CN116129617A - Low-efficiency power generation early warning method and system based on time sequence data portrait - Google Patents
Low-efficiency power generation early warning method and system based on time sequence data portrait Download PDFInfo
- Publication number
- CN116129617A CN116129617A CN202211522079.5A CN202211522079A CN116129617A CN 116129617 A CN116129617 A CN 116129617A CN 202211522079 A CN202211522079 A CN 202211522079A CN 116129617 A CN116129617 A CN 116129617A
- Authority
- CN
- China
- Prior art keywords
- power generation
- photovoltaic
- shadow
- early warning
- string
- 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.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/185—Electrical failure alarms
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Photovoltaic Devices (AREA)
Abstract
The embodiment of the invention relates to the technical field of photovoltaic power generation, and particularly discloses a low-efficiency power generation early warning method and system based on time sequence data portrait, wherein the prior art rarely considers the interference caused by periodic change, and simultaneously causes larger errors of estimated power generation loss and actual loss, thereby influencing dust early warning accuracy; therefore, in the early warning method provided by the invention, shadow images of the photovoltaic shielding time sequence are prepared, and the shadow loss electric quantity is calculated based on the shadow images; judging the ash accumulation of the photovoltaic string and calculating the lost electric quantity; and the photovoltaic string runs in an inefficient mode to give an alarm. Therefore, the invention combines the shadow image of the photovoltaic shielding time sequence to distinguish the specific reason of the reduction of the group string current, avoids the shadow shielding caused by the periodic fluctuation phenomenon of the group string, reduces the false alarm rate and improves the early warning accuracy.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to an inefficient power generation early warning method and system based on time sequence data portraits.
Background
With the increasing prominence of environmental problems, energy transformation problems are widely focused, and clean renewable energy sources such as solar energy, wind energy and the like are rapidly developed as novel energy sources. The solar photovoltaic industry is a mature industry in a new energy industry system, and the industrial scale is further expanded. In order to meet the requirement of digital transformation, the digital transformation of the photovoltaic field station is also a necessary trend.
With the continuous development of the photovoltaic industry, the gradual realization of digital operation of a photovoltaic electric field is also a current important breakthrough direction under the background that the installed capacity of new photovoltaic energy is continuously increased. The normal operation of the photovoltaic module is the basis for ensuring continuous, stable and efficient power generation of the photovoltaic power station. The photovoltaic module is the equipment with the largest quantity of photovoltaic power stations, normal operation of the module is required to be ensured, the running state of the module is required to be monitored in time, and the abnormal running state is early-warned in time, so that the operation and maintenance cost can be saved, the working efficiency of operation and maintenance personnel can be greatly improved, and the operation and maintenance personnel can accurately and rapidly find out the module with problems. In order to maintain continuous, efficient and stable power generation of the photovoltaic module, a large amount of manpower and material resources are required to be input. There is also an urgent need to perform accurate and inefficient early warning on photovoltaic strings through big data and artificial intelligence related algorithms while avoiding power generation loss.
At present, when current deviation abnormality is determined, the threshold value is usually set according to the region and experience of a photovoltaic power station, the influence on the current deviation under different categories is not considered, when the current deviation constant value is screened, descriptive statistics are usually adopted to determine the current deviation abnormality, the abnormal value of the time sequence is difficult to accurately detect in the mode, because the time dimension and the season dimension are considered, in the process of eliminating power generation loss caused by non-dust shielding, the interference caused by periodic change is rarely considered in the prior art, and meanwhile, the estimated power generation loss and the actual loss have larger errors, so that the dust early warning accuracy is influenced.
Disclosure of Invention
The invention aims to provide a low-efficiency power generation early warning method and system based on time sequence data portrait, which are used for solving the problem that the running state of a photovoltaic module cannot be early warned timely and accurately at present and ensuring the normal running of the photovoltaic module. In order to achieve the above purpose, the embodiment of the present invention provides the following technical solutions.
In a first aspect, in one embodiment of the present invention, there is provided an inefficient power generation early warning method based on a time-series data representation, the early warning method including the steps of:
shadow images of a photovoltaic shielding time sequence are prepared, and shadow loss electric quantity is calculated based on the shadow images;
judging the ash accumulation of the photovoltaic string and calculating the lost electric quantity;
and the photovoltaic string runs in an inefficient mode to give an alarm.
Further, the step of preparing the shadow representation of the photovoltaic shielding time sequence comprises the following steps:
calculating a string current deviation rate, identifying string current with abnormal fluctuation by applying a spectral clustering algorithm based on string current data, and setting a threshold according to the region and experience of the photovoltaic power station according to a clustering result;
aiming at the detection of the abnormal value of the current deviation and combining with the set threshold value, calculating the duration time of the lower string;
a shadow image is generated.
Further, the step of calculating the shadow loss power based on the shadow image includes:
analyzing the time sequence as the periodicity of the index;
calculating the current deviation rate of each group string current in the shadow time length, and simultaneously converting the electric quantity loss of each group string based on the current deviation rate;
and summing the electric quantity loss of each group string to obtain the shadow loss electric quantity of the inverter.
Further, the steps of the photovoltaic string dust accumulation judgment and the loss electric quantity calculation include:
and (3) learning the power generation performance of the component in a clean state by a statistical method, and establishing a theoretical power generation capacity prediction model.
Establishing a cleaning index model based on CNN, evaluating the accumulation degree of dust, and quantifying the influence of the dust on the power generation capacity of the component;
and (3) inputting time, actual power generation, radiation intensity, ambient temperature and wind speed into a theoretical power generation prediction model to obtain theoretical power generation, combining shadow images of a photovoltaic shielding time sequence, removing the running states of inverter faults, overhauling, electricity limiting and shutdown, and calculating to obtain the lost power caused by dust accumulation.
Furthermore, the step of establishing the theoretical power generation amount prediction model comprises the steps of respectively establishing the theoretical power generation amount prediction model for the photovoltaic module under different conditions by adopting a slicing and dicing method, so as to realize accurate prediction of the optimal power generation amount of the photovoltaic module.
Further, the feature matrix required by modeling is divided into data sets by adopting a slicing and dicing method, noise data is preprocessed by adopting a data cleaning method aiming at different slices and dicing, and the theoretical generated energy of each slice and dicing, namely the optimal generated energy under theoretical conditions, is output by adopting a statistical method.
Further, the step of alarming the photovoltaic string in an inefficient operation mode comprises the following steps of: and judging the running state of the photovoltaic string according to the calculated lost electric quantity, and alarming when the running state is low-efficiency running.
In a second aspect, in another embodiment provided by the present invention, an inefficient power generation early warning system based on time-series data portraits, the early warning system comprising:
the shadow portrait module is used for preparing shadow portraits of the photovoltaic shielding time sequence;
the first calculation module is used for calculating shadow loss electric quantity based on the shadow portrait;
the second calculation module is used for judging the dust accumulation of the photovoltaic group string and calculating the lost electric quantity;
the low-efficiency early warning module is used for alarming the low-efficiency operation of the photovoltaic string.
In a third aspect, in yet another embodiment provided by the present invention, a computer device includes a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, which when executed implement the method for inefficient power generation pre-warning based on time-series data portraits as provided in the first aspect.
In a fourth aspect, in yet another embodiment provided by the present invention, a computer-readable storage medium stores computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the method for inefficient power generation warning based on time-series data representation as provided in the first aspect.
Compared with the prior art, the embodiment of the invention has the beneficial effects that: in the early warning method provided by the invention, shadow images of a photovoltaic shielding time sequence are formulated, and the shadow loss electric quantity is calculated based on the shadow images; judging the ash accumulation of the photovoltaic string and calculating the lost electric quantity; and the photovoltaic string runs in an inefficient mode to give an alarm. Therefore, the invention combines the shadow image of the photovoltaic shielding time sequence to distinguish the specific reason of the reduction of the group string current, avoids the shadow shielding caused by the periodic fluctuation phenomenon of the group string, reduces the false alarm rate and improves the early warning accuracy.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
FIG. 1 is a flow chart of an implementation of the low-efficiency power generation early warning method based on time-series data portraits.
FIG. 2 is a sub-flowchart of the pre-warning method provided by the present invention;
FIG. 3 is another sub-flowchart of the pre-warning method provided by the present invention;
FIG. 4 is a schematic diagram of shadow images in the early warning method provided by the invention;
FIG. 5 is a block diagram of the low-efficiency power generation early warning system based on time-series data representation;
fig. 6 is a block diagram of a computer device according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
At present, when current deviation abnormality is determined, the threshold value is usually set according to the region and experience of a photovoltaic power station, the influence on the current deviation under different categories is not considered, when the current deviation constant value is screened, descriptive statistics are usually adopted to determine the current deviation abnormality, the abnormal value of the time sequence is difficult to accurately detect in the mode, because the time dimension and the season dimension are considered, in the process of eliminating power generation loss caused by non-dust shielding, the interference caused by periodic change is rarely considered in the prior art, and meanwhile, the estimated power generation loss and the actual loss have larger errors, so that the dust early warning accuracy is influenced.
In order to solve the problems, the early warning method and the early warning system provided by the invention combine shadow images of the photovoltaic shielding time sequence to distinguish specific reasons of reduced group string current, avoid shadow shielding caused by periodic fluctuation phenomenon of the group string, reduce false alarm rate and improve early warning accuracy.
Specific implementations of the invention are described in detail below in connection with specific embodiments.
Example 1
Referring to fig. 1, in one embodiment of the present invention, an inefficient power generation early warning method based on time-series data representation is provided, the early warning method includes the following steps:
step S101: shadow images of a photovoltaic shielding time sequence are prepared, and shadow loss electric quantity is calculated based on the shadow images;
step S102: judging the ash accumulation of the photovoltaic string and calculating the lost electric quantity;
step S103: and the photovoltaic string runs in an inefficient mode to give an alarm.
Further, as shown in fig. 2, in the embodiment of the present invention, the step of creating the shadow image of the photovoltaic occlusion time sequence includes:
step S1011: calculating a string current deviation rate, identifying string current with abnormal fluctuation by applying a spectral clustering algorithm based on string current data, and setting a threshold according to the region and experience of the photovoltaic power station according to a clustering result;
step S1012: aiming at the detection of the abnormal value of the current deviation and combining with the set threshold value, calculating the duration time of the lower string; generating a shadow image;
step S1013: analyzing the time sequence as the periodicity of the index;
step S1014: calculating the current deviation rate of each group string current in the shadow time length, and simultaneously converting the electric quantity loss of each group string based on the current deviation rate;
step S1015: and summing the electric quantity loss of each group string to obtain the shadow loss electric quantity of the inverter.
Specifically, in the embodiment of the invention, the cluster current deviation rate is calculated based on cluster current data, a spectral clustering algorithm is applied to identify the cluster current with abnormal fluctuation, and a threshold is set according to the region and experience of the photovoltaic power station according to the clustering result. Under the category of different clusters, the idea of transfer learning is generally adopted, and the same threshold value is adopted for power stations with the same environmental conditions such as regions, climates and the like.
Further, the duration of the lower string is calculated for the constant detection of the current bias difference and in combination with the set threshold.
Further, a shadow image as shown in fig. 4 is generated.
In the embodiment of the invention, the analysis time sequence is the periodicity of the index: because the fixed building or the plant is shielded, the string current can be caused to show a declining trend in a short term and periodically change, and meanwhile, the shadow caused by the shielding of the fixed building or the plant is further eliminated; secondly, cloud layer shielding is adopted, the string current shows the characteristic of rapid fluctuation in a short term, and no obvious periodicity and regularity are seen in a long term.
Further, a current deviation rate of each string current in the shadow time period is calculated, and the electric quantity loss of each string is converted based on the current deviation rate.
Further, the sum of the electric quantity losses of each group string is the shadow loss electric quantity of the inverter.
Further, as shown in fig. 3, in the embodiment of the present invention, the steps of determining the ash accumulation of the photovoltaic string and calculating the loss electric quantity include:
step S1021: and (3) learning the power generation performance of the component in a clean state by a statistical method, and establishing a theoretical power generation capacity prediction model.
Step S1022: establishing a cleaning index model based on CNN, evaluating the accumulation degree of dust, and quantifying the influence of the dust on the power generation capacity of the component;
step S1023: and (3) inputting time, actual power generation, radiation intensity, ambient temperature and wind speed into a theoretical power generation prediction model to obtain theoretical power generation, combining shadow images of a photovoltaic shielding time sequence, removing the running states of inverter faults, overhauling, electricity limiting and shutdown, and calculating to obtain the lost power caused by dust accumulation.
Furthermore, the step of establishing the theoretical power generation amount prediction model comprises the steps of respectively establishing the theoretical power generation amount prediction model for the photovoltaic module under different conditions by adopting a slicing and dicing method, so as to realize accurate prediction of the optimal power generation amount of the photovoltaic module.
Further, the feature matrix required by modeling is divided into data sets by adopting a slicing and dicing method, noise data is preprocessed by adopting a data cleaning method aiming at different slices and dicing, and the theoretical generated energy of each slice and dicing, namely the optimal generated energy under theoretical conditions, is output by adopting a statistical method.
The photovoltaic module is affected by dust, so that the power generation efficiency of the photovoltaic module is obviously reduced, namely, the maximum power generation power is gradually reduced under any environmental conditions such as illumination, temperature and the like. Besides local pollution, dust accumulation of all components in a photovoltaic power station generally shows large-scale consistency, and the influence degree of dust on the generated energy is difficult to analyze by a transverse comparison method. Therefore, by taking each inverter as a unit, an optimal power generation model is respectively established, the optimal power generation performance under any environmental condition is obtained, and the accurate evaluation of dust accumulation degree is realized by a method of optimal comparison with the inverter.
It can be understood that the invention learns the optimal power generation performance of the assembly in clean time by a statistical method and establishes a theoretical power generation capacity prediction model. The theoretical generated energy of the photovoltaic module is influenced by environmental conditions such as radiation intensity, ambient temperature, wind speed and the like, namely, the theoretical generated energy of the photovoltaic module under any condition is considered to be different, so that modeling of the theoretical generated energy is difficult to achieve through establishment of unified standards. In order to optimize the model precision and the generalization capability of the model, a theoretical power generation amount prediction model is respectively established for the components under different conditions by adopting a slicing and dicing method, so that the accurate prediction of the optimal power generation amount of the photovoltaic component is realized.
Specifically, the feature matrix required by modeling is divided into data sets by adopting a slicing and dicing method, the data of noise is preprocessed by adopting a data cleaning method, such as descriptive statistics, association relation constraint and the like, aiming at different slices and dicing, and the theoretical generated energy of each slice and dicing, namely the optimal generated energy under theoretical conditions, is learned by adopting a statistical method, such as a Gaussian model, maximum likelihood estimation and the like.
In the embodiment of the invention, a cleaning index model is established based on CNN, the accumulation degree of dust is evaluated, and the influence of the dust on the power generation capacity of the component is quantified. The influence degree (cleaning index) of dust accumulation on the power generation capacity of the component is shown in the difference degree of theoretical power generation capacity and actual power generation capacity, so that the cleaning index can be accurately predicted by combining the strong learning capacity of CNN on the basis of a theoretical power generation capacity prediction model.
Therefore, the time, the actual power generation amount, the radiation intensity, the ambient temperature and the wind speed are input into a theoretical power generation amount prediction model to obtain the theoretical power generation amount, the shadow images of the photovoltaic shielding time sequence are combined to be prepared, the running states of inverter faults, overhauling, electricity limiting and shutdown are eliminated, and the lost power caused by dust accumulation is calculated.
Further, the step of alarming the photovoltaic string in an inefficient operation mode comprises the following steps of: and judging the running state of the photovoltaic string according to the calculated lost electric quantity, and alarming when the running state is low-efficiency running.
Therefore, because the photovoltaic string current is influenced by environmental conditions such as radiation intensity, ambient temperature, wind speed and the like, fluctuation is very easy to occur, and particularly, under the condition of fixed shadow shielding, the string current has a periodical lower phenomenon. Therefore, it is difficult to determine that the component has a failure only by a method such as discrete rate analysis of the string current, empirical threshold setting, or the like. Therefore, the buyer can avoid shadow shielding caused by periodic fluctuation of the group string by combining shadow image of the photovoltaic shielding time sequence to distinguish the specific reason of the reduction of the group string current, thereby reducing the false alarm rate and improving the alarm accuracy.
Example 2
In another embodiment of the present invention, as shown in fig. 5, an early warning system for low-efficiency power generation based on time-series data representation, the early warning system 200 includes: a shadow representation module 201 for preparing shadow representations of the photovoltaic occlusion time series; a first calculation module 202 for calculating a shadow loss amount based on a shadow representation; the second calculation module 203 is used for judging the ash deposition of the photovoltaic group string and calculating the lost electric quantity; and the low-efficiency early warning module 204 is used for warning the low-efficiency operation of the photovoltaic string.
Example 3
In yet another embodiment provided by the present invention, as shown in fig. 6, a computer device 300 includes a memory 301, a processor 302, and computer readable instructions stored in the memory 301 and executable on the processor 302, wherein the processor 302 implements the low-efficiency power generation warning method based on time-series data representation as provided in embodiment 1 when executing the computer readable instructions; in addition, the device 300 provided in the embodiment of the present invention may further have a communication interface 303, for receiving a control instruction.
Further, an embodiment of the present invention provides a computer-readable storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the low-efficiency power generation early warning method based on the time-series data representation as provided in embodiment 1.
In various embodiments of the present invention, it should be understood that the size of the sequence numbers of the processes does not mean that the execution sequence of the processes is necessarily sequential, and the execution sequence of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
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-accessible memory. Based on this understanding, the technical solution of the present invention, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a memory, comprising several requests for a computer device (which may be a personal computer, a server or a network device, etc., in particular may be a processor in a computer device) to execute some or all of the steps of the method according to the embodiments of the present invention.
Those of ordinary skill in the art will appreciate that some or all of the steps of the various methods of the described embodiments may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random access Memory (Random Access Memory,11 RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (CD-ROM) or other optical disc Memory, magnetic disk Memory, tape Memory, or any other medium capable of being used to carry or store data.
The method, the device, the electronic equipment and the storage medium for information interaction disclosed by the embodiment of the invention are described in detail, and specific examples are applied to the description of the principle and the implementation mode of the invention, and the description of the above embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. The low-efficiency power generation early warning method based on the time sequence data portrait is characterized by comprising the following steps of:
shadow images of a photovoltaic shielding time sequence are prepared, and shadow loss electric quantity is calculated based on the shadow images;
judging the ash accumulation of the photovoltaic string and calculating the lost electric quantity;
and the photovoltaic string runs in an inefficient mode to give an alarm.
2. The method for generating electricity with low efficiency based on time series data representation according to claim 1, wherein the step of creating shadow representation of the photovoltaic occlusion time series comprises:
calculating a string current deviation rate, identifying string current with abnormal fluctuation by applying a spectral clustering algorithm based on string current data, and setting a threshold according to the region and experience of the photovoltaic power station according to a clustering result;
aiming at the detection of the abnormal value of the current deviation and combining with the set threshold value, calculating the duration time of the lower string;
a shadow image is generated.
3. The method for inefficient power generation warning based on time series data portraits of claim 2, wherein the step of calculating the shadow loss power based on shadow portraits comprises:
analyzing the time sequence as the periodicity of the index;
calculating the current deviation rate of each group string current in the shadow time length, and simultaneously converting the electric quantity loss of each group string based on the current deviation rate;
and summing the electric quantity loss of each group string to obtain the shadow loss electric quantity of the inverter.
4. The method for low-efficiency power generation early warning based on time series data portrait according to claim 3, wherein the steps of determining the accumulated ash of the photovoltaic group string and calculating the lost electric quantity comprise:
the power generation performance of the assembly in a clean state is learned through a statistical method, and a theoretical power generation capacity prediction model is established;
establishing a cleaning index model based on CNN, evaluating the accumulation degree of dust, and quantifying the influence of the dust on the power generation capacity of the component;
and (3) inputting time, actual power generation, radiation intensity, ambient temperature and wind speed into a theoretical power generation prediction model to obtain theoretical power generation, combining shadow images of a photovoltaic shielding time sequence, removing the running states of inverter faults, overhauling, electricity limiting and shutdown, and calculating to obtain the lost power caused by dust accumulation.
5. The method for low-efficiency power generation early warning based on time series data portraits according to claim 4, wherein the step of establishing a theoretical power generation amount prediction model comprises the step of respectively establishing the theoretical power generation amount prediction model for photovoltaic modules under different conditions by adopting a slicing and dicing method.
6. The low-efficiency power generation early warning method based on the time series data portrait according to claim 5 is characterized in that a feature matrix required by modeling is divided into data sets by adopting a slicing and dicing method, noisy data are preprocessed by adopting a data cleaning method aiming at different slices and dicing, and a statistical method is applied to output theoretical power generation capacity of each slice and dicing.
7. The method for generating electricity with low efficiency based on time series data representation according to claim 6, wherein the step of alarming the photovoltaic string with low efficiency comprises the steps of: and judging the running state of the photovoltaic string according to the calculated lost electric quantity, and alarming when the running state is low-efficiency running.
8. An early warning system for implementing the time series data representation-based low-efficiency power generation early warning method as claimed in any one of claims 1 to 7, characterized in that the early warning system comprises:
the shadow portrait module is used for preparing shadow portraits of the photovoltaic shielding time sequence;
the first calculation module is used for calculating shadow loss electric quantity based on the shadow portrait;
the second calculation module is used for judging the dust accumulation of the photovoltaic group string and calculating the lost electric quantity;
the low-efficiency early warning module is used for alarming the low-efficiency operation of the photovoltaic string.
9. A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein execution of the computer readable instructions by the processor implements the time-series data representation-based low-efficiency power generation warning method of any one of claims 1-7.
10. A computer-readable storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the time-series data representation-based low-efficiency power generation warning method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211522079.5A CN116129617A (en) | 2022-11-30 | 2022-11-30 | Low-efficiency power generation early warning method and system based on time sequence data portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211522079.5A CN116129617A (en) | 2022-11-30 | 2022-11-30 | Low-efficiency power generation early warning method and system based on time sequence data portrait |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116129617A true CN116129617A (en) | 2023-05-16 |
Family
ID=86307007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211522079.5A Pending CN116129617A (en) | 2022-11-30 | 2022-11-30 | Low-efficiency power generation early warning method and system based on time sequence data portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116129617A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117909791A (en) * | 2024-01-18 | 2024-04-19 | 创维互联（北京）新能源科技有限公司 | Photovoltaic power station shadow shielding recognition and positioning method and system based on artificial intelligence |
-
2022
- 2022-11-30 CN CN202211522079.5A patent/CN116129617A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117909791A (en) * | 2024-01-18 | 2024-04-19 | 创维互联（北京）新能源科技有限公司 | Photovoltaic power station shadow shielding recognition and positioning method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2024046137A1 (en) | Power prediction model construction method for multi-energy combined power generation system and power prediction method for multi-energy combined power generation system | |
| CN109872084A (en) | The failure rate statistical method and system of Wind turbines | |
| CN112699113B (en) | Industrial manufacturing process operation monitoring system driven by time sequence data stream | |
| CN113723773A (en) | Electric energy decision system based on big data analysis | |
| Li et al. | Outlier data mining method considering the output distribution characteristics for photovoltaic arrays and its application | |
| CN116129617A (en) | Low-efficiency power generation early warning method and system based on time sequence data portrait | |
| CN117687884A (en) | Intelligent optimization method and system for operation and maintenance operation ticket of power grid dispatching automation master station | |
| CN117520986A (en) | Distributed photovoltaic power generation anomaly monitoring method, system, equipment and storage medium | |
| CN117060353A (en) | Fault diagnosis method and system for high-voltage direct-current transmission system based on feedforward neural network | |
| CN115965136A (en) | Carbon emission comprehensive prediction system based on electric power big data | |
| CN114138601A (en) | Service alarm method, device, equipment and storage medium | |
| CN117591994A (en) | Power equipment state data prediction method, intelligent platform, equipment and medium | |
| CN117318291A (en) | Intelligent management system and method for distributed photovoltaic field station | |
| KR20210097613A (en) | Power consumption prediction system for optimization of demand management resources | |
| CN112835949A (en) | Load prediction method | |
| CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
| CN115545966A (en) | Photovoltaic group string power loss analysis and identification method and storage medium thereof | |
| CN113642937B (en) | Operation and maintenance scheduling method and device for fan cluster, electronic equipment and storage medium | |
| CN114154567A (en) | Wind power plant station operation data anomaly identification method based on machine learning | |
| CN115345519A (en) | Offshore wind power risk assessment method, device, equipment and storage medium | |
| CN113947223A (en) | Intelligent equipment health management system and method | |
| CN118365139B (en) | Risk situation awareness method, system, equipment and medium | |
| CN112330003B (en) | Periodic capacity data prediction method, system and storage medium based on bidirectional cyclic neural network | |
| CN118137572B (en) | Clean energy consumption capacity improving method based on power load distribution | |
| CN115063643B (en) | Automatic labeling method for power scene image data |
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 |