photovoltaic zone, and sets the power generation risk level of the household photovoltaic according to the clustering center of the photovoltaic zone. The present invention can accurately detect the power generation risk level of the household photovoltaic, effectively ensure the stable operation of the household photovoltaic equipment, and reduce losses.

[0080] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present invention.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application 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 for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A household photovoltaic power generation monitoring method, characterized in that, Including: Obtain the area where the household photovoltaic is located, and determine the environmental photovoltaic coefficient of the photovoltaic area according to the area where the household photovoltaic is located; Obtain the user power consumption characteristics of the photovoltaic area, and determine the user power consumption coefficient according to the user power consumption characteristics; Cluster each household photovoltaic according to the environmental photovoltaic coefficient and the user power consumption coefficient to obtain a photovoltaic partition; Obtain the clustering center of the photovoltaic partition, and set the power generation risk level of the household photovoltaic according to the clustering center of the photovoltaic partition; Determine the environmental photovoltaic coefficient of the photovoltaic area according to the area where the household photovoltaic is located, including: Obtain the light intensity value of the area where the household photovoltaic is located, and draw a light intensity change curve according to the change of the light intensity value; Screen out the peak points and valley points of the light intensity change curve, and calculate the variance between the remaining points in the light intensity change curve and the peak points and valley points; Determine the peak period and valley period of the light intensity according to the variance between the remaining points in the light intensity change curve and the peak points and valley points, calculate the proportion of the peak period and valley period in the light intensity change curve, and obtain the period weight; Calculate the average light intensity of the peak period and valley period, perform weighted summation on the average light intensity of the peak period and valley period, obtain the light intensity coefficient, and determine the environmental photovoltaic coefficient according to the light intensity coefficient; Obtain the weather change data of the photovoltaic area, determine the weather fluctuation value according to the weather change data, and correct the environmental photovoltaic coefficient according to the weather fluctuation value; Determine the peak period and valley period of the light intensity according to the variance between the remaining points in the light intensity change curve and the peak points and valley points, including: Obtain a preset variance threshold. When the variance between the remaining points in the light intensity change curve and the peak point is less than the preset variance threshold, set the remaining points in the light intensity change curve as peak period points; When the variance between the remaining points in the light intensity change curve and the valley point is less than the preset variance threshold, set the remaining points in the light intensity change curve as valley period points; Determine the peak period and valley period according to the peak period points and valley period points; Determine the weather fluctuation value according to the weather change data, including: Obtain the weather change data of the photovoltaic area within a preset period, and determine the number of occurrences of cloudy weather and rainy weather in the photovoltaic area within the preset period according to the weather change data; Determine the weather weight according to the number of occurrences of cloudy weather and rainy weather, and perform weighted summation on the number of occurrences of cloudy weather and rainy weather in the photovoltaic area within the preset period based on the weather weight to obtain the weather impact factor; Perform normalization processing on the weather impact factor to obtain the weather fluctuation value.

2. The household photovoltaic power generation monitoring method according to claim 1, wherein, Determine the user power consumption coefficient according to the user power consumption characteristics, including: Obtain the historical power generation data and historical power generation fault type data of each household photovoltaic to obtain a power generation fault data set, and perform data mining on the power generation fault data set based on the apriori association rule algorithm; Obtain the parameter level interval and the fault type level interval, determine the fault parameter level and the corresponding fault type level of the mining result according to the parameter level interval and the fault type level interval, and calculate the sum of the fault parameter level and the fault type level corresponding to each power generation fault type to obtain the power generation fault factor; Obtain the frequencies of various power generation fault types of household photovoltaic, set fault weights according to the frequencies of power generation fault types, perform weighted summation on power generation fault factors according to the fault weights, and obtain the user electricity consumption coefficient of household photovoltaic.

3. The household photovoltaic power generation monitoring method according to claim 2, characterized in that Perform data mining on the power generation fault data set based on the apriori association rule algorithm, including: Discretize the power generation fault data set, generate candidate item set C1 according to the discretized power generation fault data set, and calculate the support degree corresponding to each item in C1; Set the minimum support degree threshold, filter out the item sets whose support degrees corresponding to each item in C1 are greater than the minimum support degree threshold, and obtain frequent item set L1; Perform connection and pruning processing on L1 to obtain candidate item set C2, calculate the support degree corresponding to each item in C2, filter out the item sets whose support degrees corresponding to each item in C2 are greater than the minimum support degree threshold, and obtain frequent item set L2; Repeat the above operations until the maximum frequent item set Lk is obtained, set the minimum confidence threshold, and determine the power generation fault association rules according to the confidence of each item in Lk.

4. The household photovoltaic power generation monitoring method according to claim 1, characterized in that, Cluster each household photovoltaic according to the environmental photovoltaic coefficient and the user electricity consumption coefficient, including: Obtain the environmental photovoltaic coefficient and the user electricity consumption coefficient of household photovoltaic, and establish a household photovoltaic data set according to the environmental photovoltaic coefficient and the user electricity consumption coefficient; Randomly select k initial clustering centers, and calculate the Euclidean distance from the data in the household photovoltaic data set to the initial clustering centers; Divide each household photovoltaic data into corresponding partitions according to the Euclidean distance from the data in the household photovoltaic data set to the initial clustering centers; Update the clustering centers according to the average value of all household photovoltaic data in each partition, and perform repeated iteration according to the new clustering centers until the clustering centers no longer change, and obtain k final clustering centers; Divide the user photovoltaic data in the user photovoltaic data set into k partitions according to the Euclidean distance from the household photovoltaic data to the final clustering centers.

5. The household photovoltaic power generation monitoring method according to claim 4, characterized in that Set the power generation danger level of household photovoltaic according to the clustering centers of photovoltaic partitions, including: Filter out the household photovoltaic whose household photovoltaic data is closest to the clustering center according to the clustering centers of each photovoltaic partition, obtain the power generation curve of the household photovoltaic whose household photovoltaic data is closest to the clustering center, and obtain the standard curve; Calculate the correlation degree between the power generation curves of the remaining users in the photovoltaic partition and the standard curve, obtain the power generation curve correlation degree, and determine the power generation danger level of household photovoltaic according to the power generation curve correlation degree.

6. The household photovoltaic power generation monitoring method according to claim 5, characterized in that, Determine the power generation danger level of household photovoltaic according to the power generation curve correlation degree, including: Obtain the preset correlation degree threshold, calculate the difference between the power generation curve correlation degree and the preset correlation degree threshold, and judge whether the difference between the power generation curve correlation degree and the preset correlation degree threshold is greater than the first preset threshold; If the difference between the power generation curve correlation degree and the preset correlation degree threshold is greater than the first preset threshold, then set the preset first fault level as the power generation danger level of household photovoltaic; If the difference between the power generation curve correlation degree and the preset correlation degree threshold is less than or equal to the first preset threshold, then judge whether the difference between the power generation curve correlation degree and the preset correlation degree threshold is greater than the second preset threshold; If the difference between the correlation degree of the power generation curve and the preset correlation degree threshold is greater than the second preset threshold, set the preset second fault level as the power generation risk level of the household photovoltaic; If the difference between the correlation degree of the power generation curve and the preset correlation degree threshold is less than or equal to the second preset threshold, set the preset third fault level as the power generation risk level of the household photovoltaic.

7. A household photovoltaic power generation monitoring system, characterized in that, Including: An environment module, configured to obtain the area where the household photovoltaic is located, and determine the environmental photovoltaic coefficient of the photovoltaic area according to the area where the household photovoltaic is located; A user module, configured to obtain the user electricity consumption characteristics of the photovoltaic area, and determine the user electricity consumption coefficient according to the user electricity consumption characteristics; A zoning module, configured to cluster each household photovoltaic according to the environmental photovoltaic coefficient and the user electricity consumption coefficient to obtain a photovoltaic zone; A level module, configured to obtain the clustering center of the photovoltaic zone, and set the power generation risk level of the household photovoltaic according to the clustering center of the photovoltaic zone.

Images