CN116706907B - Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment - Google Patents
Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment Download PDFInfo
- Publication number
- CN116706907B CN116706907B CN202310997292.XA CN202310997292A CN116706907B CN 116706907 B CN116706907 B CN 116706907B CN 202310997292 A CN202310997292 A CN 202310997292A CN 116706907 B CN116706907 B CN 116706907B
- Authority
- CN
- China
- Prior art keywords
- photovoltaic
- data
- environment
- training
- environment data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000010248 power generation Methods 0.000 title claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 266
- 238000013528 artificial neural network Methods 0.000 claims abstract description 83
- 230000007613 environmental effect Effects 0.000 claims description 102
- 239000013598 vector Substances 0.000 claims description 61
- 230000006870 function Effects 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 8
- 241000282414 Homo sapiens Species 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 210000002569 neuron Anatomy 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011478 gradient descent method Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Power Engineering (AREA)
- Biophysics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Automation & Control Theory (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Fuzzy Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
Abstract
The invention provides a photovoltaic power generation prediction method and related equipment based on fuzzy reasoning, and relates to the technical field of photovoltaic power generation, wherein the method comprises the following steps: acquiring training environment data and training photovoltaic data; carrying out fuzzy division on training environment data to obtain a training environment data set; carrying out fuzzy division on the training photovoltaic data to obtain a training photovoltaic data set; inputting the training environment data set into a preset neural network for training to obtain a predicted photovoltaic data set corresponding to the training environment data set; according to the predicted photovoltaic data set and the training photovoltaic data set, parameter adjustment is carried out on the neural network until the neural network converges, and a photovoltaic prediction model is obtained; when the current environment data is acquired, calculating a current photovoltaic predicted value corresponding to the current environment data based on the photovoltaic predicted model. The invention can combine multisource information, fully exert the nonlinear modeling capability of the neural network and the human intelligent characteristics of fuzzy reasoning, and improve the prediction accuracy of photovoltaic power generation.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a photovoltaic power generation prediction method based on fuzzy reasoning and related equipment.
Background
Photovoltaic prediction is a key technology, and can help a photovoltaic power station to better utilize solar energy resources, improve the power generation efficiency, reduce the operation cost and ensure the safety and stability of a power grid. The main purpose of photovoltaic prediction is to predict the power generation amount or output power of a photovoltaic power station in a future period of time according to factors such as the position of the photovoltaic power station and the characteristics of components. The difficulty of photovoltaic prediction is that photovoltaic power generation is affected by various factors, such as solar radiation, cloud cover, temperature change, wind speed and direction, and the like, which have uncertainty and nonlinearity, so that the photovoltaic power generation has randomness and volatility.
Current predictions of photovoltaic power generation still lack an accurate and adaptable method.
Disclosure of Invention
The invention provides a photovoltaic power generation prediction method and related equipment based on fuzzy reasoning, which are used for solving the defect that an accurate photovoltaic power generation prediction method is lacked in the prior art and realizing accurate prediction of photovoltaic power generation.
The invention provides a photovoltaic power generation prediction method based on fuzzy reasoning, which comprises the following steps:
acquiring training environment data and training photovoltaic data;
performing fuzzy division on the training environment data to obtain a training environment data set, performing fuzzy division on the training photovoltaic data to obtain a training photovoltaic data set, wherein the training environment data set comprises a plurality of pairs of environment data pairs, each pair of environment data comprises a training environment data value and an environment label corresponding to each training environment data value, the training photovoltaic data set comprises a plurality of pairs of photovoltaic data, and each pair of photovoltaic data comprises a training photovoltaic data value and a photovoltaic label corresponding to each training photovoltaic data value;
Inputting the training environment data set into a preset neural network, and controlling the neural network to predict the training environment data set to obtain a predicted photovoltaic data set corresponding to the training environment data set, wherein the neural network comprises a fuzzy function;
according to the predicted photovoltaic data set and the training photovoltaic data set, parameter adjustment is carried out on the neural network until the neural network converges, and a photovoltaic prediction model is obtained;
when current environment data are acquired, calculating a current photovoltaic predicted value corresponding to the current environment data based on the photovoltaic predicted model.
According to the photovoltaic power generation prediction method based on fuzzy reasoning provided by the invention, the step of performing fuzzy division on the training environment data to obtain a training environment data set comprises the following steps:
calculating an environment characteristic vector corresponding to each training environment data;
according to the similarity between the environment feature vectors, primarily classifying the training environment data to obtain a plurality of initial environment clusters;
performing similarity calculation on the initial environment clusters to obtain cluster similarity values;
combining the initial environment clusters according to the cluster similarity value, and updating the data in the combined initial environment clusters until the initial environment clusters meet a preset stopping standard to obtain a plurality of target environment clusters and environment labels corresponding to the target environment clusters;
And generating an environment data pair according to the target environment cluster and the environment label.
According to the photovoltaic power generation prediction method based on fuzzy reasoning provided by the invention, the primary classification of the training environment data according to the similarity between the environment feature vectors, and the obtaining of a plurality of initial environment clusters comprises the following steps:
splitting the environment feature vector to obtain a first environment comparison value and a second environment comparison value corresponding to the environment feature vector;
calculating a first similarity between the first environmental comparison values;
dividing the environmental feature vectors according to the first similarity to obtain a first cluster;
calculating a second similarity between the second environmental comparison values in the first cluster;
and dividing the environment feature vector according to the second similarity to obtain an initial environment cluster.
According to the photovoltaic power generation prediction method based on fuzzy reasoning, before the training environment data and the training photovoltaic data are acquired, the method further comprises the following steps:
acquiring historical environment data, updated environment data, historical photovoltaic data and updated photovoltaic data;
according to a preset updating period, the updating environment data and the historical environment data are decimated to obtain training environment data; the method comprises the steps of,
And decimating the historical photovoltaic data and the updated photovoltaic data to obtain training photovoltaic data.
According to the photovoltaic power generation prediction method based on fuzzy reasoning provided by the invention, the sampling of the updated environment data and the historical environment data according to the preset updating period is carried out, and the obtaining of the training environment data comprises the following steps:
determining candidate environmental data in the updated environmental data and the historical environmental data according to the updating period;
comparing the candidate environment data with reference environment data corresponding to candidate environment time, and determining an abnormal value in the candidate environment data, wherein the candidate environment time is the time corresponding to the candidate environment data;
and adjusting the candidate environment data according to the abnormal value and the candidate environment time to obtain training environment data.
According to the photovoltaic power generation prediction method based on fuzzy reasoning, the comparing the candidate environment data with the reference environment data corresponding to the candidate environment time, and determining the abnormal value in the candidate environment data comprises the following steps:
determining a prediction parameter based on the reference environmental data;
Generating an environment prediction model according to the reference environment data and the prediction parameters;
generating predicted environment data corresponding to the candidate environment time based on the environment prediction model;
comparing the predicted environment data with the candidate environment data, and determining an abnormal value in the candidate environment data.
According to the photovoltaic power generation prediction method based on fuzzy reasoning provided by the invention, the training environment data set is input into a preset neural network, the neural network is controlled to predict the training environment data set, and the obtaining of a predicted photovoltaic data set corresponding to the training environment data set comprises the following steps:
inputting the training environment data set to an input layer of the neural network, and controlling the input layer to transmit the training environment data set to a hidden layer of the neural network;
controlling each computing node in the hidden layer to compute the training environment data set to obtain a corresponding initial value;
inputting the initial value into the fuzzy function, and controlling the fuzzy function to perform fuzzy calculation on the initial value to obtain predicted photovoltaic data;
and controlling the predicted photovoltaic data to be transmitted to an output layer of the neural network, and controlling the output layer to output.
The invention also provides a photovoltaic power generation prediction device based on fuzzy reasoning, which comprises:
the acquisition module is used for acquiring training environment data and training photovoltaic data;
the system comprises a dividing module, a fuzzy dividing module and a fuzzy dividing module, wherein the dividing module is used for carrying out fuzzy dividing on training environment data to obtain a training environment data set and carrying out fuzzy dividing on the training photovoltaic data to obtain a training photovoltaic data set, the training environment data set comprises a plurality of pairs of environment data pairs, the environment data pairs comprise training environment data values and environment labels corresponding to each training environment data value, the training photovoltaic data set comprises a plurality of pairs of photovoltaic data, and the photovoltaic data pairs comprise training photovoltaic data values and photovoltaic labels corresponding to each training photovoltaic data value;
the input module is used for inputting the training environment data set into a preset neural network, controlling the neural network to predict the training environment data set, and obtaining a predicted photovoltaic data set corresponding to the training environment data set, wherein the neural network comprises a fuzzy function;
the adjustment module is used for carrying out parameter adjustment on the neural network according to the predicted photovoltaic data set and the training photovoltaic data set until the neural network converges to obtain a photovoltaic prediction model;
And the prediction module is used for calculating a current photovoltaic predicted value corresponding to the current environment data based on the photovoltaic predicted model when the current environment data are acquired.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes any photovoltaic power generation prediction method based on fuzzy reasoning when executing the computer program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements any of the fuzzy inference based photovoltaic power generation prediction methods described above.
The photovoltaic power generation prediction method based on fuzzy reasoning can realize more accurate photovoltaic data prediction and provide important support for power dispatching and stable power supply of a photovoltaic power generation system. According to the invention, the training environment data set and the training photovoltaic data set are obtained by acquiring the training environment data and the training photovoltaic data and carrying out fuzzy division on the training environment data and the training photovoltaic data. Therefore, the multisource information is fully utilized, the input dimension is further expanded by combining with the environmental factors, the running state and influence factors of the photovoltaic power generation system are more comprehensively reflected, and the accuracy and reliability of prediction are improved. And then inputting the training environment data set into a preset neural network, and controlling the neural network to predict the training environment data set to obtain a predicted photovoltaic data set. And then, according to the predicted photovoltaic data set and the training photovoltaic data set, carrying out parameter adjustment on the neural network until the neural network converges to obtain a photovoltaic prediction model. The method fully plays the nonlinear modeling capability of the neural network and the human intelligent characteristic of fuzzy reasoning, restores the intuition and thinking of human beings and better captures the complex nonlinear relation. Therefore, finally, based on the photovoltaic prediction model, the current photovoltaic prediction value corresponding to the current environment data is calculated more accurately and has higher adaptability.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a photovoltaic power generation prediction method based on fuzzy reasoning;
FIG. 2 is a schematic structural diagram of a photovoltaic power generation prediction device based on fuzzy reasoning;
fig. 3 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention relates to a photovoltaic power generation prediction method based on fuzzy reasoning, which is described below with reference to fig. 1, and comprises the following steps:
s100, acquiring training environment data and training photovoltaic data;
s200, carrying out fuzzy division on the training environment data to obtain a training environment data set, carrying out fuzzy division on the training photovoltaic data to obtain a training photovoltaic data set, wherein the training environment data set comprises a plurality of pairs of environment data pairs, each pair of environment data pairs comprises a training environment data value and an environment label corresponding to each training environment data value, the training photovoltaic data set comprises a plurality of pairs of photovoltaic data, and each pair of photovoltaic data comprises a training photovoltaic data value and a photovoltaic label corresponding to each training photovoltaic data value;
s300, inputting the training environment data set into a preset neural network, and controlling the neural network to predict the training environment data set to obtain a predicted photovoltaic data set corresponding to the training environment data set, wherein the neural network comprises a fuzzy function;
s400, according to the predicted photovoltaic data set and the training photovoltaic data set, parameter adjustment is carried out on the neural network until the neural network converges, and a photovoltaic prediction model is obtained;
S500, when current environment data are acquired, calculating a current photovoltaic predicted value corresponding to the current environment data based on the photovoltaic predicted model.
Specifically, enough data is collected to train the neural network to build the photovoltaic predictive model. The training environment data and the training photovoltaic data can be obtained from an actual photovoltaic power station or a simulated photovoltaic system, or can be downloaded from a public database or website. Training environment data refers to environment data used to train a subsequent neural network. The training environment data are temperature, radiance, humidity, wind speed and the like corresponding to a certain moment. The training photovoltaic data refers to photovoltaic data for training the neural network, and the training photovoltaic data and the training environment data correspond to the same time for the rationality of training results. The time difference between different data can be in a unit of day or in a unit of hour, and can be adjusted according to the requirement on prediction precision. The data may be stored and represented in a table or matrix format, one for each row and one for each column. For the convenience of training, the training environment data and the training photovoltaic data can be subjected to standardized processing, for example, all inputs are converted into a range of 0-1 by maximum and minimum standardization, and training of the neural network is facilitated.
The continuous numerical data is then converted into discrete category data, thereby facilitating the input and output of the neural network. Fuzzy division is a method of dividing numerical data into a plurality of sections according to a certain rule and standard and giving each section a label. The fuzzy partitions may be set according to actual conditions and experience, or may be automatically or semi-automatically generated by using some algorithms or tools. The training environment data set comprises a plurality of pairs of environment data, and the environment data pairs comprise training environment data values and environment labels corresponding to each training environment data value. Taking temperature as an example, the environmental label may include high temperature, medium temperature, low temperature. The training photovoltaic data set comprises a plurality of photovoltaic data pairs, and the photovoltaic data pairs comprise training photovoltaic data values and photovoltaic labels corresponding to each training photovoltaic data value. Taking photovoltaic power as an example, photovoltaic labels can include high power, medium power, and low power.
Through carrying out fuzzy division on training environment data and training photovoltaic data, the diversity of the data can be increased, and the situation of over fitting or under fitting in the model training process caused by accurate numerical values is avoided. On the other hand, the fuzzy division can better divide the data into different groups, the representative characteristics of the data are more highlighted through the environment labels and the photovoltaic labels, and the difficulty of the prediction process is reduced instead of the original characteristics of the data. In addition, the photovoltaic power generation scene often has the interference of a special environment, and the fuzzy division can weaken the interference of the special environment, so that the follow-up model can have better applicability to the scene.
And then, a neural network is utilized to learn the mapping relation between the environment variable and the photovoltaic output, and a photovoltaic prediction model is obtained. A neural network is a nonlinear model composed of a plurality of nodes (neurons) and connections (weights) that can approximate any complex function by adjusting the weights. The neural network has various types and structures, and in this embodiment, a forward propagation neural network is used, that is, the number of input layer nodes is N (corresponding to N input signals), the hidden layer nodes can be freely adjusted according to requirements, in this embodiment, 10 hidden layer nodes are set, and the number of output layer nodes is 1 (corresponding to 1 output signal). The number of input layer nodes is related to the number of input environmental and photovoltaic labels. And taking each pair of environment data pairs in the training environment data set as the input of the neural network, and obtaining the predicted photovoltaic data value of the output layer through nonlinear transformation of the hidden layer. These predicted photovoltaic data values constitute a predicted photovoltaic data set corresponding to the training environment data set.
There is a gap between the predicted photovoltaic dataset and the training photovoltaic dataset, which can be expressed in terms of loss values. And calculating a loss value between the predicted photovoltaic data set and the training photovoltaic data set, and optimizing parameters of the neural network based on the loss value, so that the parameters can be better fit with the training data, and the prediction accuracy is improved. The photovoltaic labels in the photovoltaic dataset represent the relative position of a certain photovoltaic value throughout the dataset, while the photovoltaic labels in the predicted photovoltaic dataset represent the predictions of the data characteristics of the entire dataset. In this embodiment, besides the comparison of the traditional value and the loss value between the values, the comparison of the photovoltaic labels is further included, so that the training direction can be determined more quickly in the training process, the training speed is accelerated, meanwhile, the improvement of the overall data prediction effect can be better achieved by accurately predicting the photovoltaic labels, and the accuracy of the overall data is improved.
And reversely transmitting the loss value to the neural network, and updating the weight according to a certain rule and method, wherein the process can adopt a gradient descent method, a random gradient descent method, a Newton method and the like. In this embodiment, a gradient descent method is used, that is, a mean square error between predicted photovoltaic data and training photovoltaic data is calculated as a loss function, a partial derivative of the loss function with respect to the weight is solved as a gradient, and then the weight is updated in a certain step size according to the opposite direction of the gradient. This process may be repeated multiple times until the loss function reaches a minimum or the change is small, i.e., the neural network converges. At this time, parameters of the neural network are determined, and a photovoltaic prediction model is obtained.
The photovoltaic output is predicted for new or future environmental data using the already trained photovoltaic prediction model. The current environmental data refers to temperature, irradiance, humidity, wind speed, etc. at a certain time or within a certain period of time. The current environmental data also needs to be subjected to fuzzy division to obtain a current environmental data set which comprises a plurality of pairs of environmental data. And taking each pair of environmental data in the current environmental data set as the input of the neural network, and obtaining the current photovoltaic predicted value through calculation of the hidden layer and the output layer. These current photovoltaic predictors constitute a current set of photovoltaic predictors that can be used to evaluate, analyze, or control the performance and status of the photovoltaic system.
According to the invention, the training data is acquired, fuzzy division is carried out, a neural network is input, parameter adjustment is carried out, a photovoltaic prediction model is obtained, the current photovoltaic prediction value is calculated, and the like, so that multi-source information is fully utilized, the input dimension is expanded by combining with environmental factors, and the accuracy and reliability of prediction are improved. The method can also play the nonlinear modeling capability of the neural network and the human intelligent characteristic of fuzzy reasoning, restore human intuition and thinking, better capture complex nonlinear relation and improve the universality and the robustness of prediction. And finally, more accurate prediction of photovoltaic power or generated energy is realized, and important support is provided for power dispatching and stable power supply of a photovoltaic power generation system.
In another implementation manner, the performing fuzzy division on the training environment data to obtain a training environment data set includes:
calculating an environment characteristic vector corresponding to each training environment data;
according to the similarity between the environment feature vectors, primarily classifying the training environment data to obtain a plurality of initial environment clusters;
performing similarity calculation on the initial environment clusters to obtain cluster similarity values;
combining the initial environment clusters according to the cluster similarity value, and updating the data in the combined initial environment clusters until the initial environment clusters meet a preset stopping standard to obtain a plurality of target environment clusters and environment labels corresponding to the target environment clusters;
And generating an environment data pair according to the target environment cluster and the environment label.
Specifically, the training environment data is firstly converted into a numeric environment feature vector so as to carry out similarity calculation and cluster analysis subsequently. The conversion to an ambient feature vector here may be performed in the standardized manner described above, with the result that the ambient feature vector is calculated as a matrix, wherein each row represents a training ambient data and each column represents a feature dimension.
And then, according to the similarity between the environment feature vectors, classifying the similar training environment data into a group to form an initial environment cluster. The similarity is a value for measuring the similarity between two data, such as euclidean distance and cosine similarity. The larger the similarity is, the more likely the two data are of the same class, so that training environment data can be initially classified according to the similarity value to obtain a plurality of initial environment clusters. The number of primary classifications may be determined based on a predetermined similarity threshold, or may be specified prior to classification.
And then obtaining a cluster similarity value according to the similarity between the initial environment clusters so as to carry out subsequent merging operation. The cluster similarity value is a value for measuring the similarity degree between two clusters, such as average distance and minimum distance. The cluster similarity can be calculated by adopting a cluster center, a cluster boundary, cluster internal distribution and the like as numerical values adopted in calculation.
And then merging the initial environment clusters with the similarity higher than a certain threshold value into a larger cluster according to the cluster similarity value, and updating the data and the environment feature vectors in the merged cluster to improve the cluster quality and the accuracy. The merging operation is an operation of merging two or more clusters into one cluster, and the updating operation is an operation of recalculating or adjusting the data and the environmental feature vector in the merged cluster, for example, using weighted average. A stopping criterion is preset for judging whether to continue the condition of merging operation, and in this embodiment, the maximum clustering number and the maximum iteration number can be used as the stopping criterion. And obtaining a final cluster after the merging operation is finished, namely a target environment cluster. And naming or numbering each target environment cluster to obtain the environment label corresponding to each target environment cluster.
And after the target environment cluster and the environment label are obtained, generating an environment data pair. The environment data pair is a data structure consisting of two elements, wherein the first element is training environment data, and the second element is an environment label of a target environment cluster to which the training environment data belongs.
Through similar fuzzy division, the training photovoltaic data is divided to obtain a training photovoltaic data set, and the training photovoltaic data set specifically comprises:
calculating a photovoltaic sign vector corresponding to each piece of training photovoltaic data;
according to the similarity between the photovoltaic sign vectors, primarily classifying the training photovoltaic data to obtain a plurality of initial lights Fu Julei;
performing similarity calculation on the initial photovoltaic clusters to obtain cluster similarity values;
combining the initial photovoltaic clusters according to the cluster similarity value, and updating the data in the combined initial photovoltaic clusters until the initial photovoltaic clusters meet a preset stopping standard to obtain a plurality of target photovoltaic clusters and photovoltaic labels corresponding to the target photovoltaic clusters;
and generating a photovoltaic data pair according to the target photovoltaic cluster and the photovoltaic label.
According to the implementation mode, the quantity and the range of clusters can be dynamically adjusted according to different environmental characteristics, photovoltaic characteristics and conditions, so that the diversity and the complexity of photovoltaic power generation are reflected better. And flexibly combining or dividing the clusters according to the similarity value of the clusters, and helping to capture the change and trend of the photovoltaic power generation.
In another implementation manner, the performing initial classification on the training environment data according to the similarity between the environment feature vectors to obtain a plurality of initial environment clusters includes:
splitting the environment feature vector to obtain a first environment comparison value and a second environment comparison value corresponding to the environment feature vector;
calculating a first similarity between the first environmental comparison values;
dividing the environmental feature vectors according to the first similarity to obtain a first cluster;
calculating a second similarity between the second environmental comparison values in the first cluster;
and dividing the environment feature vector according to the second similarity to obtain an initial environment cluster.
Specifically, the environmental feature vector is decomposed into two sub-vectors, each representing a different environmental attribute. For example, if the environmental feature vector is a four-dimensional vector representing environmental factors such as temperature, humidity, irradiance, and wind speed, it may be split into two-dimensional vectors representing temperature, humidity, and irradiance, respectively. In this way, comparisons and clusters can be made according to different environmental properties.
A degree of similarity between each two data is calculated over the first environmental comparison value. The higher the similarity, the closer the two data are represented on the first environmental comparison value. The degree of similarity between each two data over the second environmental comparison value is then calculated. Similar to the previous step of calculating the first similarity between the first environmental comparison values, the similarity may also be calculated using different metrics. In contrast, only the similarity between data within the same category need be calculated here, and the similarity between different categories need not be considered.
The data is further subdivided into smaller categories according to the second similarity such that data within the same category is also highly similar in the second environmental comparison value, while data between different categories is also less similar in the second environmental comparison value. In this way, the data may be classified according to minor differences in the second environmental comparison value. Finally, the initial environment cluster based on the environment characteristic vector is obtained.
Through a similar clustering method, the photovoltaic feature vectors can be initially classified to obtain initial photovoltaic clusters, which specifically comprise:
splitting the photovoltaic sign vector to obtain a first photovoltaic comparison value and a second photovoltaic comparison value corresponding to the photovoltaic sign vector;
calculating a first similarity between the first photovoltaic comparison values;
dividing the photovoltaic sign vector according to the first similarity to obtain a first cluster;
calculating a second similarity between the second photovoltaic comparison values in the first cluster;
and dividing the photovoltaic sign vector according to the second similarity to obtain an initial photovoltaic cluster.
In another implementation, before the acquiring training environment data and training photovoltaic data, the method further includes:
Acquiring historical environment data, updated environment data, historical photovoltaic data and updated photovoltaic data;
according to a preset updating period, the updating environment data and the historical environment data are decimated to obtain training environment data; the method comprises the steps of,
and decimating the historical photovoltaic data and the updated photovoltaic data to obtain training photovoltaic data.
In particular, relevant data is collected from different data sources, such as weather stations, satellites, sensors, and the like. Historical environmental data refers to environmental data over a period of time including factors affecting photovoltaic power generation, such as temperature, humidity, wind speed, radiation. Updating the environmental data refers to the most recently acquired environmental data. Historical photovoltaic data refers to output power or electric quantity of a solar power generation system, and updating photovoltaic data refers to recently collected photovoltaic data.
Over time, the historical environmental data is not necessarily suitable for the existing environment, and therefore, the historical environmental data, the updated environmental data, the historical photovoltaic data, and the updated photovoltaic data need to be decimated to select training environmental data and training photovoltaic data that are suitable for training in the near future.
The update period refers to the time frame of the extracted data distribution. Such as weekly, monthly or quarterly. The decimation method can be chosen according to different objectives and conditions, such as random sampling, hierarchical sampling, or packet sampling. According to the updating period, training environment data and training photovoltaic data can be obtained through decimation, and the adaptivity of a photovoltaic prediction model obtained through subsequent training is improved.
In another implementation manner, the decimating the updated environment data and the historical environment data according to a preset update period, to obtain training environment data includes:
determining candidate environmental data in the updated environmental data and the historical environmental data according to the updating period;
comparing the candidate environment data with reference environment data corresponding to candidate environment time, and determining an abnormal value in the candidate environment data, wherein the candidate environment time is the time corresponding to the candidate environment data;
and adjusting the candidate environment data according to the abnormal value and the candidate environment time to obtain training environment data.
Specifically, the update environment data and the history environment data each have a corresponding time, so that candidate environment data in the update environment data and the history environment data can be determined according to a time range in an update period. For example, if the update environment data corresponds to one week and the update environment data corresponds to two weeks, the latest one week data is extracted from the history environment data as candidate environment data.
And comparing the historical environment data corresponding to the candidate environment time to obtain a fluctuation value. For example, when the candidate environmental data corresponds to 7 months 1 day to 7 months 31 days, the historical environmental data of the last year and the previous year may be used as the reference environmental data, and the environmental data corresponding to 6 months 1 day to 6 months 30 days may be used as the reference environmental data. From the candidate environmental data and the reference environmental data, outliers in the candidate environmental data may be determined. Outliers refer to candidate environmental data that deviate from the normal range as compared to the reference environmental data. For example, if the temperature in the candidate environmental data is higher or lower than the temperature in the reference environmental data by a certain threshold, then the temperature is an outlier.
A reasonable threshold is preset for judging whether the difference between the candidate environmental data and the reference environmental data exceeds the normal range. The selection of the threshold may be determined based on different environmental factors and data characteristics. For example, using statistical methods such as mean, standard deviation, quantiles, etc., the central trend and degree of dispersion of the reference environmental data is calculated, and then the threshold is determined according to a certain multiple or scale. Candidate environmental data is compared with reference environmental data, and those that exceed a threshold are found and marked as outliers.
The number of candidate environmental data is reduced after the outlier is removed, so that some environmental data is selected before the decimated historical environmental data based on the update period, so that the number of finally selected environmental data is the same as the number of environmental data corresponding to the update period. In the process of adding the historical environment data, abnormal value detection can be performed so as to ensure that the data in the training environment data are accurate.
The training photovoltaic data is obtained in a similar manner, including:
according to the updating period, determining candidate photovoltaic data in the updated photovoltaic data and the historical photovoltaic data;
Comparing the candidate photovoltaic data with reference photovoltaic data corresponding to candidate photovoltaic time, and determining an abnormal value in the candidate photovoltaic data, wherein the candidate photovoltaic time is the time corresponding to the candidate photovoltaic data;
and adjusting the candidate photovoltaic data according to the abnormal value and the candidate photovoltaic time to obtain training photovoltaic data.
In another implementation, the comparing the candidate environment data with the reference environment data corresponding to the candidate environment time, and determining the outlier in the candidate environment data includes:
determining a prediction parameter based on the reference environmental data;
generating an environment prediction model according to the reference environment data and the prediction parameters;
calculating predicted environment data corresponding to the candidate environment time based on the environment prediction model;
comparing the predicted environment data with the candidate environment data, and determining an abnormal value in the candidate environment data.
Specifically, the reference environmental data is subjected to differential processing to eliminate trends and seasonal factors in the data, so that the data becomes a smooth sequence. The number and order of the differential processing can be selected according to the characteristics and needs of the data. Then, a prediction parameter corresponding to the reference environmental data is calculated, and the ARIMA model is taken as an example, wherein the prediction parameter comprises an autoregressive term (p), a moving average term (q) and a difference frequency (d). And then generating an environment prediction model according to the reference environment data and the prediction parameters. Taking the ARIMA model as an example, since the basic structure of the ARIMA model is known, substituting the reference environmental data and the prediction parameters into the basic structure of the model can obtain an environmental prediction model, and checking the fitting effect and residual distribution of the environmental prediction model. If the environmental prediction model does not conform to the characteristics of the data or there is significant residual correlation, the parameters need to be readjusted. Based on the environmental prediction model, predicted environmental data corresponding to the candidate environmental time may be calculated. And e.g. inputting the candidate environmental time into the fitted environmental prediction model to obtain corresponding predicted environmental data.
Comparing the predicted environment data with the candidate environment data, and determining an abnormal value in the candidate environment data. There are various methods of comparison, such as calculating the difference, ratio, correlation, etc. between the two.
In another implementation manner, the neural network includes an input layer, a hidden layer and an output layer, the hidden layer includes a plurality of computing nodes and fuzzy functions, the inputting the training environment data set into a preset neural network, and controlling the neural network to predict the training environment data set, and obtaining a predicted photovoltaic data set corresponding to the training environment data set includes:
inputting the training environment data set to the input layer and controlling the input layer to transmit the training environment data set to the computing node;
controlling each computing node to compute the training environment data set to obtain a corresponding initial value;
inputting the initial value into the fuzzy function, and controlling the fuzzy function to perform fuzzy calculation on the initial value to obtain predicted photovoltaic data;
and controlling the predicted photovoltaic data to be transmitted to the output layer and controlling the output layer to output.
Specifically, the training environment data set is first converted into a format suitable for neural network processing and assigned to different computing nodes. A compute node is a unit in a neural network that performs a particular operation, typically consisting of multiple neurons. The structure of the input layer, such as how many neurons the input layer has, how many eigenvalues each receives, and the manner of connection between the input layer and the compute nodes, is predefined.
The environmental data sets then need to be pre-processed, e.g., normalized, missing value processed, etc., so that the input layer can properly receive and parse the data and transmit it to the compute nodes.
And then, the computing node carries out corresponding operation according to the data transmitted by the input layer, so as to obtain an initial value. The initial value refers to a value output by the computing node and not processed by the activated function. The structure of the computing nodes is predefined, and the structure comprises how many neurons are arranged in the computing nodes, how many weights and biases are arranged in each neuron, the connection mode among the computing nodes and the like. In addition, the calculation mode of the calculation node needs to be defined, for example, methods such as weighted sum, matrix multiplication, convolution and the like are used. The calculation mode of the calculation node in this embodiment preferably uses weighted summation. And converting the initial value into predicted photovoltaic data through a fuzzy function. A blur function refers to a mathematical function that is capable of handling uncertainty and ambiguity. The types of the fuzzy functions are preset, including using fuzzy logic, fuzzy aggregation, fuzzy rules and the like, and parameters of the fuzzy functions, such as using membership functions, fuzzy operators and reasoning mechanisms.
And finally, transmitting the predicted photovoltaic data from the fuzzy function to an output layer, and displaying or storing the predicted photovoltaic data by the output layer. The output layer is the layer of the neural network responsible for outputting the final result. The output layer is provided with the number of neurons, the connection mode between the output layer and the fuzzy function, and the like.
Finally, the output mode of the output layer is defined, such as inverse normalization and inverse normalization. And controlling the output layer to output data.
The method utilizes the fuzzy function to process uncertainty and ambiguity, thereby improving the accuracy and the robustness of prediction. Through the combination of the fuzzy theory and the neural network technology, the accuracy and the adaptability of photovoltaic prediction are improved.
Referring to fig. 2, the photovoltaic power generation prediction apparatus based on fuzzy reasoning provided by the present invention is described below, and the photovoltaic power generation prediction apparatus based on fuzzy reasoning described below and the photovoltaic power generation prediction method based on fuzzy reasoning described above may be referred to correspondingly with each other. The apparatus includes an acquisition module 210, a partitioning module 220, an input module 230, an adjustment module 240, and a prediction module 250.
The acquisition module 210 is configured to acquire training environment data and training photovoltaic data;
the dividing module 220 is configured to perform fuzzy division on the training environment data to obtain a training environment data set, and perform fuzzy division on the training photovoltaic data to obtain a training photovoltaic data set, where the training environment data set includes a plurality of pairs of environment data pairs, the environment data pairs include training environment data values and environment labels corresponding to each training environment data value, and the training photovoltaic data set includes a plurality of pairs of photovoltaic data, and the photovoltaic data pairs include training photovoltaic data values and photovoltaic labels corresponding to each training photovoltaic data value;
The input module 230 is configured to input the training environment data set into a preset neural network, and control the neural network to predict the training environment data set, so as to obtain a predicted photovoltaic data set corresponding to the training environment data set, where the neural network includes a fuzzy function;
the adjustment module 240 is configured to perform parameter adjustment on the neural network according to the predicted photovoltaic data set and the training photovoltaic data set until the neural network converges, so as to obtain a photovoltaic prediction model;
the prediction module 250 is configured to calculate, when current environmental data is acquired, a current photovoltaic predicted value corresponding to the current environmental data based on the photovoltaic prediction model.
Fig. 3 illustrates a physical schematic diagram of an electronic device, as shown in fig. 3, where the electronic device may include: processor 310, communication interface (Communications Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. The processor 310 may invoke logic instructions in the memory 330 to perform a fuzzy inference based photovoltaic power generation prediction method comprising:
Acquiring training environment data and training photovoltaic data;
performing fuzzy division on the training environment data to obtain a training environment data set, performing fuzzy division on the training photovoltaic data to obtain a training photovoltaic data set, wherein the training environment data set comprises a plurality of pairs of environment data pairs, each pair of environment data comprises a training environment data value and an environment label corresponding to each training environment data value, the training photovoltaic data set comprises a plurality of pairs of photovoltaic data, and each pair of photovoltaic data comprises a training photovoltaic data value and a photovoltaic label corresponding to each training photovoltaic data value;
inputting the training environment data set into a preset neural network, and controlling the neural network to predict the training environment data set to obtain a predicted photovoltaic data set corresponding to the training environment data set, wherein the neural network comprises a fuzzy function;
according to the predicted photovoltaic data set and the training photovoltaic data set, parameter adjustment is carried out on the neural network until the neural network converges, and a photovoltaic prediction model is obtained;
when current environment data are acquired, calculating a current photovoltaic predicted value corresponding to the current environment data based on the photovoltaic predicted model.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the fuzzy inference based photovoltaic power generation prediction method provided by the above methods, the method comprising:
Acquiring training environment data and training photovoltaic data;
performing fuzzy division on the training environment data to obtain a training environment data set, performing fuzzy division on the training photovoltaic data to obtain a training photovoltaic data set, wherein the training environment data set comprises a plurality of pairs of environment data pairs, each pair of environment data comprises a training environment data value and an environment label corresponding to each training environment data value, the training photovoltaic data set comprises a plurality of pairs of photovoltaic data, and each pair of photovoltaic data comprises a training photovoltaic data value and a photovoltaic label corresponding to each training photovoltaic data value;
inputting the training environment data set into a preset neural network, and controlling the neural network to predict the training environment data set to obtain a predicted photovoltaic data set corresponding to the training environment data set, wherein the neural network comprises a fuzzy function;
according to the predicted photovoltaic data set and the training photovoltaic data set, parameter adjustment is carried out on the neural network until the neural network converges, and a photovoltaic prediction model is obtained;
when current environment data are acquired, calculating a current photovoltaic predicted value corresponding to the current environment data based on the photovoltaic predicted model.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A photovoltaic power generation prediction method based on fuzzy reasoning is characterized by comprising the following steps:
acquiring training environment data and training photovoltaic data;
performing fuzzy division on the training environment data to obtain a training environment data set, performing fuzzy division on the training photovoltaic data to obtain a training photovoltaic data set, wherein the training environment data set comprises a plurality of pairs of environment data pairs, each pair of environment data comprises a training environment data value and an environment label corresponding to each training environment data value, the training photovoltaic data set comprises a plurality of pairs of photovoltaic data, and each pair of photovoltaic data comprises a training photovoltaic data value and a photovoltaic label corresponding to each training photovoltaic data value;
Inputting the training environment data set into a preset neural network, and controlling the neural network to predict the training environment data set to obtain a predicted photovoltaic data set corresponding to the training environment data set, wherein the neural network comprises a fuzzy function;
according to the predicted photovoltaic data set and the training photovoltaic data set, parameter adjustment is carried out on the neural network until the neural network converges, and a photovoltaic prediction model is obtained;
when current environment data are acquired, calculating a current photovoltaic predicted value corresponding to the current environment data based on the photovoltaic predicted model;
the performing fuzzy division on the training environment data to obtain a training environment data set comprises:
calculating an environment characteristic vector corresponding to each training environment data;
according to the similarity between the environment feature vectors, primarily classifying the training environment data to obtain a plurality of initial environment clusters;
performing similarity calculation on the initial environment clusters to obtain cluster similarity values;
combining the initial environment clusters according to the cluster similarity value, and updating the data in the combined initial environment clusters until the initial environment clusters meet a preset stopping standard to obtain a plurality of target environment clusters and environment labels corresponding to the target environment clusters;
Generating an environment data pair according to the target environment cluster and the environment label;
the step of performing fuzzy division on the training photovoltaic data to obtain a training photovoltaic data set comprises the following steps: calculating a photovoltaic sign vector corresponding to each piece of training photovoltaic data;
according to the similarity between the photovoltaic sign vectors, primarily classifying the training photovoltaic data to obtain a plurality of initial lights Fu Julei;
performing similarity calculation on the initial photovoltaic clusters to obtain cluster similarity values;
combining the initial photovoltaic clusters according to the cluster similarity value, and updating the data in the combined initial photovoltaic clusters until the initial photovoltaic clusters meet a preset stopping standard to obtain a plurality of target photovoltaic clusters and photovoltaic labels corresponding to the target photovoltaic clusters;
generating a photovoltaic data pair according to the target photovoltaic cluster and the photovoltaic label;
the initial classification of the training environment data according to the similarity between the environment feature vectors, and the obtaining of a plurality of initial environment clusters comprises:
splitting the environment feature vector to obtain a first environment comparison value and a second environment comparison value corresponding to the environment feature vector;
Calculating a first similarity between the first environmental comparison values;
dividing the environmental feature vectors according to the first similarity to obtain a first cluster;
calculating a second similarity between the second environmental comparison values in the first cluster;
dividing the environment feature vector according to the second similarity to obtain an initial environment cluster;
the training photovoltaic data is initially classified according to the similarity between the photovoltaic sign vectors to obtain a plurality of initial photovoltaic clusters, including:
splitting the photovoltaic sign vector to obtain a first photovoltaic comparison value and a second photovoltaic comparison value corresponding to the photovoltaic sign vector;
calculating a third similarity between the first photovoltaic comparison values;
dividing the photovoltaic sign vector according to the third similarity to obtain a second cluster;
calculating a fourth similarity between the second photovoltaic comparison values in the second clusters;
and dividing the photovoltaic sign vector according to the fourth similarity to obtain an initial photovoltaic cluster.
2. The fuzzy inference based photovoltaic power generation prediction method of claim 1, further comprising, prior to the acquiring the training environment data and the training photovoltaic data:
Acquiring historical environment data, updated environment data, historical photovoltaic data and updated photovoltaic data;
according to a preset updating period, the updating environment data and the historical environment data are decimated to obtain training environment data; the method comprises the steps of,
and decimating the historical photovoltaic data and the updated photovoltaic data to obtain training photovoltaic data.
3. The fuzzy inference-based photovoltaic power generation prediction method according to claim 2, wherein the decimating the updated environmental data and the historical environmental data according to a preset update period to obtain training environmental data includes:
determining candidate environmental data in the updated environmental data and the historical environmental data according to the updating period;
comparing the candidate environment data with reference environment data corresponding to candidate environment time, and determining an abnormal value in the candidate environment data, wherein the candidate environment time is the time corresponding to the candidate environment data;
and adjusting the candidate environment data according to the abnormal value and the candidate environment time to obtain training environment data.
4. The fuzzy inference-based photovoltaic power generation prediction method of claim 3, wherein the comparing the candidate environmental data with reference environmental data corresponding to a candidate environmental time, determining an outlier in the candidate environmental data comprises:
Determining a prediction parameter based on the reference environmental data;
generating an environment prediction model according to the reference environment data and the prediction parameters;
generating predicted environment data corresponding to the candidate environment time based on the environment prediction model;
comparing the predicted environment data with the candidate environment data, and determining an abnormal value in the candidate environment data.
5. The photovoltaic power generation prediction method based on fuzzy inference according to any one of claims 1 to 4, wherein the inputting the training environment data set into a preset neural network, and controlling the neural network to predict the training environment data set, to obtain a predicted photovoltaic data set corresponding to the training environment data set includes:
inputting the training environment data set to an input layer of the neural network, and controlling the input layer to transmit the training environment data set to a hidden layer of the neural network;
controlling each computing node in the hidden layer to compute the training environment data set to obtain a corresponding initial value;
inputting the initial value into the fuzzy function, and controlling the fuzzy function to perform fuzzy calculation on the initial value to obtain predicted photovoltaic data;
And controlling the predicted photovoltaic data to be transmitted to an output layer of the neural network, and controlling the output layer to output.
6. A photovoltaic power generation prediction device based on fuzzy reasoning is characterized by comprising:
the acquisition module is used for acquiring training environment data and training photovoltaic data;
the system comprises a dividing module, a fuzzy dividing module and a fuzzy dividing module, wherein the dividing module is used for carrying out fuzzy dividing on training environment data to obtain a training environment data set and carrying out fuzzy dividing on the training photovoltaic data to obtain a training photovoltaic data set, the training environment data set comprises a plurality of pairs of environment data pairs, the environment data pairs comprise training environment data values and environment labels corresponding to each training environment data value, the training photovoltaic data set comprises a plurality of pairs of photovoltaic data, and the photovoltaic data pairs comprise training photovoltaic data values and photovoltaic labels corresponding to each training photovoltaic data value;
the input module is used for inputting the training environment data set into a preset neural network, controlling the neural network to predict the training environment data set, and obtaining a predicted photovoltaic data set corresponding to the training environment data set, wherein the neural network comprises a fuzzy function;
The adjustment module is used for carrying out parameter adjustment on the neural network according to the predicted photovoltaic data set and the training photovoltaic data set until the neural network converges to obtain a photovoltaic prediction model;
the prediction module is used for calculating a current photovoltaic predicted value corresponding to the current environment data based on the photovoltaic predicted model when the current environment data are acquired;
the performing fuzzy division on the training environment data to obtain a training environment data set comprises:
calculating an environment characteristic vector corresponding to each training environment data;
according to the similarity between the environment feature vectors, primarily classifying the training environment data to obtain a plurality of initial environment clusters;
performing similarity calculation on the initial environment clusters to obtain cluster similarity values;
combining the initial environment clusters according to the cluster similarity value, and updating the data in the combined initial environment clusters until the initial environment clusters meet a preset stopping standard to obtain a plurality of target environment clusters and environment labels corresponding to the target environment clusters;
generating an environment data pair according to the target environment cluster and the environment label;
The step of performing fuzzy division on the training photovoltaic data to obtain a training photovoltaic data set comprises the following steps: calculating a photovoltaic sign vector corresponding to each piece of training photovoltaic data;
according to the similarity between the photovoltaic sign vectors, primarily classifying the training photovoltaic data to obtain a plurality of initial lights Fu Julei;
performing similarity calculation on the initial photovoltaic clusters to obtain cluster similarity values;
combining the initial photovoltaic clusters according to the cluster similarity value, and updating the data in the combined initial photovoltaic clusters until the initial photovoltaic clusters meet a preset stopping standard to obtain a plurality of target photovoltaic clusters and photovoltaic labels corresponding to the target photovoltaic clusters;
generating a photovoltaic data pair according to the target photovoltaic cluster and the photovoltaic label;
the initial classification of the training environment data according to the similarity between the environment feature vectors, and the obtaining of a plurality of initial environment clusters comprises:
splitting the environment feature vector to obtain a first environment comparison value and a second environment comparison value corresponding to the environment feature vector;
calculating a first similarity between the first environmental comparison values;
Dividing the environmental feature vectors according to the first similarity to obtain a first cluster;
calculating a second similarity between the second environmental comparison values in the first cluster;
dividing the environment feature vector according to the second similarity to obtain an initial environment cluster;
the training photovoltaic data is initially classified according to the similarity between the photovoltaic sign vectors to obtain a plurality of initial photovoltaic clusters, including:
splitting the photovoltaic sign vector to obtain a first photovoltaic comparison value and a second photovoltaic comparison value corresponding to the photovoltaic sign vector;
calculating a third similarity between the first photovoltaic comparison values;
dividing the photovoltaic sign vector according to the third similarity to obtain a second cluster;
calculating a fourth similarity between the second photovoltaic comparison values in the second clusters;
and dividing the photovoltaic sign vector according to the fourth similarity to obtain an initial photovoltaic cluster.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the fuzzy inference based photovoltaic power generation prediction method of any of claims 1 to 5 when the computer program is executed by the processor.
8. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the fuzzy inference based photovoltaic power generation prediction method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310997292.XA CN116706907B (en) | 2023-08-09 | 2023-08-09 | Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310997292.XA CN116706907B (en) | 2023-08-09 | 2023-08-09 | Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116706907A CN116706907A (en) | 2023-09-05 |
| CN116706907B true CN116706907B (en) | 2024-01-23 |
Family
ID=87831625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310997292.XA Active CN116706907B (en) | 2023-08-09 | 2023-08-09 | Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116706907B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117522156A (en) * | 2023-10-17 | 2024-02-06 | 江苏尚诚能源科技有限公司 | Distributed photovoltaic prediction evaluation method and system based on big data analysis |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106544A (en) * | 2013-02-01 | 2013-05-15 | 东南大学 | Photovoltaic power generation prediction system based on T-S-type fuzzy neural network |
| CN109858665A (en) * | 2018-12-06 | 2019-06-07 | 国网河北省电力有限公司 | Photovoltaic short term power prediction technique based on Feature Selection and ANFIS-PSO |
| CN109978284A (en) * | 2019-04-25 | 2019-07-05 | 中国人民解放军国防科技大学 | Photovoltaic power generation power time-sharing prediction method based on hybrid neural network model |
| CN110705760A (en) * | 2019-09-19 | 2020-01-17 | 广东工业大学 | Photovoltaic power generation power prediction method based on deep belief network |
| CN114638396A (en) * | 2022-01-14 | 2022-06-17 | 中国电力科学研究院有限公司 | Photovoltaic power prediction method and system based on neural network instantiation |
| CN115345301A (en) * | 2022-08-26 | 2022-11-15 | 深圳依时货拉拉科技有限公司 | Model training method and device based on mixed disturbance, storage medium and server |
| CN115907195A (en) * | 2022-12-08 | 2023-04-04 | 国电和风风电开发有限公司 | Photovoltaic power generation power prediction method, system, electronic device and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9461535B2 (en) * | 2013-12-30 | 2016-10-04 | King Fahd University Of Petroleum And Minerals | Photovoltaic systems with maximum power point tracking controller |
-
2023
- 2023-08-09 CN CN202310997292.XA patent/CN116706907B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106544A (en) * | 2013-02-01 | 2013-05-15 | 东南大学 | Photovoltaic power generation prediction system based on T-S-type fuzzy neural network |
| CN109858665A (en) * | 2018-12-06 | 2019-06-07 | 国网河北省电力有限公司 | Photovoltaic short term power prediction technique based on Feature Selection and ANFIS-PSO |
| CN109978284A (en) * | 2019-04-25 | 2019-07-05 | 中国人民解放军国防科技大学 | Photovoltaic power generation power time-sharing prediction method based on hybrid neural network model |
| CN110705760A (en) * | 2019-09-19 | 2020-01-17 | 广东工业大学 | Photovoltaic power generation power prediction method based on deep belief network |
| CN114638396A (en) * | 2022-01-14 | 2022-06-17 | 中国电力科学研究院有限公司 | Photovoltaic power prediction method and system based on neural network instantiation |
| CN115345301A (en) * | 2022-08-26 | 2022-11-15 | 深圳依时货拉拉科技有限公司 | Model training method and device based on mixed disturbance, storage medium and server |
| CN115907195A (en) * | 2022-12-08 | 2023-04-04 | 国电和风风电开发有限公司 | Photovoltaic power generation power prediction method, system, electronic device and medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于相似日聚类和贝叶斯神经网络的光伏发电功率预测研究;嵇灵 等;《中国管理科学》(第03期);第118-122页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116706907A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070226B (en) | Photovoltaic power prediction method and system based on convolutional neural network and meta-learning | |
| CN112365040A (en) | Short-term wind power prediction method based on multi-channel convolution neural network and time convolution network | |
| CN110647980A (en) | Time sequence prediction method based on GRU neural network | |
| CN111537945A (en) | Intelligent ammeter fault diagnosis method and equipment based on federal learning | |
| CN111563706A (en) | Multivariable logistics freight volume prediction method based on LSTM network | |
| CN111695731B (en) | Load prediction method, system and equipment based on multi-source data and hybrid neural network | |
| CN111148118A (en) | Flow prediction and carrier turn-off method and system based on time sequence | |
| Ibrahim et al. | Short‐Time Wind Speed Forecast Using Artificial Learning‐Based Algorithms | |
| CN111723929A (en) | Numerical prediction product correction method, device and system based on neural network | |
| CN108879732B (en) | Transient stability evaluation method and device for power system | |
| CN116706907B (en) | Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment | |
| CN114490065A (en) | Load prediction method, device and equipment | |
| CN112766603A (en) | Traffic flow prediction method, system, computer device and storage medium | |
| CN113807951A (en) | Transaction data trend prediction method and system based on deep learning | |
| CN115456306A (en) | Bus load prediction method, system, equipment and storage medium | |
| CN114444821A (en) | Integrated learning load prediction method, system and medium for power internet of things | |
| CN110738363A (en) | photovoltaic power generation power prediction model and construction method and application thereof | |
| CN114338416B (en) | Space-time multi-index prediction method and device and storage medium | |
| CN117154680A (en) | Wind power prediction method based on non-stationary transducer model | |
| CN115619563A (en) | Stock price analysis method based on neural network | |
| CN115423091A (en) | Conditional antagonistic neural network training method, scene generation method and system | |
| Bantupalli et al. | Wind Speed forecasting using empirical mode decomposition with ANN and ARIMA models | |
| CN113515890A (en) | Renewable energy day-ahead scene generation method based on federal learning | |
| CN112183814A (en) | Short-term wind speed prediction method | |
| Volkov et al. | Development of a Neural Network Algorithm for Predicting the Technical State of Complex Systems Based on an Algebraic Approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |