CN109726870A - Photovoltaic power generation power prediction method based on deep learning - Google Patents
Photovoltaic power generation power prediction method based on deep learning Download PDFInfo
- Publication number
- CN109726870A CN109726870A CN201811636335.7A CN201811636335A CN109726870A CN 109726870 A CN109726870 A CN 109726870A CN 201811636335 A CN201811636335 A CN 201811636335A CN 109726870 A CN109726870 A CN 109726870A
- Authority
- CN
- China
- Prior art keywords
- data
- power generation
- photovoltaic power
- photovoltaic
- keyword
- 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 47
- 238000010248 power generation Methods 0.000 title claims abstract description 44
- 238000013135 deep learning Methods 0.000 title claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 24
- 238000001914 filtration Methods 0.000 claims abstract description 8
- 238000003860 storage Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 13
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 8
- 230000009467 reduction Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 6
- 238000013478 data encryption standard Methods 0.000 description 4
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical group [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 229910052751 metal Inorganic materials 0.000 description 3
- 239000004065 semiconductor Substances 0.000 description 3
- 229910052710 silicon Inorganic materials 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000004087 circulation Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000005201 scrubbing Methods 0.000 description 2
- ZOXJGFHDIHLPTG-UHFFFAOYSA-N Boron Chemical group [B] ZOXJGFHDIHLPTG-UHFFFAOYSA-N 0.000 description 1
- 239000004606 Fillers/Extenders Substances 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 125000004429 atom Chemical group 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052796 boron Inorganic materials 0.000 description 1
- -1 boron atom Chemical compound 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 125000004437 phosphorous atom Chemical group 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a photovoltaic power generation power prediction method based on deep learning, which comprises the following steps of: A. collecting photovoltaic power generation data and sending the photovoltaic power generation data to a memory for storage; B. carrying out feature extraction on the stored photovoltaic power generation data; C. then encrypting the data after the characteristic extraction; D. inputting the encrypted data as a BP neural network, and outputting the BP neural network as the photovoltaic power generation power to be predicted; E. the prediction method adopted by the invention has high precision and high prediction rate, and the data preprocessing method can realize data sorting, noise reduction and filtering, thereby improving the subsequent processing efficiency of the data; by searching the first keyword and the second keyword in the adopted feature extraction method, the extraction difficulty can be reduced, and the feature extraction precision is improved; the adopted encryption method can carry out multiple encryption on the photovoltaic data, and the safety and the confidentiality of the data are improved.
Description
Technical field
The present invention relates to photovoltaic power generation electric powder prediction, specially a kind of photovoltaic generation power based on deep learning is pre-
Survey method.
Background technique
Photovoltaic power generation is the photovoltaic effect using interface and luminous energy is directly translated into a kind of skill of electric energy
Art.It is mainly made of solar panel (component), controller and inverter three parts, main component is by electronic component structure
At.Solar battery carries out packaging protection after series connection can form the solar module of large area, then matches and close power control
The components such as device processed are formed photovoltaic power generation apparatus.The cardinal principle of photovoltaic power generation is the photoelectric effect of semiconductor.Photon irradiation
When on to metal, its energy can all be absorbed by some electronics in metal, and the energy of Electron absorption is sufficiently large, can overcome gold
Belong to internal gravitation acting, leaves metal surface and escape, become photoelectron.Silicon atom has 4 outer-shell electrons, if in pure silicon
In be mixed with the atom such as phosphorus atoms of 5 outer-shell electrons, just become N-type semiconductor；If being mixed with 3 outer-shell electrons in pure silicon
Atom such as boron atom, formed P-type semiconductor.When p-type and N type junction are combined, contact surface just will form potential difference, become
Solar battery.After solar irradiation is mapped to P-N junction, hole is mobile from the polar region P toward the polar region N, and electronics is moved from the polar region N to the polar region P
It is dynamic, form electric current.
As wind Photovoltaic new energy power output permeability in the electric system generated energy rises year by year, alleviating, the energy is tight
, environmental degradation while, due to the intermittence and unstability of photovoltaic power generation, also to power grid security, reliable, economical operation band
Carry out great challenge.Accurate photovoltaic power generation power prediction predicts the photovoltaic power output in the following certain time, can be power grid
Automatic Generation Control, dispatching of power netwoks provide science decision foundation, so that large-scale photovoltaic access be effectively reduced to electric system
It influences, ensures power grid security and economical operation.
The numerical weather forecast comprising crucial meteorologic factor and irradiation level is generally required to photovoltaic power generation power prediction at present,
And it is predicted using photovoltaic power generation power predictions algorithms such as neural network, classification recurrence, time series, wavelet analysis.Wherein,
Since neural network algorithm has the features such as robustness is high, and None-linear approximation ability is strong, generally it is used in photovoltaic power generation function
In rate prediction, but its estimated performance and input dimension, training sample are closely related.And the selection of meteorologic factor is lacked at present
Theoretical analysis, so as to cause determining that obtained photovoltaic generation power error is big in advance.
Therefore, how to provide a kind of photovoltaic power generation power prediction method that precision of prediction is high becomes those skilled in the art urgently
Technical problem to be solved.
Summary of the invention
It is above-mentioned to solve the purpose of the present invention is to provide a kind of photovoltaic power generation power prediction method based on deep learning
The problem of being proposed in background technique.
To achieve the above object, the invention provides the following technical scheme: a kind of photovoltaic generation power based on deep learning
Prediction technique, comprising the following steps:
A, photovoltaic power generation data are acquired and the data of acquisition are pre-processed；
B, pretreated data are sent in memory and are stored；
C, the photovoltaic power generation data of storage are subjected to feature extraction；
D, the data after feature extraction are encrypted later；
E, it is inputted encrypted data as BP neural network, BP neural network output is photovoltaic power generation function to be predicted
Rate establishes multiple groups neural network prediction model；
F, depth training is carried out to multiple groups neural network prediction model, chooses neural network corresponding to optimum performance parameters
Prediction model predicts photovoltaic generation power as final prediction model.
Preferably, data preprocessing method is as follows in the step A:
A, collected photovoltaic power generation data are cleaned；
B, the data after cleaning are verified with whether have missing；
C, the data after verification are corrected；
D, the data after correction are filtered；
E, filtered data are updated.
Preferably, feature extracting method is as follows in the step C:
A, data set is established, multiple Sub Data Sets to feature extraction are wherein included in data set；
B, feature training is carried out to data set, obtains training pattern；
C, the first keyword and the second keyword in data set are extracted；
D, each Sub Data Set in cyclic search data set, using the first keyword and the second keyword as primary condition, antithetical phrase
Data set scans for；
E, search is matched to the first keyword or the second keyword in each Sub Data Set, then extracts to data.
Preferably, encryption method is as follows in the step D:
A, cleaning operation is carried out to data to be encrypted first；
B, the operation of primary encryption algorithm is carried out to the data after cleaning later, obtains an encrypted ciphertext data；
C, hyperchaos cryptographic calculation is carried out to a ciphertext data later again, obtains secondary ciphertext data；
D, secondary Encryption Algorithm operation, the final encryption of complete paired data finally are carried out to secondary ciphertext data.
Preferably, memory uses random access memory in the step B.
Preferably, first Encryption Algorithm uses AES encryption algorithm；Second Encryption Algorithm is calculated using des encryption
Method.
Preferably, the data cleansing includes carrying out time check to the data of acquisition and sorting, to data single-point threshold values
Filtration treatment.
Compared with prior art, the beneficial effects of the present invention are:
(1) the prediction technique precision that the present invention uses is high, and prediction rate is high, and it is pre- to solve existing photovoltaic power station power generation power
Indeterminable problem.
(2) data preprocessing method that uses of the present invention can be realized sequence to data, noise reduction, filtering data,
Improve data subsequent processing efficiency.
(3) it can reduce in the feature extracting method that the present invention uses by the first keyword of search and the second keyword
Difficulty is extracted, feature extraction precision is improved.
(4) encryption method that the present invention uses can carry out multi-enciphering to photovoltaic data, improve the safety of data
And confidentiality.
Detailed description of the invention
Fig. 1 is flow chart of the present invention；
Fig. 2 is feature of present invention extracting method flow chart；
Fig. 3 is encryption method flow chart of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Embodiment one:
Fig. 1-3 is please referred to, the invention provides the following technical scheme: a kind of photovoltaic power generation power prediction based on deep learning
Method, comprising the following steps:
A, photovoltaic power generation data are acquired and the data of acquisition are pre-processed；
B, pretreated data are sent in memory and are stored；
C, the photovoltaic power generation data of storage are subjected to feature extraction；
D, the data after feature extraction are encrypted later；
E, it is inputted encrypted data as BP neural network, BP neural network output is photovoltaic power generation function to be predicted
Rate establishes multiple groups neural network prediction model；
F, depth training is carried out to multiple groups neural network prediction model, chooses neural network corresponding to optimum performance parameters
Prediction model predicts photovoltaic generation power as final prediction model.
Photovoltaic data are acquired first, the photovoltaic data of acquisition are pre-processed, remove noise and are filtered, and will be handled
Photovoltaic afterwards, which is sent in memory, to be stored, and the data of storage are carried out feature extraction later, is extracted in photovoltaic data
Characteristic later encrypts characteristic, and encrypts and use multi-enciphering, can be improved Information Security, later will
Encrypted data input BP neural network, and establish multiple groups neural network prediction model, finally choose optimum performance parameters institute
Corresponding neural network prediction model is as final prediction model.
Wherein, BP neural network is that multilayer feedforward neural network is used than wide, which first passes through preceding to biography
Broadcast acquirement estimated value, after reuse error and counter-propagate through gradient decline to be continuously updated weight to obtain minimum
Error therefrom learns to obtain optimal weight coefficient；From the name of BP neural network it is also known that the core of the algorithm is backpropagation calculation
Method.
In the present invention, data preprocessing method is as follows in step A:
A, collected photovoltaic power generation data are cleaned；
B, the data after cleaning are verified with whether have missing；
C, the data after verification are corrected；
D, the data after correction are filtered；
E, filtered data are updated.
Data prediction refers to some processing carried out before main processing to data, and data scrubbing routine is by filling out
It writes the value of missing, smooth noise data, identification or deletes outlier and solve inconsistency and carry out " cleaning " data.Mainly reach
Following target: standardized format, abnormal data are removed, error correcting, the removing of repeated data；Wherein, data cleansing includes pair
The data of acquisition carry out time check and sort, to data single-point threshold values filtration treatment.The data prediction side that the present invention uses
Method can be realized sequence to data, noise reduction, filtering data, improve data subsequent processing efficiency.
In the present invention, feature extracting method is as follows in step C:
A, data set is established, multiple Sub Data Sets to feature extraction are wherein included in data set；
B, feature training is carried out to data set, obtains training pattern；
C, the first keyword and the second keyword in data set are extracted；
D, each Sub Data Set in cyclic search data set, using the first keyword and the second keyword as primary condition, antithetical phrase
Data set scans for；
E, search is matched to the first keyword or the second keyword in each Sub Data Set, then extracts to data.
By the first keyword of search and the second keyword in the feature extracting method that the present invention uses, extraction can reduce
Difficulty improves feature extraction precision.
Embodiment two:
A kind of photovoltaic power generation power prediction method based on deep learning, comprising the following steps:
A, photovoltaic power generation data are acquired and the data of acquisition are pre-processed；
B, pretreated data are sent in memory and are stored；
C, the photovoltaic power generation data of storage are subjected to feature extraction；
D, the data after feature extraction are encrypted later；
E, it is inputted encrypted data as BP neural network, BP neural network output is photovoltaic power generation function to be predicted
Rate establishes multiple groups neural network prediction model；
F, depth training is carried out to multiple groups neural network prediction model, chooses neural network corresponding to optimum performance parameters
Prediction model predicts photovoltaic generation power as final prediction model.
Photovoltaic data are acquired first, the photovoltaic data of acquisition are pre-processed, remove noise and are filtered, and will be handled
Photovoltaic afterwards, which is sent in memory, to be stored, and the data of storage are carried out feature extraction later, is extracted in photovoltaic data
Characteristic later encrypts characteristic, and encrypts and use multi-enciphering, can be improved Information Security, later will
Encrypted data input BP neural network, and establish multiple groups neural network prediction model, finally choose optimum performance parameters institute
Corresponding neural network prediction model is as final prediction model.
Wherein, BP neural network is that multilayer feedforward neural network is used than wide, which first passes through preceding to biography
Broadcast acquirement estimated value, after reuse error and counter-propagate through gradient decline to be continuously updated weight to obtain minimum
Error therefrom learns to obtain optimal weight coefficient；From the name of BP neural network it is also known that the core of the algorithm is backpropagation calculation
Method.
In the present invention, data preprocessing method is as follows in step A:
A, collected photovoltaic power generation data are cleaned；
B, the data after cleaning are verified with whether have missing；
C, the data after verification are corrected；
D, the data after correction are filtered；
E, filtered data are updated.
Data prediction refers to some processing carried out before main processing to data, and data scrubbing routine is by filling out
It writes the value of missing, smooth noise data, identification or deletes outlier and solve inconsistency and carry out " cleaning " data.Mainly reach
Following target: standardized format, abnormal data are removed, error correcting, the removing of repeated data；Wherein, data cleansing includes pair
The data of acquisition carry out time check and sort, to data single-point threshold values filtration treatment.The data prediction side that the present invention uses
Method can be realized sequence to data, noise reduction, filtering data, improve data subsequent processing efficiency.
In the present invention, feature extracting method is as follows in step C:
A, data set is established, multiple Sub Data Sets to feature extraction are wherein included in data set；
B, feature training is carried out to data set, obtains training pattern；
C, the first keyword and the second keyword in data set are extracted；
D, each Sub Data Set in cyclic search data set, using the first keyword and the second keyword as primary condition, antithetical phrase
Data set scans for；
E, search is matched to the first keyword or the second keyword in each Sub Data Set, then extracts to data.
By the first keyword of search and the second keyword in the feature extracting method that the present invention uses, extraction can reduce
Difficulty improves feature extraction precision.
In the present embodiment, Encryption Algorithm is additionally provided, encryption method is as follows in step D:
A, cleaning operation is carried out to data to be encrypted first；
B, the operation of primary encryption algorithm is carried out to the data after cleaning later, obtains an encrypted ciphertext data；
C, hyperchaos cryptographic calculation is carried out to a ciphertext data later again, obtains secondary ciphertext data；
D, secondary Encryption Algorithm operation, the final encryption of complete paired data finally are carried out to secondary ciphertext data.
Wherein, the first Encryption Algorithm uses AES encryption algorithm；Second Encryption Algorithm uses des encryption algorithm.AES
As a new generation data encryption standards converged strong security, high-performance, high efficiency, it is easy-to-use and flexible the advantages that.AES design
There are three key lengths: 128,192,256, in contrast, 56 keys of the 128 key ratio DES of AES are 1021 times strong.AES is calculated
Method mainly includes three aspects: wheel variation, circle number and cipher key spreading.Herein for 128, the basic principle of algorithm is introduced；Knot
AVR assembler language is closed, realizes high-level data Encryption Algorithm AES；AES is packet key, and algorithm inputs 128 data, and key is long
Degree is also 128.The wheel number to a data block encryption is indicated with Nr.Each round, which requires one, has phase with input grouping
With the participation of the expanded keys of length.Due to externally input encryption key K limited length, so close with one in the algorithm
External key K is extended to longer Bit String by key extender, to generate the encryption and decryption keys of each wheel.DES uses one
A 56 keys and additional 8 bit parity check position generate maximum 64 packet sizes.This is the grouping of an iteration
Password, using the referred to as technology of Feistel, wherein the text block of encryption is split into two halves.Wherein half is answered using sub-key
It, then will output and the other half progress nonequivalence operation with circulatory function；Then this two halves is exchanged, this process will continue to down
It goes, but the last one circulation does not exchange.DES is replaced using 16 circulations using exclusive or, replacement, four kinds of shifting function basic fortune
It calculates.The encryption method that the present invention uses can carry out multi-enciphering to photovoltaic data, improve the safety and confidentiality of data.
In conclusion the prediction technique precision that the present invention uses is high, prediction rate is high, solves existing photovoltaic power station power generation
The inaccurate problem of power prediction.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (7)
1. a kind of photovoltaic power generation power prediction method based on deep learning, it is characterised in that: the following steps are included:
A, photovoltaic power generation data are acquired and the data of acquisition are pre-processed；
B, pretreated data are sent in memory and are stored；
C, the photovoltaic power generation data of storage are subjected to feature extraction；
D, the data after feature extraction are encrypted later；
E, it being inputted encrypted data as BP neural network, BP neural network output is photovoltaic generation power to be predicted,
Establish multiple groups neural network prediction model；
F, depth training is carried out to multiple groups neural network prediction model, chooses neural network prediction corresponding to optimum performance parameters
Model predicts photovoltaic generation power as final prediction model.
2. a kind of photovoltaic power generation power prediction method based on deep learning according to claim 1, it is characterised in that: institute
It is as follows to state data preprocessing method in step A:
A, collected photovoltaic power generation data are cleaned；
B, the data after cleaning are verified with whether have missing；
C, the data after verification are corrected；
D, the data after correction are filtered；
E, filtered data are updated.
3. a kind of photovoltaic power generation power prediction method based on deep learning according to claim 1, it is characterised in that: institute
It is as follows to state feature extracting method in step C:
A, data set is established, multiple Sub Data Sets to feature extraction are wherein included in data set；
B, feature training is carried out to data set, obtains training pattern；
C, the first keyword and the second keyword in data set are extracted；
D, each Sub Data Set in cyclic search data set, using the first keyword and the second keyword as primary condition, subdata
Collection scans for；
E, search is matched to the first keyword or the second keyword in each Sub Data Set, then extracts to data.
4. a kind of photovoltaic power generation power prediction method based on deep learning according to claim 1, it is characterised in that: institute
It is as follows to state encryption method in step D:
A, cleaning operation is carried out to data to be encrypted first；
B, the operation of primary encryption algorithm is carried out to the data after cleaning later, obtains an encrypted ciphertext data；
C, hyperchaos cryptographic calculation is carried out to a ciphertext data later again, obtains secondary ciphertext data；
D, secondary Encryption Algorithm operation, the final encryption of complete paired data finally are carried out to secondary ciphertext data.
5. a kind of photovoltaic power generation power prediction method based on deep learning according to claim 1, it is characterised in that: institute
It states memory in step B and uses random access memory.
6. a kind of photovoltaic power generation power prediction method based on deep learning according to claim 4, it is characterised in that: institute
The first Encryption Algorithm is stated using AES encryption algorithm；Second Encryption Algorithm uses des encryption algorithm.
7. a kind of photovoltaic power generation power prediction method based on deep learning according to claim 2, it is characterised in that: institute
Stating data cleansing includes carrying out time check to the data of acquisition and sorting, to data single-point threshold values filtration treatment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811636335.7A CN109726870A (en) | 2018-12-29 | 2018-12-29 | Photovoltaic power generation power prediction method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811636335.7A CN109726870A (en) | 2018-12-29 | 2018-12-29 | Photovoltaic power generation power prediction method based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109726870A true CN109726870A (en) | 2019-05-07 |
Family
ID=66296099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811636335.7A Pending CN109726870A (en) | 2018-12-29 | 2018-12-29 | Photovoltaic power generation power prediction method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109726870A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111579751A (en) * | 2020-05-08 | 2020-08-25 | 广东农工商职业技术学院(农业部华南农垦干部培训中心) | High-precision soil sensor |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013074695A (en) * | 2011-09-27 | 2013-04-22 | Meiji Univ | Device, method and program for predicting photovoltaic generation |
| CN107358021A (en) * | 2017-06-01 | 2017-11-17 | 华南理工大学 | DO prediction model establishment method based on BP neural network optimization |
| CN207283595U (en) * | 2017-11-02 | 2018-04-27 | 国网重庆市电力公司合川区供电分公司 | User power utilization data analysis integrated system based on power information collection |
| CN109002948A (en) * | 2018-10-29 | 2018-12-14 | 中冶赛迪电气技术有限公司 | The short-term photovoltaic power generation power prediction method of micro-capacitance sensor based on CDA-BP |
-
2018
- 2018-12-29 CN CN201811636335.7A patent/CN109726870A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013074695A (en) * | 2011-09-27 | 2013-04-22 | Meiji Univ | Device, method and program for predicting photovoltaic generation |
| CN107358021A (en) * | 2017-06-01 | 2017-11-17 | 华南理工大学 | DO prediction model establishment method based on BP neural network optimization |
| CN207283595U (en) * | 2017-11-02 | 2018-04-27 | 国网重庆市电力公司合川区供电分公司 | User power utilization data analysis integrated system based on power information collection |
| CN109002948A (en) * | 2018-10-29 | 2018-12-14 | 中冶赛迪电气技术有限公司 | The short-term photovoltaic power generation power prediction method of micro-capacitance sensor based on CDA-BP |
Non-Patent Citations (1)
| Title |
|---|
| 刘志: "光伏电站输出功率预测研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111579751A (en) * | 2020-05-08 | 2020-08-25 | 广东农工商职业技术学院(农业部华南农垦干部培训中心) | High-precision soil sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | End-to-end encrypted traffic classification with one-dimensional convolution neural networks | |
| CN113691380B (en) | Multidimensional private data aggregation method in smart power grid | |
| CN107491832A (en) | Energy quality steady-state index prediction method based on chaology | |
| CN104168264B (en) | A kind of low cost, high security physics unclonable function circuit | |
| CN106126887B (en) | A kind of multi-peak maximum power point of photovoltaic array tracking based on parameter identification | |
| CN103763696B (en) | Energy-saving sensor data collection method based on cross layer safe compression | |
| CN107425955B (en) | High-efficiency fixable-dimension trap door derived lattice upper identity base hierarchical encryption method | |
| CN109726870A (en) | Photovoltaic power generation power prediction method based on deep learning | |
| Zhang et al. | An automatic and efficient malware traffic classification method for secure Internet of Things | |
| CN105933101A (en) | Fully homomorphic encryption public key compression method based on parameter high power offset | |
| Su et al. | Hot-carrier solar cells with quantum well and dot energy selective contacts | |
| CN105959100B (en) | A kind of AES data ciphering method of the online generation key based on FPGA | |
| CN113709152B (en) | Antagonistic domain name generation model with high-resistance detection capability | |
| CN103746770A (en) | Message authentication code and probability secret key distribution mechanism-based anti-pollution network coding method | |
| Tong et al. | BFSN: a novel method of encrypted traffic classification based on bidirectional flow sequence network | |
| CN108197752A (en) | Wind turbine output power short term prediction method based on random forest | |
| Wang et al. | A side-channel attack on a bitsliced higher-order masked CRYSTALS-Kyber implementation | |
| US20220021541A1 (en) | An online and offline circulating unbalanced oil and vinegar signature method | |
| Ardhianto et al. | Covertext generation using fuzzy logic approach in parallel encryption with digit arithmetic of covertext to improve information confidentiality | |
| CN112507366A (en) | Method and system for efficient data aggregation of multidimensional data in smart power grid | |
| CN103220128B (en) | A kind of chaos cipher production method based on taking out position quantification at random | |
| Benayad et al. | InGaN/GaN tandem solar cell parameter estimation: a comparative stud | |
| CN106788971A (en) | A kind of sub-key generation method based on stream cipher arithmetic | |
| Muralidharan et al. | A kinetic Monte Carlo approach to study transport in amorphous silicon/crystalline silicon HIT cells | |
| Liu et al. | Robust Transmission Expansion Planning Considering Massive N-1 Contingencies with High Proportion of Renewable Energy |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190507 |