Intelligent photovoltaic station management and control system and method based on data analysis

Abstract

The invention discloses an intelligent photovoltaic field station management and control system and method based on data analysis, and relates to the technical field of photovoltaic field station management and control, and the management and control method comprises the following steps: constructing a photovoltaic field station data management system to generate a detection log of any photovoltaic field station and a plurality of corresponding detection records; performing abnormity judgment on any detection record; carrying out risk level setting on any photovoltaic station, and setting a corresponding abnormity evaluation standard; obtaining the operation condition of any photovoltaic station presented in the newly generated detection record, obtaining the expected evaluation result of the photovoltaic station at the current moment, and planning the detection route between the photovoltaic stations; when the target station is detected according to the planned detection route, expected operation conditions of other photovoltaic stations are analyzed in real time, and abnormity identification is carried out on the other photovoltaic stations; and for any abnormal photovoltaic field station, a pre-planned detection route is corrected.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic station control technology, and in particular to an intelligent photovoltaic station control system and method based on data analysis. Background Art

[0002] Photovoltaic stations refer to power stations that use solar cell arrays to convert solar radiation into electrical energy. Photovoltaic stations are usually connected to the power grid and transmit electricity to the grid. They are green power development projects encouraged by the state. With the continuous advancement of technology and policy support, the construction and operation of photovoltaic stations have become more intelligent and efficient.

[0003] The current existing technology can realize the intelligent monitoring and management of photovoltaic stations. The operating status of photovoltaic stations can be detected by inspection equipment. Since the distribution of photovoltaic stations is relatively scattered, it is necessary to plan the inspection routes of each photovoltaic station. However, in the inspection route planning, there is a lack of analysis and utilization of historical data, and the operating status, fault history and environmental factors of the equipment are not fully considered, resulting in the inspection route being unable to effectively cover high-risk areas, increasing the hidden dangers of equipment failure, and causing a waste of resources. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent photovoltaic station management and control system and method based on data analysis to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: an intelligent photovoltaic station control method based on data analysis, the control method comprising the following steps:

[0006] Step S100: constructing a photovoltaic station data management system to record each detection process of any photovoltaic station, generating a detection log of the photovoltaic station and a number of corresponding detection records; analyzing the operating data stored in any detection record, and making an abnormality judgment on the detection record;

[0007] Step S200: setting a risk level for any photovoltaic station based on the frequency of abnormal occurrences in each detection record of the photovoltaic station; and setting corresponding abnormality assessment standards for different risk levels according to the level division between different photovoltaic stations;

[0008] Step S300: obtaining the operating status of any photovoltaic station in the latest generated detection record, and obtaining the expected evaluation result of the photovoltaic station at the current moment; based on the evaluation differences between different photovoltaic stations, planning the detection routes between the photovoltaic stations;

[0009] Step S400: When the target station is inspected according to the planned inspection route, the expected operation conditions of the remaining photovoltaic stations are analyzed in real time, and abnormalities of the remaining photovoltaic stations are identified; for any photovoltaic station with abnormalities, the pre-planned inspection route is corrected and an abnormality warning is sent.

[0010] Furthermore, step S100 includes the following steps:

[0011] Step S101: numbering each photovoltaic station, and generating a detection log of each photovoltaic station in the photovoltaic station data management system according to the number; collecting the operation data generated by each component device of any photovoltaic station through the detection equipment, and transmitting it to the photovoltaic station data management system, and generating and storing a detection record in the detection log of the photovoltaic station;

[0012] Step S102: acquiring the operation data stored in any detection record, and dividing the operation data according to the component devices from which the data is collected, presetting evaluation rules of several dimensions for the operation data of any component device, and obtaining the evaluation value of the component device;

[0013] Step S103: preset a capability evaluation value for each component device of any photovoltaic station, the capability evaluation value is the proportion of importance of each component device in the overall operation of the photovoltaic station, the higher the capability evaluation value, the higher the importance of the component device, and the higher the proportion in the subsequent evaluation process; set the capability evaluation value of the i-th component device in the photovoltaic station corresponding to the detection record to A i , according to the formula:

[0014]

[0015] Where i and j are positive integers and i∈(1,e), j∈(1,e), A j is the capacity evaluation value of the jth component device, e is the number of component devices in the photovoltaic field station corresponding to the detection record, B j is the evaluation value of the jth component device; and the comprehensive evaluation value C presented in the test record is calculated;

[0016] Step S104: When there is an abnormal situation in each photovoltaic station, the comprehensive evaluation value of the corresponding detection record of each photovoltaic station is obtained, and the comprehensive evaluation value with the largest value is selected and set as the abnormal evaluation value C abnormal , if C<C abnormal , then the detection record is set as an abnormal detection record.

[0017] Further, step S200 includes the following steps:

[0018] Step S201: obtaining a detection log of any photovoltaic station, extracting the record generation time of each detection record in the detection log, sorting the detection records from early to late according to the record generation time, and generating a detection record set of the detection log;

[0019] Step S202: Extract the generation time of each abnormal detection record from the detection record set to obtain the time interval between two adjacent abnormal detection records; set the k1th detection record and the k2th detection record in the detection record set as abnormal detection records, and obtain the time interval between the two abnormal detection records as Δt k1,k2 , according to the formula:

[0020]

[0021] Where k2>k1; calculate the abnormal occurrence frequency α between the k1th detection record and the k2th detection record k1,k2 ; Get the anomaly occurrence frequency between any two adjacent anomaly detection records, and calculate the average value to get the average occurrence frequency α of the anomaly detection records ’ ; Because the number of detection records between two anomaly detection records does not include the anomaly detection record itself, the formula needs to be subtracted by one;

[0022] Step S203: Set the log generation time of the detection log as t0 and the record generation time of the last detection record in the detection record set as t1, and obtain the log duration as Δt=t1-t0; obtain the number of detection records in the detection record set as m, according to the formula:

[0023]

[0024] Calculate the average abnormal frequency α of the detection log ave ; If α ’ >α ave , then the photovoltaic station is marked with the first characteristic risk. If α ’ <α ave , then the photovoltaic station is marked with the second characteristic risk; the frequency of abnormal occurrence in the detection log as a whole is compared with the frequency of occurrence of any adjacent detection records in the detection log, and the part is compared with the whole to reflect the degree of abnormality of the photovoltaic station. If the frequency of occurrence of the part is higher than that of the whole, it can be said that the frequency of occurrence of the photovoltaic station is getting higher and higher to a certain extent; the first characteristic risk mark indicates a photovoltaic station with a higher degree of abnormality, and the second characteristic risk mark indicates a photovoltaic station with a normal degree;

[0025] Step S204: Summarize the photovoltaic stations with the same characteristic risk mark to obtain a first characteristic station set and a second characteristic station set respectively; select a target photovoltaic station from the first characteristic station set, obtain the target detection log corresponding to the target photovoltaic station, and set the average abnormal frequency α of the target detection log ave and the average occurrence frequency α of anomaly detection records ’ , according to the formula:

[0026]

[0027] Among them, C abnormal is the abnormal assessment value; the abnormal assessment standard value C of the target photovoltaic station is calculated ’ abnormal ; Obtain the abnormal evaluation standard value of each photovoltaic station in the first characteristic station set, and calculate the average value to obtain the abnormal evaluation standard C1 of the first characteristic station set abnormal For each photovoltaic station in the second characteristic station set, the abnormal evaluation value C abnormal Set as the abnormal evaluation standard C2 of the second characteristic station set abnormal ; For the first characteristic station set, because the frequency of anomalies is high, the anomaly assessment standard should be adjusted in combination with the frequency of occurrence, and the value of the anomaly assessment standard should be increased accordingly. Because frequent anomalies require advance detection arrangements with higher assessment values, better troubleshooting can be carried out before the actual anomaly occurs.

[0028] Further, step S300 includes the following steps:

[0029] Step S301: randomly select a photovoltaic station, obtain the ID of the photovoltaic station, and obtain the abnormality assessment standard S of the photovoltaic station. abnormal (ID), if the photovoltaic station belongs to the first characteristic station set, then S abnormal (ID)=C1 abnormal , if the photovoltaic station belongs to the second characteristic station set, then S abnormal (ID)=C2 abnormal ;

[0030] Step S302: extract any two adjacent detection records from the corresponding detection log of the photovoltaic station. If the two detection records are not abnormal detection records, obtain the comprehensive evaluation difference ΔC and the generation time interval Δt of the two detection records, and calculate the characteristic coefficient ratio η=ΔC / Δt of the photovoltaic station between the two detection records; obtain the characteristic coefficient ratio of any two detection records that are not abnormal detection records, and calculate the average value to obtain the average coefficient ratio η aveThe average coefficient ratio is the natural loss of the photovoltaic station during normal operation, which helps provide reference data for subsequent expected evaluation;

[0031] Step S302: Obtain the operation data of the latest detection record generated in the corresponding detection log of the photovoltaic station, and obtain the comprehensive evaluation value C presented by the latest detection record according to the preset evaluation standard. new ; Get the time interval between the latest generated detection record and the current time is Δt new , the expected evaluation value of the photovoltaic station at the current moment is calculated to be C ex =C new -Δt new ×η ave ; According to the formula:

[0032]

[0033] The expected characteristic value σ of the photovoltaic station at the current moment is calculated; if σ>0, the photovoltaic station is set as the expected detection station; not all photovoltaic stations need to be detected in each detection process, because photovoltaic stations as a whole do not frequently have abnormalities, so only some photovoltaic stations with low evaluation values ​​after data analysis need to be detected, which can effectively save resources and facilitate the planning of subsequent detection routes;

[0034] Step S303: extracting an abnormality detection record with the shortest time interval from the current moment from the corresponding detection log of the photovoltaic station, and obtaining the time interval from the abnormality detection record to the current moment as Δt abnormal ; Get the number of detection records between the generation time of the abnormal detection record and the current time as m1, and calculate the actual abnormal occurrence frequency α of the photovoltaic station ac =Δt abnormal / m1;

[0035] Step S304: Obtain the average abnormal frequency of the corresponding detection log of the photovoltaic station as α ave , according to the formula:

[0036]

[0037] The detection priority value Y of the photovoltaic station is calculated; all the expected detection stations are sorted from large to small according to the detection priority value to generate a detection route; the setting of the detection priority value takes into account the deviation degree of the photovoltaic station evaluation value and the frequency of abnormal occurrence, both of which directly reflect the degree of abnormality and can set the priority in the most direct and effective way, so as to achieve more accurate detection route planning and optimize detection time and detection resources.

[0038] Further, step S400 includes the following steps:

[0039] Step S401: setting any target station waiting for detection in the detection route as the desired detection station, and when performing real-time detection on any target station according to the detection route, obtaining detection logs corresponding to the remaining photovoltaic stations except the desired detection station;

[0040] Step S402: randomly select a photovoltaic station from the remaining photovoltaic stations, obtain a newly generated detection record in the corresponding detection log of the photovoltaic station, and obtain the comprehensive evaluation value C of the detection record. ’ The waiting time t of the photovoltaic station from the last detection wait , setting the average coefficient ratio of the photovoltaic station to η ave , the expected evaluation value of the photovoltaic station when performing real-time detection on the expected detection station is calculated as C”=C ’ -t wait ×η ave ;

[0041] Step S403: Obtaining the abnormality assessment standard S of the photovoltaic station abnormal (ID), if C”<S abnormal (ID), the PV station is set as the expected detection station; if there are several PV stations set as the expected detection stations at the same time, they are sorted from small to large according to the expected evaluation value, a supplementary detection queue is generated and added to the end of the detection route, and a corrected detection route is obtained; every time the detection route is corrected, the newly set expected detection station is reminded of abnormalities, and an early warning is sent to the staff to pay special attention to the newly set expected detection station.

[0042] In order to better implement the above method, an intelligent photovoltaic station management and control system is also proposed. The management and control system includes a historical data analysis module, an abnormal level classification module, a detection route planning module and a real-time route adjustment module;

[0043] The historical data analysis module is used to construct a photovoltaic station data management system to record each detection process of any photovoltaic station, generate a detection log of the photovoltaic station and a number of corresponding detection records; analyze the operating data stored in any detection record, and make an abnormal judgment on the detection record;

[0044] The abnormality level classification module is used to set the risk level of any photovoltaic station based on the abnormality occurrence frequency presented in each detection record of the photovoltaic station; according to the level classification between different photovoltaic stations, corresponding abnormality assessment standards are set for different risk levels;

[0045] The detection route planning module is used to obtain the operating status of any photovoltaic station in the latest generated detection record, and obtain the expected evaluation result of the photovoltaic station at the current moment; based on the evaluation differences between different photovoltaic stations, the detection route between each photovoltaic station is planned;

[0046] The real-time route adjustment module is used to analyze the expected operation conditions of the remaining photovoltaic stations in real time and identify abnormalities of the remaining photovoltaic stations when the target station is inspected according to the planned inspection route; for any photovoltaic station with abnormalities, the pre-planned inspection route will be corrected and an abnormal warning will be sent.

[0047] Furthermore, the historical data analysis module includes an operation data acquisition unit and a station anomaly identification unit;

[0048] The operation data acquisition unit is used to construct a photovoltaic station data management system to record each detection process of any photovoltaic station, generate a detection log of the photovoltaic station and a number of corresponding detection records; the station abnormality identification unit is used to analyze the operation data stored in any detection record and make abnormal judgments on the detection record.

[0049] Further, the abnormal level classification module includes a risk level setting unit and an evaluation standard setting unit;

[0050] The risk level setting unit is used to set the risk level of any photovoltaic station based on the frequency of abnormal occurrence presented in each detection record of the photovoltaic station; the evaluation standard setting unit is used to set corresponding abnormal evaluation standards for different risk levels according to the level division between different photovoltaic stations.

[0051] Further, the detection route planning module includes an expectation evaluation calculation unit and a detection route generation unit;

[0052] The expected evaluation calculation unit is used to obtain the operating status of any photovoltaic station presented in the latest generated detection record, and obtain the expected evaluation result of the photovoltaic station at the current moment; the detection route generation unit is used to plan the detection route between each photovoltaic station based on the evaluation differences between different photovoltaic stations.

[0053] Further, the real-time route adjustment module includes a real-time station analysis unit and a detection route correction unit;

[0054] The real-time site analysis unit is used to analyze the expected operation conditions of the remaining photovoltaic sites in real time and identify abnormalities of the remaining photovoltaic sites when the target site is inspected according to the planned inspection route; the inspection route correction unit is used to correct the pre-planned inspection route and send an abnormality warning for any photovoltaic site with abnormalities.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] 1. The present invention analyzes historical operation data in detail, fully considers the operation status of photovoltaic stations, divides risk levels of different photovoltaic stations, and formulates different abnormality assessment standards, so as to more accurately identify abnormal conditions of photovoltaic stations, thereby more accurately planning detection routes and improving the accuracy of abnormality identification and the efficiency of abnormality detection;

[0057] 2. The present invention is different from the conventional detection route planning that arranges all photovoltaic stations at one time. The conventional detection route planning is more complicated and the route planning is difficult to be accurate. The present invention optimizes the conventional detection route and checks the photovoltaic stations in normal operation, only targeting the high-risk stations, so that the set detection route can be faster and more accurate, helping to quickly identify abnormal situations and save detection resources;

[0058] 3. Although the present invention optimizes the detection route, the real-time evaluation values ​​of other photovoltaic stations can still be predicted along the detection route, and the detection route can be adaptively adjusted to effectively avoid the occurrence of station abnormalities. While being efficient, it can also grasp the abnormal conditions of each photovoltaic station, use detection resources most efficiently, and improve detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of the steps of an intelligent photovoltaic station control method based on data analysis;

[0060] Figure 2 This is a structural diagram of an intelligent photovoltaic station management and control system based on data analysis. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Example: Figure 1 to Figure 2 As shown, the present invention provides an intelligent photovoltaic station control method based on data analysis, and the control method includes the following steps:

[0063] Step S100: constructing a photovoltaic station data management system to record each detection process of any photovoltaic station, generating a detection log of the photovoltaic station and a number of corresponding detection records; analyzing the operating data stored in any detection record, and making an abnormality judgment on the detection record;

[0064] Wherein, step S100 includes the following steps:

[0065] Step S101: numbering each photovoltaic station, and generating a detection log of each photovoltaic station in the photovoltaic station data management system according to the number; collecting the operation data generated by each component device of any photovoltaic station through the detection equipment, and transmitting it to the photovoltaic station data management system, and generating and storing a detection record in the detection log of the photovoltaic station;

[0066] Step S102: acquiring the operation data stored in any detection record, and dividing the operation data according to the component devices from which the data is collected, presetting evaluation rules of several dimensions for the operation data of any component device, and obtaining the evaluation value of the component device;

[0067] Step S103: preset a capability evaluation value for each component device in any photovoltaic station, and set the capability evaluation value of the i-th component device in the photovoltaic station corresponding to the detection record to A i , according to the formula:

[0068]

[0069] Where i and j are positive integers and i∈(1,e), j∈(1,e), A j is the capacity evaluation value of the jth component device, e is the number of component devices in the photovoltaic field station corresponding to the detection record, B j is the evaluation value of the jth component device; and the comprehensive evaluation value C presented in the test record is calculated;

[0070] Example 1: Assume that the component equipment of a photovoltaic station includes four component equipments, namely, photovoltaic components, inverters, combiner boxes, and transformers, and the capacity evaluation values ​​are 10, 9, 7, and 4 respectively; obtain the evaluation values ​​of the four component equipments as 90, 95, 93, and 94 respectively, and calculate the comprehensive evaluation value C=10 / 30×90+9 / 30×95+7 / 30×93+4 / 30×94=30+28.5+21.7+12.53=92.73;

[0071] Step S104: When there is an abnormal situation in each photovoltaic station, the comprehensive evaluation value of the corresponding detection record of each photovoltaic station is obtained, and the comprehensive evaluation value with the largest value is selected and set as the abnormal evaluation value C abnormal , if C<C abnormal, then the detection record is set as an abnormal detection record.

[0072] Step S200: setting a risk level for any photovoltaic station based on the frequency of abnormal occurrences in each detection record of the photovoltaic station; and setting corresponding abnormality assessment standards for different risk levels according to the level division between different photovoltaic stations;

[0073] Wherein, step S200 includes the following steps:

[0074] Step S201: obtaining a detection log of any photovoltaic station, extracting the record generation time of each detection record in the detection log, sorting the detection records from early to late according to the record generation time, and generating a detection record set of the detection log;

[0075] Step S202: Extract the generation time of each abnormal detection record from the detection record set to obtain the time interval between two adjacent abnormal detection records; set the k1th detection record and the k2th detection record in the detection record set as abnormal detection records, and obtain the time interval between the two abnormal detection records as Δt k1,k2 , according to the formula:

[0076]

[0077] Where k2>k1; calculate the abnormal occurrence frequency α between the k1th detection record and the k2th detection record k1,k2 ; Get the anomaly occurrence frequency between any two adjacent anomaly detection records, and calculate the average value to get the average occurrence frequency α of the anomaly detection records ’ ;

[0078] Step S203: Set the log generation time of the detection log as t0 and the record generation time of the last detection record in the detection record set as t1, and obtain the log duration as Δt=t1-t0; obtain the number of detection records in the detection record set as m, according to the formula:

[0079]

[0080] Calculate the average abnormal frequency α of the detection log ave ; If α ’ >α ave , then the photovoltaic station is marked with the first characteristic risk. If α ’ <α ave , then the photovoltaic station is marked with a second characteristic risk;

[0081] Step S204: Summarize the photovoltaic stations with the same characteristic risk mark to obtain a first characteristic station set and a second characteristic station set respectively; select a target photovoltaic station from the first characteristic station set, obtain the target detection log corresponding to the target photovoltaic station, and set the average abnormal frequency α of the target detection log ave and the average occurrence frequency α of anomaly detection records ’ , according to the formula:

[0082]

[0083] Among them, C abnormal is the abnormal assessment value; the abnormal assessment standard value C of the target photovoltaic station is calculated ’ abnormal ; Obtain the abnormal evaluation standard value of each photovoltaic station in the first characteristic station set, and calculate the average value to obtain the abnormal evaluation standard C1 of the first characteristic station set abnormal For each photovoltaic station in the second characteristic station set, the abnormal evaluation value C abnormal Set as the abnormal evaluation standard C2 of the second characteristic station set abnormal .

[0084] Step S300: obtaining the operating status of any photovoltaic station in the latest generated detection record, and obtaining the expected evaluation result of the photovoltaic station at the current moment; based on the evaluation differences between different photovoltaic stations, planning the detection routes between the photovoltaic stations;

[0085] Wherein, step S300 includes the following steps:

[0086] Step S301: randomly select a photovoltaic station, obtain the ID of the photovoltaic station, and obtain the abnormality assessment standard S of the photovoltaic station. abnormal (ID), if the photovoltaic station belongs to the first characteristic station set, then S abnormal (ID)=C1 abnormal , if the photovoltaic station belongs to the second characteristic station set, then S abnormal (ID)=C2 abnormal ;

[0087] Step S302: extract any two adjacent detection records from the corresponding detection log of the photovoltaic station. If the two detection records are not abnormal detection records, obtain the comprehensive evaluation difference ΔC and the generation time interval Δt of the two detection records, and calculate the characteristic coefficient ratio η=ΔC / Δt of the photovoltaic station between the two detection records; obtain the characteristic coefficient ratio of any two detection records that are not abnormal detection records, and calculate the average value to obtain the average coefficient ratio ηave ;

[0088] Step S302: Obtain the operation data of the latest detection record generated in the corresponding detection log of the photovoltaic station, and obtain the comprehensive evaluation value C presented by the latest detection record according to the preset evaluation standard. new ; Get the time interval between the latest generated detection record and the current time is Δt new , the expected evaluation value of the photovoltaic station at the current moment is calculated to be C ex =C new -Δt new ×η ave ; According to the formula:

[0089]

[0090] Calculate and obtain the expected characteristic value σ of the photovoltaic station at the current moment; if σ>0, set the photovoltaic station as the expected detection station;

[0091] Example 2: The comprehensive evaluation value of the latest detection record generated by the photovoltaic station is 95, and the average coefficient of the photovoltaic station accounts for 5%. The time interval between the latest detection record generated by the photovoltaic station and the current moment is set to 100 hours, and the expected evaluation value is C ex =95-5%×100=90; Set the photovoltaic station as the second characteristic station set, and get S abnormal (ID)=C2 abnormal =94, the expected characteristic value is σ=(94-90) / 94>0, then the photovoltaic station is set as the expected detection station;

[0092] Step S303: extracting an abnormality detection record with the shortest time interval from the current moment from the corresponding detection log of the photovoltaic station, and obtaining the time interval from the abnormality detection record to the current moment as Δt abnormal ; Get the number of detection records between the generation time of the abnormal detection record and the current time as m1, and calculate the actual abnormal occurrence frequency α of the photovoltaic station ac =Δt abnormal / m1;

[0093] Step S304: Obtain the average abnormal frequency of the corresponding detection log of the photovoltaic station as α ave , according to the formula:

[0094]

[0095] Calculate and obtain the detection priority value Y of the photovoltaic station; sort all the desired detection stations from large to small according to the detection priority value to generate a detection route;

[0096] Example 3: Based on Example 2, the expected characteristic value σ of the photovoltaic station is obtained to be 4.255%, and the average abnormal frequency of the corresponding detection log of the photovoltaic station is set to 100h / time, and the actual abnormal frequency of the photovoltaic station is 96h / time; the interval time from the abnormal detection record to the current moment is 95h, and the time interval from the latest generated detection record to the current moment is 50h, and it is calculated that Y=(4.255%+4 / 100)×95+50=57.84225.

[0097] Step S400: when the target station is inspected according to the planned inspection route, the expected operation conditions of the remaining photovoltaic stations are analyzed in real time, and abnormalities of the remaining photovoltaic stations are identified; for any photovoltaic station with abnormalities, the pre-planned inspection route is corrected and an abnormality warning is sent;

[0098] Wherein, step S400 includes the following steps:

[0099] Step S401: setting any target station waiting for detection in the detection route as the desired detection station, and when performing real-time detection on any target station according to the detection route, obtaining detection logs corresponding to the remaining photovoltaic stations except the desired detection station;

[0100] Step S402: randomly select a photovoltaic station from the remaining photovoltaic stations, obtain a newly generated detection record in the corresponding detection log of the photovoltaic station, and obtain the comprehensive evaluation value C of the detection record. ’ The waiting time t of the photovoltaic station from the last detection wait , setting the average coefficient ratio of the photovoltaic station to η ave , the expected evaluation value of the photovoltaic station when performing real-time detection on the expected detection station is calculated as C”=C ’ -t wait ×η ave ;

[0101] Step S403: Obtaining the abnormality assessment standard S of the photovoltaic station abnormal (ID), if C”<S abnormal (ID), the PV station is set as the expected detection station; if there are several PV stations set as the expected detection stations at the same time, they are sorted from small to large according to the expected evaluation value, a supplementary detection queue is generated and added to the end of the detection route, and a corrected detection route is obtained; every time the detection route is corrected, the newly set expected detection station is reminded of abnormalities, and an early warning is sent to the staff to pay special attention to the newly set expected detection station.

[0102] An intelligent photovoltaic station management and control system, the management and control system includes a historical data analysis module, an abnormal level classification module, a detection route planning module and a real-time route adjustment module;

[0103] The historical data analysis module is used to construct a photovoltaic station data management system to record each detection process of any photovoltaic station, generate a detection log of the photovoltaic station and a number of corresponding detection records; analyze the operating data stored in any detection record, and make an abnormal judgment on the detection record;

[0104] The abnormality level classification module is used to set the risk level of any photovoltaic station based on the abnormality occurrence frequency presented in each detection record of the photovoltaic station; according to the level classification between different photovoltaic stations, corresponding abnormality assessment standards are set for different risk levels;

[0105] The detection route planning module is used to obtain the operating status of any photovoltaic station in the latest generated detection record, and obtain the expected evaluation result of the photovoltaic station at the current moment; based on the evaluation differences between different photovoltaic stations, the detection route between each photovoltaic station is planned;

[0106] The real-time route adjustment module is used to analyze the expected operation conditions of the remaining photovoltaic stations in real time and identify abnormalities of the remaining photovoltaic stations when the target station is inspected according to the planned inspection route; for any photovoltaic station with abnormalities, the pre-planned inspection route will be corrected and an abnormal warning will be sent.

[0107] Among them, the historical data analysis module includes an operation data collection unit and a station abnormality identification unit;

[0108] The operation data acquisition unit is used to construct a photovoltaic station data management system to record each detection process of any photovoltaic station, generate a detection log of the photovoltaic station and a number of corresponding detection records; the station abnormality identification unit is used to analyze the operation data stored in any detection record and make abnormal judgments on the detection record.

[0109] Among them, the abnormal level classification module includes a risk level setting unit and an evaluation standard setting unit;

[0110] The risk level setting unit is used to set the risk level of any photovoltaic station based on the frequency of abnormal occurrence presented in each detection record of the photovoltaic station; the evaluation standard setting unit is used to set corresponding abnormal evaluation standards for different risk levels according to the level division between different photovoltaic stations.

[0111] Among them, the detection route planning module includes an expectation evaluation calculation unit and a detection route generation unit;

[0112] The expected evaluation calculation unit is used to obtain the operating status of any photovoltaic station presented in the latest generated detection record, and obtain the expected evaluation result of the photovoltaic station at the current moment; the detection route generation unit is used to plan the detection route between each photovoltaic station based on the evaluation differences between different photovoltaic stations.

[0113] Among them, the real-time route adjustment module includes a real-time station analysis unit and a detection route correction unit;

[0114] The real-time site analysis unit is used to analyze the expected operation conditions of the remaining photovoltaic sites in real time and identify abnormalities of the remaining photovoltaic sites when the target site is inspected according to the planned inspection route; the inspection route correction unit is used to correct the pre-planned inspection route and send an abnormality warning for any photovoltaic site with abnormalities.

[0115] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent photovoltaic station control method based on data analysis, characterized in that: The control method comprises the following steps: Step S100: constructing a photovoltaic station data management system to record each detection process of any photovoltaic station, generating a detection log of the photovoltaic station and a number of corresponding detection records; analyzing the operating data stored in any detection record, and making an abnormality judgment on the detection record; Step S200: setting a risk level for any photovoltaic station based on the frequency of abnormal occurrences in each detection record of the photovoltaic station; and setting corresponding abnormality assessment standards for different risk levels according to the level division between different photovoltaic stations; Step S300: obtaining the operating status of any photovoltaic station in the latest generated detection record, and obtaining the expected evaluation result of the photovoltaic station at the current moment; based on the evaluation differences between different photovoltaic stations, planning the detection routes between the photovoltaic stations; Step S400: When the target station is inspected according to the planned inspection route, the expected operation conditions of the remaining photovoltaic stations are analyzed in real time, and abnormalities of the remaining photovoltaic stations are identified; for any photovoltaic station with abnormalities, the pre-planned inspection route is corrected and an abnormality warning is sent.

2. According to claim 1, a method for intelligent photovoltaic station control based on data analysis is characterized in that: The step S100 includes the following steps: Step S101: numbering each photovoltaic station, and generating a detection log of each photovoltaic station in the photovoltaic station data management system according to the number; collecting the operation data generated by each component device of any photovoltaic station through the detection equipment, and transmitting it to the photovoltaic station data management system, and generating and storing a detection record in the detection log of the photovoltaic station; Step S102: acquiring the operation data stored in any detection record, and dividing the operation data according to the component devices from which the data is collected, presetting evaluation rules of several dimensions for the operation data of any component device, and obtaining the evaluation value of the component device; Step S103: preset a capability evaluation value for each component device in any photovoltaic station, and set the capability evaluation value of the i-th component device in the photovoltaic station corresponding to the detection record to A i , according to the formula: Where i and j are positive integers and i∈(1,e), j∈(1,e), A j is the capacity evaluation value of the jth component device, e is the number of component devices in the photovoltaic field station corresponding to the detection record, B j is the evaluation value of the jth component device; and the comprehensive evaluation value C presented in the test record is calculated; Step S104: When there is an abnormal situation in each photovoltaic station, the comprehensive evaluation value of the corresponding detection record of each photovoltaic station is obtained, and the comprehensive evaluation value with the largest value is selected and set as the abnormal evaluation value C abnormal , if C<C abnormal , then the detection record is set as an abnormal detection record.

3. According to the data analysis-based intelligent photovoltaic station control method of claim 2, it is characterized by: The step S200 includes the following steps: Step S201: obtaining a detection log of any photovoltaic station, extracting the record generation time of each detection record in the detection log, sorting the detection records from early to late according to the record generation time, and generating a detection record set of the detection log; Step S202: Extract the generation time of each abnormal detection record from the detection record set to obtain the time interval between two adjacent abnormal detection records; set the k1th detection record and the k2th detection record in the detection record set as abnormal detection records, and obtain the time interval between the two abnormal detection records as Δt k1,k2 , according to the formula: Where k2>k1; calculate the abnormal occurrence frequency α between the k1th detection record and the k2th detection record k1,k2 ; Get the anomaly occurrence frequency between any two adjacent anomaly detection records, and calculate the average value to get the average occurrence frequency α of the anomaly detection records ’ ; Step S203: Set the log generation time of the detection log as t0 and the record generation time of the last detection record in the detection record set as t1, and obtain the log duration as Δt=t1-t0; obtain the number of detection records in the detection record set as m, according to the formula: Calculate the average abnormal frequency α of the detection log ave ; If α ’ >α ave , then the photovoltaic station is marked with the first characteristic risk. If α ’ <α ave , then the photovoltaic station is marked with a second characteristic risk; Step S204: Summarize the photovoltaic stations with the same characteristic risk mark to obtain a first characteristic station set and a second characteristic station set respectively; select a target photovoltaic station from the first characteristic station set, obtain the target detection log corresponding to the target photovoltaic station, and set the average abnormal frequency α of the target detection log ave and the average occurrence frequency α of anomaly detection records ’ , according to the formula: Among them, C abnormal is the abnormal assessment value; the abnormal assessment standard value C of the target photovoltaic station is calculated ’ abnormal ; Obtain the abnormal evaluation standard value of each photovoltaic station in the first characteristic station set, and calculate the average value to obtain the abnormal evaluation standard C1 of the first characteristic station set abnormal For each photovoltaic station in the second characteristic station set, the abnormal evaluation value C abnormal Set as the abnormal evaluation standard C2 of the second characteristic station set abnormal .

4. According to claim 3, a method for intelligent photovoltaic station control based on data analysis is characterized in that: The step S300 includes the following steps: Step S301: randomly select a photovoltaic station, obtain the ID of the photovoltaic station, and obtain the abnormality assessment standard S of the photovoltaic station. abnormal (ID), if the photovoltaic station belongs to the first characteristic station set, then S abnormal (ID)=C1 abnormal , if the photovoltaic station belongs to the second characteristic station set, then S abnormal (ID)=C2 abnormal ; Step S302: extract any two adjacent detection records from the corresponding detection log of the photovoltaic station. If the two detection records are not abnormal detection records, obtain the comprehensive evaluation difference ΔC and the generation time interval Δt of the two detection records, and calculate the characteristic coefficient ratio η=ΔC / Δt of the photovoltaic station between the two detection records; obtain the characteristic coefficient ratio of any two detection records that are not abnormal detection records, and calculate the average value to obtain the average coefficient ratio η ave ; Step S302: Obtain the operation data of the latest detection record generated in the corresponding detection log of the photovoltaic station, and obtain the comprehensive evaluation value C presented by the latest detection record according to the preset evaluation standard. new ; Get the time interval between the latest generated detection record and the current time is Δt new , the expected evaluation value of the photovoltaic station at the current moment is calculated to be C ex =C new -Δt new ×η ave ; According to the formula: Calculate and obtain the expected characteristic value σ of the photovoltaic station at the current moment; if σ>0, set the photovoltaic station as the expected detection station; Step S303: extracting an abnormality detection record with the shortest time interval from the current moment from the corresponding detection log of the photovoltaic station, and obtaining the time interval from the abnormality detection record to the current moment as Δt abnormal ; Get the number of detection records between the generation time of the abnormal detection record and the current time as m1, and calculate the actual abnormal occurrence frequency α of the photovoltaic station ac =Δt abnormal / m1; Step S304: Obtain the average abnormal frequency of the corresponding detection log of the photovoltaic station as α ave , according to the formula: The detection priority value Y of the photovoltaic station is calculated; all the desired detection stations are sorted from large to small according to the detection priority value to generate a detection route.

5. According to claim 4, a method for intelligent photovoltaic station control based on data analysis is characterized in that: The step S400 includes the following steps: Step S401: setting any target station waiting for detection in the detection route as the desired detection station, and when performing real-time detection on any target station according to the detection route, obtaining detection logs corresponding to the remaining photovoltaic stations except the desired detection station; Step S402: randomly select a photovoltaic station from the remaining photovoltaic stations, obtain a newly generated detection record in the corresponding detection log of the photovoltaic station, and obtain the comprehensive evaluation value C of the detection record. ’ The waiting time t of the photovoltaic station from the last detection wait , setting the average coefficient ratio of the photovoltaic station to η ave , the expected evaluation value of the photovoltaic station when performing real-time detection on the expected detection station is calculated as C”=C ’ -t wait ×η ave ; Step S403: Obtaining the abnormality assessment standard S of the photovoltaic station abnormal (ID), if C”<S abnormal (ID), the PV station is set as the expected detection station; if there are several PV stations set as the expected detection stations at the same time, they are sorted from small to large according to the expected evaluation value, a supplementary detection queue is generated and added to the end of the detection route, and a corrected detection route is obtained; every time the detection route is corrected, the newly set expected detection station is reminded of abnormalities, and an early warning is sent to the staff to pay special attention to the newly set expected detection station.

6. An intelligent photovoltaic station control system, used to execute an intelligent photovoltaic station control method based on data analysis as described in any one of claims 1 to 5, characterized in that: The control system includes a historical data analysis module, an abnormal level classification module, a detection route planning module and a real-time route adjustment module; The historical data analysis module is used to construct a photovoltaic station data management system to record each detection process of any photovoltaic station, generate a detection log of the photovoltaic station and a number of corresponding detection records; analyze the operating data stored in any detection record, and make an abnormality judgment on the detection record; The abnormal level classification module is used to set the risk level of any photovoltaic station based on the abnormal occurrence frequency presented in each detection record of the photovoltaic station; according to the level classification between different photovoltaic stations, corresponding abnormal assessment standards are set for different risk levels; The detection route planning module is used to obtain the operating status of any photovoltaic station in the latest generated detection record, and obtain the expected evaluation result of the photovoltaic station at the current moment; based on the evaluation differences between different photovoltaic stations, the detection route between each photovoltaic station is planned; The real-time route adjustment module is used to analyze the expected operation conditions of the remaining photovoltaic stations in real time and identify abnormalities of the remaining photovoltaic stations when the target station is inspected according to the planned inspection route; for any photovoltaic station with abnormalities, the pre-planned inspection route is corrected and an abnormality warning is sent.

7. The intelligent photovoltaic station control system according to claim 6 is characterized by: The historical data analysis module includes an operation data acquisition unit and a station abnormality identification unit; The operation data acquisition unit is used to construct a photovoltaic station data management system to record each detection process of any photovoltaic station, generate a detection log of the photovoltaic station and a corresponding number of detection records; the station abnormality identification unit is used to analyze the operation data stored in any detection record and make abnormal judgments on the detection record.

8. The intelligent photovoltaic station control system according to claim 6 is characterized by: The abnormal level classification module includes a risk level setting unit and an evaluation standard setting unit; The risk level setting unit is used to set the risk level of any photovoltaic station based on the frequency of abnormal occurrence presented in each detection record of the photovoltaic station; the evaluation standard setting unit is used to set corresponding abnormal evaluation standards for different risk levels according to the level division between different photovoltaic stations.

9. The intelligent photovoltaic station control system according to claim 6 is characterized by: The detection route planning module includes an expectation evaluation calculation unit and a detection route generation unit; The expected evaluation calculation unit is used to obtain the operating status of any photovoltaic station presented in the latest generated detection record, and obtain the expected evaluation result of the photovoltaic station at the current moment; the detection route generation unit is used to plan the detection route between each photovoltaic station based on the evaluation differences between different photovoltaic stations.

10. The intelligent photovoltaic station management and control system according to claim 6, characterized in that: The real-time route adjustment module includes a real-time station analysis unit and a detection route correction unit; The real-time station analysis unit is used to analyze the expected operating conditions of the remaining photovoltaic stations in real time and identify abnormalities in the remaining photovoltaic stations when the target station is inspected according to the planned inspection route; the inspection route correction unit is used to correct the pre-planned inspection route and send an abnormality warning for any photovoltaic station with abnormalities.

Images