CN116192005A - Photovoltaic tracking method, system and medium based on micro space-time scale irradiation prediction - Google Patents
Photovoltaic tracking method, system and medium based on micro space-time scale irradiation prediction Download PDFInfo
- Publication number
- CN116192005A CN116192005A CN202211514186.3A CN202211514186A CN116192005A CN 116192005 A CN116192005 A CN 116192005A CN 202211514186 A CN202211514186 A CN 202211514186A CN 116192005 A CN116192005 A CN 116192005A
- Authority
- CN
- China
- Prior art keywords
- tracking
- cloud
- irradiation
- space
- irradiance
- 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 46
- 238000010248 power generation Methods 0.000 claims abstract description 60
- 230000033001 locomotion Effects 0.000 claims abstract description 59
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 35
- 238000004364 calculation method Methods 0.000 claims abstract description 33
- 230000008859 change Effects 0.000 claims abstract description 31
- 238000013135 deep learning Methods 0.000 claims abstract description 14
- 238000009826 distribution Methods 0.000 claims description 42
- 238000012544 monitoring process Methods 0.000 claims description 34
- 238000010586 diagram Methods 0.000 claims description 23
- 238000005259 measurement Methods 0.000 claims description 23
- 238000004891 communication Methods 0.000 claims description 18
- 230000005855 radiation Effects 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012876 topography Methods 0.000 claims description 7
- 239000000758 substrate Substances 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 15
- 238000007726 management method Methods 0.000 description 14
- 230000003287 optical effect Effects 0.000 description 5
- 238000002834 transmittance Methods 0.000 description 5
- 235000011034 Rubus glaucus Nutrition 0.000 description 4
- 235000009122 Rubus idaeus Nutrition 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 240000007651 Rubus glaucus Species 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000035699 permeability Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 244000235659 Rubus idaeus Species 0.000 description 1
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S20/00—Supporting structures for PV modules
- H02S20/30—Supporting structures being movable or adjustable, e.g. for angle adjustment
- H02S20/32—Supporting structures being movable or adjustable, e.g. for angle adjustment specially adapted for solar tracking
-
- 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
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
-
- 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
Abstract
The invention provides a photovoltaic tracking method, a system and a medium based on micro space-time scale irradiation prediction, wherein the method comprises the following steps: acquiring foundation cloud image data and ground irradiation data, and acquiring plane characteristics and three-dimensional characteristics of a cloud layer based on the foundation cloud image data and the ground irradiation data; determining a movement track of cloud shadows in a deployment area according to the solar position relationship and the cloud characteristics; establishing an irradiance space-time sequence prediction model based on deep learning according to the motion trail of cloud layer shadows in the deployment area, so as to obtain irradiance space-time sequence prediction results of a full time period according to the irradiance space-time sequence prediction model; and establishing an irradiation calculation model of the inclined plane of the tracking bracket component based on irradiance space-time sequence prediction results, and calculating component power generation output of each tracking angle. The invention can solve the problems that the real-time sensing mode can not meet the quantitative requirement of the photovoltaic tracking system on the irradiation change trend and the tracking system astronomical algorithm has inaccurate scattered irradiation tracking.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to the technical field of photovoltaic tracking.
Background
Solar photovoltaic power generation is an effective way to solve the current increasingly serious energy and environmental problems. Photovoltaic tracking technology is one of the main ways to increase the efficiency of photovoltaic systems. The traditional flat single-axis tracking system can accurately track the position of the sun, but the problems that the tracking of scattered radiation is inaccurate, the tracking efficiency is limited and the like still exist due to the fact that the information such as the direct scattered radiation duty ratio and the spatial distribution under the shielding of a cloud layer cannot be combined. Aiming at the problems that the tracking efficiency is low caused by inaccurate scattered radiation tracking and the real-time sensing mode of an astronomical algorithm of a photovoltaic tracking system cannot meet the quantitative requirement of tracking on the radiation change trend, the invention collects the multi-view foundation cloud picture, extracts the multi-dimensional characteristic parameters of the cloud layer which influence the ground shadow casting characteristics, quantifies the weight of the cloud layer ground shadow gradient on the scattering anisotropy distribution under the sun shielding, calculates the optimal tracking angle, determines the tracking path optimization strategy, combines the software and hardware of a tracker and the like, and realizes the high-efficiency tracking.
The photovoltaic manufacture and market scale of China are the first world, but the market share and permeability of the tracking bracket are low, the permeability of the intelligent tracking photovoltaic power generation system in 2021 China is about 9% according to the analysis of IHS marks of third-party assessment institutions, only 2 enterprises in the ten first world of the market share rank of the global tracking are trained, and the intelligent tracking core technology is mostly mastered in enterprises such as the United states, europe and the like. The problems of inaccurate scattered radiation tracking and low tracking efficiency caused by the quantitative requirement of tracking on radiation change trend due to a real-time sensing mode in the astronomical algorithm of the conventional photovoltaic tracking system can not be met.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention aims to provide a photovoltaic tracking method, a system and a medium based on micro space-time scale irradiation prediction, which are used for realizing real-time tracking and scattering direct irradiation simultaneous tracking, so that the total irradiation amount obtained by the surface of a photovoltaic module is maximized, and the efficiency of a photovoltaic tracking system is improved.
To achieve the above and other related objects, the present invention provides a photovoltaic tracking method based on micro-spatio-temporal scale irradiation prediction, the method comprising: acquiring foundation cloud image data and ground irradiation data, and acquiring plane characteristics and three-dimensional characteristics of cloud layers based on the foundation cloud image data and the ground irradiation data; determining a movement track of cloud shadows in a deployment area according to the solar position relationship and the cloud characteristics; establishing an irradiance space-time sequence prediction model based on deep learning according to a motion track of cloud layer shadows in a deployment area, so as to obtain irradiance space-time sequence prediction results of a whole time period according to the irradiance space-time sequence prediction model; and establishing a tracking bracket assembly inclined plane irradiation calculation model based on the irradiance space-time sequence prediction result, and calculating assembly power generation output of each tracking angle based on the tracking bracket assembly inclined plane irradiation calculation model.
In an embodiment of the present invention, the acquiring the planar feature and the three-dimensional feature of the cloud layer based on the ground cloud image data and the ground irradiation data includes: according to the data correlation between the cloud image characteristics and the irradiation attenuation data, determining cloud layer planes and three-dimensional cloud image characteristics with strong influence factors; establishing a cloud layer vector motion model based on the foundation cloud image data, and acquiring plane displacement change characteristics of a cloud layer in a cloud image; and determining the positions of the same cloud layer in different cloud pictures through feature matching, and estimating the height features of the three-dimensional substrate of the cloud layer.
In an embodiment of the present invention, determining a motion trajectory of cloud shadows in a deployment area according to a solar location relationship and cloud characteristics includes: calculating the spatial position of the sun at any moment by utilizing a sun position algorithm, constructing a relative motion model of the sun and the cloud layer by combining real motion vector information of the cloud layer, and establishing a projection function relation from sky cloud layer motion to ground shadow motion; and identifying cloud layer edge points which reach the deployment area earliest and cloud layer edge points which leave the deployment area last, calculating ground shadow edge points corresponding to the cloud layer edge points according to the projection function relation, and calculating the time when the cloud layer shadow edge points reach and leave the deployment area so as to determine the movement track of the cloud layer shadow in the deployment area.
In one embodiment of the present invention, the establishing the irradiance spatiotemporal sequence prediction model based on deep learning includes: according to the motion trail of cloud shadows in the deployment area, measuring the spatial nonlinear correlation of the time irradiance data, and obtaining a spatial nonlinear correlation measurement rule; and establishing an irradiance space-time sequence prediction model based on deep learning based on irradiance space-time sequence data and the space nonlinear correlation measurement rule.
In an embodiment of the present invention, the obtaining a spatial nonlinear correlation measurement rule according to a spatial nonlinear correlation measurement of temporal irradiance data according to a motion track of cloud shadows in a deployment area includes: according to the movement track of the cloud layer shadow in the deployment area, extracting time sequence data of irradiance sensor nodes on a track path in a shadow propagation period; according to the abrupt change information of irradiance on time sequence, analyzing the change condition of three states of each node before shading, during shading and after shading; and calculating the spatial correlation among the nodes according to the change condition, analyzing the spatial correlation change rule under the condition of different shadow tracks, and further obtaining the spatial nonlinear correlation measurement rule.
In an embodiment of the present invention, the establishing the irradiance spatiotemporal sequence prediction model based on deep learning based on the irradiance spatiotemporal sequence data and the spatial nonlinear correlation measurement rule includes: converting irradiance space-time sequence data into a space-time diagram data structure, and connecting space diagrams of adjacent time steps into space-time diagrams; according to the space nonlinear correlation measurement rule, extracting space-time characteristics of the current time step range, and carrying out irradiance prediction on each graph node; and according to the time and the motion trail of the cloud layer shadow entering and exiting the deployment area, deploying a plurality of space-time diagram convolution modules in a plurality of time periods before, during and after shadow shielding, capturing the heterogeneity of space-time data in a longer time range, and finally obtaining irradiance space-time sequence prediction results in all time periods.
In an embodiment of the invention, the establishing the irradiation calculation model of the inclined plane of the tracking bracket component based on the irradiance space-time sequence prediction result includes: constructing a direct and scattered radiation distribution model based on the ground-day relation, the radiation intensity and the distribution weight of the irradiance space-time sequence prediction result, and dividing the area below the component into a plurality of shadow areas and light areas; and respectively calculating the irradiation intensity and distribution of the earth surface shadow region and the bright region reflected to the back surface of the tracking bracket assembly, and calculating the irradiation intensity and distribution of the front surface of the tracking bracket assembly so as to construct an inclined surface irradiation calculation model of the tracking bracket assembly.
In an embodiment of the present invention, further includes: calculating the power generation output of the component of each tracking angle, and establishing a tracking algorithm by iterative optimization so that the bracket operates at the angle of the optimal power generation output; calculating the power generation of the components of the support under different angles and the power generation loss of the components under the shielding condition, and determining the optimal inverse tracking angle of each row of components for avoiding the shielding loss according to the difference of the topography environments of the adjacent tracking supports of each row; and iteratively calculating the power generation output and shielding mismatch loss of each angle of the tracking bracket based on the irradiance space-time sequence prediction result and the tracking bracket assembly inclined plane irradiation calculation model, so as to realize the optimization of the tracking angle.
To achieve the above and other related objects, the present invention also provides a photovoltaic tracking system based on micro-spatio-temporal scale irradiation prediction, comprising: the foundation cloud picture acquisition system is used for acquiring foundation cloud picture data; the foundation cloud picture acquisition system at least comprises a fisheye lens, a CCD camera and a microcomputer processor; the meteorological acquisition system is used for acquiring ground irradiation data; the meteorological acquisition system at least comprises a temperature sensor, an radiometer and an air velocity meter; the tracking bracket monitoring system is respectively connected with the foundation cloud image acquisition system and the meteorological acquisition system and is used for acquiring and monitoring data of the photovoltaic system; the tracking bracket monitoring system comprises a tracking controller and a communication controller; the component power generation monitoring system is used for monitoring power generation of the photovoltaic system; the assembly power generation monitoring system at least comprises an inverter, a power tester and a tour detector; the control management system is respectively connected with the foundation cloud image acquisition system, the meteorological acquisition system, the tracking bracket monitoring system and the component power generation monitoring system, and comprises a memory for storing a computer program; at least one processor for executing the computer program to implement the steps of the photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction as described above.
In an embodiment of the invention, the ground cloud image acquisition system at least comprises a fisheye lens, a CCD camera and a microcomputer processor; the meteorological acquisition system at least comprises a temperature sensor, an radiometer and an air velocity meter; the tracking bracket monitoring system comprises a tracking controller and a communication controller; the component power generation monitoring system at least comprises an inverter, a power tester and a tour detector.
In an embodiment of the invention, the deployment area is divided according to the range of the pre-deployment area, and the foundation cloud image acquisition system, the meteorological acquisition system and the tracking bracket monitoring system are subjected to gridding deployment according to the divided area.
To achieve the above and other related objects, the present invention also provides a computer storage medium storing program instructions which, when executed, implement the steps of a photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction as described above.
To achieve the above and other related objects, the present invention also provides an electronic device including a memory for storing a computer program; a processor for running the computer program to implement the steps of the photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction as described above.
As described above, the photovoltaic tracking method, system and medium based on micro space-time scale irradiation prediction of the present invention have the following beneficial effects:
the invention can solve the problems that the real-time sensing mode can not meet the quantitative requirement of the photovoltaic tracking system on the irradiation change trend and the tracking system astronomical algorithm has inaccurate scattered irradiation tracking. The cloud layer multidimensional characteristic parameters affecting the ground drop shadow characteristic are extracted through collecting the multi-view foundation cloud image, a characteristic parameter and irradiation attenuation intensity relation model is established, the micro-space-time scale solar irradiation distribution of a photovoltaic power station area is predicted, the solar scattering and direct irradiation prediction is included, the power generation output corresponding to different tracking angles is calculated, an efficient intelligent tracking algorithm under the complex weather condition is established, and the power generation capacity of the system is improved compared with that of a conventional astronomical algorithm tracking system by adopting a tracking electric control system and a mechanical structure.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the overall flow of a photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction in an embodiment of the present application;
FIG. 2 is a technical roadmap of an irradiation prediction scheme in a photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction in an embodiment of the application;
FIG. 3 shows a schematic block diagram of a photovoltaic tracking system based on micro-spatiotemporal scale irradiance prediction in an embodiment of the present application;
fig. 4 is a schematic block diagram of a control management system in an embodiment of the present application.
FIG. 5 is a diagram illustrating a control management system intelligent tracking technology in an embodiment of the present application.
Description of element reference numerals
100. Photovoltaic tracking system based on micro space-time scale irradiation prediction
110. Foundation cloud picture acquisition system
120. Meteorological acquisition system
130. Tracking support monitoring system
140. Assembly power generation monitoring system
150. Control management system
1001. Processor and method for controlling the same
1002. Memory device
S100 to S400 steps
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
The embodiment aims to provide a photovoltaic tracking method, a photovoltaic tracking system and a photovoltaic tracking medium based on micro space-time scale irradiation prediction, which are used for realizing real-time tracking and scattering direct irradiation simultaneous tracking, so that the total irradiation amount obtained by the surface of a photovoltaic module is maximum, and the efficiency of the photovoltaic tracking system is improved.
Aiming at the further improvement of the efficiency of the photovoltaic power generation system, the embodiment provides an intelligent tracking system based on the irradiation prediction of the micro space-time scale of the foundation cloud image, and solves the problems that the real-time sensing mode cannot meet the quantitative requirement of the photovoltaic tracking system on the irradiation change trend and the tracking system astronomical algorithm has inaccurate scattered irradiation tracking. The cloud layer multidimensional characteristic parameters affecting the ground drop shadow characteristic are extracted through collecting the multi-view foundation cloud image, a characteristic parameter and irradiation attenuation intensity relation model is established, the micro-space-time scale solar irradiation distribution of a photovoltaic power station area is predicted, the solar scattering and direct irradiation prediction is included, the power generation output corresponding to different tracking angles is calculated, an efficient intelligent tracking algorithm under the complex weather condition is established, and the power generation capacity of the system is improved compared with that of a conventional astronomical algorithm tracking system by adopting a tracking electric control system and a mechanical structure.
The technical problems to be solved by the embodiment are that scattering radiation tracking is inaccurate and a real-time sensing mode cannot meet the problem of low tracking efficiency caused by the quantitative demand of tracking on radiation change trend in an astronomical algorithm of a photovoltaic tracking system, so that real-time tracking and scattering direct irradiation simultaneous tracking are realized, the total radiation amount acquired by the surface of a photovoltaic module is maximum, and the efficiency of the photovoltaic tracking system is improved.
The principles and embodiments of the photovoltaic tracking method, system, and medium based on micro-spatiotemporal irradiation prediction of the present invention will be described in detail below, so that those skilled in the art can understand the photovoltaic tracking method, system, and medium based on micro-spatiotemporal irradiation prediction of the present invention without the need for creative effort.
Example 1
The present embodiment provides a photovoltaic tracking method based on micro-space-time scale irradiation prediction, specifically, as shown in fig. 1, the photovoltaic tracking method based on micro-space-time scale irradiation prediction in the present embodiment includes:
step S100, acquiring foundation cloud image data and ground irradiation data, and acquiring plane characteristics and three-dimensional characteristics of a cloud layer based on the foundation cloud image data and the ground irradiation data;
step S200, determining a motion track of cloud shadows in a deployment area according to the daily position relation and cloud characteristics;
Step S300, establishing an irradiance space-time sequence prediction model based on deep learning according to a motion track of cloud layer shadows in a deployment area, so as to obtain irradiance space-time sequence prediction results of a whole time period according to the irradiance space-time sequence prediction model;
and step S400, establishing a tracking bracket assembly inclined plane irradiation calculation model based on the irradiance space-time sequence prediction result, and calculating assembly power generation output of each tracking angle based on the tracking bracket assembly inclined plane irradiation calculation model.
The following describes in detail the above steps S100 to S400 of the photovoltaic tracking method based on the micro-spatiotemporal scale irradiation prediction of the present embodiment.
Step S100, acquiring foundation cloud image data and ground irradiation data, and acquiring plane characteristics and three-dimensional characteristics of cloud layers based on the foundation cloud image data and the ground irradiation data.
In this embodiment, the acquiring the planar feature and the three-dimensional feature of the cloud layer based on the ground cloud image data and the ground irradiation data includes:
1) And determining cloud layer planes and three-dimensional cloud image features with strong influence factors according to data correlation between the cloud image features and irradiation attenuation data. Specifically, a ground cloud image and ground irradiation database is built by the ground cloud image acquisition system 110 of fig. 3, and plane and three-dimensional cloud image features with strong influence factors are determined according to data correlation between cloud image features and irradiation attenuation data.
2) And establishing a cloud layer vector motion model based on the foundation cloud image data, and obtaining the plane displacement change characteristics of the cloud layer in the cloud image. Specifically, for a single ground cloud, the cloud plane coverage characteristics were evaluated based on the image R, B channel color characteristics. And analyzing continuous moment images acquired by the cloud image acquisition instrument, and establishing a cloud layer vector motion model according to the assumption of invariance of optical flow to obtain the plane displacement change characteristics of the cloud layer in the cloud image.
3) And determining the positions of the same cloud layer in different cloud pictures through feature matching, and estimating the height features of the three-dimensional substrate of the cloud layer. Specifically, the multi-view foundation cloud pictures of a plurality of cloud picture collectors are integrated, the positions of the same cloud layer in different cloud pictures are determined through feature matching, and the estimation of the height features of the three-dimensional base of the cloud layer is realized by combining the relative positions of the ground imagers.
Step S200, determining a movement track of cloud shadows in a deployment area according to the daily position relation and the cloud characteristics.
In this embodiment, determining the movement track of the cloud shadow in the deployment area according to the solar location relationship and the cloud characteristics includes:
calculating the spatial position of the sun at any moment by utilizing a sun position algorithm, constructing a relative motion model of the sun and the cloud layer by combining real motion vector information of the cloud layer, and establishing a projection function relation from sky cloud layer motion to ground shadow motion; and identifying cloud layer edge points which reach the deployment area earliest and cloud layer edge points which leave the deployment area last, calculating ground shadow edge points corresponding to the cloud layer edge points according to the projection function relation, and calculating the time when the cloud layer shadow edge points reach and leave the deployment area so as to determine the movement track of the cloud layer shadow in the deployment area.
In the embodiment, a space projection function relation among the sun, the cloud layer and the ground is established, and the time when the cloud layer shadow enters and leaves the deployment area is calculated. Specifically, a solar position algorithm is utilized to calculate the spatial position of the sun at any moment, a relative motion model of the sun and the cloud layer is constructed by combining real motion vector information of the cloud layer, a projection function relation from sky cloud layer motion to ground shadow motion is established, cloud layer edge points which reach a deployment area at the earliest and cloud layer edge points which leave the deployment area at the latest are identified, ground shadow edge points corresponding to the edge points are calculated according to the projection function relation, the time when the shadow edge points reach and leave the deployment area is calculated, and the motion track of the shadow edge points in the deployment area is determined.
According to the embodiment, a dynamic projection physical model moving from the sky cloud layer to the ground shadow motion is determined according to the space projection function relation of the sun, the cloud layer and the ground.
1) Based on R, G, B and R/B ratio values of the acquired images, the cloud layer and the sky in the cloud picture are accurately identified, and the coverage rate of the cloud layer in the sky is estimated. Estimating the height of the adjacent cloud layer base according to the geometric relation of the ground acquisition instrument, thereby integrating the spectral characteristics of the cloud layer about R, G, B, the texture characteristics of the cloud layer base about R, G, B, the sky cloud layer coverage rate and the cloud layer base height, and carrying out high-efficiency identification on the cloud layer category by combining a k-nearest neighbor classifier; finally, the evaluation and calculation of the cloud deck movement speed are realized by carrying out optical flow calculation on cloud deck block division areas.
2) Combining the solar position relationship and the cloud layer morphology distribution rule to obtain a physical calculation model of ideal shadow space distribution under the direct irradiation condition. Scattering in the anisotropic scattering model according to the optical refraction characteristics of the cloud layer.
In this embodiment, the method further includes establishing a solar irradiation intensity distribution model under cloud layer shielding.
1) Analyzing the texture characteristics, the color characteristics, the height characteristics and the average transmittance characteristics of the cloud layer, combining the acquired cloud layer data, establishing a cloud layer characteristic database, and judging the type of the cloud layer. By identifying the cloud layer type, integrating the upper-boundary solar irradiation of the atmosphere and the ground solar irradiation observation data, and establishing a basic relationship between the average transmittance of the cloud layer and the cloud layer type under the condition that the atmospheric transmittance does not change in a short time; and then, by adopting atmospheric clear sky index (kt) and definition index (kh) evaluation, establishing mathematical models of kt and kh about atmospheric transmittance index, cloud layer transmittance index and cloud layer motion index and functions of cloud layer edge and solar edge distance, and predicting and evaluating the distribution of direct solar irradiation and total irradiation intensity about time of the horizontal planes of the position shielding area and the non-shielding area of the collector arrangement by combining the direct irradiation intensity and the total irradiation intensity of the outside atmosphere.
2) Based on the calculation of the cloud layer shielding intensity characteristic distribution, a scattering anisotropy distribution model under the cloud layer shielding is established, and solar scattering is divided into 3 areas to calculate: and further optimizing and calculating the scattering irradiation space direction distribution under the shielding of the cloud layer in the sky dome, the ring sun and the cloud layer area.
In the embodiment, the method further comprises the step of establishing an irradiation calculation model of the inclined plane of the tracking bracket component based on irradiation distribution prediction.
Specifically, according to design parameters of a photovoltaic tracking bracket system and a space rectangular coordinate system, based on a Perez scattering irradiation model, the front irradiation intensity and distribution of a tracking bracket component are calculated, a component irradiation model calculation model is constructed, and the irradiation intensity calculation of the front surface and the back surface of the tracking bracket component is realized. And further, according to the electrical model of the photovoltaic module, according to the irradiation intensity and distribution received by the front and back surfaces of the photovoltaic module and the module circuit structure, establishing a module power generation output calculation model in each tracking angle.
In this embodiment, the method further includes: by combining the power generation output of the tracking bracket component, the tracker tracks the steps and losses, and an optimal tracking algorithm of a tracking system is established
1) And calculating the power generation output of the component of each tracking angle, and establishing a tracking algorithm by iterative optimization so that the bracket operates at the angle of the optimal power generation output. Based on the change of irradiation prediction data in the past 1 hour, a discrete rate calculation model is constructed to identify whether the current weather is a strongly fluctuating multi-day weather type. And the tracking algorithm is optimized by considering that the frequent tracking rotation under the severe and changeable cloud weather type can cause the loss of the support structural member and the battery.
2) According to characteristics of a large-scale ground power station, such as characteristics of uneven east-west terrain, an optimized slope angle model is established, wherein the optimized slope angle model comprises a basic model, an iterative model and a decision model; and calculating the power generation of the component under different angles and the power generation loss of the component under the shielding condition based on the component irradiation and the electrical model, and iteratively outputting a globally optimal angle set by adopting a disturbance algorithm.
3) Based on the micro space-time scale irradiation prediction and the irradiation model of the double-sided component of the tracking bracket, the power generation output and the shielding mismatch loss of each angle of the tracking bracket are calculated in an iterative mode, and the tracking angle optimization is realized under the conditions of high scattering weather and complex topography.
And step S300, establishing an irradiance space-time sequence prediction model based on deep learning according to the motion track of cloud layer shadows in the deployment area, so as to obtain irradiance space-time sequence prediction results of a whole time period according to the irradiance space-time sequence prediction model.
In this example, the irradiation prediction embodiment is shown in fig. 2.
1. Irradiation and image sensor network deployment
1) All-sky imager equipped with silicon-based irradiance sensor
The total irradiance meter adopts a solar battery as a sensor, the voltage at two ends of a load resistor is sampled through a singlechip, the total irradiance intensity is obtained through calculation, and the total irradiance of the horizontal plane sun can be continuously monitored; the all-sky imager is composed of other accessory parts such as a high-definition fisheye camera and a raspberry group microprocessor, and can realize continuous shooting of all-sky images.
2) Deployment space sensor network coordinate planning
Aiming at the pre-deployment area range, meshing and dividing deployment areas, and performing meshing deployment on the irradiation sensor network according to the divided areas; according to historical meteorological data of a deployment area, a reasonable range of visual field cross dimensions and deployment intervals of an imager are determined by combining a substrate height change range of a local common type cloud layer and a rate probability distribution of local cloud layer movement, so that the multi-view all-sky imager system can monitor the cloud layer conditions of the deployment area and the surrounding area in the vertical direction.
3) Sensor network data transmission and data preprocessing
And receiving irradiance and ground cloud image data of a group of sensor network nodes through the Raspberry group carried Zigbee wireless communication module, uploading and storing the irradiance and ground cloud image data to a local server or a cloud end, and simultaneously providing integral time synchronization information for the group of sensor nodes at fixed time. Developing a data preprocessing algorithm, identifying abnormal data of irradiance in real time, eliminating abnormal conditions such as data noise and the like, and simultaneously, carrying out preprocessing steps such as distortion correction, denoising and the like on the foundation cloud picture.
2. Cloud shadow vector tracking based on multi-view foundation cloud image physical information
1) Cloud layer substrate height and actual motion vector calculation based on multi-view foundation cloud picture
And (3) integrating the multi-view foundation cloud pictures of the all-sky imager system, determining the positions of the same cloud layer in different cloud pictures through characteristic point matching, and calculating the base height of the cloud layer by combining the ground deployment coordinates of the all-sky imager system based on the epipolar geometry principle. And selecting a certain sky imager as a reference point, obtaining a pixel displacement vector of the cloud layer in the ground cloud picture through an optical flow invariance assumption, combining the base height of the cloud layer, and calculating to obtain the real movement speed and movement direction of the cloud layer through conversion from a camera coordinate system to a world coordinate system.
Specifically, in this embodiment, the establishing the irradiance spatiotemporal sequence prediction model based on deep learning includes:
1) And according to the motion trail of the cloud shadow in the deployment area, measuring the spatial nonlinear correlation of the time irradiance data, and obtaining a spatial nonlinear correlation measurement rule.
In this embodiment, the obtaining the spatial nonlinear correlation measurement rule according to the spatial nonlinear correlation measurement of the temporal irradiance data according to the motion trail of the cloud cover shadow in the deployment area includes:
according to the movement track of the cloud layer shadow in the deployment area, extracting time sequence data of irradiance sensor nodes on a track path in a shadow propagation period; according to the abrupt change information of irradiance on time sequence, analyzing the change condition of three states of each node before shading, during shading and after shading; and calculating the spatial correlation among the nodes according to the change condition, analyzing the spatial correlation change rule under the condition of different shadow tracks, and further obtaining the spatial nonlinear correlation measurement rule.
In this embodiment, firstly, the spatial nonlinear correlation of the space-time irradiance data is measured:
according to the movement track of cloud layer shadows in a deployment area, extracting time sequence data of irradiance sensor nodes on a track path in a shadow propagation period, mining mutation information of irradiance on the time sequence by adopting methods such as first-order difference, wavelet transformation and the like, analyzing the change conditions of three states of each node before shadow shielding, during shielding and after shielding, further calculating the spatial correlation among the nodes through time-lag pearson coefficients, analyzing the spatial correlation change rule under the condition of different shadow tracks, and further obtaining the spatial nonlinear correlation measurement rule.
2) And establishing an irradiance space-time sequence prediction model based on deep learning based on irradiance space-time sequence data and the space nonlinear correlation measurement rule.
In this embodiment, the establishing the irradiance spatiotemporal sequence prediction model based on deep learning based on the irradiance spatiotemporal sequence data and the spatial nonlinear correlation measurement rule includes:
converting irradiance space-time sequence data into a space-time diagram data structure, and connecting space diagrams of adjacent time steps into space-time diagrams; according to the space nonlinear correlation measurement rule, extracting space-time characteristics of the current time step range, and carrying out irradiance prediction on each graph node; and according to the time and the motion trail of the cloud layer shadow entering and exiting the deployment area, deploying a plurality of space-time diagram convolution modules in a plurality of time periods before, during and after shadow shielding, capturing the heterogeneity of space-time data in a longer time range, and finally obtaining irradiance space-time sequence prediction results in all time periods.
Converting irradiance space-time sequence data into a space-time diagram data structure, connecting space diagrams of adjacent time steps into space-time diagrams, calculating the space nonlinear correlation of each node relation pair according to a space nonlinear correlation measurement rule, constructing a weight adjacency matrix among nodes of each space-time diagram, and constructing a local space-time diagram convolution module for extracting space-time characteristics of the current time step range and carrying out irradiance prediction of each diagram node; and a plurality of space-time diagram convolution modules are deployed in a plurality of time periods such as before shadow shielding, during shielding, after shielding and the like according to the time and the movement track of the cloud layer shadow entering and exiting the deployment area, so as to capture the heterogeneity of space-time data in a longer time range and finally obtain irradiance space-time sequence prediction results in all time periods.
And step S400, establishing a tracking bracket assembly inclined plane irradiation calculation model based on the irradiance space-time sequence prediction result, and calculating assembly power generation output of each tracking angle based on the tracking bracket assembly inclined plane irradiation calculation model.
In the embodiment, a tracking bracket component inclined plane irradiation calculation model is established based on the micro space-time scale irradiation distribution prediction and the double-sided component irradiation model.
Specifically, in this embodiment, the establishing the irradiation calculation model of the inclined plane of the tracking bracket assembly based on the irradiance spatiotemporal sequence prediction result includes:
1) And constructing a direct and scattered radiation distribution model based on the ground-day relation, the radiation intensity and the distribution weight of the irradiance space-time sequence prediction result, and dividing the area below the component into a plurality of shadow areas and light areas.
Specifically, a digital three-dimensional model of the photovoltaic tracking bracket system is constructed based on design parameters of the photovoltaic tracking bracket system and a space rectangular coordinate system. Based on the ground-day relation and the irradiation intensity and the distribution weight predicted by the micro space-time scale, a direct and scattered irradiation distribution model is constructed, and the area below the component is divided into a plurality of shadow areas and light areas, wherein the shadow areas are formed by scattered radiation incidence, the light areas simultaneously contain direct irradiation and scattered irradiation, and each area can be effectively reflected to the back of the component.
2) And respectively calculating the irradiation intensity and distribution of the earth surface shadow region and the bright region reflected to the back surface of the tracking bracket assembly, and calculating the irradiation intensity and distribution of the front surface of the tracking bracket assembly so as to construct an inclined surface irradiation calculation model of the tracking bracket assembly.
Specifically, a three-dimensional view angle coefficient calculation model is built based on a Monte Carlo function, the irradiation intensity and distribution of the earth surface shadow area and the bright area reflected to the back surface of the tracking support component are calculated respectively, the irradiation intensity and distribution of the front surface of the tracking support component are calculated based on a Perez scattering irradiation model, a double-sided component irradiation model calculation model is built, and the irradiation intensity calculation of the front surface and the back surface of the tracking support component is realized. And further, based on the photovoltaic module electrical model, building a module power generation output calculation model in each tracking angle according to irradiation intensity and distribution received by the front side and the back side of the photovoltaic module and a module circuit structure.
In addition, in the embodiment, the method also comprises the steps and losses of tracking by combining the power generation output of the tracking bracket component and the tracking steps and losses of the tracker, and the optimal tracking strategy and algorithm of the tracking system are researched and established. The method specifically comprises the following steps:
1) And calculating the power generation output of the component of each tracking angle, and establishing a tracking algorithm by iterative optimization so that the bracket operates at the angle of the optimal power generation output.
Specifically, the power generation output of the component of each tracking angle is calculated, and the iterative optimization establishes a tracking algorithm so that the bracket operates at the angle of the optimal power generation output. Based on the change of irradiation prediction data in the past 1 hour, a discrete rate calculation model is constructed to identify whether the current weather is a strongly fluctuating multi-day weather type. And the tracking algorithm is optimized by considering that the frequent tracking rotation under the severe and changeable cloud weather type can cause the loss of the support structural member and the battery.
2) And calculating the power generation of the components of the support under different angles and the power generation loss of the components under the shielding condition, and determining the optimal inverse tracking angle of each row of components for avoiding shielding loss according to the difference of the topography environments of the adjacent tracking supports of each row.
Specifically, an optimized slope angle model is established according to characteristics of a large-scale ground power station, such as characteristics of uneven east-west terrain, and the like, and the optimized slope angle model comprises a basic model, an iterative model and a decision model; calculating the power generation of the components of the bracket under different angles and the power generation loss of the components under the shielding condition based on the component irradiation and the electrical model, adopting a disturbance algorithm, iteratively outputting a globally optimal angle set, and carrying out 'secondary verification' of east-west direction topography height difference evaluation by combining an unmanned plane technology; and determining the optimal inverse tracking angle of each row of components for avoiding shielding loss according to the difference of the topography environments of the adjacent tracking brackets of each row.
3) And iteratively calculating the power generation output and shielding mismatch loss of each angle of the tracking bracket based on the irradiance space-time sequence prediction result and the tracking bracket assembly inclined plane irradiation calculation model, so as to realize the optimization of the tracking angle.
Specifically, based on the irradiation prediction of the micro space-time scale and the irradiation model of the double-sided component of the tracking bracket, the power generation output and the shielding mismatch loss of each angle of the tracking bracket are calculated in an iterative mode, and the tracking angle optimization is realized under the conditions of high scattering weather and complex topography respectively.
From the above, the innovation of the embodiment is that the multi-view foundation cloud image method is adopted to realize the prediction of the micro space-time scale dispersion and direct irradiation distribution of the photovoltaic power station area, so that the problems that the scattered radiation tracking is inaccurate and the real-time sensor mode can not meet the quantitative requirement of the tracking on the irradiation change trend in the astronomical algorithm of the photovoltaic tracking system are solved:
1. and (3) performing ground cloud picture splicing registration through a machine vision technology, extracting all-sky cloud layer three-dimensional morphological characteristics based on the ground cloud picture, constructing an all-sky cloud layer morphological characteristic distribution model of a photovoltaic power station area, calculating to obtain ground irradiation attenuation intensity gradient distribution under cloud layer shadow, and improving irradiation distribution identification space resolution by combining a spatial interpolation algorithm to realize shadow area photovoltaic module-level microscale irradiation distribution prediction.
2. The space-time solar irradiation prediction technology of the foundation cloud picture and the loss of the photovoltaic tracker are comprehensively applied to the aspect of solar tracking path optimization, the anisotropic distribution weight of scattered irradiation under shielding of different cloud layers is quantized, the irradiation intensity of a tracking inclined plane and the power output of a photovoltaic module are accurately calculated, the tracker path optimization strategy under different weather conditions in 15 minutes in the future is determined, the problem of tracking loss of the astronomical algorithm in the photovoltaic tracking system under the weather of multi-cloud high scattering is solved, and the efficiency of the tracking system is improved.
Example 2
As shown in fig. 3, the present embodiment provides a photovoltaic tracking system 100 based on micro-space-time scale irradiation prediction, the photovoltaic tracking system 100 based on micro-space-time scale irradiation prediction includes: a ground cloud image acquisition system 110, a weather acquisition system 120, a tracking bracket monitoring system 130, a component power generation monitoring system 140 and a control management system 150.
Specifically, in this embodiment, the ground cloud image acquisition system 110 is configured to acquire ground cloud image data. The foundation cloud image acquisition system 110 at least comprises a fisheye lens (the visual angle is more than or equal to 180 degrees), a high definition microcomputer processor (a raspberry group microcomputer processor). The all-sky imager establishes a low-cost all-sky foundation cloud image collector through a fisheye lens (the visual angle is more than or equal to 180 degrees), a high-definition CCD camera, a raspberry group microcomputer processor and other accessory equipment, and realizes continuous shooting of all-sky images.
Specifically, in the present embodiment, the weather collection system 120 is configured to obtain ground irradiation data. The weather acquisition system 120 includes at least a temperature sensor, an radiometer, and a wind speed meter.
Specifically, in this embodiment, the tracking bracket monitoring system 130 is respectively connected to the ground cloud image collecting system 110 and the weather collecting system 120, and is used for collecting and monitoring data of the photovoltaic system. The tracking bracket monitoring system 130 comprises a tracking controller and a communication controller, and is used for collecting and monitoring data such as the angle of the tracking bracket, the state of the bracket, the working mode of the bracket and the like;
specifically, in the present embodiment, the component power generation monitoring system 140 is used to monitor power generation of the photovoltaic system. The component power generation monitoring system 140 at least comprises an inverter, a power tester and a tour detector.
Specifically, in this embodiment, the control management system 150 is respectively connected to the ground cloud image acquisition system 110, the weather acquisition system 120, the tracking bracket monitoring system 130, and the component power generation monitoring system. As shown in fig. 4, the control management system 150 includes a memory for storing a computer program; at least one processor for executing the computer program to implement the steps of the photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction as described in embodiment 1.
In this embodiment, the control management system 150 includes a microcontroller, and adopts a wireless communication technology with low power consumption, long transmission distance and strong anti-interference capability to connect the communication controller and the tracking controllers, where the communication controller can control multiple tracking controllers. The communication controller integrates the technology of sensor equipment such as anemometers, snow depth meters, radiometers and the like, integrates various extreme weather type judgment strategies, timely identifies various extreme weather and sends corresponding protection instructions to the tracking controller. And the communication controller is communicated with the intelligent equipment monitoring platform to realize the function of forwarding the intelligent tracking algorithm optimization instruction and the platform remote control.
The control management system 150 can accurately and rapidly collect the operation data of the sensing layer equipment, establish a foundation cloud picture and a ground irradiation database, and realize cloud shielding micro space-time scale irradiation distribution prediction under complex weather conditions. And integrating an intelligent tracking algorithm strategy, automatically identifying different weather types based on equipment operation data, issuing an optimization instruction for tracking the angle of the support according to each weather type, and finishing the protection of the tracking support and improving the power generation efficiency of the system.
In this embodiment, the deployment area is divided by meshing according to the pre-deployment area range, and the ground cloud image acquisition system 110, the weather acquisition system 120 and the tracking bracket monitoring system 130 are deployed by meshing according to the divided area.
Aiming at the pre-deployment area range, meshing and dividing deployment areas, and performing meshing deployment on the irradiation sensor network according to the divided areas; according to historical meteorological data of a deployment area, a reasonable range of visual field cross dimensions and deployment intervals of an imager are determined by combining a substrate height change range of a local common type cloud layer and a rate probability distribution of local cloud layer movement, so that the multi-view all-sky imager system can monitor the cloud layer conditions of the deployment area and the surrounding area in the vertical direction.
The control management system 150 in this embodiment has the following features and advantages:
1) The control management system 150 is based on an advanced tracking system electric control technology of a Microcontroller (MCU) power electronic control technology, and is used for completing the development of a reliable tracker and realizing that the static average power consumption of the tracking controller is less than 1.5W. The tracking controller is integrated with the high-precision inclination angle sensing module, and can accurately grasp the inclination angle of the tracking bracket by combining with the motor driving device.
2) The control management system 150 is based on wind tunnel tests, aerodynamic simulation and flexible structure wind-induced vibration analysis, researches a multi-point driving technology and a rotary driving system, improves the natural frequency of a tracking bracket, reduces wind actuation state response, and solves the problems that the traditional tracking bracket is easy to generate torsion flutter and poor in wind resistance in single-point driving. And (3) researching energy storage battery management and motor driving design in a complex environment, and researching a strong wind grading protection, a strong snow protection and hail protection strategy, so as to realize the operation capability in severe environments such as-30 ℃ to 60 ℃ and high altitude.
3) The control management system 150 is based on an advanced tracking system electric control technology of a Microcontroller (MCU) power electronic control technology, so as to complete the research and development of a communication controller, and research a LoRa wireless communication technology with low power consumption, long transmission distance and strong anti-interference capability, and realize the connection of the communication controller and the tracking controllers, wherein the communication controller can control a plurality of tracking controllers. The technology that the communication controller integrates sensor equipment such as an anemometer, a snow depth meter and an irradiator is researched, various extreme weather type judging strategies are integrated, various extreme weather is timely identified, and corresponding protection instructions are sent to the tracking controller. And the communication between the communication controller and the intelligent equipment monitoring platform is researched, so that the function of forwarding the intelligent tracking algorithm optimization instruction and the platform remote control is realized.
Since the specific implementation of the steps of the photovoltaic tracking method based on the micro-spatio-temporal scale irradiation prediction has been described in detail in embodiment 1, no further description is given here.
The processor 1001 is (Central Processing Unit ). The memory 1002 is connected to the processor 1001 through a system bus and performs communication with each other, the memory 1002 is configured to store a computer program, and the processor 1001 is configured to execute the computer program, so that the processor 1001 performs the photovoltaic tracking method based on the micro space-time scale irradiation prediction. The memory 1002 may include a random access memory (Random Access Memory, simply referred to as RAM), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory.
Furthermore, the present embodiment also provides a computer-readable storage medium, on which a computer program is stored, which when executed by the processor 1001 implements the steps in the micro spatiotemporal irradiation prediction based photovoltaic tracking method described in embodiment 1. Embodiment 1 has already described the photovoltaic tracking method based on the micro-space-time scale irradiation prediction in detail, and will not be described herein.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by computer program related hardware. The aforementioned computer program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
In conclusion, the method can solve the problems that the real-time sensing mode can not meet the irradiation change trend quantification requirement of the photovoltaic tracking system and the scattered irradiation tracking inaccuracy exists in the astronomical algorithm of the tracking system. The cloud layer multidimensional characteristic parameters affecting the ground drop shadow characteristic are extracted through collecting the multi-view foundation cloud image, a characteristic parameter and irradiation attenuation intensity relation model is established, the micro-space-time scale solar irradiation distribution of a photovoltaic power station area is predicted, the solar scattering and direct irradiation prediction is included, the power generation output corresponding to different tracking angles is calculated, an efficient intelligent tracking algorithm under the complex weather condition is established, and the power generation capacity of the system is improved compared with that of a conventional astronomical algorithm tracking system by adopting a tracking electric control system and a mechanical structure. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims of this invention, which are within the skill of those skilled in the art, be included within the spirit and scope of this invention.
Claims (10)
1. A photovoltaic tracking method based on micro space-time scale irradiation prediction is characterized by comprising the following steps of: the method comprises the following steps:
acquiring foundation cloud image data and ground irradiation data, and acquiring plane characteristics and three-dimensional characteristics of cloud layers based on the foundation cloud image data and the ground irradiation data;
determining a movement track of cloud shadows in a deployment area according to the solar position relationship and the cloud characteristics;
establishing an irradiance space-time sequence prediction model based on deep learning according to a motion track of cloud layer shadows in a deployment area, so as to obtain irradiance space-time sequence prediction results of a whole time period according to the irradiance space-time sequence prediction model;
and establishing a tracking bracket assembly inclined plane irradiation calculation model based on the irradiance space-time sequence prediction result, and calculating assembly power generation output of each tracking angle based on the tracking bracket assembly inclined plane irradiation calculation model.
2. The photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction according to claim 1, characterized in that: the obtaining the plane characteristics and the three-dimensional characteristics of the cloud layer based on the foundation cloud image data and the ground irradiation data comprises the following steps:
according to the data correlation between the cloud image characteristics and the irradiation attenuation data, determining cloud layer planes and three-dimensional cloud image characteristics with strong influence factors;
establishing a cloud layer vector motion model based on the foundation cloud image data, and acquiring plane displacement change characteristics of a cloud layer in a cloud image;
and determining the positions of the same cloud layer in different cloud pictures through feature matching, and estimating the height features of the three-dimensional substrate of the cloud layer.
3. The photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction according to claim 1 or 2, characterized in that: according to the solar position relationship and the cloud layer characteristics, determining the movement track of the cloud layer shadow in the deployment area comprises the following steps:
calculating the spatial position of the sun at any moment by utilizing a sun position algorithm, constructing a relative motion model of the sun and the cloud layer by combining real motion vector information of the cloud layer, and establishing a projection function relation from sky cloud layer motion to ground shadow motion;
And identifying cloud layer edge points which reach the deployment area earliest and cloud layer edge points which leave the deployment area last, calculating ground shadow edge points corresponding to the cloud layer edge points according to the projection function relation, and calculating the time when the cloud layer shadow edge points reach and leave the deployment area so as to determine the movement track of the cloud layer shadow in the deployment area.
4. A photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction according to claim 3, characterized in that: the establishing the irradiance space-time sequence prediction model based on the deep learning comprises the following steps:
according to the motion trail of cloud shadows in the deployment area, measuring the spatial nonlinear correlation of the time irradiance data, and obtaining a spatial nonlinear correlation measurement rule;
and establishing an irradiance space-time sequence prediction model based on deep learning based on irradiance space-time sequence data and the space nonlinear correlation measurement rule.
5. The photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction according to claim 4, characterized in that: the step of obtaining the spatial nonlinear correlation measurement rule according to the spatial nonlinear correlation measurement of the time irradiance data according to the motion trail of the cloud layer shadow in the deployment area comprises the following steps:
According to the movement track of the cloud layer shadow in the deployment area, extracting time sequence data of irradiance sensor nodes on a track path in a shadow propagation period;
according to the abrupt change information of irradiance on time sequence, analyzing the change condition of three states of each node before shading, during shading and after shading;
and calculating the spatial correlation among the nodes according to the change condition, analyzing the spatial correlation change rule under the condition of different shadow tracks, and further obtaining the spatial nonlinear correlation measurement rule.
6. The photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction according to claim 4, characterized in that: the establishing the irradiance space-time sequence prediction model based on deep learning based on irradiance space-time sequence data and the spatial nonlinear correlation measurement rule comprises the following steps:
converting irradiance space-time sequence data into a space-time diagram data structure, and connecting space diagrams of adjacent time steps into space-time diagrams;
according to the space nonlinear correlation measurement rule, extracting space-time characteristics of the current time step range, and carrying out irradiance prediction on each graph node;
and according to the time and the motion trail of the cloud layer shadow entering and exiting the deployment area, deploying a plurality of space-time diagram convolution modules in a plurality of time periods before, during and after shadow shielding, capturing the heterogeneity of space-time data in a longer time range, and finally obtaining irradiance space-time sequence prediction results in all time periods.
7. The photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction according to claim 1 or 6, characterized in that: the establishing a tracking bracket component inclined plane irradiation calculation model based on the irradiance space-time sequence prediction result comprises the following steps:
constructing a direct and scattered radiation distribution model based on the ground-day relation, the radiation intensity and the distribution weight of the irradiance space-time sequence prediction result, and dividing the area below the component into a plurality of shadow areas and light areas;
and respectively calculating the irradiation intensity and distribution of the earth surface shadow region and the bright region reflected to the back surface of the tracking bracket assembly, and calculating the irradiation intensity and distribution of the front surface of the tracking bracket assembly so as to construct an inclined surface irradiation calculation model of the tracking bracket assembly.
8. The photovoltaic tracking method based on micro-spatiotemporal scale irradiation prediction of claim 7, characterized in that: further comprises:
calculating the power generation output of the component of each tracking angle, and establishing a tracking algorithm by iterative optimization so that the bracket operates at the angle of the optimal power generation output;
calculating the power generation of the components of the support under different angles and the power generation loss of the components under the shielding condition, and determining the optimal inverse tracking angle of each row of components for avoiding the shielding loss according to the difference of the topography environments of the adjacent tracking supports of each row;
And iteratively calculating the power generation output and shielding mismatch loss of each angle of the tracking bracket based on the irradiance space-time sequence prediction result and the tracking bracket assembly inclined plane irradiation calculation model, so as to realize the optimization of the tracking angle.
9. A photovoltaic tracking system based on micro-spatiotemporal scale irradiance prediction, comprising:
the foundation cloud picture acquisition system is used for acquiring foundation cloud picture data; the foundation cloud picture acquisition system at least comprises a fisheye lens, a CCD camera and a microcomputer processor;
the meteorological acquisition system is used for acquiring ground irradiation data; the meteorological acquisition system at least comprises a temperature sensor, an radiometer and an air velocity meter;
the tracking bracket monitoring system is respectively connected with the foundation cloud image acquisition system and the meteorological acquisition system and is used for acquiring and monitoring data of the photovoltaic system; the tracking bracket monitoring system comprises a tracking controller and a communication controller;
the component power generation monitoring system is used for monitoring power generation of the photovoltaic system; the assembly power generation monitoring system at least comprises an inverter, a power tester and a tour detector;
the control management system is respectively connected with the foundation cloud image acquisition system, the meteorological acquisition system, the tracking bracket monitoring system and the component power generation monitoring system, and comprises a memory for storing a computer program; at least one processor for running the computer program to implement the steps of the micro-spatio-temporal scale irradiation prediction based photovoltaic tracking method of any of claims 1 to 6.
10. A computer storage medium storing program instructions, characterized by: the program instructions, when executed, implement the steps of a micro-spatiotemporal radiation prediction based photovoltaic tracking method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211514186.3A CN116192005A (en) | 2022-11-29 | 2022-11-29 | Photovoltaic tracking method, system and medium based on micro space-time scale irradiation prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211514186.3A CN116192005A (en) | 2022-11-29 | 2022-11-29 | Photovoltaic tracking method, system and medium based on micro space-time scale irradiation prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116192005A true CN116192005A (en) | 2023-05-30 |
Family
ID=86431440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211514186.3A Pending CN116192005A (en) | 2022-11-29 | 2022-11-29 | Photovoltaic tracking method, system and medium based on micro space-time scale irradiation prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116192005A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117220597A (en) * | 2023-11-08 | 2023-12-12 | 徐州工程学院 | Quick frequency response rate monitoring system of photovoltaic power station |
-
2022
- 2022-11-29 CN CN202211514186.3A patent/CN116192005A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117220597A (en) * | 2023-11-08 | 2023-12-12 | 徐州工程学院 | Quick frequency response rate monitoring system of photovoltaic power station |
| CN117220597B (en) * | 2023-11-08 | 2024-01-30 | 徐州工程学院 | Quick frequency response rate monitoring system of photovoltaic power station |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11748946B2 (en) | Solar access measurement | |
| US20140083413A1 (en) | Method and apparatus for mapping cloud shading on the ground in a large area | |
| US11830137B2 (en) | Automated three-dimensional building model estimation | |
| WO2017193153A1 (en) | Solar power forecasting | |
| CN113378459B (en) | Photovoltaic power station ultra-short-term power prediction method based on satellite and internet of things information | |
| WO2015104281A1 (en) | Solar irradiance forecasting | |
| CA2798827A1 (en) | Systems and methods for forecasting solar power | |
| CN110514298B (en) | Solar radiation intensity calculation method based on foundation cloud picture | |
| US10989839B1 (en) | Ground-based sky imaging and irradiance prediction system | |
| CN107133685B (en) | Method and system for predicting power generation capacity of photovoltaic power generation system | |
| CN111079073A (en) | Building three-dimensional solar potential calculation method | |
| Lonij et al. | Forecasts of PV power output using power measurements of 80 residential PV installs | |
| Dissawa et al. | Sky image-based localized, short-term solar irradiance forecasting for multiple pv sites via cloud motion tracking | |
| CN103712685B (en) | Photovoltaic array irradiance measurement identification method | |
| CN116192005A (en) | Photovoltaic tracking method, system and medium based on micro space-time scale irradiation prediction | |
| Quinn | Energy gleaning for extracting additional energy and improving the efficiency of 2-axis time-position tracking photovoltaic arrays under variably cloudy skies | |
| CN108008633A (en) | Irradiation level comprising a variety of Changes in weather and photovoltaic module coordinate incidence relation method for building up | |
| Vega-Garita et al. | A practical method for considering shading on photovoltaics systems energy yield | |
| Han et al. | Use of UAV Photogrammetry to Estimate the Solar Energy Potential of Residential Buildings in Severe Cold Region | |
| Bill et al. | 3D Model for Solar Energy Potential on Buildings from Urban LiDAR Data. | |
| Mengen et al. | Solar Irradiance Measuring sites in Bangladesh | |
| CN204442542U (en) | A kind of mobile power transmission line shaft tower region mountain fire and disaster of mountain massif coast on-line monitoring system | |
| Li | Development of an IoT Based Photovoltaic Monitoring System Using Hybrid Modeling | |
| Baig | Evaluating the Tree Shading Effect on Solar PV Panels to Maximize the Energy Production using LIDAR Data | |
| Grubesic et al. | Unmanned aerial systems for energy infrastructure assessment |
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 |