CN117076898A - Photoelectric conversion method, device, equipment and storage medium - Google Patents
Photoelectric conversion method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117076898A CN117076898A CN202311054897.1A CN202311054897A CN117076898A CN 117076898 A CN117076898 A CN 117076898A CN 202311054897 A CN202311054897 A CN 202311054897A CN 117076898 A CN117076898 A CN 117076898A
- Authority
- CN
- China
- Prior art keywords
- photoelectric
- conversion efficiency
- signal
- module
- photoelectric conversion
- 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
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 469
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000003287 optical effect Effects 0.000 claims abstract description 274
- 230000005540 biological transmission Effects 0.000 claims abstract description 168
- 238000004458 analytical method Methods 0.000 claims abstract description 48
- 238000011156 evaluation Methods 0.000 claims abstract description 48
- 238000013507 mapping Methods 0.000 claims abstract description 14
- 239000013598 vector Substances 0.000 claims description 101
- 238000010586 diagram Methods 0.000 claims description 35
- 230000006870 function Effects 0.000 claims description 32
- 230000003595 spectral effect Effects 0.000 claims description 32
- 230000006855 networking Effects 0.000 claims description 22
- 238000013139 quantization Methods 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000004927 fusion Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 4
- 230000005693 optoelectronics Effects 0.000 description 14
- 230000008569 process Effects 0.000 description 14
- 238000012545 processing Methods 0.000 description 9
- 239000000284 extract Substances 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 230000003750 conditioning effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Optical Communication System (AREA)
Abstract
The invention relates to the field of optical communication, and discloses a photoelectric conversion method, a device, equipment and a storage medium, which are used for improving photoelectric transmission efficiency between photoelectric modules. The method comprises the following steps: calculating a first photoelectric conversion efficiency from the input optical signal and the output electrical signal, and calculating a second photoelectric conversion efficiency from the input electrical signal and the output optical signal; performing distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and performing distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map; extracting features to obtain a plurality of first conversion efficiency features and a plurality of second conversion efficiency features; inputting the first conversion efficiency characteristics and the second conversion efficiency characteristics into a photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index; and constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the photoelectric conversion performance evaluation index of each photoelectric module.
Description
Technical Field
The present invention relates to the field of optical communications, and in particular, to a photoelectric conversion method, apparatus, device, and storage medium.
Background
With the rapid development of photoelectric transmission technology, a photoelectric module plays an important role as a key component in the fields of optical communication, optical sensing, optical network and the like. In order to ensure efficient performance and reliability of the photoelectric transmission system, performance evaluation of the photoelectric module is an indispensable task. Conventional methods typically require testing and evaluation of each photovoltaic module individually, which is not only time consuming and labor intensive, but also fails to fully analyze interactions and synergies between photovoltaic modules.
The conventional method for evaluating the performance of the photoelectric module needs to test each module one by one, and may have limitations on different types and scales of photoelectric modules, so that the transmission efficiency of the existing scheme is low, and the transmission performance of the photoelectric module is not high.
Disclosure of Invention
The invention provides a photoelectric conversion method, a photoelectric conversion device, photoelectric conversion equipment and a storage medium, which are used for improving photoelectric transmission efficiency between photoelectric modules.
The first aspect of the present invention provides a photoelectric conversion method including:
controlling a plurality of photoelectric modules to carry out photoelectric transmission through a preset first photoelectric transmission strategy, and collecting a transmission signal set of each photoelectric module;
Classifying the transmission signals of the transmission signal set to obtain an input optical signal and an output electrical signal when each photoelectric module is used as a signal receiving end and an input electrical signal and an output optical signal when each photoelectric module is used as a signal transmitting end;
calculating a first photoelectric conversion efficiency of each photoelectric module according to the input optical signal and the output electrical signal, and calculating a second photoelectric conversion efficiency of each photoelectric module according to the input electrical signal and the output optical signal;
performing distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and performing distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map;
extracting features of the first conversion efficiency distribution diagram to obtain a plurality of first conversion efficiency features, and extracting features of the second conversion efficiency distribution diagram to obtain a plurality of second conversion efficiency features;
inputting the first conversion efficiency characteristics and the second conversion efficiency characteristics into a preset photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index of each photoelectric module;
And constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the photoelectric conversion performance evaluation index of each photoelectric module.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the classifying the transmission signal set to obtain an input optical signal and an output electrical signal when each optoelectronic module is used as a signal receiving end, and an input electrical signal and an output optical signal when each optoelectronic module is used as a signal sending end includes:
acquiring first optical power and spectral characteristics of an optical signal and first voltage characteristics of an electric signal when each photoelectric module is used as a signal receiving end, and acquiring second optical power and spectral characteristics of the optical signal and second voltage characteristics of the electric signal when each photoelectric module is used as a signal transmitting end;
determining a first optical signal clustering center based on the first optical power and the spectral characteristics, determining a first electric signal clustering center according to the first voltage characteristics, and simultaneously determining a second optical signal clustering center based on the second optical power and the spectral characteristics, and determining a second electric signal clustering center according to the second voltage characteristics;
carrying out optical signal clustering on the transmission signal set based on the first optical signal clustering center to obtain an input optical signal when each photoelectric module is used as a signal receiving end, and carrying out electric signal clustering on the transmission signal set based on the first electric signal clustering center to obtain an output electric signal when each photoelectric module is used as the signal receiving end;
And carrying out optical signal clustering on the transmission signal set based on the second optical signal clustering center to obtain an output optical signal when each photoelectric module is used as a signal transmitting end, and carrying out electric signal clustering on the transmission signal set based on the first electric signal clustering center to obtain an input electric signal when each photoelectric module is used as the signal transmitting end.
With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, the calculating a first photoelectric conversion efficiency of each photoelectric module according to the input optical signal and the output electrical signal, and calculating a second photoelectric conversion efficiency of each photoelectric module according to the input electrical signal and the output optical signal includes:
performing optical power quantization conversion on the input optical signals to obtain a first optical power value of each input optical signal, and performing voltage quantization conversion on the output electrical signals to obtain a first voltage value of each output electrical signal;
performing optical power quantization conversion on the output optical signals to obtain a second optical power value of each output optical signal, and performing voltage quantization conversion on the input electrical signals to obtain a second voltage value of each input electrical signal;
And calculating the first photoelectric conversion efficiency of each photoelectric module according to the first optical power value and the first voltage value, and calculating the second photoelectric conversion efficiency of each photoelectric module according to the second optical power value and the second voltage value.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, the performing profile conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency profile, and performing profile mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency profile, where the performing step includes:
calculating a first kernel bandwidth of the first photoelectric conversion efficiency based on a preset first kernel density function;
performing kernel density estimation according to the first kernel density function and the first kernel bandwidth to obtain a first conversion efficiency distribution diagram;
calculating a second kernel bandwidth of the second photoelectric conversion efficiency based on a preset second kernel density function;
and performing kernel density estimation according to the second kernel density function and the second kernel bandwidth to obtain a second conversion efficiency distribution diagram.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the performing feature extraction on the first conversion efficiency distribution map to obtain a plurality of first conversion efficiency features, and performing feature extraction on the second conversion efficiency distribution map to obtain a plurality of second conversion efficiency features, where the performing step includes:
Extracting a plurality of first distribution characteristic data points corresponding to the first conversion efficiency distribution map, and calculating a plurality of second distribution characteristic data points corresponding to the second conversion efficiency distribution map;
generating a first standard characteristic value and a second standard characteristic value of the first conversion efficiency distribution diagram through a preset box diagram rule;
the first characteristic comparison result of each first distribution characteristic data point is obtained through characteristic comparison between the plurality of first distribution characteristic data points and the first standard characteristic value, and a plurality of first conversion efficiency characteristics are generated according to the first characteristic comparison result;
and respectively carrying out feature comparison on the plurality of second distribution feature data points and the second standard feature values to obtain a second feature comparison result of each second distribution feature data point, and generating a plurality of second conversion efficiency features according to the second feature comparison result.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, inputting the plurality of first conversion efficiency features and the plurality of second conversion efficiency features into a preset photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, to obtain a photoelectric conversion performance evaluation index of each photoelectric module, where the method includes:
Performing feature coding on the plurality of first conversion efficiency features to obtain a first feature vector, and performing feature coding on the plurality of second conversion efficiency features to obtain a second feature vector;
vector fusion is carried out on the first feature vector and the second feature vector, and a first target feature vector is obtained;
inputting the first target feature vector into a preset photoelectric conversion performance analysis model, wherein the photoelectric conversion performance analysis model comprises: a first threshold cycle network, a second threshold cycle network, and two full-connection layers;
extracting hidden state features of the first target feature vector through the first threshold cycle network to obtain a hidden state feature vector;
inputting the hidden state feature vector into the second threshold circulation network to perform feature conversion to obtain a second target feature vector;
and inputting the second target feature vector into the two full-connection layers to predict the photoelectric conversion performance, so as to obtain the photoelectric conversion performance evaluation index of each photoelectric module.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, the constructing a second photoelectric transmission policy of the plurality of photoelectric modules according to a photoelectric conversion performance evaluation index of each photoelectric module includes:
Constructing a photoelectric transmission networking distribution structure among the plurality of photoelectric modules;
performing dependency calculation on transmission nodes of the photoelectric transmission networking distribution structure according to the photoelectric conversion performance evaluation index of each photoelectric module to obtain the dependency networking distribution structure of the plurality of photoelectric modules;
and constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the membership networking distribution structure.
A second aspect of the present invention provides a photoelectric conversion apparatus including:
the transmission module is used for controlling the plurality of photoelectric modules to carry out photoelectric transmission through a preset first photoelectric transmission strategy and collecting a transmission signal set of each photoelectric module;
the classification module is used for classifying the transmission signals of the transmission signal set to obtain an input optical signal and an output electrical signal when each photoelectric module is used as a signal receiving end and an input electrical signal and an output optical signal when each photoelectric module is used as a signal transmitting end;
a calculation module for calculating a first photoelectric conversion efficiency of each photoelectric module from the input optical signal and the output optical signal, and calculating a second photoelectric conversion efficiency of each photoelectric module from the input optical signal and the output optical signal;
The conversion module is used for carrying out distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and carrying out distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map;
the extraction module is used for carrying out feature extraction on the first conversion efficiency distribution diagram to obtain a plurality of first conversion efficiency features, and carrying out feature extraction on the second conversion efficiency distribution diagram to obtain a plurality of second conversion efficiency features;
the analysis module is used for inputting the first conversion efficiency characteristics and the second conversion efficiency characteristics into a preset photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index of each photoelectric module;
and the construction module is used for constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the photoelectric conversion performance evaluation index of each photoelectric module.
A third aspect of the present invention provides a photoelectric conversion apparatus comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the photoelectric conversion apparatus to perform the photoelectric conversion method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the above-described photoelectric conversion method.
In the technical scheme provided by the invention, the first photoelectric conversion efficiency is calculated according to the input optical signal and the output electrical signal, and the second photoelectric conversion efficiency is calculated according to the input electrical signal and the output optical signal; performing distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and performing distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map; extracting features to obtain a plurality of first conversion efficiency features and a plurality of second conversion efficiency features; inputting the first conversion efficiency characteristics and the second conversion efficiency characteristics into a photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index; according to the invention, the photoelectric transmission and signal acquisition of the plurality of photoelectric modules are controlled simultaneously, so that the testing efficiency is greatly improved. By classifying the transmission signals and extracting the characteristics, the photoelectric conversion efficiency of the photoelectric module serving as a signal receiving end and a signal transmitting end can be comprehensively evaluated. By evaluating the photoelectric conversion performance of a plurality of photoelectric modules, the performance difference and consistency between the modules can be better understood. This helps to find and solve mismatch, mismatch or failure problems between modules, improving the reliability and stability of the photovoltaic transmission system. And constructing an optimized photoelectric transmission strategy based on the photoelectric conversion performance evaluation index of the photoelectric module. By adjusting the photoelectric transmission strategy according to the module performance evaluation index, the transmission efficiency, response speed and signal quality of the whole system can be improved, and the optimal performance of the photoelectric transmission system can be realized.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a photoelectric conversion method according to an embodiment of the present invention;
FIG. 2 is a flow chart of calculating photoelectric conversion efficiency according to an embodiment of the present invention;
FIG. 3 is a flow chart of profile conversion in an embodiment of the present invention;
FIG. 4 is a flow chart of feature extraction in an embodiment of the invention;
FIG. 5 is a schematic diagram of an embodiment of a photoelectric conversion device according to the present invention;
fig. 6 is a schematic diagram of an embodiment of a photoelectric conversion apparatus according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a photoelectric conversion method, a photoelectric conversion device, photoelectric conversion equipment and a storage medium, which are used for improving photoelectric transmission efficiency between photoelectric modules. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and one embodiment of a photoelectric conversion method in an embodiment of the present invention includes:
s101, controlling a plurality of photoelectric modules to carry out photoelectric transmission through a preset first photoelectric transmission strategy, and collecting a transmission signal set of each photoelectric module;
it is to be understood that the execution body of the present invention may be a photoelectric conversion device, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, the server first designs the photoelectric transmission system. The system is composed of a plurality of photoelectric modules, and each module comprises an optical sensor, an optical transmitter, a signal processing circuit and other components. The optical sensor is used for receiving the optical signal and converting the optical signal into an electric signal, and the optical transmitter is used for converting the electric signal into the optical signal for transmission. The signal processing circuit is used for processing and adjusting the characteristics of the signal. Secondly, a first photoelectric transmission strategy is preset. This includes defining parameters of the transmission signal such as frequency, wavelength, power and transmission mode. For example, the server sets a certain optoelectronic module as a main transmitter, and other modules as receivers, and sets the frequency of the transmission signal to 10MHz and the wavelength to 850nm. Then, control of the photovoltaic module is achieved by the control circuit. And controlling the main transmitter to emit an optical signal according to a preset transmission strategy, and transmitting the optical signal to the receiver. The control circuit may employ a microcontroller or Programmable Logic Controller (PLC) or the like. The control circuitry will ensure that the light signal is emitted in accordance with a preset strategy while the receiver is properly configured and adjusted. In the transmission process, other photoelectric modules convert the received optical signals into electric signals, and the signals are subjected to processing such as enhancement and filtering through a signal processing circuit. These processing steps help to improve the reliability and interference immunity of the transmission. And simultaneously, a data acquisition system is used for acquiring the transmission signal of each photoelectric module. The data acquisition device may be connected to the output of each module to convert its output signal into digital data. The data can be collected and recorded by an analog signal collection card, a digital interface module or a special data collection device. For example, assume that there is an optical-electrical transmission system that includes a main transmitter and three receivers. The preset transmission strategy requires the main transmitter to transmit to the receiver an optical signal at a frequency of 20MHz and a wavelength of 1550 nm. And through the control circuit, the main transmitter is ensured to emit light signals according to a preset strategy, and the receiver is properly configured. The data acquisition system is connected to the output of each receiver and converts it into digital data. The collected data can be used for calculating the photoelectric conversion efficiency, signal-to-noise ratio and other indexes of each receiver. By analyzing and evaluating the collected signal set, the performance of each photoelectric module can be known, and the photoelectric module is optimized and improved according to the evaluation result.
S102, classifying transmission signals of the transmission signal set to obtain an input optical signal and an output electrical signal when each photoelectric module is used as a signal receiving end and an input electrical signal and an output optical signal when each photoelectric module is used as a signal transmitting end;
specifically, the server first obtains the characteristics of the input optical signal and the output electrical signal when the photoelectric module is used as the signal receiving end. The first optical power and the spectral characteristic of each photoelectric module serving as a signal receiving end can be obtained by collecting the optical signal data received by each photoelectric module in the transmission signal set and analyzing the optical power and the spectral characteristic. Meanwhile, through collecting the electric signal data output by each photoelectric module in the transmission signal set and carrying out voltage characteristic analysis, the first voltage characteristic of each photoelectric module serving as a signal receiving end can be obtained. Then, the input electrical signal and the output optical signal characteristics of the photoelectric module as the signal transmitting end are obtained. And acquiring the electric signal data transmitted by each photoelectric module in the transmission signal set, and performing voltage characteristic analysis to obtain a second voltage characteristic when each photoelectric module is used as a signal transmitting end. Meanwhile, by collecting the optical signal data output by each photoelectric module in the transmission signal set and analyzing the optical power and the spectral characteristics, the second optical power and the spectral characteristics of each photoelectric module when the photoelectric module is used as a signal transmitting end can be obtained. A first optical signal cluster center is determined based on the acquired first optical power and spectral characteristics, and a first electrical signal cluster center is determined based on the first voltage characteristics. Likewise, a second optical signal cluster center is determined based on the second optical power and the spectral characteristics, and a second electrical signal cluster center is determined based on the first voltage characteristics. These cluster centers serve as reference points for classification. Next, the set of transmission signals is clustered based on the first optical signal cluster center. Comparing and matching the collected optical signal data with a first optical signal clustering center, and classifying similar optical signals into input optical signal sets when corresponding photoelectric modules are used as signal receiving ends. Similarly, the first electric signal clustering center is used for carrying out electric signal clustering on the transmission signal set, and similar electric signals are classified into the output electric signal set when the corresponding photoelectric module is used as a signal receiving end. Similarly, the second optical signal clustering center is used for carrying out optical signal clustering on the transmission signal set, and similar optical signals are classified into the output optical signal set when the corresponding photoelectric modules serve as signal sending ends. Meanwhile, the transmission signal set is subjected to electric signal clustering based on the first electric signal clustering center, and similar electric signals are classified into the input electric signal set when the corresponding photoelectric modules are used as signal sending ends. For example, assume that there is an optical-electrical transmission system including two optical-electrical modules, one as a transmitting end and the other as a receiving end. The transmission signal set is collected in advance, and analysis of optical power, spectral characteristics and voltage characteristics is performed. A first optical signal cluster center is determined based on the first optical power and the spectral characteristics, and a first electrical signal cluster center is determined based on the first voltage characteristics. Based on these cluster centers, the set of transmission signals are clustered into optical signals and electrical signals. The result shows that part of the transmission signal set is matched with the first optical signal clustering center and classified as the input optical signal set of the receiving end. Meanwhile, part of the transmission signal set is matched with the first electric signal clustering center and classified as an output electric signal set of the receiving end. On the other hand, a second optical signal cluster center is determined based on the second optical power and the spectral characteristics, and a second electrical signal cluster center is determined based on the first voltage characteristics. Based on these cluster centers, the set of transmission signals are clustered into optical signals and electrical signals. And the result shows that part of the transmission signal set is matched with the second optical signal clustering center and classified as the output optical signal set of the transmitting end. Meanwhile, part of the transmission signal set is matched with the first electric signal clustering center and classified as an input electric signal set of the transmitting end.
S103, calculating the first photoelectric conversion efficiency of each photoelectric module according to the input optical signal and the output electrical signal, and calculating the second photoelectric conversion efficiency of each photoelectric module according to the input electrical signal and the output optical signal;
it should be noted that, first, for the input optical signals, the server performs optical power quantization conversion on the input optical signals to obtain a first optical power value of each input optical signal. This process may use an instrument such as an optical power meter to measure the input optical signal and then convert the measurement result to a digital representation. The first optical power value reflects the optical power intensity of the input optical signal. Then, the server performs voltage quantization conversion on the output electric signals to obtain a first voltage value of each output electric signal. The output electrical signal is measured by using a measuring device such as a voltmeter, and the measurement result is converted into a corresponding voltage value representation. Thus, the server obtains a first voltage value of the output electrical signal. Meanwhile, for the output optical signals, the server performs optical power quantization conversion to obtain a second optical power value of each output optical signal. Similarly, the server measures the output optical signal using an instrument such as an optical power meter, and converts the measurement result into a digital representation. In addition, the server performs voltage quantization conversion on the input electric signals to obtain a second voltage value of each input electric signal. The input electrical signal is measured by using a measuring device such as a voltmeter, and the measurement result is converted into a corresponding voltage value representation. With the first optical power value and the first voltage value, the server calculates a first photoelectric conversion efficiency of each of the photovoltaic modules. The server obtains a first photoelectric conversion efficiency of each photoelectric module by dividing the first optical power value by the first voltage value. This efficiency index may help evaluate the energy conversion efficiency of the optoelectronic module between the input optical signal and the output electrical signal. Similarly, the server calculates a second photoelectric conversion efficiency of each of the photovoltaic modules by using the second optical power value and the second voltage value. Dividing the second light power value by the second voltage value, and obtaining the second photoelectric conversion efficiency of each photoelectric module by the server. This efficiency index can be used to evaluate the energy conversion efficiency of the optoelectronic module between an input electrical signal and an output optical signal. For example, assume that the server has one photovoltaic module for a solar panel. The server measures the optical power value of the input optical signal to be 100 watts and the voltage value of the output electrical signal to be 10 volts. Thus, the server calculates the first photoelectric conversion efficiency of the photoelectric module to be 10 w/v. Next, the server measures the optical power value of the output optical signal to 50 watts and the voltage value of the input electrical signal to 5 volts. Through calculation, the server obtains the second photoelectric conversion efficiency of the photoelectric module to be 10W/V. These calculations can help the server evaluate the performance and efficiency of the optoelectronic module and provide guidance for further optimization and improvement.
S104, performing distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and performing distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map;
specifically, first, the server calculates a first kernel bandwidth of the first photoelectric conversion efficiency based on a preset first kernel density function. The kernel bandwidth is a parameter for controlling the smoothness of the kernel density estimation, which determines the degree of refinement and smoothness of the estimation result. And calculating the first nuclear bandwidth of the first photoelectric conversion efficiency by the server according to the preset nuclear density function and the corresponding algorithm. Then, the server performs kernel density estimation by using the obtained first kernel bandwidth to obtain a distribution diagram of the first conversion efficiency. The kernel density estimation is a non-parametric statistical method for estimating probability density functions. The server obtains a first conversion efficiency profile by combining the sample data of the first photoelectric conversion efficiency with the first kernel bandwidth. The profile will show the relative frequencies of the different conversion efficiency values to help the server understand the distribution of conversion efficiency. Similarly, the server also needs to calculate a second kernel bandwidth for a second photoelectric conversion efficiency based on a preset second kernel density function. The server determines a second core bandwidth for a second photoelectric conversion efficiency, which will be used for the core density estimation process, by using a corresponding calculation method. Then, the server performs kernel density estimation of the second photoelectric conversion efficiency by using the second kernel bandwidth, and obtains a distribution diagram of the second conversion efficiency. This profile will show the relative frequency distribution of the different conversion efficiency values, helping the server to know the pattern and range of variation of the second conversion efficiency. For example, assume that the server has sample data of a first photoelectric conversion efficiency of one photoelectric module, including 10 observations: [0.6,0.7,0.5,0.8,0.7,0.6,0.6,0.9,0.8,0.7]. The server calculates a first kernel bandwidth of the first photoelectric conversion efficiency to be 0.1 by using a preset first kernel density function. Then, the server performs kernel density estimation, and obtains a distribution diagram of the first conversion efficiency by using the observed values and the first kernel bandwidth. Likewise, assume that the server has sample data of the second photoelectric conversion efficiency of one photoelectric module, including 8 observations: [0.4,0.5,0.6,0.4,0.5,0.5,0.6,0.7]. The server calculates a second kernel bandwidth of the second photoelectric conversion efficiency to be 0.08 using a preset second kernel density function. Then, based on these observations and the second kernel bandwidth, the server performs kernel density estimation to obtain a profile of the second conversion efficiency.
S105, performing feature extraction on the first conversion efficiency distribution map to obtain a plurality of first conversion efficiency features, and performing feature extraction on the second conversion efficiency distribution map to obtain a plurality of second conversion efficiency features;
specifically, first, the server extracts a plurality of first distribution feature data points corresponding to the first conversion efficiency distribution map, and calculates a plurality of second distribution feature data points corresponding to the second conversion efficiency distribution map. These characteristic data points may be statistics of peaks, means, variances, etc. in the distribution map that describe the shape and characteristics of the distribution. Next, the server generates a first standard characteristic value and a second standard characteristic value of the first conversion efficiency profile using a preset box map rule. The box diagram rule is a common statistical method for identifying outliers and calculating eigenvalues. By this rule, the server determines outliers and outliers in the first conversion efficiency profile and generates a first standard eigenvalue and a second standard eigenvalue. And then, respectively carrying out feature comparison with the first standard feature values by utilizing a plurality of first distribution feature data points to obtain a first feature comparison result of each first distribution feature data point. These comparison results may represent the location and degree of deviation of each feature data point from the standard feature values. Based on these comparison results, the server generates a plurality of first conversion efficiency features describing the relative merits and merits of the first conversion efficiency and the degree of deviation. Similarly, the second characteristic comparison result of each second distribution characteristic data point can be obtained by respectively comparing the plurality of second distribution characteristic data points with the second standard characteristic values. These comparison results reflect the difference and degree of similarity of each characteristic data point relative to the standard characteristic value. Based on the comparison results, the server generates a plurality of second conversion efficiency features for describing the features and the change modes of the second conversion efficiency. For example, assume that the server has a first conversion efficiency profile comprising a set of characteristic data points: [0.6,0.7,0.5,0.8,0.7,0.6,0.6,0.9,0.8,0.7]. The server generates a first standard characteristic value of 0.65 and a second standard characteristic value of 0.75 using a preset box diagram rule. The server then performs a feature comparison for each feature data point, for example, assuming that for 0.6 this feature data point, its comparison with the first standard feature value is-0.05, indicating its degree of deviation from the standard feature value. Through a similar comparison process, the server generates a plurality of first conversion efficiency features, such as degree of deviation, relative position, etc. A similar operation may be performed for the second conversion efficiency profile as well. Assume that the server has a set of second distribution characteristic data points: [0.2,0.3,0.25,0.4,0.35,0.3,0.2,0.5,0.45,0.3]. Feature comparison is performed using a second standard feature value of 0.75, for example, for a feature data point of 0.2, the comparison with the second standard feature value results in a value of-0.55, indicating the degree of difference relative to the standard feature value. Through a similar comparison process, the server generates a plurality of second conversion efficiency features, such as degree of difference, similarity, and the like. Through the feature extraction process, the server obtains a plurality of first conversion efficiency features and second conversion efficiency features, which are used for further analyzing and comparing the conversion efficiency performances of different photoelectric modules, identifying potential advantages and improvement spaces, and providing basis for subsequent optimization and decision.
S106, inputting the first conversion efficiency characteristics and the second conversion efficiency characteristics into a preset photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index of each photoelectric module;
specifically, first, feature encoding is performed on a plurality of first conversion efficiency features to obtain a first feature vector. The feature encoding method may adopt a common encoding technology, for example, a feature value normalization process or a single-hot encoding mode is used to convert each feature into a form of a numerical vector. Similarly, a plurality of second conversion efficiency features are feature-encoded to obtain a second feature vector. And then, carrying out vector fusion on the first feature vector and the second feature vector to obtain a first target feature vector. Vector fusion may combine the first feature vector and the second feature vector into one integrated feature vector using simple vector concatenation or weighted averaging, etc. Then, the first target feature vector is input into a preset photoelectric conversion performance analysis model. This model may include a first threshold loop network, a second threshold loop network, two full connection layers, and so on. These components can be used to extract features, transform features, and make performance predictions. And extracting hidden state features of the first target feature vector through a first threshold cycle network to obtain the hidden state feature vector. The threshold cycle network is a recurrent neural network structure that can capture long-term dependencies in sequence data and extract key features. And then, inputting the hidden state feature vector into a second threshold loop network to perform feature conversion to obtain a second target feature vector. The second threshold loop network may perform further nonlinear mapping and feature extraction on the hidden state feature vectors to generate more representative feature vectors. And finally, inputting the second target feature vector into two fully-connected layers to predict the photoelectric conversion performance, and obtaining the photoelectric conversion performance evaluation index of each photoelectric module. The two full-connection layers can establish a mapping relation between input characteristics and performance indexes through learning and training so as to realize prediction and evaluation of photoelectric conversion performance. For example, assume that the server has a data set of one optoelectronic module that includes a plurality of first conversion efficiency features and a plurality of second conversion efficiency features. The server encodes the first conversion efficiency characteristic to obtain a first characteristic vector; and encoding the second conversion efficiency characteristic to obtain a second characteristic vector. And then, fusing the first feature vector and the second feature vector to obtain a first target feature vector. And then, inputting the first target feature vector into a photoelectric conversion performance analysis model, extracting the hidden state feature vector through a threshold cyclic network, and converting the hidden state feature vector through a second threshold cyclic network to obtain a second target feature vector. And finally, inputting the second target feature vector into two fully-connected layers for performance prediction to obtain the photoelectric conversion performance evaluation index of the photoelectric module.
S107, constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the photoelectric conversion performance evaluation index of each photoelectric module.
Specifically, the server first needs to construct a distribution structure of the optical transmission network between the plurality of optical modules. This structure describes the connection and transmission path between the photovoltaic modules. It is contemplated that the network topology or graph theory model may be used to represent the photovoltaic transport networking architecture, where nodes represent photovoltaic modules and edges represent transport connections between modules. And then, according to the photoelectric conversion performance evaluation index of each photoelectric module, performing dependency calculation on the transmission nodes of the photoelectric transmission networking distribution structure. The dependencies reflect the dependencies and transmission priorities between the optoelectronic modules. This may be calculated based on the photoelectric conversion efficiency, transmission distance, signal-to-noise ratio, and the like. By comparing the performance evaluation index of each photovoltaic module, it is possible to determine which modules have higher priority or are more suitable as transmission nodes. And constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the calculated membership networking distribution structure. The transmission strategy determines the transmission path and manner of the optical signal from the source module to the target module. This may determine the order of transmission, the choice of path, the setting of transmission parameters, etc. according to the affiliation. For example, assume that a server has one photoelectric transmission system in which a plurality of photoelectric modules are included, and photoelectric conversion performance of each module has been evaluated. The server wishes to build a second photoelectric transmission strategy for these modules. First, the server establishes a distribution structure of the optical-electrical transmission networking, which can be represented by using a topological graph. For example, assuming a server has 5 photovoltaic modules, they can be represented as a directed graph, where each module is a node and the edges represent the connections between modules. Next, the server calculates the affiliation from the photoelectric conversion performance evaluation index of each module. It is assumed that module a has the highest conversion efficiency and therefore the server sets it as the starting node for the transmission. The server then calculates the transmission priority of the other modules relative to module a. If the conversion efficiency of module B and module C is higher and the connection with module a is closer, they may have higher priority and may act as slave nodes. Likewise, the server calculates dependencies of other modules based on other performance metrics and connection conditions. And constructing a photoelectric transmission strategy by the server according to the calculated membership networking distribution structure. For example, the server determines the transmission order of the optical signals, and sequentially transmits the optical signals from the module a to the module B, the module C, and the like. The server may also determine the transmission path and select the shortest distance or the best quality transmission path. In addition, the server sets transmission parameters such as power level, modulation scheme, etc.
In the embodiment of the invention, the first photoelectric conversion efficiency is calculated according to the input optical signal and the output electrical signal, and the second photoelectric conversion efficiency is calculated according to the input electrical signal and the output optical signal; performing distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and performing distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map; extracting features to obtain a plurality of first conversion efficiency features and a plurality of second conversion efficiency features; inputting the first conversion efficiency characteristics and the second conversion efficiency characteristics into a photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index; according to the invention, the photoelectric transmission and signal acquisition of the plurality of photoelectric modules are controlled simultaneously, so that the testing efficiency is greatly improved. By classifying the transmission signals and extracting the characteristics, the photoelectric conversion efficiency of the photoelectric module serving as a signal receiving end and a signal transmitting end can be comprehensively evaluated. By evaluating the photoelectric conversion performance of a plurality of photoelectric modules, the performance difference and consistency between the modules can be better understood. This helps to find and solve mismatch, mismatch or failure problems between modules, improving the reliability and stability of the photovoltaic transmission system. And constructing an optimized photoelectric transmission strategy based on the photoelectric conversion performance evaluation index of the photoelectric module. By adjusting the photoelectric transmission strategy according to the module performance evaluation index, the transmission efficiency, response speed and signal quality of the whole system can be improved, and the optimal performance of the photoelectric transmission system can be realized.
In a specific embodiment, the process of executing step S102 may specifically include the following steps:
(1) Acquiring first optical power and spectral characteristics of an optical signal and first voltage characteristics of an electric signal when each photoelectric module is used as a signal receiving end, and acquiring second optical power and spectral characteristics of the optical signal and second voltage characteristics of the electric signal when each photoelectric module is used as a signal transmitting end;
(2) Determining a first optical signal clustering center based on the first optical power and the spectral characteristics, determining a first electric signal clustering center according to the first voltage characteristics, determining a second optical signal clustering center based on the second optical power and the spectral characteristics, and determining a second electric signal clustering center according to the second voltage characteristics;
(3) Carrying out optical signal clustering on the transmission signal set based on the first optical signal clustering center to obtain an input optical signal when each photoelectric module is used as a signal receiving end, and carrying out electric signal clustering on the transmission signal set based on the first electric signal clustering center to obtain an output electric signal when each photoelectric module is used as the signal receiving end;
(4) And carrying out optical signal clustering on the transmission signal set based on the second optical signal clustering center to obtain output optical signals when each photoelectric module is used as a signal transmitting end, and carrying out electric signal clustering on the transmission signal set based on the first electric signal clustering center to obtain input electric signals when each photoelectric module is used as the signal transmitting end.
Specifically, the server first measures an optical signal when each photoelectric module is used as a signal receiving end, and obtains a first optical power and a spectral characteristic. The value of the optical power received by each module can be obtained by an optical power measuring device, and the spectral characteristics can be obtained by a spectrum analyzer. At the same time, the first voltage characteristic of the electrical signal received by each module is also measured, which can be measured by a corresponding voltage measuring device. And secondly, performing cluster analysis on the optical signals by using the acquired optical power and spectral characteristic data. The first optical signal cluster center can be determined by a clustering algorithm (such as K-means clustering), i.e., similar optical signals are classified into the same category. Meanwhile, according to the first voltage characteristic of the electric signal received by each photoelectric module, clustering analysis of the electric signal can be performed. The electrical signals are grouped through a clustering algorithm, and a first electrical signal clustering center is determined. And then, carrying out optical signal clustering on the transmission signal set by using the first optical signal clustering center, and grouping the optical signals in the signal set according to the similarity between the optical signals and the first optical signal clustering center. Thus, an input optical signal when each photoelectric module is used as a signal receiving end can be obtained. And meanwhile, carrying out electric signal clustering on the transmission signal set according to the first electric signal clustering center. And grouping the electric signals in the signal set according to the similarity between the electric signals and the first electric signal clustering center to obtain the output electric signals when each photoelectric module is used as a signal receiving end. In addition, the steps can be repeated, and the output optical signal and the input electrical signal of each photoelectric module serving as the signal transmitting end can be obtained by acquiring the optical signal and the electrical signal characteristics of each photoelectric module serving as the signal transmitting end and performing clustering analysis for the second time according to the second optical power, the spectral characteristics and the second voltage characteristics. For example, assume a set of photovoltaic modules, A, B, C respectively. When the optical signal is used as a signal receiving end, the first optical power of the optical signal received by the module A is measured to be 10mW, the spectral characteristic is red light, and the first voltage of the electric signal is 5V; the first optical power of the optical signal received by the module B is 8mW, the spectral characteristic is green light, and the first voltage of the electric signal is 4V; the first optical power of the optical signal received by the module C is 12mW, the spectral characteristic is blue light, and the first voltage of the electrical signal is 6V. When the optical signal is used as a signal transmitting end, the second optical power of the optical signal transmitted by the module A is measured to be 6mW, the spectral characteristic is red light, and the second voltage of the electric signal is 3V; the second optical power of the optical signal sent by the module B is 5mW, the spectral characteristic is green light, and the second voltage of the electric signal is 2.5V; the second optical power of the optical signal sent by the module C is 7mW, the spectral characteristic is blue light, and the second voltage of the electrical signal is 3.5V. And determining the first optical signal clustering center as red light and the second optical signal clustering center as green light based on the cluster analysis of the first optical power and the spectral characteristics. And determining that the first electric signal clustering center is 5V and the second electric signal clustering center is 4V according to the clustering analysis of the first voltage characteristic. And carrying out optical signal clustering on the transmission signal set according to the first optical signal clustering center, and classifying the received optical signals into red light, red light and green light according to colors. And carrying out electric signal clustering on the transmission signal set according to the first electric signal clustering center, and classifying the received electric signals into 5V, 5V and 4V according to the voltage. And carrying out optical signal clustering on the transmission signal set according to the second optical signal clustering center, and classifying the transmitted optical signals into red light, green light and green light according to colors. And carrying out electric signal clustering on the transmission signal set according to the first electric signal clustering center, and classifying the transmitted electric signals into 3V, 2.5V and 2.5V according to the voltage.
In a specific embodiment, as shown in fig. 2, the process of performing step S103 may specifically include the following steps:
s201, performing optical power quantization conversion on input optical signals to obtain a first optical power value of each input optical signal, and performing voltage quantization conversion on output electrical signals to obtain a first voltage value of each output electrical signal;
s202, performing optical power quantization conversion on output optical signals to obtain a second optical power value of each output optical signal, and performing voltage quantization conversion on input electrical signals to obtain a second voltage value of each input electrical signal;
s203, calculating the first photoelectric conversion efficiency of each photoelectric module according to the first optical power value and the first voltage value, and calculating the second photoelectric conversion efficiency of each photoelectric module according to the second optical power value and the second voltage value.
Specifically, the server first performs optical power quantization conversion on the input optical signal. Each input optical signal is measured by an optical power sensor or an optical power meter to obtain a first optical power value thereof. The optical power value represents the power level of the optical signal and can be used to measure the intensity of the optical signal. Meanwhile, voltage quantization conversion is performed on the output electric signal. Each output electrical signal is measured by a voltage sensor or a voltage measuring device to obtain a first voltage value thereof. The voltage value represents the voltage level of the electrical signal and may reflect the intensity or amplitude of the electrical signal. Next, optical power quantization conversion is performed on the output optical signal. And measuring the optical power of each output optical signal by using an optical power sensor or an optical power meter to obtain a second optical power value. This value represents the optical power level of the output optical signal. Meanwhile, voltage quantization conversion is performed on the input electric signal. The voltage of each input electrical signal is measured by a voltage sensor or a voltage measuring device to obtain a second voltage value. This value reflects the voltage level of the input electrical signal. Further, based on the first optical power value and the first voltage value, a first photoelectric conversion efficiency of each of the photovoltaic modules may be calculated. The photoelectric conversion efficiency means the efficiency with which the photoelectric module converts an input optical signal into an output electrical signal. The calculation method is to divide the first light power value by the first voltage value to obtain photoelectric conversion efficiency. Likewise, from the second optical power value and the second voltage value, the second photoelectric conversion efficiency of each photoelectric module may be calculated. This represents the efficiency of the optoelectronic module in converting an input electrical signal into an output optical signal. The calculation method is to divide the second light power value by the second voltage value to obtain the photoelectric conversion efficiency. For example, assume that there is an optoelectronic module, and when the optoelectronic module is used as a signal receiving end, a first optical power value of an input optical signal is measured to be 2mW, and a first voltage value of an output electrical signal is measured to be 3V. When the optical fiber is used as a signal transmitting end, the second optical power value of the output optical signal is measured to be 4mW, and the second voltage value of the input electric signal is measured to be 2V. And calculating the first photoelectric conversion efficiency of the photoelectric module to be 2mW/3 V=0.67 mW/V according to the first optical power value and the first voltage value. This means that the input optical power per unit can be converted to an output voltage of 0.67 units. And calculating the second photoelectric conversion efficiency of the photoelectric module to be 4mW/2 V=2 mW/V according to the second optical power value and the second voltage value. This means that the input voltage per unit can be converted into 2 units of output optical power. Through the quantitative conversion of optical power and voltage and the calculation of photoelectric conversion efficiency, the performance and efficiency of the photoelectric module can be evaluated for optimization and adjustment in an optical communication system.
In a specific embodiment, as shown in fig. 3, the process of executing step S104 may specifically include the following steps:
s301, calculating a first kernel bandwidth of a first photoelectric conversion efficiency based on a preset first kernel density function;
s302, performing kernel density estimation according to a first kernel density function and a first kernel bandwidth to obtain a first conversion efficiency distribution diagram;
s303, calculating a second kernel bandwidth of a second photoelectric conversion efficiency based on a preset second kernel density function;
s304, performing kernel density estimation according to the second kernel density function and the second kernel bandwidth to obtain a second conversion efficiency distribution diagram.
Specifically, the server first sets a preset first kernel density function for the first photoelectric conversion efficiency. The kernel density function is a statistical function for describing data distribution, and can reflect probability distribution of photoelectric conversion efficiency. The preset first kernel density function may be determined based on a priori knowledge, experimental data, or expertise. And calculating a first kernel bandwidth of the first photoelectric conversion efficiency according to a preset first kernel density function. The kernel bandwidth is a parameter of the kernel density function that determines the smoothness of the kernel density estimate. Typically, the selection of the core bandwidth requires consideration of the distribution characteristics of the data and the accuracy of the estimation. Next, a kernel density estimation is performed using the first kernel density function and the first kernel bandwidth. Kernel density estimation is a non-parametric statistical method for inferring the shape of probability density functions from finite data samples. By performing nuclear density estimation on the first photoelectric conversion efficiency sample data, a probability density estimation map of the first conversion efficiency can be obtained. Similarly, a preset second kernel density function is set for the second photoelectric conversion efficiency. And calculating a second kernel bandwidth of the second photoelectric conversion efficiency according to a preset second kernel density function. And then, performing kernel density estimation by using a second kernel density function and a second kernel bandwidth to obtain a probability density estimation graph of the second conversion efficiency. For example, assume that the server performs a study on the first photoelectric conversion efficiency of a certain photoelectric module. Based on previous experimental data and analysis, the server selects a gaussian kernel density function as a preset first kernel density function and sets an appropriate kernel bandwidth. Through calculation, the first nuclear bandwidth of the server, which obtains the first photoelectric conversion efficiency, is 0.1. Next, a core density estimation is performed using the core bandwidth and the previously collected first photoelectric conversion efficiency data. Finally, a probability density estimation map of the first conversion efficiency is obtained, which shows the distribution of the first conversion efficiency, which can be used for further analysis and decision-making. Similarly, the server performs a similar procedure to study the second photoelectric conversion efficiency of the photoelectric module. And selecting a proper second kernel density function and kernel bandwidth, and then performing kernel density estimation to obtain a probability density estimation graph of the second conversion efficiency.
In a specific embodiment, as shown in fig. 4, the process of performing step S105 may specifically include the following steps:
s401, extracting a plurality of first distribution characteristic data points corresponding to a first conversion efficiency distribution chart, and calculating a plurality of second distribution characteristic data points corresponding to a second conversion efficiency distribution chart;
s402, generating a first standard characteristic value and a second standard characteristic value of a first conversion efficiency distribution diagram through a preset box diagram rule;
s403, performing feature comparison with the first standard feature values through a plurality of first distribution feature data points to obtain a first feature comparison result of each first distribution feature data point, and generating a plurality of first conversion efficiency features according to the first feature comparison result;
s404, performing feature comparison with the second standard feature values through the plurality of second distribution feature data points to obtain a second feature comparison result of each second distribution feature data point, and generating a plurality of second conversion efficiency features according to the second feature comparison result.
Specifically, the server first extracts a plurality of first distribution feature data points according to the first conversion efficiency distribution map. These data points may be peaks, inflection points, or other representative data points in the profile. By analyzing the distribution map, the extracted data points are determined and their values and locations are recorded. Similarly, a plurality of second distribution characteristic data points are extracted from the second conversion efficiency profile. According to the actual demand and the form of the distribution diagram, proper characteristic data points are selected, and the numerical values and positions of the characteristic data points are recorded. Next, a first standard characteristic value and a second standard characteristic value of the first conversion efficiency distribution map are generated by a preset box diagram rule. The box diagram rule is a common statistical method for determining the range of outliers and standard eigenvalues. And calculating a first standard characteristic value and a second standard characteristic value according to the conversion efficiency data, and taking the first standard characteristic value and the second standard characteristic value as reference standards for comparison. And then, respectively comparing the plurality of first distribution characteristic data points with the first standard characteristic values. By comparing the relationship between the data points and the standard feature values, a first feature comparison for each data point can be determined. For example, if the data point is above a standard feature value, a high conversion efficiency feature may be determined; if the data point is below the standard characteristic value, a low conversion efficiency characteristic may be determined. Similarly, a plurality of second distribution characteristic data points are respectively subjected to characteristic comparison with second standard characteristic values. And determining a second characteristic comparison result of each data point according to the comparison result. And finally, generating a plurality of first conversion efficiency features and second conversion efficiency features according to the first feature comparison result and the second feature comparison result. Based on the results of the feature comparison, the data points can be classified into different feature categories, such as high conversion efficiency, low conversion efficiency, normal range, and the like. For example, suppose that the server studies the conversion efficiency distribution of a certain type of solar panel. By analyzing the first conversion efficiency profile, the server extracted two first distribution feature data points, 0.85 and 0.90, respectively. Meanwhile, according to the second conversion efficiency profile, the server extracted two second distribution characteristic data points, 0.80 and 0.88, respectively. According to a preset box diagram rule, a first standard characteristic value of the first conversion efficiency distribution diagram is calculated to be 0.82, and a second standard characteristic value of the first conversion efficiency distribution diagram is calculated to be 0.87. Comparing the first distribution feature data points to the first standard feature values, it is found that 0.85 is higher than 0.82 and 0.90 is higher than 0.82, so they can be judged as high conversion efficiency features. Comparing the second distribution characteristic data point with the second standard characteristic value, it is found that 0.80 is lower than 0.87 and 0.88 is close to 0.87, so that it can be determined that 0.80 is a low conversion efficiency characteristic and 0.88 is a normal range characteristic. According to the first characteristic comparison result, the server generates two first conversion efficiency characteristics, namely high conversion efficiency and high conversion efficiency. According to the second characteristic comparison result, the server generates two second conversion efficiency characteristics, namely low conversion efficiency and normal range.
In a specific embodiment, the process of executing step S106 may specifically include the following steps:
(1) Performing feature coding on the plurality of first conversion efficiency features to obtain a first feature vector, and performing feature coding on the plurality of second conversion efficiency features to obtain a second feature vector;
(2) Vector fusion is carried out on the first feature vector and the second feature vector, and a first target feature vector is obtained;
(3) Inputting the first target feature vector into a preset photoelectric conversion performance analysis model, wherein the photoelectric conversion performance analysis model comprises: a first threshold cycle network, a second threshold cycle network, and two full-connection layers;
(4) Extracting hidden state features of the first target feature vector through a first threshold cycle network to obtain a hidden state feature vector;
(5) Inputting the hidden state feature vector into a second threshold cyclic network for feature conversion to obtain a second target feature vector;
(6) And inputting the second target feature vector into two full-connection layers to predict the photoelectric conversion performance, and obtaining the photoelectric conversion performance evaluation index of each photoelectric module.
Specifically, first, feature encoding is performed on a plurality of first conversion efficiency features to obtain a first feature vector. Feature encoding may take various forms, such as single-hot encoding, tag encoding, or numerical normalization. Each first conversion efficiency feature is encoded into a numerical or vector form and combined into a first feature vector. Similarly, a plurality of second conversion efficiency features are feature-encoded to obtain a second feature vector. Likewise, each second conversion efficiency feature is encoded in the form of a value or vector, and combined into a second feature vector. And then, carrying out vector fusion on the first feature vector and the second feature vector to obtain a first target feature vector. Vector fusion may be achieved by simple vector stitching, weighted averaging, or other complex fusion algorithms. The first feature vector and the second feature vector are combined into one integrated feature vector as a first target feature vector. And inputting the first target feature vector into a preset photoelectric conversion performance analysis model for analysis and prediction. The photoelectric conversion performance analysis model may be composed of a plurality of components, such as a first threshold cycle network, a second threshold cycle network, and two full-connection layers. The goal of these components is to extract key information from the feature vectors and predict the photoelectric conversion performance. And extracting hidden state features of the first target feature vector through a first threshold cycle network to obtain the hidden state feature vector. The first threshold cycle network may capture timing relationships in the sequence data and extract hidden state features, which may contain more abundant conversion performance information. And inputting the hidden state feature vector into a second threshold cyclic network to perform feature conversion to obtain a second target feature vector. The second threshold loop network may further transform and extract hidden state features to obtain more representative feature vectors. And finally, inputting the second target feature vector into two fully-connected layers to predict the photoelectric conversion performance, and obtaining the photoelectric conversion performance evaluation index of each photoelectric module. The two full-connection layers can map the feature vectors to the conversion performance evaluation index space and generate a final prediction result. For example, assume that the server has studied different models of solar panels, collecting a first conversion efficiency characteristic and a second conversion efficiency characteristic for each panel. For the first feature vector, the server encodes the first conversion efficiency feature of each panel as a numerical value and combines them into a vector. Similarly, for the second feature vector, the server encodes the second conversion efficiency feature for each panel as a numerical value and combines into a vector. And then, carrying out vector fusion on the first feature vector and the second feature vector to obtain a first target feature vector. And inputting the first target feature vector into a photoelectric conversion performance analysis model, wherein the photoelectric conversion performance analysis model comprises a first threshold circulation network, a second threshold circulation network and two full-connection layers. Through the processing of these components, the server extracts hidden state features from the first target feature vector, performs feature conversion, and finally predicts the photoelectric conversion performance evaluation index of each solar cell panel, such as energy conversion efficiency or power output.
In a specific embodiment, the process of executing step S107 may specifically include the following steps:
(1) Constructing a photoelectric transmission networking distribution structure among a plurality of photoelectric modules;
(2) Performing dependency calculation on transmission nodes of the photoelectric transmission networking distribution structure according to the photoelectric conversion performance evaluation index of each photoelectric module to obtain the dependency networking distribution structure of a plurality of photoelectric modules;
(3) And constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the membership networking distribution structure.
Specifically, first, a photoelectric transmission networking distribution structure between photoelectric modules is constructed. This may be a topology in which the photovoltaic modules are connected together to form a transmission network. The topology may take different forms, such as star, ring, mesh, etc., depending on the application requirements and feasibility. Next, according to the photoelectric conversion performance evaluation index of each photoelectric module, the affiliation in the photoelectric transmission networking distribution structure is calculated. The dependency calculation may be performed based on factors such as the magnitude of the photoelectric conversion performance evaluation index, the relative difference, and the like. By comparing performance indicators between different photovoltaic modules, it is possible to determine the dependencies between the transmission nodes, i.e. which photovoltaic modules play a dominant role and which photovoltaic modules play a subordinate role in the transmission process. And constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the membership networking distribution structure. This includes determining factors such as the transmission path, transmission mode, and signal conditioning of the optical signal. The transmission path may be a direct connection or a transmission through other relay devices. The transmission mode can be unidirectional or bidirectional transmission, and is adjusted according to the requirement. Signal conditioning may include operations such as amplification, filtering, modulation, etc., to ensure stability and reliability of the transmission. For example, it is assumed that the server constructs a solar power generation system including a plurality of photovoltaic modules such as a solar panel and a photovoltaic conversion device. The server desirably connects the photovoltaic modules to form a photovoltaic transmission networking distribution structure to effect the collection and transmission of energy. The server calculates the dependency relationship between each photoelectric module based on the photoelectric conversion performance evaluation index, such as the energy conversion efficiency or the power output, of the photoelectric module. It is assumed that some solar panels have higher energy conversion efficiency, while other photoelectric conversion devices have lower energy conversion efficiency. This means that the solar panel plays a dominant role in the transport process, while the photoelectric conversion device plays a secondary role. Based on the subordinate relation networking distribution structure, the server makes a photoelectric transmission strategy. For example, the server selects a solar panel as the main optical signal source, and transmits the signal to the photoelectric conversion device through a direct connection or through a relay device. In addition, the server can also use the signal conditioning device to adjust the transmitted optical signal to ensure stable transmission quality and proper signal strength.
The photoelectric conversion method in the embodiment of the present invention is described above, and the photoelectric conversion device in the embodiment of the present invention is described below, referring to fig. 5, where an embodiment of the photoelectric conversion device in the embodiment of the present invention includes:
the transmission module 501 is configured to control the plurality of photoelectric modules to perform photoelectric transmission through a preset first photoelectric transmission strategy, and collect a transmission signal set of each photoelectric module;
the classification module 502 is configured to classify the transmission signal set to obtain an input optical signal and an output electrical signal when each optoelectronic module is used as a signal receiving end, and an input electrical signal and an output optical signal when each optoelectronic module is used as a signal transmitting end;
a calculation module 503 for calculating a first photoelectric conversion efficiency of each photoelectric module from the input optical signal and the output optical signal, and calculating a second photoelectric conversion efficiency of each photoelectric module from the input optical signal and the output optical signal;
the conversion module 504 is configured to perform distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and perform distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map;
The extracting module 505 is configured to perform feature extraction on the first conversion efficiency distribution map to obtain a plurality of first conversion efficiency features, and perform feature extraction on the second conversion efficiency distribution map to obtain a plurality of second conversion efficiency features;
the analysis module 506 is configured to input the plurality of first conversion efficiency features and the plurality of second conversion efficiency features into a preset photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index of each photoelectric module;
a construction module 507, configured to construct a second photoelectric transmission policy of the plurality of photoelectric modules according to the photoelectric conversion performance evaluation index of each photoelectric module.
Calculating a first photoelectric conversion efficiency according to the input optical signal and the output electrical signal and calculating a second photoelectric conversion efficiency according to the input electrical signal and the output optical signal by the cooperative cooperation of the components; performing distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and performing distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map; extracting features to obtain a plurality of first conversion efficiency features and a plurality of second conversion efficiency features; inputting the first conversion efficiency characteristics and the second conversion efficiency characteristics into a photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index; according to the invention, the photoelectric transmission and signal acquisition of the plurality of photoelectric modules are controlled simultaneously, so that the testing efficiency is greatly improved. By classifying the transmission signals and extracting the characteristics, the photoelectric conversion efficiency of the photoelectric module serving as a signal receiving end and a signal transmitting end can be comprehensively evaluated. By evaluating the photoelectric conversion performance of a plurality of photoelectric modules, the performance difference and consistency between the modules can be better understood. This helps to find and solve mismatch, mismatch or failure problems between modules, improving the reliability and stability of the photovoltaic transmission system. And constructing an optimized photoelectric transmission strategy based on the photoelectric conversion performance evaluation index of the photoelectric module. By adjusting the photoelectric transmission strategy according to the module performance evaluation index, the transmission efficiency, response speed and signal quality of the whole system can be improved, and the optimal performance of the photoelectric transmission system can be realized.
The photoelectric conversion apparatus in the embodiment of the present invention is described in detail from the point of view of the modularized functional entity in fig. 5 above, and the photoelectric conversion device in the embodiment of the present invention is described in detail from the point of view of hardware processing below.
Fig. 6 is a schematic structural diagram of a photoelectric conversion device according to an embodiment of the present invention, where the photoelectric conversion device 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the photoelectric conversion apparatus 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the photoelectric conversion apparatus 600.
The optoelectronic conversion device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the photoelectric conversion apparatus structure shown in fig. 6 does not constitute a limitation of the photoelectric conversion apparatus, and may include more or fewer components than shown, or may combine certain components, or may have a different arrangement of components.
The present invention also provides a photoelectric conversion apparatus including a memory and a processor, the memory storing computer-readable instructions that, when executed by the processor, cause the processor to perform the steps of the photoelectric conversion method in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, in which instructions are stored which, when executed on a computer, cause the computer to perform the steps of the photoelectric conversion method.
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, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including 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 according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random acceS memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A photoelectric conversion method, characterized by comprising:
controlling a plurality of photoelectric modules to carry out photoelectric transmission through a preset first photoelectric transmission strategy, and collecting a transmission signal set of each photoelectric module;
classifying the transmission signals of the transmission signal set to obtain an input optical signal and an output electrical signal when each photoelectric module is used as a signal receiving end and an input electrical signal and an output optical signal when each photoelectric module is used as a signal transmitting end;
calculating a first photoelectric conversion efficiency of each photoelectric module according to the input optical signal and the output electrical signal, and calculating a second photoelectric conversion efficiency of each photoelectric module according to the input electrical signal and the output optical signal;
Performing distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and performing distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map;
extracting features of the first conversion efficiency distribution diagram to obtain a plurality of first conversion efficiency features, and extracting features of the second conversion efficiency distribution diagram to obtain a plurality of second conversion efficiency features;
inputting the first conversion efficiency characteristics and the second conversion efficiency characteristics into a preset photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index of each photoelectric module;
and constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the photoelectric conversion performance evaluation index of each photoelectric module.
2. The method according to claim 1, wherein the classifying the transmission signals to obtain the input optical signal and the output electrical signal when each of the photoelectric modules is used as the signal receiving end and the input electrical signal and the output optical signal when each of the photoelectric modules is used as the signal transmitting end includes:
Acquiring first optical power and spectral characteristics of an optical signal and first voltage characteristics of an electric signal when each photoelectric module is used as a signal receiving end, and acquiring second optical power and spectral characteristics of the optical signal and second voltage characteristics of the electric signal when each photoelectric module is used as a signal transmitting end;
determining a first optical signal clustering center based on the first optical power and the spectral characteristics, determining a first electric signal clustering center according to the first voltage characteristics, and simultaneously determining a second optical signal clustering center based on the second optical power and the spectral characteristics, and determining a second electric signal clustering center according to the second voltage characteristics;
carrying out optical signal clustering on the transmission signal set based on the first optical signal clustering center to obtain an input optical signal when each photoelectric module is used as a signal receiving end, and carrying out electric signal clustering on the transmission signal set based on the first electric signal clustering center to obtain an output electric signal when each photoelectric module is used as the signal receiving end;
and carrying out optical signal clustering on the transmission signal set based on the second optical signal clustering center to obtain an output optical signal when each photoelectric module is used as a signal transmitting end, and carrying out electric signal clustering on the transmission signal set based on the first electric signal clustering center to obtain an input electric signal when each photoelectric module is used as the signal transmitting end.
3. The photoelectric conversion method according to claim 1, wherein the calculating the first photoelectric conversion efficiency of each photoelectric module from the input optical signal and the output optical signal and the calculating the second photoelectric conversion efficiency of each photoelectric module from the input optical signal and the output optical signal includes:
performing optical power quantization conversion on the input optical signals to obtain a first optical power value of each input optical signal, and performing voltage quantization conversion on the output electrical signals to obtain a first voltage value of each output electrical signal;
performing optical power quantization conversion on the output optical signals to obtain a second optical power value of each output optical signal, and performing voltage quantization conversion on the input electrical signals to obtain a second voltage value of each input electrical signal;
and calculating the first photoelectric conversion efficiency of each photoelectric module according to the first optical power value and the first voltage value, and calculating the second photoelectric conversion efficiency of each photoelectric module according to the second optical power value and the second voltage value.
4. The photoelectric conversion method according to claim 1, wherein performing profile conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency profile, and performing profile mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency profile, comprises:
Calculating a first kernel bandwidth of the first photoelectric conversion efficiency based on a preset first kernel density function;
performing kernel density estimation according to the first kernel density function and the first kernel bandwidth to obtain a first conversion efficiency distribution diagram;
calculating a second kernel bandwidth of the second photoelectric conversion efficiency based on a preset second kernel density function;
and performing kernel density estimation according to the second kernel density function and the second kernel bandwidth to obtain a second conversion efficiency distribution diagram.
5. The photoelectric conversion method according to claim 1, wherein the performing feature extraction on the first conversion efficiency distribution map to obtain a plurality of first conversion efficiency features, and performing feature extraction on the second conversion efficiency distribution map to obtain a plurality of second conversion efficiency features, includes:
extracting a plurality of first distribution characteristic data points corresponding to the first conversion efficiency distribution map, and calculating a plurality of second distribution characteristic data points corresponding to the second conversion efficiency distribution map;
generating a first standard characteristic value and a second standard characteristic value of the first conversion efficiency distribution diagram through a preset box diagram rule;
the first characteristic comparison result of each first distribution characteristic data point is obtained through characteristic comparison between the plurality of first distribution characteristic data points and the first standard characteristic value, and a plurality of first conversion efficiency characteristics are generated according to the first characteristic comparison result;
And respectively carrying out feature comparison on the plurality of second distribution feature data points and the second standard feature values to obtain a second feature comparison result of each second distribution feature data point, and generating a plurality of second conversion efficiency features according to the second feature comparison result.
6. The method according to claim 1, wherein inputting the plurality of first conversion efficiency features and the plurality of second conversion efficiency features into a preset photoelectric conversion performance analysis model for performing photoelectric conversion performance analysis, to obtain a photoelectric conversion performance evaluation index of each photoelectric module, comprises:
performing feature coding on the plurality of first conversion efficiency features to obtain a first feature vector, and performing feature coding on the plurality of second conversion efficiency features to obtain a second feature vector;
vector fusion is carried out on the first feature vector and the second feature vector, and a first target feature vector is obtained;
inputting the first target feature vector into a preset photoelectric conversion performance analysis model, wherein the photoelectric conversion performance analysis model comprises: a first threshold cycle network, a second threshold cycle network, and two full-connection layers;
Extracting hidden state features of the first target feature vector through the first threshold cycle network to obtain a hidden state feature vector;
inputting the hidden state feature vector into the second threshold circulation network to perform feature conversion to obtain a second target feature vector;
and inputting the second target feature vector into the two full-connection layers to predict the photoelectric conversion performance, so as to obtain the photoelectric conversion performance evaluation index of each photoelectric module.
7. The photoelectric conversion method according to claim 1, wherein the constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the photoelectric conversion performance evaluation index of each photoelectric module includes:
constructing a photoelectric transmission networking distribution structure among the plurality of photoelectric modules;
performing dependency calculation on transmission nodes of the photoelectric transmission networking distribution structure according to the photoelectric conversion performance evaluation index of each photoelectric module to obtain the dependency networking distribution structure of the plurality of photoelectric modules;
and constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the membership networking distribution structure.
8. A photoelectric conversion device, characterized by comprising:
The transmission module is used for controlling the plurality of photoelectric modules to carry out photoelectric transmission through a preset first photoelectric transmission strategy and collecting a transmission signal set of each photoelectric module;
the classification module is used for classifying the transmission signals of the transmission signal set to obtain an input optical signal and an output electrical signal when each photoelectric module is used as a signal receiving end and an input electrical signal and an output optical signal when each photoelectric module is used as a signal transmitting end;
a calculation module for calculating a first photoelectric conversion efficiency of each photoelectric module from the input optical signal and the output optical signal, and calculating a second photoelectric conversion efficiency of each photoelectric module from the input optical signal and the output optical signal;
the conversion module is used for carrying out distribution map conversion on the first photoelectric conversion efficiency to obtain a first conversion efficiency distribution map, and carrying out distribution map mapping on the second photoelectric conversion efficiency to obtain a second conversion efficiency distribution map;
the extraction module is used for carrying out feature extraction on the first conversion efficiency distribution diagram to obtain a plurality of first conversion efficiency features, and carrying out feature extraction on the second conversion efficiency distribution diagram to obtain a plurality of second conversion efficiency features;
The analysis module is used for inputting the first conversion efficiency characteristics and the second conversion efficiency characteristics into a preset photoelectric conversion performance analysis model to perform photoelectric conversion performance analysis, so as to obtain a photoelectric conversion performance evaluation index of each photoelectric module;
and the construction module is used for constructing a second photoelectric transmission strategy of the plurality of photoelectric modules according to the photoelectric conversion performance evaluation index of each photoelectric module.
9. A photoelectric conversion apparatus, characterized by comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the photoelectric conversion apparatus to perform the photoelectric conversion method of any of claims 1-7.
10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the photoelectric conversion method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311054897.1A CN117076898B (en) | 2023-08-22 | 2023-08-22 | Photoelectric conversion method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311054897.1A CN117076898B (en) | 2023-08-22 | 2023-08-22 | Photoelectric conversion method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117076898A true CN117076898A (en) | 2023-11-17 |
| CN117076898B CN117076898B (en) | 2024-04-23 |
Family
ID=88714815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311054897.1A Active CN117076898B (en) | 2023-08-22 | 2023-08-22 | Photoelectric conversion method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117076898B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190356174A1 (en) * | 2017-01-04 | 2019-11-21 | Zte Corporation | Charging method and apparatus |
| US10826428B1 (en) * | 2019-12-06 | 2020-11-03 | King Abdulaziz University | Monitoring and fault detection method and system for photovoltaic plants |
| CN114723284A (en) * | 2022-04-07 | 2022-07-08 | 三峡大学 | Reliability evaluation method for power distribution network comprising distributed power supply and electric automobile |
| CN115660421A (en) * | 2022-10-27 | 2023-01-31 | 国网上海市电力公司 | Risk early warning classification method for new energy power system |
| CN116036492A (en) * | 2023-03-29 | 2023-05-02 | 北京新科以仁科技发展有限公司 | Laser power control method, device, equipment and storage medium |
-
2023
- 2023-08-22 CN CN202311054897.1A patent/CN117076898B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190356174A1 (en) * | 2017-01-04 | 2019-11-21 | Zte Corporation | Charging method and apparatus |
| US10826428B1 (en) * | 2019-12-06 | 2020-11-03 | King Abdulaziz University | Monitoring and fault detection method and system for photovoltaic plants |
| CN114723284A (en) * | 2022-04-07 | 2022-07-08 | 三峡大学 | Reliability evaluation method for power distribution network comprising distributed power supply and electric automobile |
| CN115660421A (en) * | 2022-10-27 | 2023-01-31 | 国网上海市电力公司 | Risk early warning classification method for new energy power system |
| CN116036492A (en) * | 2023-03-29 | 2023-05-02 | 北京新科以仁科技发展有限公司 | Laser power control method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 雷芳;邓炳光;: "光电信号转换的激光接收器设计", 激光杂志, no. 07, 25 July 2018 (2018-07-25) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117076898B (en) | 2024-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xia et al. | A real-time monitoring system based on ZigBee and 4G communications for photovoltaic generation | |
| Junior et al. | Low voltage smart meter for monitoring of power quality disturbances applied in smart grid | |
| CN111343650B (en) | Urban scale wireless service flow prediction method based on cross-domain data and loss resistance | |
| CN110782071A (en) | Method for predicting wind power by convolutional neural network based on time-space characteristic fusion | |
| CN113220751A (en) | Metering system and evaluation method for multi-source data state quantity | |
| CN110363334A (en) | Grid-connected grid line loss prediction technique based on Grey Neural Network Model | |
| Liu et al. | Lightweight, fluctuation insensitive multi-parameter fusion link quality estimation for wireless sensor networks | |
| CN109275096A (en) | A kind of indoor orientation method based on multilayer converged network Dynamic Matching | |
| Hernandez et al. | Development of a non-intrusive load monitoring (nilm) with unknown loads using support vector machine | |
| Liu et al. | Experiment‐based supervised learning approach toward condition monitoring of PV array mismatch | |
| CN106295877B (en) | Method for predicting electric energy consumption of smart power grid | |
| CN117076898B (en) | Photoelectric conversion method, device, equipment and storage medium | |
| CN116681186B (en) | Power quality analysis method and device based on intelligent terminal | |
| Siva et al. | Hybrid LSTM-PCA-powered renewable energy-based battery life prediction and management for IoT applications | |
| Treiber et al. | Aggregation of features for wind energy prediction with support vector regression and nearest neighbors | |
| Sun et al. | A novel GCN based indoor localization system with multiple access points | |
| CN116644306B (en) | Power data management method and system based on intelligent terminal | |
| Kreidl et al. | An efficient message-passing algorithm for optimizing decentralized detection networks | |
| Wang et al. | An efficient state-of-health estimation method for lithium-ion batteries based on feature-importance ranking strategy and PSO-GRNN algorithm | |
| CN111222078B (en) | Model building device and load analysis system | |
| CN116167465A (en) | Solar irradiance prediction method based on multivariate time series ensemble learning | |
| CN115208308A (en) | Photovoltaic system direct-current fault arc detection method and related equipment | |
| Luo et al. | Fine-grained bandwidth estimation for smart grid communication network | |
| Zhang et al. | Topology identification method of low voltage aea based on topological data analysis | |
| Langa | Communication technology selection method for smart energy metering based on analytic hierarchy process |
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 | ||
| GR01 | Patent grant |