CN113689045B - Photovoltaic area grid-connected electric quantity prediction method, device and medium - Google Patents
Photovoltaic area grid-connected electric quantity prediction method, device and medium Download PDFInfo
- Publication number
- CN113689045B CN113689045B CN202110997927.7A CN202110997927A CN113689045B CN 113689045 B CN113689045 B CN 113689045B CN 202110997927 A CN202110997927 A CN 202110997927A CN 113689045 B CN113689045 B CN 113689045B
- Authority
- CN
- China
- Prior art keywords
- data
- time
- power generation
- photovoltaic
- grid
- 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 45
- 238000010248 power generation Methods 0.000 claims abstract description 125
- 230000007246 mechanism Effects 0.000 claims abstract description 72
- 230000007774 longterm Effects 0.000 claims abstract description 62
- 230000005611 electricity Effects 0.000 claims abstract description 25
- 238000013527 convolutional neural network Methods 0.000 claims description 50
- 238000012549 training Methods 0.000 claims description 34
- 238000013439 planning Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 11
- 238000005286 illumination Methods 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000004146 energy storage Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 101000628535 Homo sapiens Metalloreductase STEAP2 Proteins 0.000 description 1
- 102100026711 Metalloreductase STEAP2 Human genes 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013082 photovoltaic technology Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Photovoltaic Devices (AREA)
Abstract
The embodiment of the specification discloses a method for predicting grid-connected electric quantity of a photovoltaic area, which is used for solving the problem of inaccurate grid-connected electric quantity prediction in the prior art. The method comprises the following steps: dividing distributed photovoltaic power generation equipment of a region to be detected to obtain a plurality of photovoltaic regions; based on a preset time interval, inputting real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected power value of the photovoltaic area; inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area data; and continuously predicting the long-term prediction electricity quantity of the photovoltaic area according to the long-term prediction model to obtain a prediction grid-connected electricity quantity sequence of the photovoltaic area.
Description
Technical Field
The present disclosure relates to the field of digital new energy technologies, and in particular, to a method, an apparatus, and a medium for predicting grid-connected power of a photovoltaic area.
Background
In recent years, problems such as environmental pollution and climate change are increasingly prominent due to the large-scale development and utilization of traditional fossil energy sources in the global scope. Solar energy is the cleanest, safe and reliable energy source at present, and development and utilization of the solar energy are the main content of the energy revolution. Photovoltaic is a short term of solar photovoltaic power generation system, which is a novel power generation system that directly converts solar radiation energy into electric energy by utilizing the photovoltaic effect of solar cell semiconductor materials. The distributed photovoltaic power generation is used as an important direction of the photovoltaic new energy industry, is mostly built near a user site, exists in a mode of self-power-consumption and surplus electric quantity on the user side in a network operation mode, and realizes energy effective utilization through distributed photovoltaic grid connection. However, the randomness and fluctuation of the grid-connected electric quantity of the distributed photovoltaic self-power-consumption and the running mode of the surplus internet surfing greatly affect the power distribution network, so that the safe running of the existing power distribution network is ensured, and the grid-connected electric quantity of the distributed photovoltaic power generation needs to be effectively predicted.
In the prior art, the prediction of the grid-connected electric quantity is carried out by adopting a deep learning technology based on a convolutional neural network. However, in the field of time sequence performance such as video processing, the two-dimensional convolutional neural network adopted at present cannot well capture information on time sequence, and cannot find time correlation and space correlation between data, so that the prediction accuracy of grid-connected electric quantity is low, and the fine management of electric grid-connected service cannot be realized.
Therefore, a method for continuously improving the prediction accuracy of the grid-connected electric quantity of the distributed photovoltaic power generation is needed.
Disclosure of Invention
One or more embodiments of the present disclosure provide a photovoltaic region power generation amount prediction method, which is used to solve the following technical problems: how to improve the accuracy of grid-connected electric quantity prediction of the photovoltaic area.
One or more embodiments of the present disclosure adopt the following technical solutions:
one or more embodiments of the present disclosure provide a method for predicting grid-connected power of a photovoltaic area, where the method includes:
dividing distributed photovoltaic power generation equipment of a region to be detected to obtain a plurality of photovoltaic regions;
based on a preset time interval, inputting real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected electricity value of the photovoltaic area;
inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area;
and continuously predicting the long-term prediction electric quantity of the photovoltaic area according to the long-term prediction model to obtain a prediction grid-connected electric quantity sequence of the photovoltaic area.
Optionally, in one or more embodiments of the present disclosure, the dividing the distributed photovoltaic power generation device of the area to be measured to obtain a plurality of photovoltaic areas specifically includes:
acquiring the urban planning condition of the region to be measured; wherein the city planning situation comprises at least: a load threshold of the grid;
determining a preliminary division area of the photovoltaic equipment according to the urban planning condition of the area to be detected and the distribution condition of the distributed photovoltaic power generation equipment;
dividing the region to be measured into a plurality of photovoltaic regions according to the preliminary dividing region of the photovoltaic equipment.
Optionally, in one or more embodiments of the present disclosure, before inputting the real-time data and the weather mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into the preset short-time prediction model, the method further includes:
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud data center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data; wherein the real-time data comprises: the system comprises a grid-connected power value, a temperature value, a humidity value, illumination intensity, acquisition data of an Internet of things sensor and distributed photovoltaic operation data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the filtered data as first training characteristic data, and inputting the first training characteristic data into the 3D convolutional neural network through multiple channels;
and training a short-time prediction model meeting requirements based on the 3D convolutional neural network.
Optionally, in one or more embodiments of the present disclosure, before the inputting the real-time data, the predicted data, and the short-time predicted power value into the preset long-term prediction model based on a preset time interval, the method further includes:
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud data center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the short-term predicted electric quantity determined by the filtered data and the short-term predicted model as second training characteristic data and inputting the second training characteristic data into the 3D convolutional neural network based on multiple channels;
and obtaining a long-term prediction model meeting the requirements through training and learning of the 3D convolutional neural network.
Optionally, in one or more embodiments of the present disclosure, before the cloud-based data center obtains real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device, analyzes the real-time data and weather mechanism prediction data, and filters error data to obtain filtered data, the method further includes:
collecting Internet of things collected data, distributed photovoltaic operation data and grid-connectable electric quantity of each distributed photovoltaic power generation device, and environment data serving as real-time data of the distributed photovoltaic power generation devices; wherein the environmental data includes at least: temperature value, humidity value, illumination intensity;
acquiring weather mechanism forecast data of the photovoltaic area based on an authoritative weather mechanism, wherein the weather mechanism forecast data comprises: cloud image data, meteorological data and meteorological mechanism prediction data;
and storing the real-time data of the distributed photovoltaic power generation equipment and the meteorological mechanism prediction data into a cloud data center so as to perform data analysis processing based on the cloud data center.
Optionally, in one or more embodiments of the present disclosure, the collecting data collected by the internet of things of each distributed photovoltaic power generation device specifically includes:
acquiring the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
setting a data acquisition calculation formula of a photovoltaic area according to the sensing data acquisition frequency of the Internet of things, the time dimension of the 3D convolutional neural network and the range of the photovoltaic area;
acquiring acquisition data of the sensor of the Internet of things based on the data acquisition calculation formula.
Optionally, in one or more embodiments of the present disclosure, after the continuously predicting the long-term predicted electrical quantity of the photovoltaic region according to the long-term prediction model, the method further includes:
acquiring the grid-connectable electric quantity of each photovoltaic power generation device according to the predicted electric quantity sequence;
and adjusting the division of the photovoltaic power generation equipment according to the grid-connectable electric quantity and the urban planning condition of the area to be detected, and obtaining an updated photovoltaic area.
Optionally, in one or more embodiments of the present disclosure, after the obtaining the updated photovoltaic region, the method further includes:
adjusting the data acquisition calculation formula of the data acquisition frequency and the photovoltaic area of the Internet of things of the photovoltaic discovery equipment according to the predicted electric quantity sequence, and obtaining adjusted acquisition parameters;
and respectively optimizing the short-term prediction model and the long-term prediction model based on the updated photovoltaic region size and the adjusted acquisition parameters, namely the predicted electric quantity sequence.
One or more embodiments of the present disclosure provide a prediction apparatus for grid-connected electricity quantity of a photovoltaic region, the apparatus including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
dividing distributed photovoltaic power generation equipment of a region to be detected to obtain a plurality of photovoltaic regions;
based on a preset time interval, inputting real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected electricity value of the photovoltaic area;
inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area data;
and continuously predicting the long-term prediction electric quantity of the photovoltaic area according to the long-term prediction model to obtain a prediction grid-connected electric quantity sequence of the photovoltaic area.
One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer-executable instructions configured to:
dividing distributed photovoltaic power generation equipment of a region to be detected to obtain a plurality of photovoltaic regions;
based on a preset time interval, inputting real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected electricity value of the photovoltaic area;
inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area data;
and continuously predicting the long-term prediction electric quantity of the photovoltaic area according to the long-term prediction model to obtain a prediction grid-connected electric quantity sequence of the photovoltaic area.
The above-mentioned at least one technical scheme that this description embodiment adopted can reach following beneficial effect:
by dividing the photovoltaic area into the areas to be detected, grouping management of the photovoltaic equipment is realized. Based on a short-time prediction model and a long-time prediction model of the 3D convolutional neural network, the time correlation and the space correlation between data can be effectively found, the grid-connectable electric quantity of the photovoltaic power generation equipment can be accurately predicted, and safe and efficient data support is provided for a safe grid-connection strategy. By means of mixed prediction of the short-time prediction model and the long-time prediction model, the problems of low prediction precision and low reliability of a single prediction model are avoided.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some of the embodiments described in the present description, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a schematic flow chart of a method for predicting grid-connected electric quantity of a photovoltaic area according to an embodiment of the present disclosure;
fig. 2 is a block diagram of a photovoltaic region power generation amount prediction model in an application scenario in fig. 1 according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of a photovoltaic power generation system in an application scenario in fig. 1 according to an embodiment of the present disclosure;
fig. 4 is an internal device structure diagram of a photovoltaic area grid-connected electric quantity prediction device according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of an internal structure of a nonvolatile storage medium according to an embodiment of the present disclosure.
Detailed Description
The embodiment of the specification provides a method, equipment and medium for predicting grid-connected electric quantity of a photovoltaic area.
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.
With the continuous development of photovoltaic technology, various large-scale photovoltaic power generation systems are gradually developed, and photovoltaic power generation equipment after grid connection is a supplement to an original power system, however, as the principle of the photovoltaic power generation equipment is to convert light energy into electric energy by utilizing a photovoltaic conversion technology, the efficiency of the photovoltaic power generation process is seriously dependent on weather conditions of an area where the photovoltaic power generation system is located, namely, fluctuation of weather parameters such as air temperature, wind speed and the like can directly influence the generated energy of the photovoltaic power generation system, in other words, the photovoltaic power generation system is not a continuous stable power supply system, has extreme fluctuation and intermittence, which inevitably brings great difficulty to power scheduling of the whole power system, and once the generated energy of the photovoltaic power generation system is greatly changed, the stability of a power grid is directly influenced. Therefore, the grid-connected electric quantity of the photovoltaic power generation equipment needs to be predicted, so that the grid-connected strategy of the photovoltaic power generation equipment is adjusted in real time, and the safety of the power grid in the area is ensured.
In the prior art, with the rapid development of deep learning technology and the support of mass data and high-efficiency computing capacity in the Internet and cloud computing era, the deep learning technology represented by convolutional neural networks is used as a learning prediction model to bring subversive changes to the whole society. The traditional convolutional neural network is improved in the identification of the text and image fields, but the traditional 2D convolutional neural network cannot well capture information on time sequences, and cannot extract characteristic data of photovoltaic power generation equipment from time and space dimensions, so that prediction accuracy of grid-connected electric quantity of the photovoltaic power generation equipment is low, and a power grid system cannot be protected safely.
In order to solve the above problems, in one or more embodiments of the present disclosure, according to the characteristics of distributed photovoltaic power generation, a monitoring position is divided into fixed area units according to the actual conditions of a city, real-time data of the distributed photovoltaic power generation device and prediction data of a meteorological mechanism are collected, and based on a 3D convolutional neural network, grid-connected power of a photovoltaic area at a future moment is predicted, so that data support is provided for better realizing a high-efficiency and safe grid-connected mode, two grid-connected services of fine management power are realized, and safety of a grid system is ensured.
The technical scheme provided in the specification is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, a method flow diagram of a method for predicting grid-connected electricity quantity of a photovoltaic area according to one or more embodiments of the present disclosure is provided.
As can be seen from fig. 1, in one or more embodiments of the present disclosure, a method for predicting grid-connected electricity quantity of a photovoltaic area includes the following steps:
s101: dividing the distributed photovoltaic power generation equipment of the region to be detected to obtain a plurality of photovoltaic regions.
In one or more embodiments of the present disclosure, the dividing the distributed photovoltaic power generation device of the area to be measured to obtain a plurality of photovoltaic areas specifically includes:
acquiring the urban planning condition of the region to be measured; wherein the city planning situation comprises at least: a load threshold of the grid;
determining a preliminary division area of the distributed photovoltaic power generation equipment according to the urban planning condition of the area to be detected and the distribution condition of the distributed photovoltaic power generation equipment;
dividing the region to be measured into a plurality of photovoltaic regions according to the preliminary dividing region of the distributed photovoltaic power generation equipment.
By acquiring the urban planning condition of the region to be measured, the requirement of the city of the region to be measured on the running load of the power grid system can be obtained, namely, in order to ensure the safe running of the power grid system, the electric quantity which can be connected in a grid is limited by the loadable load of the power grid, so as to avoid the unavoidable safety problem when the power grid runs under high load. Therefore, according to the urban planning condition of the area to be measured and the distribution condition of the distributed photovoltaic power generation equipment, after the distribution density of the distributed photovoltaic power generation equipment is fully considered, the area to be measured is initially divided into a plurality of photovoltaic areas. Through the division of the photovoltaic areas, the grouping management of the distributed photovoltaic power generation equipment is realized, and the management refinement degree of a power grid system is improved.
The following description is needed: distributed photovoltaic power generation devices, also known as decentralized power generation or distributed energy supply, refer to the deployment of smaller photovoltaic power generation and supply systems at or near the consumer site to meet the needs of a particular consumer, support the economical operation of existing power distribution networks, or both. In practical application, the running mode of the distributed photovoltaic power generation equipment is that under the condition of solar radiation, the solar energy is converted by the solar cell module array of the photovoltaic power generation equipment to output electric energy, the electric energy is intensively sent into the direct current power distribution cabinet through the direct current combiner box, the electric energy is changed into alternating current by the grid-connected inverter to be supplied to the load of the building, and redundant or insufficient electric power is regulated by connecting a power grid.
S102: based on a preset time interval, inputting real-time data of each distributed photovoltaic power generation device and weather mechanism prediction data in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected electricity value of the photovoltaic area.
In one or more embodiments of the present disclosure, before inputting the real-time data and the weather mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into the preset short-time prediction model, the method further includes:
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data; wherein the real-time data comprises: the system comprises a grid-connected power value, a temperature value, a humidity value, illumination intensity, acquisition data of an Internet of things sensor and distributed photovoltaic operation data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the filtered data as first training characteristic data, and inputting the first training characteristic data into the 3D convolutional neural network through multiple channels;
and training a short-time prediction model meeting requirements based on the 3D convolutional neural network.
In one or more embodiments of the present disclosure, the method further includes, before the cloud-based data center obtains real-time data and weather-mechanism prediction data of each distributed photovoltaic power generation device, analyzes the real-time data and weather-mechanism prediction data, and filters the error data to obtain filtered data:
collecting Internet of things collected data, distributed photovoltaic operation data and grid-connectable electric quantity of each distributed photovoltaic power generation device, and environment data serving as real-time data of the distributed photovoltaic power generation devices; wherein the environmental data includes at least: temperature value, humidity value, illumination intensity;
acquiring weather mechanism forecast data of the photovoltaic area based on an authoritative weather mechanism, wherein the weather mechanism forecast data comprises: cloud image data, meteorological data and meteorological mechanism prediction data;
and storing the real-time data of the distributed photovoltaic power generation equipment and the meteorological mechanism prediction data into a cloud data center so as to perform data analysis processing based on the cloud data center.
In one or more embodiments of the present disclosure, the collecting data collected by the internet of things of each distributed photovoltaic power generation device specifically includes:
acquiring the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
setting a data acquisition calculation formula of a photovoltaic area according to the sensing data acquisition frequency of the Internet of things, the time dimension of the 3D convolutional neural network and the range of the photovoltaic area;
acquiring acquisition data of the sensor of the Internet of things based on the data acquisition calculation formula.
The method comprises the steps of collecting Internet of things collected data, grid-connectable electric quantity data and environment data from distributed photovoltaic power generation equipment at the current moment and the past moment to serve as real-time data of the distributed photovoltaic power generation equipment, and converging the real-time data to a cloud data center. Meanwhile, cloud image data, meteorological data and forecast data of future time periods of the meteorological mechanism are obtained based on an authoritative meteorological mechanism to serve as the forecast data of the meteorological mechanism, and the forecast data are converged to a cloud data center, so that the real-time data and the forecast data of the meteorological mechanism are called in real time based on the cloud data center. Among them, it should be noted that, because the distributed photovoltaic power generation device affects its own power generation amount due to environmental factors, the real-time data includes: the system can be used for grid-connected electricity values, temperature values, humidity values, illumination intensity, collected data of sensors of the Internet of things, operation data of distributed photovoltaic power generation equipment and the like.
According to the sensing data acquisition frequency of the actual Internet of things of the distributed photovoltaic power generation equipment, the time dimension of the 3D convolutional neural network can be set. And meanwhile, acquiring a data acquisition calculation formula of the photovoltaic area through the sensing data acquisition frequency of the Internet of things, the time dimension of the 3D convolutional neural network and the range of the photovoltaic area. Acquiring acquisition data of the Internet of things sensor in the real-time data according to the data acquisition consensus.
And calling real-time data of each distributed photovoltaic charging device and weather mechanism prediction data from the cloud data center, and cleaning and filtering the data to remove obvious error data, so that the prediction accuracy of grid-connected electric quantity is improved. And inputting the filtered data serving as first training characteristic data into a 3D convolutional neural network through multiple channels to obtain a short-time prediction model meeting the requirements.
In one or more embodiments of the present specification, the Short-time prediction model is a next-time prediction model (Short-Term Predict Model, STPM). The prediction model STPM is composed of a normalization layer, a 3D convolutional neural network layer, a pooling layer, a full connection layer and the like. As shown in fig. 2 below, the prediction model STMP forms three-dimensional structural features according to the actual current moment and the actual current moment that can be connected to the grid, the temperature, the humidity, the illumination, the actual data collected by the photovoltaic operation internet of things and the cloud image by taking the area as a unit and combining the time dimension of the 3D convolutional neural network, and inputs each feature as an independent channel into the deep learning neural network model through multiple channels, so as to output the predicted value of the next moment, namely the prediction of the grid-connected electric quantity in a short time. By adopting the 3D convolutional neural network as the core of the prediction model, the time correlation and the space correlation between data can be more effectively found, and the grid-connectable electric quantity of the distributed photovoltaic power generation can be more accurately predicted.
The following description is needed: the cloud data center as shown in fig. 3 aggregates a large amount of computing, storage and network resources, and provides cloud services such as computing services, storage services, network resource services, internet of things connection services, deep learning basic training services, artificial intelligent hardware acceleration services, database services, message middleware services and the like; the distributed photovoltaic power generation equipment is a device for directly converting solar radiation energy into electric energy by utilizing the photovoltaic effect of a solar cell semiconductor material, comprises hardware such as photovoltaic equipment, an inverter, an Internet of things sensor, energy storage equipment and the like, and has the functions of energy storage, data acquisition, power generation grid connection, electric quantity control and the like; the energy storage function is based on equipment such as storage battery energy storage equipment and the like, and redundant power generation which meets the requirement of off-grid spontaneous self-use is stored; the data acquisition function is based on the sensing device of the Internet of things, acquires data such as temperature, humidity, illumination, effective current, photovoltaic running condition information and the like, and gathers the data to the cloud data center in real time through network connection; the power generation grid-connected function enables photovoltaic power generation to be integrated into a main power grid through an inverter and a related control device according to actual conditions.
S103: and inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area data.
In one or more embodiments of the present disclosure, before the inputting the real-time data, the predicted data, and the short-time predicted electricity value into the predetermined long-term prediction model, the method further includes:
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud data center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the short-term predicted electric quantity determined by the filtered data and the short-term predicted model as second training characteristic data and inputting the second training characteristic data into the 3D convolutional neural network based on multiple channels;
and obtaining a long-term prediction model meeting the requirements through training and learning of the 3D convolutional neural network.
The long-term prediction model is trained by a process similar to the short-term prediction model in step S103 described above. Specifically, firstly, real-time data and meteorological mechanism prediction data of each distributed photovoltaic discovery device are obtained in a cloud data center, and the time dimension of the 3D convolutional neural network is set according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation device. As shown in fig. 2, the short-time grid-connected electric power value output by the short-time prediction model in the step S103 is used as the second training feature to be input into the 3D convolutional neural network for training after the data processing, and the long-time grid-connected electric power value of the photovoltaic area is obtained according to the long-time prediction model.
In one or more embodiments of the present specification, the Long-term prediction model is a future time prediction model (Long-Term Predict Model, LTPM) based on a 3D convolutional neural network. The prediction model LTPM mainly adopts a 3D convolutional neural network, and is mainly based on grid-connected electricity quantity values at the previous stage and temperature and cloud picture conditions from weather prediction, and electricity quantity predicted values in the future period are continuously output. By adopting the short-time prediction model and the long-time prediction model, the real-time acquisition data is used for realizing short-time accurate judgment at the next moment, meanwhile, the model prediction data and the future prediction data provided by a meteorological mechanism can be fully utilized, and the accuracy of a long-time prediction value is good.
S104: and continuously predicting the long-term prediction electric quantity of the photovoltaic area according to the long-term prediction model to obtain a prediction grid-connected electric quantity sequence of the photovoltaic area.
In one or more embodiments of the present disclosure, after the continuously predicting the long-term predicted electrical quantity of the photovoltaic region according to the long-term prediction model to obtain the predicted electrical quantity sequence of the photovoltaic region, the method further includes:
acquiring the grid-connectable electric quantity of each distributed photovoltaic power generation device according to the predicted electric quantity sequence;
and adjusting the division of the distributed photovoltaic power generation equipment according to the grid-connectable electric quantity and the urban planning condition of the area to be detected, and obtaining an updated photovoltaic area.
In one or more embodiments of the present disclosure, after the obtaining the updated photovoltaic region, the method further comprises:
adjusting the data acquisition calculation formula of the data acquisition frequency and the photovoltaic area of the Internet of things of the photovoltaic discovery equipment according to the predicted electric quantity sequence, and obtaining adjusted acquisition parameters;
and respectively optimizing the short-term prediction model and the long-term prediction model based on the updated photovoltaic region size and the adjusted acquisition parameters, namely the predicted electric quantity sequence.
After the grid-connected electric quantity is predicted through the short-time prediction model and the long-time prediction model, the actual grid-connectable electric quantity data can be collected continuously, and a predicted electric quantity sequence of the grid-connectable electric quantity is obtained. According to the predicted grid-connected electricity value sequence and the actual city planning condition of the city in which the region to be measured is located, the matching degree of the current photovoltaic region and the power grid load specified by the city can be obtained through real-time analysis, so that the deployment planning of the distributed photovoltaic region is adjusted, and the power grid system is more reasonably managed.
After the grid-connected electric quantity is predicted through the short-time prediction model and the long-time prediction model, actual grid-connected electric quantity data can be collected continuously, parameters such as the frequency of the physical acquisition data of the distributed photovoltaic power generation equipment, a data acquisition calculation formula of a breadth area and the like are adjusted according to an actual result, and the adjusted parameters are obtained. Through the adjusted size of the photovoltaic area and the adjusted parameters, real-time feedback and optimization of a prediction model are realized, so that the grid-connected electric quantity prediction accuracy of the photovoltaic area can be improved continuously.
As shown in fig. 4, one or more embodiments of the present disclosure provide an apparatus internal structure diagram of a photovoltaic area grid-connected electricity quantity prediction apparatus. As can be seen from fig. 4, the apparatus comprises:
at least one processor 401; the method comprises the steps of,
a memory 402 communicatively coupled to the at least one processor 401; wherein,,
the memory 402 stores instructions executable by the at least one processor 401, the instructions being executable by the at least one processor 401 to enable the at least one processor 401 to:
dividing distributed photovoltaic power generation equipment of a region to be detected to obtain a plurality of photovoltaic regions;
based on a preset time interval, inputting real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected electricity value of the photovoltaic area;
inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area data;
and continuously predicting the long-term prediction electric quantity of the photovoltaic area according to the long-term prediction model to obtain a prediction grid-connected electric quantity sequence of the photovoltaic area.
As shown in fig. 5, one or more embodiments of the present specification provide a schematic internal structure of a nonvolatile storage medium. As can be seen from fig. 5, a non-volatile storage medium stores executable instructions 501 of a computer, wherein the executable instructions 501 include:
dividing distributed photovoltaic power generation equipment of a region to be detected to obtain a plurality of photovoltaic regions;
based on a preset time interval, inputting real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected electricity value of the photovoltaic area;
inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area data;
and continuously predicting the long-term prediction electric quantity of the photovoltaic area according to the long-term prediction model to obtain a prediction grid-connected electric quantity sequence of the photovoltaic area.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.
Claims (8)
1. A method for predicting grid-connected electricity quantity of a photovoltaic area, the method comprising:
dividing distributed photovoltaic power generation equipment of a region to be detected to obtain a plurality of photovoltaic regions;
based on a preset time interval, inputting real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected electricity value of the photovoltaic area;
inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area;
continuously predicting long-term predicted electric quantity of the photovoltaic area according to the long-term prediction model to obtain a predicted grid-connected electric quantity sequence of the photovoltaic area;
before the real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area are input into a preset short-time prediction model, the method further comprises the steps of:
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud data center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data; wherein the real-time data comprises: the system comprises a grid-connected power value, a temperature value, a humidity value, illumination intensity, acquisition data of an Internet of things sensor and distributed photovoltaic operation data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the filtered data as first training characteristic data, and inputting the first training characteristic data into the 3D convolutional neural network through multiple channels;
training a short-time prediction model meeting requirements based on the 3D convolutional neural network;
the method further comprises the steps of, before inputting the real-time data, the predicted data and the short-time predicted electricity value into a preset long-term prediction model based on a preset time interval:
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud data center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the short-time predicted electric quantity determined by the filtered data and the short-time predicted model as second training characteristic data and inputting the second training characteristic data into the 3D convolutional neural network based on multiple channels;
and obtaining a long-term prediction model meeting the requirements through training and learning of the 3D convolutional neural network.
2. The method for predicting grid-connected electric quantity of a photovoltaic area according to claim 1, wherein the dividing the distributed photovoltaic power generation equipment of the area to be measured to obtain a plurality of photovoltaic areas specifically comprises:
acquiring the urban planning condition of the region to be measured; wherein the city planning situation comprises at least: a load threshold of the grid;
determining a preliminary division area of the distributed photovoltaic power generation equipment according to the urban planning condition of the area to be detected and the distribution condition of the distributed photovoltaic power generation equipment;
dividing the region to be measured into a plurality of photovoltaic regions according to the preliminary dividing region of the distributed photovoltaic power generation equipment.
3. The method for predicting grid-connected electricity quantity of a photovoltaic area according to claim 1, wherein the method further comprises, before the cloud data center obtains real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device, analyzes the real-time data and weather mechanism prediction data, and filters erroneous data to obtain filtered data:
collecting Internet of things collected data, distributed photovoltaic operation data and grid-connectable electric quantity of each distributed photovoltaic power generation device, and environment data serving as real-time data of the distributed photovoltaic power generation devices; wherein the environmental data includes at least: temperature value, humidity value, illumination intensity;
acquiring weather mechanism forecast data of the photovoltaic area based on an authoritative weather mechanism, wherein the weather mechanism forecast data comprises: cloud image data, meteorological data and meteorological mechanism prediction data;
and storing the real-time data of the distributed photovoltaic power generation equipment and the meteorological mechanism prediction data into a cloud data center so as to perform data analysis processing based on the cloud data center.
4. The method for predicting grid-connected electric quantity of a photovoltaic area according to claim 3, wherein the acquiring data acquired by the internet of things of each distributed photovoltaic power generation device specifically comprises:
acquiring the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
setting a data acquisition calculation formula of a photovoltaic area according to the sensing data acquisition frequency of the Internet of things, the time dimension of the 3D convolutional neural network and the range of the photovoltaic area;
acquiring acquisition data of the sensor of the Internet of things based on the data acquisition calculation formula.
5. The method for predicting grid-connected power of a photovoltaic area according to claim 1, wherein the method further comprises, after continuously predicting the long-term predicted power of the photovoltaic area according to the long-term prediction model and obtaining the predicted power sequence of the photovoltaic area:
acquiring the grid-connectable electric quantity of each distributed photovoltaic power generation device according to the predicted electric quantity sequence;
and adjusting the division of the distributed photovoltaic power generation equipment according to the grid-connectable electric quantity and the urban planning condition of the area to be detected, and obtaining an updated photovoltaic area.
6. The method for predicting grid-tied electrical power to a photovoltaic area of claim 5, wherein after obtaining the updated photovoltaic area, the method further comprises:
according to the predicted electric quantity sequence, adjusting the data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment and a data acquisition calculation formula of a photovoltaic area to obtain adjusted acquisition parameters;
and respectively optimizing the short-term prediction model and the long-term prediction model based on the updated photovoltaic region size and the adjusted acquisition parameters, namely the predicted electric quantity sequence.
7. A photovoltaic area grid-tied electrical quantity prediction apparatus, characterized in that the apparatus comprises:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
dividing distributed photovoltaic power generation equipment of a region to be detected to obtain a plurality of photovoltaic regions;
based on a preset time interval, inputting real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected electricity value of the photovoltaic area;
inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area;
continuously predicting long-term predicted electric quantity of the photovoltaic area according to the long-term prediction model to obtain a predicted grid-connected electric quantity sequence of the photovoltaic area;
before the real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area are input into a preset short-time prediction model,
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud data center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data; wherein the real-time data comprises: the system comprises a grid-connected power value, a temperature value, a humidity value, illumination intensity, acquisition data of an Internet of things sensor and distributed photovoltaic operation data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the filtered data as first training characteristic data, and inputting the first training characteristic data into the 3D convolutional neural network through multiple channels;
training a short-time prediction model meeting requirements based on the 3D convolutional neural network;
the real-time data, the predicted data and the short-time predicted electricity value are input into a preset long-term prediction model based on a preset time interval,
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud data center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the short-time predicted electric quantity determined by the filtered data and the short-time predicted model as second training characteristic data and inputting the second training characteristic data into the 3D convolutional neural network based on multiple channels;
and obtaining a long-term prediction model meeting the requirements through training and learning of the 3D convolutional neural network.
8. A non-volatile storage medium storing executable instructions for a computer, the executable instructions being executable by the computer to enable the computer to:
dividing distributed photovoltaic power generation equipment of a region to be detected to obtain a plurality of photovoltaic regions;
based on a preset time interval, inputting real-time data and meteorological mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area into a preset short-time prediction model to obtain a short-time grid-connected electricity value of the photovoltaic area;
inputting the real-time data, the meteorological mechanism prediction data and the short-time prediction electric quantity value into a preset long-term prediction model based on a preset time interval to obtain a long-term grid-connected electric quantity value of the photovoltaic area;
continuously predicting long-term predicted electric quantity of the photovoltaic area according to the long-term prediction model to obtain a predicted grid-connected electric quantity sequence of the photovoltaic area;
before the real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device in the photovoltaic area are input into a preset short-time prediction model,
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud data center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data; wherein the real-time data comprises: the system comprises a grid-connected power value, a temperature value, a humidity value, illumination intensity, acquisition data of an Internet of things sensor and distributed photovoltaic operation data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the filtered data as first training characteristic data, and inputting the first training characteristic data into the 3D convolutional neural network through multiple channels;
training a short-time prediction model meeting requirements based on the 3D convolutional neural network;
the real-time data, the predicted data and the short-time predicted electricity value are input into a preset long-term prediction model based on a preset time interval,
acquiring real-time data and weather mechanism prediction data of each distributed photovoltaic power generation device based on a cloud data center, analyzing the real-time data and the weather mechanism prediction data, and filtering error data to obtain filtered data;
setting the time dimension of a 3D convolutional neural network according to the sensing data acquisition frequency of the Internet of things of the distributed photovoltaic power generation equipment;
taking the short-time predicted electric quantity determined by the filtered data and the short-time predicted model as second training characteristic data and inputting the second training characteristic data into the 3D convolutional neural network based on multiple channels;
and obtaining a long-term prediction model meeting the requirements through training and learning of the 3D convolutional neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110997927.7A CN113689045B (en) | 2021-08-27 | 2021-08-27 | Photovoltaic area grid-connected electric quantity prediction method, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110997927.7A CN113689045B (en) | 2021-08-27 | 2021-08-27 | Photovoltaic area grid-connected electric quantity prediction method, device and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113689045A CN113689045A (en) | 2021-11-23 |
| CN113689045B true CN113689045B (en) | 2023-06-27 |
Family
ID=78583666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110997927.7A Active CN113689045B (en) | 2021-08-27 | 2021-08-27 | Photovoltaic area grid-connected electric quantity prediction method, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113689045B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909919A (en) * | 2019-11-07 | 2020-03-24 | 哈尔滨工程大学 | Photovoltaic power prediction method of depth neural network model with attention mechanism fused |
| CN111754026A (en) * | 2020-05-28 | 2020-10-09 | 国网冀北电力有限公司 | Photovoltaic power station group power prediction method and device, computer equipment and storage medium |
| CN112101626A (en) * | 2020-08-14 | 2020-12-18 | 安徽继远软件有限公司 | Distributed photovoltaic power generation power prediction method and system |
| CN112580876A (en) * | 2020-12-21 | 2021-03-30 | 国网甘肃省电力公司电力科学研究院 | Photovoltaic power station power generation sub-band prediction method based on improved EMD-LSTM combined model |
| CN113052389A (en) * | 2021-04-01 | 2021-06-29 | 中国电力科学研究院有限公司 | Distributed photovoltaic power station ultra-short-term power prediction method and system based on multiple tasks |
-
2021
- 2021-08-27 CN CN202110997927.7A patent/CN113689045B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909919A (en) * | 2019-11-07 | 2020-03-24 | 哈尔滨工程大学 | Photovoltaic power prediction method of depth neural network model with attention mechanism fused |
| CN111754026A (en) * | 2020-05-28 | 2020-10-09 | 国网冀北电力有限公司 | Photovoltaic power station group power prediction method and device, computer equipment and storage medium |
| CN112101626A (en) * | 2020-08-14 | 2020-12-18 | 安徽继远软件有限公司 | Distributed photovoltaic power generation power prediction method and system |
| CN112580876A (en) * | 2020-12-21 | 2021-03-30 | 国网甘肃省电力公司电力科学研究院 | Photovoltaic power station power generation sub-band prediction method based on improved EMD-LSTM combined model |
| CN113052389A (en) * | 2021-04-01 | 2021-06-29 | 中国电力科学研究院有限公司 | Distributed photovoltaic power station ultra-short-term power prediction method and system based on multiple tasks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113689045A (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Elma et al. | A comparative sizing analysis of a renewable energy supplied stand-alone house considering both demand side and source side dynamics | |
| CN109103926A (en) | Photovoltaic power generation based on more Radiation Characteristics year meteorology scenes receives capacity calculation method | |
| CN103390199A (en) | Photovoltaic power generation capacity/power prediction device | |
| CN107204615B (en) | Method and system for realizing power prediction | |
| CN104600713A (en) | Device and method for generating day-ahead reactive power dispatch of power distribution network containing wind/photovoltaic power generation | |
| CN113410874B (en) | Load resource optimization control method based on virtual power plant peak regulation auxiliary service | |
| CN105656026A (en) | Equipment construction resource configuration method and system of renewable energy sources | |
| CN114154558A (en) | Distributed energy power generation load prediction system and method based on graph neural network | |
| CN116826714A (en) | Power distribution method, system, terminal and storage medium based on photovoltaic power generation | |
| CN109978277B (en) | Regional internet load prediction method and device in photovoltaic power generation | |
| Elmouatamid et al. | Deployment and experimental evaluation of micro-grid systems | |
| CN103916071B (en) | A kind of uniform output intelligent control system of wind light mutual complementing power generation and method | |
| CN105391082A (en) | Photovoltaic power station theoretical power calculation method based on classification sample inverters | |
| Vlasov et al. | Predictive control algorithm for A variable load hybrid power system on the basis of power output forecast | |
| CN116736893B (en) | Intelligent energy management method of optical storage device and optical storage device | |
| CN113689045B (en) | Photovoltaic area grid-connected electric quantity prediction method, device and medium | |
| YanQi et al. | The key technology for optimal scheduling and control of wind-photovoltaic-storage multi-energy complementary system | |
| CN107947208B (en) | Wind curtailment and large-scale battery energy storage coordinated operation method | |
| CN117856339B (en) | Micro-grid electric energy data control system and method based on big data | |
| Batsala et al. | Mathematical model for forecasting the process of electric power generation by photoelectric stations | |
| Hu et al. | SWAF: a distributed solar wsn adaptive framework | |
| CN117996757B (en) | Distributed wind power based power distribution network scheduling method, device and storage medium | |
| CN115313377B (en) | Power load prediction method and system | |
| CN210430947U (en) | Solar energy charging station | |
| CN107194620B (en) | Linear point value Zadeh fuzzy calculation method and device for daily power generation amount of photovoltaic power 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 |