CN116896116B - Solar grid-connected regulation and control method and system based on artificial intelligence - Google Patents
Solar grid-connected regulation and control method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN116896116B CN116896116B CN202311166409.6A CN202311166409A CN116896116B CN 116896116 B CN116896116 B CN 116896116B CN 202311166409 A CN202311166409 A CN 202311166409A CN 116896116 B CN116896116 B CN 116896116B
- Authority
- CN
- China
- Prior art keywords
- output power
- maximum output
- day
- prediction result
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 25
- 239000011159 matrix material Substances 0.000 claims abstract description 21
- 230000007613 environmental effect Effects 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000005286 illumination Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 5
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000010248 power generation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
- H02J2300/26—The renewable source being solar energy of photovoltaic origin involving maximum power point tracking control for photovoltaic sources
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Photovoltaic Devices (AREA)
Abstract
The application relates to the field of solar grid-connected regulation and control, in particular to a solar grid-connected regulation and control method and system based on artificial intelligence, wherein the method comprises the following steps: calculating shadow shielding degree according to the acquired image data, and constructing a four-dimensional environment vector according to the shadow shielding degree, the temperature, the voltage and the current of the solar cell panel to obtain an environment matrix; calculating an environment complexity index according to the environment matrix; constructing a first prediction model and obtaining a first prediction result of the maximum output power; constructing and training a second prediction model according to the collected historical data, and calculating a second prediction result of the maximum output power; and constructing a third prediction model of the maximum output power according to the first prediction result and the second prediction result, generating a third prediction result of the maximum output power, and adjusting the preset output power of the inverter to be the third prediction result. The method combines the influence of the environmental complexity on the maximum output power of the solar panel, and has the effect of improving the accuracy of the maximum output power result.
Description
Technical Field
The application relates to the field of solar grid-connected regulation and control, in particular to a solar grid-connected regulation and control method and system based on artificial intelligence.
Background
The solar grid connection refers to connecting a solar power generation system with a power grid, and directly injecting the generated electric energy of the solar power generation system into the power grid for other users to use. Solar grid connection is of two types: one is a micro grid, i.e. a solar power system is connected to a small-scale grid, such as a solar power system is connected to a single building or micro community; the other is a large-scale power grid, which connects a solar power generation system with a power grid in the whole country or region. Solar grid connection can help to reduce dependence on traditional fossil fuels, reduce pollution emission, improve energy utilization efficiency, and promote sustainable development in the renewable energy field.
In the method for tracking and controlling the maximum power point of solar photovoltaic grid-connected power generation provided by the Chinese patent with the publication number of CN102130631B, the current output voltage and current of the photovoltaic cell are detected, the output power is compared with the power at the previous moment, and the duty ratio is changed until the output power reaches a minimum area near the maximum point, so that the maximum power point is predicted. The maximum power point is an operation state in which the maximum power can be output in the solar cell panel or other energy source device.
However, the influence of weather changes on the maximum output power of the solar panel is not considered in the prior art, and the result is obtained by continuous iterative calculation, so that the maximum output power prediction result is inaccurate.
Disclosure of Invention
In order to combine the influence of environmental complexity on the maximum output power of the solar cell panel and improve the accuracy of the maximum output power result, the application provides a solar grid-connected regulation and control method and system based on artificial intelligence.
In a first aspect, the application provides a solar grid-connected regulation and control method based on artificial intelligence, which adopts the following technical scheme:
the solar grid-connected regulation and control method based on artificial intelligence comprises the following steps: calculating shadow shielding degree according to the acquired image data, and constructing a four-dimensional environment vector according to the shadow shielding degree, the acquired temperature, voltage and current of the solar cell panel to obtain an environment matrix from 0 to i; according to the environment matrix, calculating an environment complexity index, wherein the calculation formula of the environment complexity index is as follows:
，/>wherein, the day of record is set as day a, < > on>An environmental complexity index from 0 to i time, < +.>An initial value of the environmental complexity index from 0 to i time,/-, for>Cosine similarity, < >>For the characteristic value sequence of the environment matrix on day a,/i>A characteristic value sequence of the environment matrix on the nth day; constructing a first prediction model and obtaining a first prediction result of maximum output power, wherein the first prediction model comprises the following polynomials:wherein->As a first prediction result of the maximum output power at the (i+1) th day of the a-th,maximum output power at the (i+1) th day; />The weight of the maximum output power at the time i+1 of the nth day; constructing and training a second prediction model according to the collected historical data, and calculating a second prediction result of the maximum output power; constructing a third prediction model of the maximum output power, generating a third prediction result of the maximum output power, and adjusting the preset inverter output power to be the third prediction result, wherein the third prediction model comprises the following polynomials:wherein->Third prediction result representing maximum output power, +.>For the second prediction of maximum output power, +.>Is the first predicted result of maximum output power.
By adopting the technical scheme, the influence of the environment on the solar panel is considered, the environment complexity index is set, and a first prediction model is constructed according to the environment complexity index and the historical maximum output power of the solar panel, so that a first prediction result of the maximum output power of the solar panel at the next moment is obtained. When the environment of the solar panel is unstable, the first prediction result may deviate, the second prediction model is built and trained by collecting the historical maximum output power of the solar panel, the third prediction model is built by combining the first prediction model and the second prediction model, the third prediction result of the maximum output power is obtained, and the effect of the accuracy of the maximum output power result is improved.
Optionally, in the constructing of the first prediction model, the method includes the following steps: obtaining the maximum output power at the moment of the m day i according to the real-time maximum output power of the collected solar cell panel; constructing a weight model of maximum output power, wherein the weight model comprises the following polynomials:
wherein->Maximum output power weight at time i+1 on day m, < >>For the pearson coefficient calculation, +.>For the maximum output power at time m, day i, < >>Maximum output at time m 0Power (I)>Maximum output power at time a, day i, < >>For maximum output power at time a, day 0, m is { a-1, a-2, a-3, a-4}; and constructing the first prediction model and obtaining the first prediction result.
By adopting the technical proposal, the utility model has the advantages that,the larger it is, the more similar the maximum output power variation from 0 to i on day m is to that on day a. .
Optionally, the constructing and training a second prediction model according to the collected historical data, and calculating a second prediction result of the maximum output power includes: set of maximum output powerThe first 90% of data are used as training sets and the last 10% are used as test sets in the order of the date from the morning to the evening.
By adopting the technical scheme, the aim of training a model is fulfilled, and the set of maximum output power on the same day is adoptedThe data changes within are predicted.
Optionally, the calculating the shadow shielding degree according to the acquired image data includes the following steps:
converting the image data into a gray scale image; setting a gray image sample, marking the pixel value of a shadow area in the gray image sample as 0, and marking the pixel value of an illumination area as 1 to obtain label data of the gray image sample; and calculating the proportion of the label data pixel points to obtain the shadow shielding degree.
By adopting the technical scheme, the purpose of calculating the shadow shielding degree is achieved, and the shadow shielding degree can reflect the influence degree of the shadow on illumination in the environment of the solar cell panel.
In a second aspect, the application provides an artificial intelligence-based solar grid-connected regulation and control system, which adopts the following technical scheme:
solar grid-connected regulation and control system based on artificial intelligence includes: the solar grid-connected control system comprises a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions realize the artificial intelligence-based solar grid-connected control method when executed by the processor.
By adopting the technical scheme, the solar grid-connected regulation and control method based on the artificial intelligence generates a computer program, and the computer program is stored in the memory to be loaded and executed by the processor, so that terminal equipment is manufactured according to the memory and the processor, and the use is convenient.
The application has the following technical effects:
1. setting an environment complexity index in consideration of the influence of the environment on the solar panel, and constructing a first prediction model according to the environment complexity index and the historical maximum output power of the solar panel to obtain a first prediction result of the maximum output power of the solar panel at the next moment. When the environment of the solar panel is unstable, the first prediction result may deviate, the second prediction model is built and trained by collecting the historical maximum output power of the solar panel, the third prediction model is built by combining the first prediction model and the second prediction model, the third prediction result of the maximum output power is obtained, and the effect of the accuracy of the maximum output power result is improved.
2. And at the next moment of obtaining the third predicted result, regulating the output power to be the third predicted result through the inverter, so that the solar cell panel is in a high-efficiency running state, and the instantaneity and the accuracy of maximum output power regulation are improved.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the application are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a flow chart of a method of steps S1-S5 in an artificial intelligence based solar grid-connected regulation method according to an embodiment of the application.
FIG. 2 is a flowchart of a method for steps S10-S12 in an artificial intelligence based solar grid-connected control method according to an embodiment of the application.
FIG. 3 is a flowchart of a method for steps S30-S32 in an artificial intelligence based solar grid-connected control method according to an embodiment of the application.
FIG. 4 is a logic framework diagram of an artificial intelligence based solar grid-connected regulation system in accordance with an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be understood that when the terms "first," "second," and the like are used in the claims, the specification and the drawings of the present application, they are used merely for distinguishing between different objects and not for describing a particular sequential order. The terms "comprises" and "comprising" when used in the specification and claims of the present application are taken to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The embodiment of the application discloses a solar grid-connected regulation and control method based on artificial intelligence, which comprises the following steps S1-S5, wherein the method specifically comprises the following steps:
s1: according to the acquired image data, calculating shadow shielding degree, and constructing a four-dimensional environment vector according to the shadow shielding degree, the acquired temperature, voltage and current of the solar cell panel to obtain an environment matrix from 0 to i.
Referring to fig. 2, calculating the shadow mask level from the acquired image data in step S1 includes steps S10 to S12, specifically as follows:
s10: the image data is converted into a grayscale image.
The method includes photographing a solar panel through a CCD camera to collect image data of the solar panel, and performing gray level conversion to obtain a real-time gray level image of the solar panel, wherein the CCD camera is a camera using a Charge-Coupled Device (CCD) as an image sensor.
S11: setting a gray image sample, marking the pixel value of a shadow area in the gray image sample as 0, and marking the pixel value of an illumination area as 1 to obtain label data of the gray image sample.
Taking a plurality of collected solar panel gray level images as gray level image samples, marking the pixel value of a shadow area in one solar panel gray level image sample as 0, marking the pixel value of an illumination area as 1 to obtain the label data of the solar panel gray level image sample, and calculating the proportion of the pixel points of the label data (0, 1) on the gray level image to obtain the shadow shielding degree.
S12: and calculating the proportion of the pixel points of the tag data to obtain the shadow shielding degree.
After the shadow shielding degree is obtained, the shadow shielding degree is recorded as S, and a four-dimensional environment vector is constructed by combining the temperature, the voltage and the current of the collected solar cell panel, specifically, the real-time current of the solar cell panel is measured through a high-precision multipurpose electric power meter and recorded as I; measuring the real-time voltage of the solar panel by a digital voltmeter, and recording the real-time voltage as V; measuring the real-time temperature of the solar panel by a thermometer, and marking the real-time temperature as T;
an illumination environment vector is constructed, wherein the illumination environment vector is a four-dimensional environment vector constructed by shadow shielding degree S, temperature T, voltage V and current I at the same moment, an environment vector from the initial moment 0 to the current moment I is obtained, a 4 Xn environment matrix is formed according to time sequencing, the day is taken as a period, and the initial moment is 0 point moment. Thereby, an environment matrix of 0 to i time is obtained.
The shielding of the household solar panel is mainly divided into fixed shielding and random shielding. The fixed shielding sources are buildings and plants. The household solar cell panel has a complex use environment, buildings or trees exist around the solar cell panel, the buildings can block the projection of sunlight to the solar cell panel, the sunlight irradiation angle change is small in a plurality of adjacent days, the change can be ignored, and the illumination received by the solar cell panel shows regular change. The random shielding source is the clouds, and the clouds can randomly shield the illumination of the solar cell panel under the influence of wind power.
Since the maximum output power of the solar panel is directly affected by the shadow mask level s, the temperature T, the voltage V, and the current I in the environment matrix, it is necessary to judge the degree of environmental change of the solar panel. The quantitative judgment of the change of the environmental change degree of the solar cell panel is carried out by an environmental complexity index, and the method comprises the following step S2:
s2: and calculating an environment complexity index according to the environment matrix.
Specifically, taking an environment matrix from the moment 0 to the moment i of the day as an example, calculating the eigenvalue of the square matrix, and recording the eigenvalue as an eigenvalue sequence of the environment matrix at the moment i.
The stationary shielding suffered by the household solar panel due to the small change in the angle of sunlight irradiation within several adjacent days can be considered as a stable change. Random shielding is affected by weather changes, so that the similarity between adjacent days and the weather changes of the same day is preferentially compared, and the more similar the two are, the more stable the weather changes are.
The application sets the comparison period as four days, calculates the characteristic value sequence of the environmental matrix from 0 to i time per day in the first four days by using the method for calculating the characteristic value sequence, records the current day as the a day, and the characteristic value sequences of the first four days are respectively。
The environment complexity index is constructed, and the calculation formula of the environment complexity index is as follows:
wherein the recording day is set as the a-th day,an environmental complexity index from 0 to i time, < +.>An initial value of the environmental complexity index from 0 to i time,/-, for>Cosine similarity, < >>Is the eigenvalue sequence of the environment matrix of the a day,is the eigenvalue sequence of the environment matrix of the nth day.
Environmental complexity indexThe larger indicates that the more stable the environmental change from day 0 to i,/is>The smaller the environmental change from day 0 to i, the less stable the environment change.
S3: and constructing a first prediction model and obtaining a first prediction result of the maximum output power.
Solar panels are subject to environmental complexity such that the maximum output power varies unstably. In combination with the environmental complexity index and the collected data, a first prediction model is constructed, and referring to fig. 3, step S3 includes steps S30 to S32, specifically as follows:
s30: and obtaining the maximum output power at the m-th day i according to the real-time maximum output power of the collected solar cell panel.
The real-time maximum output power of the solar panel is recorded by a maximum power point tracking controller (Maximum Power Point Tracking Controller, mppt) to obtain the maximum output power at the moment iThe superscript i is the i-th moment and the subscript m is the m-th day.
S31: and constructing a weight model of the maximum output power.
The weight model includes the following polynomials:
wherein,maximum output power weight at time i+1 on day m, < >>For the pearson coefficient calculation, +.>Maximum output power for day m, +.>Maximum output power at time i on day m, < >>Maximum output power at day 0 of m, +.>Maximum output power at time a, day i, < >>For maximum output power at time 0 on day a, m is { a-1, a-2, a-3, a-4}.
The larger it is, the more similar the maximum output power variation from 0 to i on day m is to that on day a. Obtain the weight of maximum output power of four days in comparison period +.>。
S32: and constructing a first prediction model and obtaining a first prediction result.
The first predictive model includes the following polynomials:
wherein,for the first prediction of maximum output power at time i+1 on day a,/o>Maximum output power at the (i+1) th day; />The weight of the maximum output power at time i+1 on the nth day.
When the environment of the solar cell panel is unstable, the first prediction result of the maximum output power is inaccurate in prediction, and a second prediction model is set, specifically as follows:
s4: and constructing and training a second prediction model according to the collected historical data, and calculating a second prediction result of the maximum output power.
Specifically, the prediction was made on day a using a back propagation neural network (Backpropagation Neural Network, bp).
The input of the bp neural network is the set of maximum output power from 0 to i time. Set maximum output power->The first 90% of data are used as training sets and the last 10% are used as test sets in the order of the date from the morning to the evening. The loss function uses a mean square error loss function. Maximum output power +.>。
In using Bp neural networks for steady prediction, i.e. based on the set of maximum output powers on the same dayThe data change in the solar panel is predicted, and the reference to the past history data is lacking, so that the predicted data is relative to the step ∈>The prediction accuracy is low.
S5: and constructing a third prediction model of the maximum output power according to the first prediction result and the second prediction result, generating a third prediction result of the maximum output power, and adjusting the preset output power of the inverter to be the third prediction result.
The third predictive model includes the following polynomials:
wherein,third prediction result representing maximum output power, +.>For the second prediction of maximum output power, +.>Is the first predicted result of maximum output power.
w is the final predicted maximum output power, and the historical data change and the neural network prediction result are combined. And regulating the output power to be the maximum output power w through the inverter at the next moment according to the obtained final predicted maximum output power w, so that the solar panel is in a state of high-efficiency operation.
The implementation principle of the solar grid-connected regulation and control method based on artificial intelligence in the embodiment of the application is as follows: setting an environment complexity index in consideration of the influence of the environment on the solar panel, and constructing a first prediction model according to the environment complexity index and the historical maximum output power of the solar panel to obtain a first prediction result of the maximum output power of the solar panel at the next moment. When the environment of the solar panel is unstable, the first prediction result may deviate, the second prediction model is built and trained by collecting the historical maximum output power of the solar panel, the third prediction model is built by combining the first prediction model and the second prediction model, the third prediction result of the maximum output power is obtained, and the effect of the accuracy of the maximum output power result is improved.
The embodiment of the application also discloses a solar grid-connected regulation system based on artificial intelligence, and referring to fig. 4, the solar grid-connected regulation system comprises a processor and a memory, wherein the memory stores computer program instructions, and the solar grid-connected regulation method based on artificial intelligence is realized when the computer program instructions are executed by the processor.
The above system further comprises other components well known to those skilled in the art, such as a communication bus and a communication interface, the arrangement and function of which are known in the art and therefore are not described in detail herein.
In the context of this patent, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistive random access memory RRAM (ResistiveRandomAccessMemory), dynamic random access memory DRAM (DynamicRandomAccessMemory), static random access memory SRAM (static random access memory), enhanced dynamic random access memory EDRAM (EnhancedDynamicRandomAccessMemory), high-bandwidth memory HBM (High-bandwidth memory), hybrid storage cube HMC (HybridMemoryCube), etc., or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device. Any of the applications or modules described herein may be implemented using computer-readable/executable instructions that may be stored or otherwise maintained by such computer-readable media.
While various embodiments of the present application have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the application. It should be understood that various alternatives to the embodiments of the application described herein may be employed in practicing the application.
The above embodiments are not intended to limit the scope of the present application, so: all equivalent changes in structure, shape and principle of the application should be covered in the scope of protection of the application.
Claims (5)
1. The solar grid-connected regulation and control method based on artificial intelligence is characterized by comprising the following steps:
calculating shadow shielding degree according to the acquired image data, and constructing a four-dimensional environment vector according to the shadow shielding degree, the acquired temperature, voltage and current of the solar cell panel to obtain an environment matrix from 0 to i;
according to the environment matrix, calculating an environment complexity index, wherein the calculation formula of the environment complexity index is as follows:
wherein the recording day is set as the a-th day,an environmental complexity index from 0 to i time, < +.>An initial value of the environmental complexity index from 0 to i time,/-, for>Cosine similarity, < >>For the characteristic value sequence of the environment matrix on day a,/i>A characteristic value sequence of the environment matrix on the nth day;
constructing a first prediction model and obtaining a first prediction result of maximum output power, wherein the first prediction model comprises the following polynomials:
wherein,for the first prediction of maximum output power at time i+1 on day a,/o>Maximum output power at the (i+1) th day; />The weight of the maximum output power at the time i+1 of the nth day;
constructing and training a second prediction model according to the collected historical data, and calculating a second prediction result of the maximum output power;
constructing a third prediction model of the maximum output power according to the first prediction result and the second prediction result, generating a third prediction result of the maximum output power, and adjusting the preset inverter output power to be the third prediction result, wherein the third prediction model comprises the following polynomials:
wherein,third prediction result representing maximum output power, +.>As a second prediction result of the maximum output power,is the first predicted result of maximum output power.
2. The solar grid-connected control method based on artificial intelligence according to claim 1, wherein the construction of the first prediction model comprises the following steps:
obtaining the maximum output power at the moment of the m day i according to the real-time maximum output power of the collected solar cell panel;
constructing a weight model of maximum output power, wherein the weight model comprises the following polynomials:
wherein,maximum output power weight at time i+1 on day m, < >>For the pearson coefficient calculation, +.>For the maximum output power at time m, day i, < >>Maximum output power at day 0 of m, +.>Maximum output power at time a, day i, < >>For maximum output power at time a, day 0, m is { a-1, a-2, a-3, a-4};
and constructing the first prediction model and obtaining the first prediction result.
3. The artificial intelligence based solar grid-connected control method according to claim 2, wherein the constructing and training a second prediction model according to the collected historical data, calculating a second prediction result of the maximum output power, comprises: set of maximum output powerThe first 90% of data are used as training sets and the last 10% are used as test sets in the order of the date from the morning to the evening.
4. The artificial intelligence based solar grid-tie control method according to any one of claims 1 to 3, wherein the calculating the shadow mask according to the collected image data comprises the steps of:
converting the image data into a gray scale image;
setting a gray image sample, marking the pixel value of a shadow area in the gray image sample as 0, and marking the pixel value of an illumination area as 1 to obtain label data of the gray image sample;
and calculating the proportion of the label data pixel points to obtain the shadow shielding degree.
5. Solar grid-connected regulation and control system based on artificial intelligence, characterized by comprising: a processor and a memory storing computer program instructions that when executed by the processor implement the artificial intelligence based solar grid tie regulation method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311166409.6A CN116896116B (en) | 2023-09-11 | 2023-09-11 | Solar grid-connected regulation and control method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311166409.6A CN116896116B (en) | 2023-09-11 | 2023-09-11 | Solar grid-connected regulation and control method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116896116A CN116896116A (en) | 2023-10-17 |
| CN116896116B true CN116896116B (en) | 2023-11-28 |
Family
ID=88311145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311166409.6A Active CN116896116B (en) | 2023-09-11 | 2023-09-11 | Solar grid-connected regulation and control method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116896116B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2891904A1 (en) * | 2014-01-07 | 2015-07-08 | ABB Technology AB | Solar irradiance forecasting |
| CN106059492A (en) * | 2016-05-05 | 2016-10-26 | 江苏方天电力技术有限公司 | Photovoltaic assembly shadow fault type determination method based on power prediction |
| CN107562992A (en) * | 2017-07-25 | 2018-01-09 | 华南理工大学 | A kind of Photovoltaic array maximum power tracking method based on SVM and particle cluster algorithm |
| CN109934423A (en) * | 2019-04-25 | 2019-06-25 | 山东大学 | Predicting power of photovoltaic plant method and system based on gird-connected inverter operation data |
| CN113470016A (en) * | 2021-08-31 | 2021-10-01 | 江苏裕荣光电科技有限公司 | Photovoltaic cell panel abnormity detection method and device based on artificial intelligence |
| CN115579858A (en) * | 2022-08-31 | 2023-01-06 | 武汉城市职业学院 | Photovoltaic power generation power prediction method based on time-sharing gating circulation unit |
-
2023
- 2023-09-11 CN CN202311166409.6A patent/CN116896116B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2891904A1 (en) * | 2014-01-07 | 2015-07-08 | ABB Technology AB | Solar irradiance forecasting |
| CN106059492A (en) * | 2016-05-05 | 2016-10-26 | 江苏方天电力技术有限公司 | Photovoltaic assembly shadow fault type determination method based on power prediction |
| CN107562992A (en) * | 2017-07-25 | 2018-01-09 | 华南理工大学 | A kind of Photovoltaic array maximum power tracking method based on SVM and particle cluster algorithm |
| CN109934423A (en) * | 2019-04-25 | 2019-06-25 | 山东大学 | Predicting power of photovoltaic plant method and system based on gird-connected inverter operation data |
| CN113470016A (en) * | 2021-08-31 | 2021-10-01 | 江苏裕荣光电科技有限公司 | Photovoltaic cell panel abnormity detection method and device based on artificial intelligence |
| CN115579858A (en) * | 2022-08-31 | 2023-01-06 | 武汉城市职业学院 | Photovoltaic power generation power prediction method based on time-sharing gating circulation unit |
Non-Patent Citations (2)
| Title |
|---|
| Accurate Simulation of MPPT Methods Performance When Applied to Commercial Photovoltaic Panels;Javier Cubas等;《Electrification and Renewable Energy Generation》;第1-16页 * |
| 特定舆情的意见领袖挖掘和关键传播路径预测;徐雅斌 等;《数据分析与知识发现》(第2期);第32-42页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116896116A (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109902863B (en) | Wind speed prediction method and device based on multi-factor time-space correlation | |
| Zhang et al. | Memetic reinforcement learning based maximum power point tracking design for PV systems under partial shading condition | |
| Nguyen et al. | High PV penetration impacts on five local distribution networks using high resolution solar resource assessment with sky imager and quasi-steady state distribution system simulations | |
| Chen et al. | Calculation of the optimum installation angle for fixed solar-cell panels based on the genetic algorithm and the simulated-annealing method | |
| Dong et al. | A general radial basis function neural network assisted hybrid modeling method for photovoltaic cell operating temperature prediction | |
| Kurokawa | Energy from the desert: practical proposals for very large scale photovoltaic systems | |
| CN112561058B (en) | Short-term photovoltaic power prediction method based on Stacking-integrated learning | |
| CN105354655B (en) | Photovoltaic power station group confidence capacity evaluation method considering power correlation | |
| Kurokawa | Energy from the Desert: Feasibility of Very Large Scale Power Generation (VLS-PV) Systems | |
| CN112070311A (en) | Day-ahead light power prediction method based on similar day clustering and meteorological factor weighting | |
| Schmelas et al. | Photovoltaics energy prediction under complex conditions for a predictive energy management system | |
| Kanchana et al. | PV Power Forecasting with Holt-Winters Method | |
| Herlambang et al. | Numerical estimation of photovoltaic–electrolyzer system performance on the basis of a weather database | |
| Dou et al. | Elman neural network based short-term photovoltaic power forecasting using association rules and kernel principal component analysis | |
| Bai et al. | Investigation on photovoltaic array modeling and the MPPT control method under partial shading conditions | |
| CN116896116B (en) | Solar grid-connected regulation and control method and system based on artificial intelligence | |
| El Kounni et al. | Solar power output forecasting using Artificial Neural Network | |
| Zhang et al. | Joint forecasting of regional wind and solar power based on attention neural network | |
| Elena et al. | Multi-agent system for smart grids with produced energy from photovoltaic energy sources | |
| Shi et al. | Short-term photovoltaic power forecast based on long short-term memory network | |
| CN113178896B (en) | Method and system for configuring installed capacity of fixed-output light-storage combined power station | |
| CN111798034B (en) | Wind power prediction system and prediction method based on wind flow field space-time image learning | |
| Han et al. | Electrical performance and power prediction of a roll-bond photovoltaic thermal array under dewing and frosting conditions | |
| Khalil et al. | Verification of Solar Energy Measurements by (ERA-5) and Its Impact on Electricity Costs in North Africa | |
| Bobkov et al. | Simulation of photovoltaic module operation modes and tilt angle optimization according to the criterion of maximum electricity generation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |