CN115640903A - Photovoltaic power generation prediction method and system considering wavelet decomposition and multi-objective optimization - Google Patents
Photovoltaic power generation prediction method and system considering wavelet decomposition and multi-objective optimization Download PDFInfo
- Publication number
- CN115640903A CN115640903A CN202211371660.1A CN202211371660A CN115640903A CN 115640903 A CN115640903 A CN 115640903A CN 202211371660 A CN202211371660 A CN 202211371660A CN 115640903 A CN115640903 A CN 115640903A
- Authority
- CN
- China
- Prior art keywords
- prediction
- power generation
- photovoltaic power
- scene set
- subsystem
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 29
- 238000005457 optimization Methods 0.000 title claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 241000282461 Canis lupus Species 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000002068 genetic effect Effects 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 241000160777 Hipparchia semele Species 0.000 claims 1
- 230000008569 process Effects 0.000 description 6
- 230000007547 defect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000005619 thermoelectricity Effects 0.000 description 1
Images
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a photovoltaic power generation prediction method and a system considering wavelet decomposition and multi-objective optimization, belonging to the technical field of photovoltaic power generation prediction, wherein the method comprises the following steps: obtaining an initial scene set of photovoltaic power generation; denoising the photovoltaic power generation initial scene set to reconstruct a photovoltaic power generation scene set; predicting the reconstructed photovoltaic power generation scene set by adopting a combined prediction system, selecting a single prediction system as a prediction subsystem of the combined system, and outputting a prediction result by each prediction subsystem according to the reconstructed photovoltaic power generation scene set; determining a weight parameter of each prediction subsystem; and weighting and outputting a final prediction result by utilizing the obtained weight parameters of the prediction subsystems and the prediction results of the prediction subsystems on the reconstructed photovoltaic power generation scene set. The stability and accuracy of photovoltaic power generation prediction can be improved, and reasonable optimized scheduling is carried out by an effective auxiliary comprehensive energy system.
Description
Technical Field
The invention belongs to the technical field of photovoltaic power generation prediction, and particularly relates to a photovoltaic power generation prediction method and system considering wavelet decomposition and a multi-objective optimization algorithm.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The energy structure of China always gives priority to fossil energy such as coal, petroleum and the like, and the current situation can be maintained for a long time. However, fossil energy is limited in reserves, non-renewable, inefficient in use, and produces a large amount of polluting emissions during production and utilization, causing irreversible damage to the environment. Therefore, the contradiction between energy supply and environmental protection is increasingly prominent.
With the increasing utilization degree of renewable energy sources such as solar energy, wind energy and the like, the permeability of the renewable energy sources in a comprehensive energy source system is increased, and the photovoltaic power generation technology is also gradually changed into thermoelectricity researched by various countries. However, the photovoltaic development process has the characteristics of imbalance, randomness, volatility and the like, and the power network is easily impacted when the photovoltaic development process is connected to a power grid.
Therefore, the prediction of the photovoltaic power generation becomes indispensable work for maintaining the stability of the power system and optimizing and scheduling the comprehensive energy system, the photovoltaic power generation power is accurately predicted in advance according to historical data, a power scheduling department can timely adjust a scheduling scheme, the economy and stability of the operation of a power grid are improved, the light abandoning phenomenon is reduced, and the solar photovoltaic power generation prediction method has great significance for promoting the development and utilization of solar energy. The existing photovoltaic prediction method mainly adopts a neural network, but the problems of low prediction precision, inaccurate result and the like inevitably occur in a single neural network algorithm.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides the photovoltaic power generation prediction method and system considering wavelet decomposition and multi-objective optimization, which can improve the stability and accuracy of photovoltaic power generation prediction and effectively assist the comprehensive energy system to carry out reasonable optimization scheduling.
In order to achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
in a first aspect, the invention discloses a photovoltaic power generation prediction method considering wavelet decomposition and multi-objective optimization, which comprises the following steps:
obtaining an initial scene set of photovoltaic power generation;
denoising the photovoltaic power generation initial scene set to reconstruct a photovoltaic power generation scene set;
predicting the reconstructed photovoltaic power generation scene set by adopting a combined prediction system, selecting a single prediction system as a prediction subsystem of the combined system, and outputting a prediction result by each prediction subsystem according to the reconstructed photovoltaic power generation scene set;
determining a weight parameter of each prediction subsystem;
and weighting and outputting a final prediction result by utilizing the obtained weight parameters of the prediction subsystems and the prediction results of the prediction subsystems on the reconstructed photovoltaic power generation scene set.
As a further technical scheme, a wavelet threshold denoising method is selected to reduce high-frequency noise of the photovoltaic power generation initial scene set, and denoising is achieved.
In a second aspect, the invention discloses a photovoltaic power generation prediction system considering wavelet decomposition and multi-objective optimization, comprising:
a photovoltaic power generation scene set reconstruction module configured to: obtaining an initial scene set of photovoltaic power generation;
denoising the photovoltaic power generation initial scene set to reconstruct a photovoltaic power generation scene set;
a subsystem prediction module configured to: predicting the reconstructed photovoltaic power generation scene set by adopting a combined prediction system, selecting a single prediction system as a prediction subsystem of the combined system, and outputting a prediction result by each prediction subsystem according to the reconstructed photovoltaic power generation scene set;
a final prediction module configured to: determining a weight parameter of each prediction subsystem;
and weighting and outputting a final prediction result by utilizing the obtained weight parameters of the prediction subsystems and the prediction results of the prediction subsystems on the reconstructed photovoltaic power generation scene set.
The above one or more technical solutions have the following beneficial effects:
1. the method considers that the wavelet decomposition technology is adopted to optimize the initial scene set of the photovoltaic power generation, high-frequency noise points of the scene set are reduced, inferior scenes are eliminated, main parameters of a wavelet decomposition mechanism are automatically optimized by using a genetic algorithm, and the applicability of the system is enhanced.
2. And a combined prediction system is adopted to predict the reconstructed scene set, so that the defects of a single prediction system are overcome, the prediction error is obviously reduced, and the prediction precision and stability are improved.
3. The weight parameters of a single prediction system in the combined prediction system are determined by adopting a multi-objective wolf optimization algorithm, so that errors caused by subjective factors are overcome, and the final prediction result is more effective.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are included to illustrate an exemplary embodiment of the invention and not to limit the invention.
FIG. 1 is a flowchart illustrating a prediction method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a wavelet decomposition algorithm solving process according to a first embodiment of the present invention;
fig. 3 is a flowchart of the solving process of the multi-objective grayish wolf optimization algorithm in the first embodiment of the present invention.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example one
The embodiment discloses a photovoltaic power generation prediction method considering wavelet decomposition and multi-objective optimization, as shown in fig. 1, comprising the following steps:
s1: by referring to a historical database of the photovoltaic power station, an initial scene set of photovoltaic power generation is obtained, wherein the initial scene set comprises parameters such as historical ambient temperature, humidity, average irradiation intensity, illumination intensity and illumination rate and photovoltaic power generation power in corresponding time periods, and the parameters are used as a test set of a prediction system.
S2: the method comprises the steps of selecting a wavelet threshold denoising method to reduce high-frequency noise of a photovoltaic power generation initial scene set, namely eliminating data dead pixels, reducing influence of extreme environment factors on photovoltaic power generation prediction, reconstructing the scene set, automatically optimizing main parameters of the wavelet threshold denoising method by using a genetic algorithm, wherein the main parameters comprise decomposition layer number k and each layer of threshold value alpha, and reducing randomness and volatility of the initial scene.
Step 101: initializing genetic algorithm parameters including population number, iteration times, hierarchical range, threshold range and correlation coefficient.
Step 102: selecting a wavelet and determining the level N of wavelet decomposition, and performing N-layer wavelet decomposition calculation on the signal.
Step 103: and selecting a threshold value for quantizing each layer of high-frequency coefficients (in three directions) from the 1 st layer to the Nth layer, wherein the quantizing method adopts a soft threshold value quantizing method.
Step 104: selecting a combination index containing an average absolute error, an average absolute percentage error, a root mean square error, a consistency level and a correlation coefficient as a target function of a genetic algorithm, carrying out iterative optimization on wavelet decomposition, and finally selecting the best group of decomposition layer number k, each layer threshold value alpha and a wavelet decomposition result.
Step 105: performing wavelet reconstruction on the signals according to the low-frequency coefficient of the Nth layer of wavelet decomposition and the high-frequency coefficients of the 1 st layer to the Nth layer after quantization processing to obtain a typical daily photovoltaic power generation power value G without dead pixels real (t)。
The number of the populations is the number of data which are selected and optimized at one time, the layering range and the threshold range are ranges of decision variables, and the wavelet decomposition optimization overall idea is to decompose original typical photovoltaic power generation power data in a layering mode and then eliminate extreme conditions in the photovoltaic power generation power data, so that the volatility of an overall photovoltaic power generation data set is reduced, and the relation connection between a photovoltaic power generation power value and environmental parameters is accurate.
S3: in order to better obtain and utilize the characteristics of a typical daily photovoltaic power generation scene set, a combined prediction system is adopted to predict a reconstructed scene set. Four common prediction indexes (average absolute error, root-mean-square error, square absolute percentage error and determination coefficient) are referred, and four single prediction systems with better prediction results are selected as subsystems of a combined system, including a cyclic neural network, a deep convolutional neural network, a long-time and short-time memory neural network and a back propagation neural networkThrough the network, each prediction subsystem outputs a prediction result (Y) according to the reconstructed scene set i (t),i∈[1,4]}。
S4: taking the weight parameter of each prediction subsystem as a decision variable { alpha i ,i∈[1,4]And determining the weight parameters of each prediction subsystem by adopting a multi-target improved Hurricane algorithm by taking the root mean square error and the square absolute percentage error of the combined prediction value and the actual photovoltaic power generation value of the prediction system as target functions.
The method comprises the following steps of solving an objective function of each prediction subsystem weight parameter set by using a multi-objective wolf optimization algorithm:
in the formula: f 1 The square absolute percentage error of the combined predicted value and the actual photovoltaic power generation value of the prediction system is obtained; f 2 The root mean square error of the combined predicted value and the actual photovoltaic power generation value of the prediction system is obtained; alpha (alpha) ("alpha") i A weight parameter for the ith prediction subsystem prediction value; y is i (t) the photovoltaic power generation predicted value of the ith prediction subsystem at the time t; g (t) is the actual photovoltaic power generation power value at the time t.
Wherein, an observation strategy is added in the multi-target wolf optimization algorithm, and after the position updating of the wolf population is completed by each iteration, the surrounding positions are observed randomly. And adding an external storage Archive set P to save the optimal solution in the algorithm solving process.
As shown in fig. 3, the process of solving the weight parameter set of each prediction subsystem by using the multi-objective grayish wolf optimization algorithm is as follows:
step 201: initialization algorithm parameter Greenwolf population position X (i.e. weight parameter { alpha) i ,i∈[1,4]}), the population number G N Number of iterations N G Upper and lower weight limits H d And L d Etc.;
step 202: initializing an external storage Archive set P, and enabling the iteration time t =1;
step 203: calculating a fitness function for each individual in the population, finding out a current global optimal solution, and storing the optimal individual position as M;
step 204: selecting three wolfs of the current population by using a roulette strategy;
step 205: updating the positions of the wolfs repore through a position updating formula;
step 206: observing the vicinity of the position of each wolf by adopting an observation strategy, and moving to the position if the new position is more optimal;
step 207: calculating and comparing the individual historical optimal position and the population optimal position of each wolf;
step 208: archiving the optimal position of each grey wolf, comparing the optimal solution scheme of Pareto with M, and updating the optimal individual position M;
step 209: comparing the new non-dominant solution with each non-dominant solution in the Archive set, and updating an externally stored Archive set P;
step 210: judging whether the external storage Archive set P is full, if so, executing step 211, otherwise, executing step 212;
step 211: excluding a set of weighting coefficients using a non-dominated sorting strategy;
step 212: adding the new result to an external storage Archive set P;
step 213: judging whether the iteration number reaches an upper limit, if so, executing step 215, otherwise, executing step 214;
step 214: the iteration time t = t +1, and the step 203 is returned;
step 215: outputting an externally stored Archive set P, and selecting an optimal weight coefficient set { alpha ] from P i ,i∈[1,4]}。
S5: and combining the obtained weight parameters of the prediction subsystems with the prediction models of the prediction subsystems to obtain a combined prediction model.
According to the method, a wavelet threshold denoising technology is adopted to optimize an original scene set of photovoltaic power generation, the influence of data noise points is effectively reduced, four single-index better prediction models are selected as prediction subsystems, the weight of the subsystems is determined through a multi-objective wolf grey optimization algorithm, the defects of a single prediction system are overcome, the stability and the accuracy of photovoltaic power generation prediction are improved, a comprehensive energy system is effectively assisted to carry out reasonable optimization scheduling, the energy consumption of the system is reduced, and the running economy of the system is improved.
Example two
It is an object of this embodiment to provide a computer device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method.
EXAMPLE III
An object of the present embodiment is to provide a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
Example four
The embodiment aims to provide a photovoltaic power generation prediction system considering wavelet decomposition and multi-objective optimization, and the system comprises:
a photovoltaic power generation scene set reconstruction module configured to: obtaining an initial scene set of photovoltaic power generation;
denoising the photovoltaic power generation initial scene set to reconstruct a photovoltaic power generation scene set;
a subsystem prediction module configured to: predicting the reconstructed photovoltaic power generation scene set by adopting a combined prediction system, selecting a single prediction system as a prediction subsystem of the combined system, and outputting a prediction result by each prediction subsystem according to the reconstructed photovoltaic power generation scene set;
a final prediction module configured to: determining a weight parameter of each prediction subsystem;
and weighting and outputting a final prediction result by using the obtained weight parameters of the prediction subsystems and the prediction results of the prediction subsystems on the reconstructed photovoltaic power generation scene set.
The steps involved in the apparatuses of the above second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description section of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present invention.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means for execution by the computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. The photovoltaic power generation prediction method considering wavelet decomposition and multi-objective optimization is characterized by comprising the following steps of:
obtaining an initial scene set of photovoltaic power generation;
denoising the photovoltaic power generation initial scene set to reconstruct a photovoltaic power generation scene set;
predicting the reconstructed photovoltaic power generation scene set by adopting a combined prediction system, selecting a single prediction system as a prediction subsystem of the combined system, and outputting a prediction result by each prediction subsystem according to the reconstructed photovoltaic power generation scene set;
determining a weight parameter of each prediction subsystem;
and weighting and outputting a final prediction result by utilizing the obtained weight parameters of the prediction subsystems and the prediction results of the prediction subsystems on the reconstructed photovoltaic power generation scene set.
2. The method for predicting photovoltaic power generation considering wavelet decomposition and multiobjective optimization according to claim 1, wherein the initial scene set of photovoltaic power generation includes parameters such as historical ambient temperature, humidity, average irradiation intensity, illumination rate and the like, and photovoltaic power generation power of corresponding time periods.
3. The photovoltaic power generation prediction method considering wavelet decomposition and multi-objective optimization as claimed in claim 1, wherein denoising the initial scene set of photovoltaic power generation to reconstruct the scene set of photovoltaic power generation specifically comprises:
a wavelet threshold denoising method is selected to reduce high-frequency noise of the photovoltaic power generation initial scene set, namely, data dead spots are eliminated, influence of extreme environment factors on photovoltaic power generation prediction is reduced, and the scene set is reconstructed.
4. The photovoltaic power generation prediction method considering wavelet decomposition and multi-objective optimization as claimed in claim 3, wherein the main parameters of the wavelet threshold denoising method, including the number k of decomposition layers and the threshold α of each layer, are automatically optimized using a genetic algorithm, reducing the randomness and volatility of the initial scene.
5. The photovoltaic power generation prediction method considering wavelet decomposition and multi-objective optimization as claimed in claim 1, wherein a combined prediction system is adopted to predict the reconstructed photovoltaic power generation scene set, and a single prediction system is selected as a prediction subsystem of the combined system, specifically:
and referring to four common prediction indexes, namely average absolute error, root mean square error, square absolute percentage error and determination coefficient, selecting four single prediction systems with better prediction results as subsystems of a combined system, wherein the four single prediction systems comprise a cyclic neural network, a deep convolutional neural network, a long-time memory neural network and a back propagation neural network.
6. The photovoltaic power generation prediction method considering wavelet decomposition and multi-objective optimization as claimed in claim 1, wherein determining the weight parameters of each prediction subsystem specifically comprises:
taking the weight parameter of each prediction subsystem as a decision variable { alpha i ,i∈[1,4]And determining the weight parameters of each prediction subsystem by adopting a multi-target improved grayling algorithm by taking the root mean square error and the square absolute percentage error of the combined prediction value and the actual photovoltaic power generation value of the prediction system as target functions.
7. The method for photovoltaic power generation prediction considering wavelet decomposition and multi-objective optimization of claim 6, wherein the objective function of the set of weight parameters for each prediction subsystem is determined by using a multi-objective grayish wolf optimization algorithm as follows:
in the formula: f 1 The square absolute percentage error of the combined predicted value of the prediction system and the actual photovoltaic power generation value is calculated; f 2 The root mean square error of the combined predicted value and the actual photovoltaic power generation value of the prediction system is obtained; alpha (alpha) ("alpha") i A weight parameter for the ith prediction subsystem prediction value; y is i (t) the photovoltaic power generation predicted value of the ith prediction subsystem at the time t; g (t) is the actual photovoltaic power generation power value at the time t.
8. The photovoltaic power generation prediction system considering wavelet decomposition and multi-objective optimization is characterized by comprising the following steps of:
a photovoltaic power generation scene set reconstruction module configured to: obtaining an initial scene set of photovoltaic power generation;
denoising the photovoltaic power generation initial scene set to reconstruct a photovoltaic power generation scene set;
a subsystem prediction module configured to: predicting the reconstructed photovoltaic power generation scene set by adopting a combined prediction system, selecting a single prediction system as a prediction subsystem of the combined system, and outputting a prediction result by each prediction subsystem according to the reconstructed photovoltaic power generation scene set;
a final prediction module configured to: determining a weight parameter of each prediction subsystem;
and weighting and outputting a final prediction result by utilizing the obtained weight parameters of the prediction subsystems and the prediction results of the prediction subsystems on the reconstructed photovoltaic power generation scene set.
9. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1-7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211371660.1A CN115640903A (en) | 2022-11-03 | 2022-11-03 | Photovoltaic power generation prediction method and system considering wavelet decomposition and multi-objective optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211371660.1A CN115640903A (en) | 2022-11-03 | 2022-11-03 | Photovoltaic power generation prediction method and system considering wavelet decomposition and multi-objective optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115640903A true CN115640903A (en) | 2023-01-24 |
Family
ID=84946793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211371660.1A Pending CN115640903A (en) | 2022-11-03 | 2022-11-03 | Photovoltaic power generation prediction method and system considering wavelet decomposition and multi-objective optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115640903A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117293817A (en) * | 2023-10-10 | 2023-12-26 | 华润电力技术研究院有限公司 | Power generation parameter prediction method and device |
-
2022
- 2022-11-03 CN CN202211371660.1A patent/CN115640903A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117293817A (en) * | 2023-10-10 | 2023-12-26 | 华润电力技术研究院有限公司 | Power generation parameter prediction method and device |
| CN117293817B (en) * | 2023-10-10 | 2024-06-07 | 华润电力技术研究院有限公司 | Power generation parameter prediction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cheng et al. | A new combined model based on multi-objective salp swarm optimization for wind speed forecasting | |
| Zhang et al. | A comprehensive wind speed prediction system based on Monte Carlo and artificial intelligence algorithms | |
| Wang et al. | A novel combined model based on hybrid optimization algorithm for electrical load forecasting | |
| CN110705743B (en) | New energy consumption electric quantity prediction method based on long-term and short-term memory neural network | |
| CN113128113B (en) | Lean information building load prediction method based on deep learning and transfer learning | |
| Zhang et al. | Wind speed prediction research considering wind speed ramp and residual distribution | |
| CN111611692A (en) | Equal-reliability-based design flood calculation method and system under climate change situation | |
| CN117613883A (en) | Method and device for predicting generated power, computer equipment and storage medium | |
| CN112215442A (en) | Method, system, device and medium for predicting short-term load of power system | |
| Wang et al. | Quantile deep learning model and multi-objective opposition elite marine predator optimization algorithm for wind speed prediction | |
| CN115907131B (en) | Method and system for constructing electric heating load prediction model in northern area | |
| CN113205228B (en) | Method for predicting short-term wind power generation output power | |
| CN115438833A (en) | Short-term power load hybrid prediction method | |
| CN115640903A (en) | Photovoltaic power generation prediction method and system considering wavelet decomposition and multi-objective optimization | |
| CN101587154A (en) | Quick mode estimation mode estimating method suitable for complicated node and large scale metric data | |
| CN117293809A (en) | Multi-time space scale new energy generation power prediction method based on large model | |
| Li et al. | Hybrid forecasting system considering the influence of seasonal factors under energy sustainable development goals | |
| CN118040678A (en) | Short-term offshore wind power combination prediction method | |
| CN118114813A (en) | Method and system for predicting load of battery replacement station based on variable screening time convolution | |
| Huang et al. | Short-term PV power forecasting based on CEEMDAN and ensemble DeepTCN | |
| Wang et al. | Grid load forecasting based on dual attention BiGRU and DILATE loss function | |
| Zhu | Research on adaptive combined wind speed prediction for each season based on improved gray relational analysis | |
| CN113779861B (en) | Photovoltaic Power Prediction Method and Terminal Equipment | |
| Quan et al. | An Ensemble Model of Wind Speed Forecasting Based on Variational Mode Decomposition and Bare‐Bones Fireworks Algorithm | |
| CN116128211A (en) | Wind-light-water combined short-term optimization scheduling method based on wind-light uncertainty prediction scene |
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 |