CN117728583A - Distributed photovoltaic cluster energy control monitoring system based on transfer learning - Google Patents
Distributed photovoltaic cluster energy control monitoring system based on transfer learning Download PDFInfo
- Publication number
- CN117728583A CN117728583A CN202311816631.6A CN202311816631A CN117728583A CN 117728583 A CN117728583 A CN 117728583A CN 202311816631 A CN202311816631 A CN 202311816631A CN 117728583 A CN117728583 A CN 117728583A
- Authority
- CN
- China
- Prior art keywords
- energy
- distributed photovoltaic
- module
- warning
- generated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 38
- 238000013526 transfer learning Methods 0.000 title claims abstract description 17
- 238000004146 energy storage Methods 0.000 claims abstract description 56
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 238000012546 transfer Methods 0.000 claims abstract description 22
- 238000013480 data collection Methods 0.000 claims abstract description 14
- 230000007613 environmental effect Effects 0.000 claims abstract description 14
- 238000013508 migration Methods 0.000 claims abstract description 7
- 230000005012 migration Effects 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Landscapes
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a distributed photovoltaic cluster energy control monitoring system based on transfer learning, and particularly relates to the field of remote control systems, comprising a data collection module, a transfer learning module, a monitoring module, an analysis comparison module, a warning module and an energy control module; the data collection module is used for collecting real-time energy output, environmental conditions and equipment state data from each distributed photovoltaic of the distributed photovoltaic cluster, and then transmitting the real-time energy output, environmental conditions and equipment state data to the migration learning module and the energy control module; the monitoring module is used for carrying out video monitoring on each distributed photovoltaic of the distributed photovoltaic clusters, storing the video as a monitoring video and then transmitting the monitoring video to the analysis and comparison module; the invention can rationally adjust the real-time energy output of the transfer energy storage equipment of the distributed photovoltaic cluster, can reduce the energy storage burden of the transfer energy storage equipment, avoid potential safety hazards, prolong the service life of the transfer energy storage equipment and ensure that the distributed photovoltaic cluster has more enough service life.
Description
Technical Field
The invention relates to the field of remote control systems, in particular to a distributed photovoltaic cluster energy control monitoring system based on transfer learning.
Background
A distributed photovoltaic cluster refers to a structure in which a plurality of independent but mutually coordinated photovoltaic power generation systems are combined together. Unlike large-scale centralized photovoltaic power stations, the design concept of the distributed photovoltaic clusters is to arrange small or medium-sized photovoltaic power generation systems at a plurality of places and to perform centralized management and scheduling by utilizing advanced communication and control technologies, the distributed photovoltaic clusters are widely popularized and applied in a plurality of countries and regions due to the advantages of the distributed photovoltaic clusters, particularly in cities and industrial areas, clean and renewable power resources can be effectively provided, but with use, the problem of unstable power conversion easily occurs due to environmental factors and use conditions of the distributed photovoltaic clusters, and if real-time energy output of transfer energy storage equipment of the distributed photovoltaic clusters cannot be well adjusted, huge potential safety hazards can be caused once supersaturation conditions occur, and the distributed photovoltaic clusters cannot be ensured to have more sufficient service lives.
In order to solve the above-mentioned defect, a technical scheme is provided.
Disclosure of Invention
In order to achieve the above purpose, the present invention provides the following technical solutions:
the distributed photovoltaic cluster energy control monitoring system based on transfer learning comprises a data collection module, a transfer learning module, a monitoring module, an analysis comparison module, a warning module and an energy control module;
the data collection module is used for collecting real-time energy output, environmental conditions and equipment state data from each distributed photovoltaic of the distributed photovoltaic cluster, and then transmitting the real-time energy output, environmental conditions and equipment state data to the migration learning module and the energy control module;
the monitoring module is used for carrying out video monitoring on each distributed photovoltaic of the distributed photovoltaic clusters, storing the video as a monitoring video and then transmitting the monitoring video to the analysis and comparison module;
the migration learning module inputs the real-time energy output, the environmental conditions and the equipment state data collected in the data collection module by means of the trained LSTM model, outputs the generated energy FDi when a time window is constructed according to the predicted demand, and transmits the generated energy FDi to the analysis and comparison module;
the analysis and comparison module is used for comparing the generated energy FDi and the actual generated energy in each distributed photovoltaic time window to obtain an offset index PYi, extracting image frames in a video in the time window, and then carrying out analysis operation to obtain an appearance interference index GRi in the time window;
the warning module respectively carries out warning judgment operation on the offset index PYi and the appearance interference index GRi to respectively obtain an offset grade value PJi and an appearance interference grade value GJi, and then converts the offset grade value PJi and the appearance interference grade value GJi into a warning signal set and transmits the warning signal set to the energy control module;
and the energy control module is used for adjusting the real-time energy output of the transfer energy storage equipment of the distributed photovoltaic cluster according to the warning signal set and the percentage BFI of the total energy storage occupied by the current energy storage energy of the transfer energy storage equipment of the distributed photovoltaic cluster.
In a preferred embodiment, the analysis comparison module performs a comparison operation on the generated energy FDi and the actual generated energy in each time window of the distributed photovoltaic, and the obtained offset index PYi refers to:
the actual generated energy of each distributed photovoltaic in the time window is marked as SFi, and then the SFi and the generated energy FDi of the corresponding distributed photovoltaic in the time window are substituted into an offset index PYi calculation formulaIn the method, k is the number of times of occurrence of a time window in a preset time interval, f1 and f2 are respectively the generated energy FDi when the distributed photovoltaic time window is generated, the actual generated energy is marked as a first proportionality coefficient preset by SFi, e1 and e2 are respectively the generated energy FDi when the distributed photovoltaic time window is generated, the actual generated energy is marked as a second proportionality coefficient preset by SFi, and f1, f2, e1 and e2 are all larger than zero.
In a preferred embodiment, the analysis and comparison module extracts image frames in the monitoring video within a time window, and then performs analysis operation to obtain an appearance interference index GRi in the time window;
the analysis comparison module extracts image frames in a monitoring video in a time window, each frame of image is divided into d grids by equidistant transverse lines and vertical lines respectively, the number g of grids which are shielded is counted, the proportion coefficient BLi of the total number of grids which are obtained by dividing the grids which are shielded in each frame of image by equidistant transverse lines and vertical lines is obtained through calculation, BLi=g/d is 100%, and then the average value of the proportion coefficient BLi in each frame of image in the extraction time window is calculated， />M is the number of frames of the image frame, and then the appearance interference index GRi,/-within the time window is calculated>。
In a preferred embodiment, the warning module performs a warning determination operation on the offset index PYi, and obtaining the offset ranking value PJi refers to:
offset index PYi and a preset warning threshold intervalComparing and judging to obtain a deviation grade value PJi when the deviation index is + ->When the offset level value PJ1 is generated, when the offset index +.>When the offset level value PJ2 is generated, when the offset index +.>At this time, an offset gradation value PJ3 is generated.
The warning module respectively warns the appearance interference index GRi of the judging operation, and the obtaining of the appearance interference grade value GJi refers to:
the appearance interference index GRi is compared with a preset warning threshold valueComparing and judging to obtain appearance interference grade value GJi, when the deviation index is +>In this case, the appearance interference level GJ1 is generated, and the shift index +.>In this case, the appearance interference level value GJ2 is generated.
In a preferred embodiment, the warning module converting the offset ranking value PJi and the appearance interference ranking value GJi into a set of warning signals means:
when the level value PJ1 is shifted, a first-level shifting warning signal is generated, when the level value PJ2 is shifted, a second-level shifting warning signal is generated, when the level value PJ3 is shifted, a third-level shifting warning signal is generated, when the level value GJ1 is interfered, a first-class interference warning signal is generated, when the level value GJ2 is interfered, a second-class interference warning signal is generated, then time unification processing is carried out, namely, in a preset time interval, the level value GJi of the appearance interference at each time window carries out signal conversion, and finally, a warning signal set is obtained through unification and summarization.
In a preferred embodiment, the energy control module adjusts the real-time energy output of the transfer energy storage devices of the distributed photovoltaic clusters according to the warning signal set and the percentage BFi of the total energy storage occupied by the current energy storage devices of the transfer energy storage devices of the distributed photovoltaic clusters, which is:
counting the number s1 of the first-stage offset warning signals, the number s2 of the second-stage offset warning signals, the number s3 of the third-stage offset warning signals, the number s4 of the first-stage interference warning signals and the number s5 of the second-stage interference warning signals in all warning signal sets sent by distributed photovoltaics in a preset time interval, marking the current energy storage energy of the transit energy storage equipment of the distributed photovoltaics as Dqi, marking the rated total energy storage energy as ZQi, calculating a warning value JGi, jgi= (a1+a1+a2+a2+a3+a3+a4+a4+a5) s 5/k, a1, a2, a3, a4, a5 are respectively the number of primary offset warning signals s1, the number of secondary offset warning signals s2, the number of tertiary offset warning signals s3, the number of class-one interference warning signals s4, the number of class-two interference warning signals s5, a preset number scaling factor of bfi=dqi/ZQi ×100%, and then the adjustment scaling value TZi is calculated by the warning value JGi, tzi= (JGi-T)/T, T is a preset standard adjustment scaling value whenThe real-time energy output Pgi of the transit energy storage device is maintained at a maximum value Pgmax when +.>When the real-time energy output Pgi is changed to pgi=pvi (tzi+1), PVi is the energy output of the transfer energy storage device in the previous time interval.
The invention has the technical effects and advantages that:
the invention can better control the energy situation of the distributed photovoltaic cluster by means of the data in the LSTM model with the memory capability, extracts the image frames in the video through the analysis and comparison module, monitors the image frames in the video, then carries out analysis operation to obtain the appearance interference index in the time window so as to control the self use situation of the distributed photovoltaic cluster, finally rationalizes and adjusts the real-time energy output of the intermediate energy storage equipment of the distributed photovoltaic cluster according to the warning signal set and the percentage value of the total energy occupied by the current energy storage energy of the intermediate energy storage equipment of the distributed photovoltaic cluster by the energy control module, reduces the energy storage burden of the intermediate energy storage equipment, avoids the potential safety hazard, prolongs the service life of the intermediate energy storage equipment and ensures the distributed photovoltaic cluster to have more sufficient service life.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
fig. 1 is a schematic diagram of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the following examples, i is represented by a project number only, and is not specifically defined as f1, f2, e1, e2,、/>、All of a1, a2, a3, a4, a5, T, q, d are greater than zero,/->。
Example 1
The distributed photovoltaic cluster energy control monitoring system based on transfer learning comprises a data collection module, a transfer learning module, a monitoring module, an analysis comparison module, a warning module and an energy control module;
the data collection module is used for collecting real-time energy output, environmental conditions and equipment state data from each distributed photovoltaic of the distributed photovoltaic cluster, and then transmitting the real-time energy output, environmental conditions and equipment state data to the migration learning module and the energy control module;
the monitoring module is used for carrying out video monitoring on each distributed photovoltaic of the distributed photovoltaic clusters, storing the video as a monitoring video and then transmitting the monitoring video to the analysis and comparison module;
the migration learning module inputs the real-time energy output, the environmental conditions and the equipment state data collected in the data collection module by means of the trained LSTM model, outputs the generated energy FDi when a time window is constructed according to the predicted demand, and transmits the generated energy FDi to the analysis and comparison module; the device state data refers to the on and off states of each distributed photovoltaic of the distributed photovoltaic cluster, and under the condition that the device state is off, the energy output and the environmental conditions of the distributed photovoltaic are not collected, and the long-short-term memory network, namely the LSTM model, is described as follows:
the LSTM model is a special recurrent neural network structure, is suitable for processing sequence data with time dependence, and can predict future generated energy according to historical weather data, solar radiation, temperature, humidity and other factors for predicting the generated energy of the photovoltaic power. The following is a simplified step description illustrating how the LSTM is used to make predictions of photovoltaic power generation:
and (3) data collection: historical photovoltaic power generation data (such as hourly or daily power generation) is collected, and other environmental parameters related to the power generation, such as solar irradiance, temperature, wind speed, humidity and the like, are collected.
Data preprocessing: missing value processing: any missing values in the dataset are processed.
Normalization or normalization: to make model training more stable, all input features are normalized or normalized to a fixed range, such as [0,1].
Sequence construction: a time window is constructed according to the predicted demand, for example, using data of the past 24 hours to predict the amount of power generation of the next hour.
Model construction: an appropriate LSTM architecture is selected. This may include multiple layers of LSTM cells, dropout layers, and one or more dense layers, and determining the number of input features and the time step.
Model training: the LSTM model is trained using historical data, using a portion of the data as a validation set to monitor the performance of the model and avoid overfitting.
Model evaluation: a separate test dataset is used to evaluate the performance of the model and a measure of prediction error, such as mean square error or root mean square error, is calculated.
Model prediction: for new, unknown input data, predictions are made using a trained LSTM model.
Because the LSTM model has memory capability, long-term dependence in time series data can be captured, so that the LSTM model is very suitable for predicting photovoltaic power generation capacity with complex time dynamic characteristics, and distributed photovoltaic cluster energy sources can be better controlled and monitored through data acquisition in the LSTM model.
The analysis and comparison module is used for comparing the generated energy FDi and the actual generated energy in each distributed photovoltaic time window to obtain an offset index PYi, extracting image frames in a video in the time window, and then carrying out analysis operation to obtain an appearance interference index GRi in the time window; the time window may be a time segment in units of minutes, hours, days, months, etc.;
the warning module respectively carries out warning judgment operation on the offset index PYi and the appearance interference index GRi to respectively obtain an offset grade value PJi and an appearance interference grade value GJi, and then converts the offset grade value PJi and the appearance interference grade value GJi into a warning signal set and transmits the warning signal set to the energy control module;
and the energy control module is used for adjusting the real-time energy output of the transfer energy storage equipment of the distributed photovoltaic cluster according to the warning signal set and the percentage BFI of the total energy storage occupied by the current energy storage energy of the transfer energy storage equipment of the distributed photovoltaic cluster.
The analysis and comparison module compares the generated energy FDi and the actual generated energy in each distributed photovoltaic time window, and the obtained offset index PYi refers to:
marking the actual generated energy of each distributed photovoltaic in a time windowRecorded as SFi, and then the generated energy FDi when the SFi and the corresponding distributed photovoltaic time window are substituted into an offset index PYi calculation formulaWherein k is the number of times of occurrence of a time window in a preset time interval, f1 and f2 are respectively the generated energy FDi when the distributed photovoltaic time window is generated, the actual generated energy is marked as a first proportionality coefficient preset by SFi, e1 and e2 are respectively the generated energy FDi when the distributed photovoltaic time window is generated, the actual generated energy is marked as a second proportionality coefficient preset by SFi, f1, f2, e1 and e2 are all larger than zero, the time difference value of the preset time interval is an integer multiple of the time difference value of the time window, for example, the time difference value of the time interval is 24 hours, and the time difference value of the time window is 8 hours.
The analysis and comparison module extracts image frames in a time window, monitors the video, and then performs analysis operation to obtain an appearance interference index GRi in the time window;
the analysis and comparison module extracts image frames in a monitoring video in a time window, each frame of image is divided into d grids by equidistant transverse lines and vertical lines respectively, the number g of grids which are shielded is counted, the shielded grids refer to that distributed photovoltaic cannot absorb light energy well due to dirt or other abnormal conditions, the proportion coefficient BLi of the total number of grids which are obtained by dividing the shielded grids in each frame of image by equidistant transverse lines and vertical lines is obtained through calculation, BLi=g/d is 100%, and then the average value of the proportion coefficient BLi in each frame of image in the extraction time window is calculated， />M is the number of frames of the image frame, and then the appearance interference index GRi,/-within the time window is calculated>。
The warning module performs a warning determination operation on the offset index PYi, and obtaining the offset grade value PJi refers to:
offset index PYi and a preset warning threshold intervalComparing and judging to obtain a deviation grade value PJi when the deviation index is + ->When the offset level value PJ1 is generated, when the offset index +.>When the offset level value PJ2 is generated, when the offset index +.>At this time, an offset gradation value PJ3 is generated.
The warning module respectively warns the appearance interference index GRi of the judging operation, and the obtaining of the appearance interference grade value GJi refers to:
the appearance interference index GRi is compared with a preset warning threshold valueComparing and judging to obtain appearance interference grade value GJi, when the deviation index is +>In this case, the appearance interference level GJ1 is generated, and the shift index +.>In this case, the appearance interference level value GJ2 is generated.
The warning module converting the offset ranking value PJi and the appearance interference ranking value GJi into a set of warning signals refers to:
when the level value PJ1 is shifted, a first-level shifting warning signal is generated, when the level value PJ2 is shifted, a second-level shifting warning signal is generated, when the level value PJ3 is shifted, a third-level shifting warning signal is generated, when the level value GJ1 is interfered, a first-class interference warning signal is generated, when the level value GJ2 is interfered, a second-class interference warning signal is generated, then time unification processing is carried out, namely, in a preset time interval, the level value GJi of the first-class interference warning signal and the second-class interference warning signal are subjected to signal conversion in each time window, and finally, warning signal sets are unified and collected, so that multiple times of the first-class interference warning signal and the second-class interference warning signal can occur in the warning signal sets.
The energy control module occupies the percentage value BFI of the total energy storage capacity of the energy storage equipment according to the warning signal set and the transfer energy storage equipment of the distributed photovoltaic cluster, and the adjustment of the real-time energy output capacity of the transfer energy storage equipment of the distributed photovoltaic cluster is as follows:
counting the number s1 of the first-stage offset warning signals, the number s2 of the second-stage offset warning signals, the number s3 of the third-stage offset warning signals, the number s4 of the first-stage interference warning signals and the number s5 of the second-stage interference warning signals in all warning signal sets sent by distributed photovoltaics in a preset time interval, marking the current energy storage energy of the transit energy storage equipment of the distributed photovoltaics as Dqi, marking the rated total energy storage energy as ZQi, calculating a warning value JGi, jgi= (a1+a1+a2+a2+a3+s3+a4+a4+a5+a5)/k, a1, a2, a3, a4, a5 are preset number scaling coefficients of the number of primary offset warning signals s1, the number of secondary offset warning signals s2, the number of tertiary offset warning signals s3, the number of one type of interference warning signals s4, the number of two type of interference warning signals s5, respectively, bfi=dqi/ZQi ×100% and then the real-time energy output of the intermediate-conversion energy storage devices of the distributed photovoltaic cluster is adjusted by means of the warning values JGi, BFi.
Example 2
In embodiment 1, the adjustment of the real-time energy output of the intermediate-conversion energy storage device of the distributed photovoltaic cluster by the warning values JGi, BFi means:
calculating a regulating proportion value TZi by a warning value JGi, wherein TZi= (JGi-T)/T is a preset standard regulating contrast value, and whenThe real-time energy output Pgi of the transit energy storage device is maintained at a maximum value Pgmax when +.>When the real-time energy output Pgi is changed to pgi=pvi (tzi+1), PVi is the energy output of the transfer energy storage device in the previous time interval, PVi is obtained by data collection of the data collection module, q is a preset health threshold of the transfer energy storage device, and when->When the power generation system is used, the real-time energy output Pgi of the transfer energy storage equipment is maintained at the maximum value Pgmax, so that the energy storage burden of the transfer energy storage equipment can be reduced, the service life of the transfer energy storage equipment can be prolonged, and the transfer energy storage equipment is the existing equipment configured in the distributed photovoltaic cluster and used for uniformly collecting and outputting the power, and is not repeated herein.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present application are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.
In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. The distributed photovoltaic cluster energy control monitoring system based on transfer learning is characterized by comprising a data collection module, a transfer learning module, a monitoring module, an analysis and comparison module, a warning module and an energy control module;
the data collection module is used for collecting real-time energy output, environmental conditions and equipment state data from each distributed photovoltaic of the distributed photovoltaic cluster, and then transmitting the real-time energy output, environmental conditions and equipment state data to the migration learning module and the energy control module;
the monitoring module is used for carrying out video monitoring on each distributed photovoltaic of the distributed photovoltaic clusters, storing the video as a monitoring video and then transmitting the monitoring video to the analysis and comparison module;
the migration learning module inputs the real-time energy output, the environmental conditions and the equipment state data collected in the data collection module by means of the trained LSTM model, outputs the generated energy FDi when a time window is constructed according to the predicted demand, and transmits the generated energy FDi to the analysis and comparison module;
the analysis and comparison module is used for comparing the generated energy FDi and the actual generated energy in each distributed photovoltaic time window to obtain an offset index PYi, extracting image frames in a video in the time window, and then carrying out analysis operation to obtain an appearance interference index GRi in the time window;
the warning module respectively carries out warning judgment operation on the offset index PYi and the appearance interference index GRi to respectively obtain an offset grade value PJi and an appearance interference grade value GJi, and then converts the offset grade value PJi and the appearance interference grade value GJi into a warning signal set and transmits the warning signal set to the energy control module;
and the energy control module is used for adjusting the real-time energy output of the transfer energy storage equipment of the distributed photovoltaic cluster according to the warning signal set and the percentage BFI of the total energy storage occupied by the current energy storage energy of the transfer energy storage equipment of the distributed photovoltaic cluster.
2. The transfer learning-based distributed photovoltaic cluster energy control monitoring system according to claim 1, wherein the analysis comparison module performs a comparison operation on the generated energy FDi and the actual generated energy in each of the time windows of the distributed photovoltaic, and the obtaining of the offset index PYi refers to:
the actual generated energy of each distributed photovoltaic in the time window is marked as SFi, and then the SFi and the generated energy FDi of the corresponding distributed photovoltaic in the time window are substituted into an offset index PYi calculation formulaIn the method, k is the number of times of occurrence of a time window in a preset time interval, f1 and f2 are respectively the generated energy FDi when the distributed photovoltaic time window is generated, the actual generated energy is marked as a first proportionality coefficient preset by SFi, e1 and e2 are respectively the generated energy FDi when the distributed photovoltaic time window is generated, the actual generated energy is marked as a second proportionality coefficient preset by SFi, and f1, f2, e1 and e2 are all larger than zero.
3. The distributed photovoltaic cluster energy control monitoring system based on transfer learning according to claim 2, wherein the analysis and comparison module extracts image frames in the monitoring video within a time window, and then performs an analysis operation to obtain an appearance interference index GRi within the time window;
the analysis and comparison module extracts image frames in the monitoring video in a time window, and each frame of image is respectively marked by equidistant transverse lines and vertical linesDividing the frame image into d grids, counting the number g of the blocked grids, calculating to obtain the proportionality coefficient BLi of the total number of the grids which are obtained by dividing the blocked grids in each frame image by equidistant transverse lines and vertical lines, wherein BLi=g/d is 100%, and calculating the average value of the proportionality coefficients BLi in each frame image in the extraction time window，/>M is the number of frames of the image frame, and then the appearance interference index GRi,/-within the time window is calculated>。
4. The distributed photovoltaic cluster energy control monitoring system based on transfer learning of claim 3, wherein the warning module performs a warning determination operation on the offset index PYi, and obtaining the offset grade value PJi refers to:
offset index PYi and a preset warning threshold intervalComparing and judging to obtain a deviation grade value PJi when the deviation index is + ->When the offset level value PJ1 is generated, when the offset index +.>When the offset level value PJ2 is generated, when the offset index +.>At this time, an offset gradation value PJ3 is generated.
5. The distributed photovoltaic cluster energy control monitoring system based on transfer learning of claim 4, wherein the warning module respectively warns the appearance interference index GRi of the determining operation, and obtaining the appearance interference level value GJi means:
the appearance interference index GRi is compared with a preset warning threshold valueComparing and judging to obtain appearance interference grade value GJi, when the deviation index is +>In this case, the appearance interference level GJ1 is generated, and the shift index +.>In this case, the appearance interference level value GJ2 is generated.
6. The distributed photovoltaic cluster energy control monitoring system based on transfer learning of claim 5, wherein the conversion of the offset ranking value PJi and the appearance interference ranking value GJi into a warning signal set by the warning module means:
when the level value PJ1 is shifted, a first-level shifting warning signal is generated, when the level value PJ2 is shifted, a second-level shifting warning signal is generated, when the level value PJ3 is shifted, a third-level shifting warning signal is generated, when the level value GJ1 is interfered, a first-class interference warning signal is generated, when the level value GJ2 is interfered, a second-class interference warning signal is generated, then time unification processing is carried out, namely, in a preset time interval, the level value GJi of the appearance interference at each time window carries out signal conversion, and finally, a warning signal set is obtained through unification and summarization.
7. The transfer learning-based distributed photovoltaic cluster energy control monitoring system of claim 6, wherein the energy control module adjusts the real-time energy output of the intermediate energy storage devices of the distributed photovoltaic cluster according to the warning signal set and the percentage BFi of the total energy stored by the current energy stored by the intermediate energy storage devices of the distributed photovoltaic cluster, which is:
counting the number s1 of the first-stage offset warning signals, the number s2 of the second-stage offset warning signals, the number s3 of the third-stage offset warning signals, the number s4 of the first-stage interference warning signals and the number s5 of the second-stage interference warning signals in all warning signal sets sent by distributed photovoltaics in a preset time interval, marking the current energy storage energy of the transit energy storage equipment of the distributed photovoltaics as Dqi, marking the rated total energy storage energy as ZQi, calculating a warning value JGi, jgi= (a1+a1+a2+a2+a3+a3+a4+a4+a5) s 5/k, a1, a2, a3, a4, a5 are respectively the number of primary offset warning signals s1, the number of secondary offset warning signals s2, the number of tertiary offset warning signals s3, the number of class-one interference warning signals s4, the number of class-two interference warning signals s5, a preset number scaling factor of bfi=dqi/ZQi ×100%, and then the adjustment scaling value TZi is calculated by the warning value JGi, tzi= (JGi-T)/T, T is a preset standard adjustment scaling value whenThe real-time energy output Pgi of the transit energy storage device is maintained at a maximum value Pgmax when +.>When the real-time energy output Pgi is changed to pgi=pvi (tzi+1), PVi is the energy output of the transfer energy storage device in the previous time interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311816631.6A CN117728583B (en) | 2023-12-27 | Distributed photovoltaic cluster energy control monitoring system based on transfer learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311816631.6A CN117728583B (en) | 2023-12-27 | Distributed photovoltaic cluster energy control monitoring system based on transfer learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117728583A true CN117728583A (en) | 2024-03-19 |
| CN117728583B CN117728583B (en) | 2024-05-31 |
Family
ID=
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20220049390A (en) * | 2020-10-14 | 2022-04-21 | (주) 티이에프 | Apparatus and method for automatically monitoring the condition of facilities by integrated management of the data collected from the solar power generation system |
| CN114386314A (en) * | 2021-12-09 | 2022-04-22 | 国网辽宁省电力有限公司经济技术研究院 | Non-invasive modeling method of comprehensive energy system based on zero sample learning |
| CN115173550A (en) * | 2022-06-07 | 2022-10-11 | 华能南京金陵发电有限公司 | Distributed photovoltaic power generation real-time monitoring method and system |
| CN115699149A (en) * | 2020-07-10 | 2023-02-03 | 谷歌有限责任公司 | Dynamic power converter switching for displays based on predicted power usage |
| US20230080737A1 (en) * | 2020-05-27 | 2023-03-16 | North China Electric Power University | Federated Learning-Based Regional Photovoltaic Power Probabilistic Forecasting Method and Coordinated Control System |
| CN116720631A (en) * | 2023-08-09 | 2023-09-08 | 深圳市洛丁光电有限公司 | Distributed photovoltaic power generation electric quantity analysis and prediction method, system and storage medium |
| CN116760031A (en) * | 2023-08-17 | 2023-09-15 | 北京弘象科技有限公司 | High-time-resolution photovoltaic power prediction method and device based on meteorological data |
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230080737A1 (en) * | 2020-05-27 | 2023-03-16 | North China Electric Power University | Federated Learning-Based Regional Photovoltaic Power Probabilistic Forecasting Method and Coordinated Control System |
| CN115699149A (en) * | 2020-07-10 | 2023-02-03 | 谷歌有限责任公司 | Dynamic power converter switching for displays based on predicted power usage |
| KR20220049390A (en) * | 2020-10-14 | 2022-04-21 | (주) 티이에프 | Apparatus and method for automatically monitoring the condition of facilities by integrated management of the data collected from the solar power generation system |
| CN114386314A (en) * | 2021-12-09 | 2022-04-22 | 国网辽宁省电力有限公司经济技术研究院 | Non-invasive modeling method of comprehensive energy system based on zero sample learning |
| CN115173550A (en) * | 2022-06-07 | 2022-10-11 | 华能南京金陵发电有限公司 | Distributed photovoltaic power generation real-time monitoring method and system |
| CN116720631A (en) * | 2023-08-09 | 2023-09-08 | 深圳市洛丁光电有限公司 | Distributed photovoltaic power generation electric quantity analysis and prediction method, system and storage medium |
| CN116760031A (en) * | 2023-08-17 | 2023-09-15 | 北京弘象科技有限公司 | High-time-resolution photovoltaic power prediction method and device based on meteorological data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| De Benedetti et al. | Anomaly detection and predictive maintenance for photovoltaic systems | |
| KR102159692B1 (en) | solar photovoltatic power generation forecasting apparatus and method based on big data analysis | |
| CN108256697B (en) | Prediction method for short-term load of power system | |
| Xiao et al. | Data mining in building automation system for improving building operational performance | |
| CN110807550B (en) | Distribution transformer overload recognition and early warning method based on neural network and terminal equipment | |
| WO2019196869A1 (en) | Method for determining list of patrolling base stations, and patrolling apparatus | |
| CN111488896B (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
| CN116739562A (en) | LSTM-based power distribution network stability operation and maintenance method | |
| KR20230038281A (en) | Monitoring method, system and computer readable storage medium of wind turbine generator system | |
| Cui et al. | An optimized swinging door algorithm for wind power ramp event detection | |
| Nolting et al. | Can energy system modeling benefit from artificial neural networks? Application of two-stage metamodels to reduce computation of security of supply assessments | |
| CN115313355A (en) | Automatic prediction method and system for big data of smart power grid in short-term load prediction | |
| CN114266602A (en) | Deep learning electricity price prediction method and device for multi-source data fusion of power internet of things | |
| CN117728583B (en) | Distributed photovoltaic cluster energy control monitoring system based on transfer learning | |
| CN117200352A (en) | Photovoltaic power generation regulation and control method and system based on cloud edge fusion | |
| CN117728583A (en) | Distributed photovoltaic cluster energy control monitoring system based on transfer learning | |
| CN114460890B (en) | Remote monitoring system and method for unattended power distribution room | |
| Guan et al. | Advanced load forecast with hierarchical forecasting capability | |
| CN114429240A (en) | Method and device for monitoring running state of highway equipment | |
| Dong et al. | Image-based with peak load ensemble prediction system for demand response in smart grid | |
| CN117728587B (en) | Real-time monitoring system and method for operation data of new energy power generation equipment | |
| US20210304099A1 (en) | Technique for Utility Network Management | |
| CN117113267B (en) | Prediction model training method based on big data and photovoltaic power generation performance detection method | |
| Lin et al. | Early fault prediction for wind turbines based on deep learning | |
| CN115811278B (en) | Distributed photovoltaic fault detection method and device based on discrete rate |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |