CN117493766A - Regional photovoltaic typical daily curve similarity anomaly identification method, device and medium - Google Patents
Regional photovoltaic typical daily curve similarity anomaly identification method, device and medium Download PDFInfo
- Publication number
- CN117493766A CN117493766A CN202311447770.6A CN202311447770A CN117493766A CN 117493766 A CN117493766 A CN 117493766A CN 202311447770 A CN202311447770 A CN 202311447770A CN 117493766 A CN117493766 A CN 117493766A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic
- data
- power generation
- regional
- curve
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000010248 power generation Methods 0.000 claims abstract description 83
- 230000002776 aggregation Effects 0.000 claims abstract description 30
- 238000004220 aggregation Methods 0.000 claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 19
- 230000005856 abnormality Effects 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000003860 storage Methods 0.000 claims description 15
- 238000005070 sampling Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 2
- 238000004590 computer program Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 230000006872 improvement Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Remote Sensing (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention relates to a method, a device and a medium for identifying regional photovoltaic typical daily curve similarity abnormality, wherein the method comprises the following steps: acquiring photovoltaic data and weather data, and preprocessing the photovoltaic data; dividing the preprocessed photovoltaic data according to weather data to obtain photovoltaic data of different weather conditions; combining a dynamic time warping algorithm and a density clustering method, clustering photovoltaic data, extracting characteristic values from the clustered data, and forming a photovoltaic cluster characteristic typical curve with aggregation characteristics based on the characteristic values; and acquiring an actual regional photovoltaic power generation power sequence, judging an inconsistency coefficient between the regional photovoltaic power generation power sequence and a photovoltaic cluster characteristic typical curve, and outputting the existing abnormality. Compared with the prior art, the method has the advantages of improving the accuracy and efficiency of identifying the abnormal condition of the photovoltaic power generation and the like.
Description
Technical Field
The invention relates to the technical field of photovoltaic user power generation management, in particular to a regional photovoltaic typical daily curve similarity anomaly identification method, device and medium.
Background
At present, the scale and the number of the photovoltaic power generation systems are continuously increased, but a series of operation and maintenance technology and management problems such as equipment faults, equipment ageing, human factors and the like are faced with the increase of potential safety hazards of the photovoltaic power generation systems.
The operation and maintenance of the traditional photovoltaic power generation system requires a great deal of manpower and material resources to be invested, such as daily inspection, maintenance, inspection and the like. Likewise, the construction of the novel power system enables equipment in the power grid to present more various and distributed characteristics, abnormal data under different weather conditions are different in expression mode, abnormal operation and maintenance are required to be identified from photovoltaic big data, input workload is large, labor work is completely relied on, and efficiency is low.
In summary, the existing abnormal condition recognition of photovoltaic power generation is difficult to face diversification, such as the photovoltaic power generation big data of different weather conditions, and the recognition accuracy is poor and the efficiency is low.
Disclosure of Invention
The invention aims to provide a regional photovoltaic typical daily curve similarity anomaly identification method, device and medium for improving the accuracy and efficiency of identification of abnormal conditions of photovoltaic power generation.
The aim of the invention can be achieved by the following technical scheme:
a regional photovoltaic typical daily curve similarity anomaly identification method based on time sequence aggregation comprises the following steps:
acquiring photovoltaic data and weather data, and preprocessing the photovoltaic data;
dividing the preprocessed photovoltaic data according to weather data to obtain photovoltaic data of different weather conditions;
combining a dynamic time warping algorithm and a density clustering method, clustering photovoltaic data, extracting characteristic values from the clustered data, and forming a photovoltaic cluster characteristic typical curve with aggregation characteristics based on the characteristic values;
and acquiring an actual regional photovoltaic power generation power sequence, judging an inconsistency coefficient between the regional photovoltaic power generation power sequence and a photovoltaic cluster characteristic typical curve, if the inconsistency exceeds a threshold value, no abnormality exists, otherwise, the regional photovoltaic power generation power sequence is abnormal, and the existing abnormality is output.
Further, the specific steps of extracting characteristic values from clustered data and forming a photovoltaic cluster characteristic typical curve with aggregation characteristic based on the characteristic values are as follows:
and selecting the median of the power generation P_t at the moment t from clustered data of the same weather condition as a characteristic value, smoothly connecting the characteristic values at all the moments to form a photovoltaic cluster characteristic typical curve with aggregation characteristics, wherein the photovoltaic cluster characteristic typical curve takes time as an abscissa and the power generation as an ordinate, and the photovoltaic cluster characteristic typical curve comprises a plurality of curves corresponding to different weather conditions.
Further, the inconsistency between the regional photovoltaic power generation power sequence and the photovoltaic cluster characteristic typical curve is:
wherein K is inconsistency, n represents sequence length, f i The non-uniformity is indicated by the fact that,P 1 representation and P 2 Corresponding sequence of characteristic curves of photovoltaic clusters with same weather conditions, P 2 Representing a regional photovoltaic power generation power sequence.
Further, the inconsistency is:
wherein,is P 1 Is the i-th sampling point of +.>Representing P 2 Is the i-th sampling point of (c).
Further, the threshold is 0.5.
Further, the specific steps of preprocessing the photovoltaic data are as follows:
calculating k nearest neighbor data nearby the abnormal value in the photovoltaic data to obtain an average value of the k data, replacing the abnormal value by the average value, and normalizing.
Further, the specific steps of normalization are as follows:
dividing the photovoltaic data by the power generation capacity of the photovoltaic project to obtain normalized photovoltaic data.
Further, different weather conditions include sunny days, cloudy days, and rainy days.
In another aspect of the present invention, a device for identifying regional photovoltaic typical day curve similarity abnormality based on time sequence aggregation is further provided, including a memory, a processor, and a program stored in the memory, where the processor implements the above method when executing the program.
In another aspect of the present invention, a computer-readable storage medium is also presented, on which a program is stored, which program, when executed, implements a method as described above.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, unsupervised clustering is performed through a time sequence aggregation algorithm, different weather conditions such as sunny days, cloudy days, rainy days and the like are comprehensively considered, a typical photovoltaic power generation day curve in the region is constructed in different weather conditions, the curve can fully represent the typical power generation condition of photovoltaic equipment in the region, a regional photovoltaic aggregation characteristic curve is accurately drawn, and the photovoltaic power generation abnormal identification method based on similarity is combined to realize the accurate identification of photovoltaic power generation abnormal users in the region, grasp the operation state of a photovoltaic system, improve the accuracy and efficiency of identifying the abnormal condition of photovoltaic power generation, ensure the safety and service life of the photovoltaic equipment, improve the photovoltaic power generation efficiency and promote the safe and stable operation of the whole power system.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. The present embodiment is implemented on the premise of the technical scheme of the present invention, and a detailed implementation manner and a specific operation process are given, but the protection scope of the present invention is not limited to the following examples.
Example 1:
the invention provides a regional photovoltaic typical daily curve similarity anomaly identification method, and a flow chart of the method is shown in figure 1. The method comprises the following steps:
s1, acquiring photovoltaic data and weather data;
s2, preprocessing photovoltaic data;
s3, dividing the preprocessed photovoltaic data according to weather data to obtain photovoltaic data of different weather conditions;
s4, clustering the photovoltaic data by combining a dynamic time warping algorithm and a density clustering method;
s5, extracting characteristic values from clustered data, and forming a photovoltaic cluster characteristic typical curve with aggregation characteristics based on the characteristic values;
s6, acquiring an actual regional photovoltaic power generation power sequence, judging an inconsistency coefficient between the regional photovoltaic power generation power sequence and a photovoltaic cluster characteristic typical curve, if the inconsistency exceeds a threshold value, no abnormality exists, otherwise, the regional photovoltaic power generation power sequence is abnormal;
s7, outputting possible abnormality in S6.
In S1, photovoltaic data and meteorological data need to be acquired first. And acquiring data of the photovoltaic user electricity generation meter in detail by relying on a plurality of systems. The collected data comprise data such as power generation capacity of the photovoltaic equipment, voltage and current of the minute-scale photovoltaic power generation equipment, daily meteorological conditions and the like.
Specifically, 96-point voltage, current, photovoltaic user file data information and photovoltaic power generation capacity of a photovoltaic user power generation meter are obtained, and weather condition data of a local area are obtained. The photovoltaic data collected in the step S1 can be power generation data under the condition of different weather in the same area.
In S2, preprocessing the collected photovoltaic related data, and screening the data with obvious abnormality, such as missing data, data which is always 0, oversized data and the like, in the data processing process. And filling missing data, data standardization processing and the like are carried out so as to support subsequent data aggregation processing, typical power generation characteristic curve construction and anomaly identification.
Because the photovoltaic power generation data has strong continuity, namely the data change at adjacent moments is not very large, the k nearest neighbor method is adopted to complement the missing value.
In a given data sample, the algorithm obtains the average value of k nearest neighbors from the k nearest neighbors near the outlier, in the following manner, wherein X i-k Is the kth data preceding the outlier.
In addition, since the photovoltaic power generation power is positively correlated with the installed capacity, in order to eliminate the influence of the power generation capacity on the photovoltaic power generation efficiency, the data needs to be normalized, and then a photovoltaic cluster aggregation characteristic curve is extracted, which is specifically calculated as follows:
wherein P' is the power generated by the photovoltaic project at a certain moment, W is the power generation capacity of the photovoltaic project, and P is the power generated by the power generation project per unit power generation capacity.
And S3, dividing the processed data set according to the weather conditions of the research area, wherein the weather conditions comprise sunny days, cloudy days and rainy days. And respectively researching the power generation conditions of the photovoltaic equipment under different weather conditions to form a regional typical photovoltaic power generation day curve under different weather conditions.
In S4, the similarity measurement is performed on the photovoltaic power generation curves under the same area and weather conditions by using a dynamic time warping (Dynamic Time Warping, DTW) algorithm, that is, the smaller the cumulative distance value of the two curves is, the greater the similarity between the 2 original time sequences is. And aggregating all photovoltaic power generation power curves in the region through a DBSCAN algorithm, removing outlier curves, and ensuring the representativeness of the regional photovoltaic power generation power curves.
First, an aggregate similarity measure is determined by a Dynamic Time Warping (DTW) algorithm. DTW is a common method for measuring similarity, and compared with euclidean distance, the DTW algorithm solves the problem that euclidean distance fails when a time sequence drifts. For a given time length T of time series X and Y in the preprocessed photovoltaic data, a matrix T of T X T is established, wherein the matrix elements are any 2X i And x j Euclidean distance between them. Curved path e= { E 1 ，e 2 ，...,e l }，t<l, a set of consecutive matrix elements, defines the mapping between X and Y.
In determining the curved path, the element r (i, j) of the accumulated distance can be solved by dynamic programming, and is the sum of the distance of the current point and the distance of the smallest adjacent element capable of reaching the point, and the specific contents are as follows:
r(i,j)＝ED(i,j)+min{r(i-1,j-1),r(i-1,j),r(i,j-1)}
wherein r (i, j) is the cumulative similarity between the first i points of the X sequence and the first j points of the Y sequence; ED (i, j) is the distance, i.e., similarity, between the ith point of the X sequence and the jth point of the Y sequence.
Thus, the DTW distance is r (t, t).
Combining the above to obtain a curved path E= { E 1 ，e 2 ，...,e l E satisfies that the sum of local distances along this regular path is minimal.
And performing DBSCAN clustering on the data sets under different weather conditions by using a DTW similarity measurement method. DBSCAN clustering is an unsupervised ML clustering algorithm that groups time series data directly into similar groups or clusters without using pre-labeled targets to cluster data points. The method can effectively remove outliers and improve reliability and accuracy of the photovoltaic power generation data set under different weather conditions.
The method for clustering the photovoltaic data by combining the dynamic time warping algorithm and the density clustering method comprises the following specific steps:
a1, acquiring a sequence in preprocessed photovoltaic data as a sample, and initializing a core object set, wherein the photovoltaic data is photovoltaic power generation power data;
a2 for one sample x i Calculating a DTW distance, determining a curved path to obtain a sub-sample set, and if the number of samples in the sub-sample set is greater than or equal to a sample number threshold value, determining x i As a core object, and taking a union set with the core object set, repeating A2 until all samples are traversed;
a3, randomly taking out a core object from the core object set, marking the core object as a first core object, marking the core object as accessed, and adding samples which are not added with other clusters in all sub-sample sets of the first core object into the clusters of the first core object;
a4, for each sample in the cluster of the first core object, if the sample is also the core object, marking the sample as the second core object and marking the sample as accessed, adding the samples which are not added with other clusters in all sub-sample sets of the second core object into the cluster of the first core object, traversing each sample in the cluster of all the first core object, and repeating the step A4;
a5, taking out the core objects which are not marked as accessed from the core object set, repeating the step A3 until all the core objects are marked as accessed, completing clustering, and outputting clusters after each clustering.
In S5, a photovoltaic power generation power curve set with high similarity can be obtained based on a time sequence aggregation model, and then the curve set is fitted to obtain a photovoltaic power generation power typical curve, namely the curve can represent the photovoltaic overall power generation condition of the area.
And (3) performing curve fitting work on the photovoltaic power generation day data according to the photovoltaic power generation data set which is obtained in the step (4) and is analyzed based on the time sequence aggregation model. Because the photovoltaic power generation curve is special and does not accord with the subsection characteristic of the conventional curve, the invention selects the power P generated at the moment t in the same weather in the photovoltaic power generation data set t The median of the photovoltaic cluster in the weather is taken as a characteristic value of the regional photovoltaic cluster at the time t, the time is taken as an abscissa, the generated power data is taken as an ordinate, and the characteristic typical curve of the photovoltaic cluster in the weather with aggregation characteristics is formed after smooth connection.
And S6, after the photovoltaic power generation power typical curve in the area is obtained, comparing the power generation power curve of the photovoltaic equipment to be detected with the area typical power generation power curve through a similarity measurement algorithm, and if the similarity measurement value of the power generation power curve and the area typical power generation power curve is lower than a certain threshold value, determining that the photovoltaic power generation equipment is suspected to be abnormal.
Under the same weather condition, the regional photovoltaic power generation power sequences have strong correlation, and if the correlation between the single photovoltaic power generation power sequence and the cluster characteristic curve is weak or no correlation exists, the photovoltaic equipment can be primarily judged to have abnormal operation. The invention quantifies the irrelevance of random fluctuation of a single photovoltaic project power generation curve and a regional photovoltaic typical characteristic curve in the change by using an inconsistency coefficient K, and the calculation formula is as follows:
wherein P is 1 Representing a sequence of regional photovoltaic typical power generation efficiencies, P 2 Represents a sequence of power generation efficiency of a certain photovoltaic project,
f i (P 1 ,P 2 ) The expression is as follows:
f i (P 1 ,P 2 ) And (3) representing the inconsistency of the power generation efficiency curve trend between the i=1 sampling point and the i sampling point, and taking 1 when the trends are inconsistent, and otherwise taking 0. The inconsistency coefficient K represents the ratio of the number of sampling intervals with inconsistent trend on the two power generation efficiency curves to the total number of intervals, and is a number larger than 0 and smaller than 1, and the index only reflects the influence of random fluctuation because the inherent fluctuation of the two power generation efficiency curves has the same trend, so that the inconsistency coefficient K can be used for explaining regional photovoltaic cluster aggregation, and the smaller the K value is, the higher the similarity of the two is. Through a large amount of data calculation, when the inconsistency coefficient K is higher than 0.5, the correlation between the inconsistency coefficient K and the data is considered to be poor, namely the suspected anomaly is considered.
In S7, the abnormality of S6 is output. And early warning the abnormal photovoltaic power generation in time according to the result of model abnormality identification and analysis, and actively taking measures to avoid influence expansion, so that the operation stability of photovoltaic equipment and a power system is improved.
The technical scheme can comprehensively and accurately describe the typical characteristics of regional photovoltaic power generation, greatly improves the recognition precision and accuracy of photovoltaic power generation abnormality, and has important significance for guaranteeing the stable operation of a photovoltaic system and a power grid.
The regional photovoltaic typical daily curve similarity anomaly identification method based on time sequence aggregation can comprehensively consider the external influence factor of weather, analyze the power generation condition of photovoltaic equipment in the region and perform typical curve fitting, and greatly improve the accuracy of photovoltaic anomaly identification.
By introducing weather elements, the power generation conditions of photovoltaic equipment under four conditions of sunny days, cloudy days and rainy days are comprehensively considered, so that the method can adapt to daily weather conditions, and the accuracy of the description of the photovoltaic power generation typical curve in the area is improved. The method also eliminates the influence of daily outlier data on the typical curve by constructing the time sequence aggregation model, and ensures that the regional photovoltaic power generation daily curve is more typical.
Through a similarity measurement mode, the overall power generation efficiency of the photovoltaic equipment can be accurately estimated, the method has high abnormality identification accuracy, and the method has strong universality and expandability, can be suitable for abnormal identification of photovoltaic power generation in different areas and under different weather conditions, and is beneficial to improving the operation efficiency and the energy utilization rate of a photovoltaic system.
Example 2:
the invention also provides a device for identifying the regional photovoltaic typical daily curve similarity abnormality based on time sequence aggregation, which comprises a memory, a processor and a program stored in the memory, wherein the processor realizes the method of the embodiment 1 when executing the program.
Example 3:
the present invention also proposes a computer-readable storage medium having stored thereon a program that, when executed, implements the method of embodiment 1.
Improvements to one technology can clearly distinguish between improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) and software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable Gate Array, FPGA)) is an integrated circuit whose logic function is determined by the programming of the device by a user. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), lava, lola, myHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in the same piece or pieces of software and/or hardware when implementing the present invention.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (10)
1. A regional photovoltaic typical daily curve similarity anomaly identification method based on time sequence aggregation is characterized by comprising the following steps:
acquiring photovoltaic data and weather data, and preprocessing the photovoltaic data;
dividing the preprocessed photovoltaic data according to weather data to obtain photovoltaic data of different weather conditions;
combining a dynamic time warping algorithm and a density clustering method, clustering photovoltaic data, extracting characteristic values from the clustered data, and forming a photovoltaic cluster characteristic typical curve with aggregation characteristics based on the characteristic values;
and acquiring an actual regional photovoltaic power generation power sequence, judging an inconsistency coefficient between the regional photovoltaic power generation power sequence and a photovoltaic cluster characteristic typical curve, if the inconsistency exceeds a threshold value, no abnormality exists, otherwise, the regional photovoltaic power generation power sequence is abnormal, and the existing abnormality is output.
2. The method for identifying regional photovoltaic typical daily curve similarity abnormality based on time sequence aggregation according to claim 1, wherein the specific steps of extracting characteristic values from clustered data and forming a photovoltaic cluster characteristic curve with aggregation characteristics based on the characteristic values are as follows:
selecting the power P at the t moment from clustered data of the same weather condition t The characteristic values at all times are smoothly connected to form a photovoltaic cluster characteristic typical curve with aggregation characteristics, the photovoltaic cluster characteristic typical curve takes time as an abscissa and generated power as an ordinate, and the photovoltaic cluster characteristic typical curve comprises a plurality of curves corresponding to different weather conditions.
3. The method for identifying the regional photovoltaic typical daily curve similarity abnormality based on time sequence aggregation according to claim 2, wherein the inconsistency between the regional photovoltaic power generation power sequence and the photovoltaic cluster characteristic typical curve is as follows:
wherein K is inconsistency, n represents sequence length, f i Representing inconsistencies, P 1 Representation and P 2 Corresponding sequence of characteristic curves of photovoltaic clusters with same weather conditions, P 2 Representing a regional photovoltaic power generation power sequence.
4. The method for identifying regional photovoltaic typical daily curve similarity anomalies based on time sequence aggregation according to claim 3, wherein the inconsistency is:
wherein,is P 1 Is the i-th sampling point of +.>Representing P 2 Is the i-th sampling point of (c).
5. The method for identifying regional photovoltaic typical daily curve similarity anomalies based on time sequence aggregation according to claim 4, wherein the threshold is 0.5.
6. The method for identifying regional photovoltaic typical daily curve similarity anomalies based on time sequence aggregation according to claim 1, which is characterized by comprising the following specific steps of:
calculating k nearest neighbor data nearby the abnormal value in the photovoltaic data to obtain an average value of the k data, replacing the abnormal value by the average value, and normalizing.
7. The method for identifying regional photovoltaic typical daily curve similarity anomalies based on time sequence aggregation according to claim 6, wherein the specific normalization steps are as follows:
dividing the photovoltaic data by the power generation capacity of the photovoltaic project to obtain normalized photovoltaic data.
8. The method for identifying regional photovoltaic typical daily curve similarity anomalies based on time sequence aggregation according to claim 1, wherein different weather conditions comprise sunny days, cloudy days and rainy days.
9. A regional photovoltaic typical daily curve similarity anomaly identification device based on time sequence aggregation, comprising a memory, a processor and a program stored in the memory, wherein the processor implements the method of any one of claims 1-8 when executing the program.
10. A computer readable storage medium, on which a program is stored, characterized in that the program, when executed, implements the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311447770.6A CN117493766A (en) | 2023-11-02 | 2023-11-02 | Regional photovoltaic typical daily curve similarity anomaly identification method, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311447770.6A CN117493766A (en) | 2023-11-02 | 2023-11-02 | Regional photovoltaic typical daily curve similarity anomaly identification method, device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117493766A true CN117493766A (en) | 2024-02-02 |
Family
ID=89668426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311447770.6A Pending CN117493766A (en) | 2023-11-02 | 2023-11-02 | Regional photovoltaic typical daily curve similarity anomaly identification method, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117493766A (en) |
-
2023
- 2023-11-02 CN CN202311447770.6A patent/CN117493766A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110750524A (en) | Method and system for determining fault characteristics of active power distribution network | |
| CN110245047B (en) | Time sequence abnormality detection method, device and equipment | |
| CN110262937B (en) | Identification method and device for index abnormality reasons | |
| Fu et al. | Correlation analysis and augmentation of samples for a bidirectional gate recurrent unit network for the remaining useful life prediction of bearings | |
| CN107526667A (en) | A kind of Indexes Abnormality detection method, device and electronic equipment | |
| CN110634030B (en) | Method, device and equipment for mining service indexes of applications | |
| CN114386537B (en) | Lithium battery fault diagnosis method and device based on Catboost and electronic equipment | |
| CN109325607A (en) | A kind of short-term wind power forecast method and system | |
| CN107909212B (en) | Climbing event prediction method based on mesoscale wind power development process serialization | |
| CN112180258B (en) | Method, device, medium, terminal and system for measuring average coulombic efficiency of battery | |
| CN110858072B (en) | Method and device for determining running state of equipment | |
| US9613271B2 (en) | Determining severity of a geomagnetic disturbance on a power grid using similarity measures | |
| CN116628616A (en) | Data processing method and system for high-power charging energy | |
| CN116299008A (en) | Battery SOH prediction method and device, electronic equipment and storage medium | |
| CN116011158A (en) | Topology identification method, system and device for low-voltage transformer area | |
| KR102192067B1 (en) | Apparatus and method for estimating the power generation of photovoltaic generator | |
| CN117113247A (en) | Drainage system abnormality monitoring method, equipment and storage medium based on two-classification and clustering algorithm | |
| CN117493766A (en) | Regional photovoltaic typical daily curve similarity anomaly identification method, device and medium | |
| CN114723147A (en) | New energy power prediction method based on improved wavelet transform and neural network | |
| CN116976530B (en) | Cable equipment state prediction method, device and storage medium | |
| CN117270476B (en) | Production control method and system based on intelligent factory | |
| Traxler | Fault detection of large amounts of photovoltaic systems | |
| Tian et al. | Non-intrusive Load Identification Decision Method Based on Time Signatures | |
| CN112348074B (en) | Power distribution network power failure event accurate diagnosis method, device and system based on data driving | |
| Li et al. | Power plant fan fault warning based on bidirectional feature compression and state estimation |
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 |