CN117039894B - Photovoltaic power short-term prediction method and system based on improved dung beetle optimization algorithm - Google Patents
Photovoltaic power short-term prediction method and system based on improved dung beetle optimization algorithm Download PDFInfo
- Publication number
- CN117039894B CN117039894B CN202311295678.2A CN202311295678A CN117039894B CN 117039894 B CN117039894 B CN 117039894B CN 202311295678 A CN202311295678 A CN 202311295678A CN 117039894 B CN117039894 B CN 117039894B
- Authority
- CN
- China
- Prior art keywords
- dung
- beetles
- dung beetles
- neural network
- photovoltaic power
- 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
- 241000254173 Coleoptera Species 0.000 title claims abstract description 149
- 210000003608 fece Anatomy 0.000 title claims abstract description 149
- 238000000034 method Methods 0.000 title claims abstract description 108
- 238000005457 optimization Methods 0.000 title claims abstract description 49
- 238000013528 artificial neural network Methods 0.000 claims abstract description 72
- 238000010248 power generation Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims description 42
- 241001229848 Aphodius granarius Species 0.000 claims description 36
- 238000005096 rolling process Methods 0.000 claims description 34
- 238000009395 breeding Methods 0.000 claims description 24
- 230000001488 breeding effect Effects 0.000 claims description 24
- 230000002431 foraging effect Effects 0.000 claims description 18
- 238000003860 storage Methods 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 239000003795 chemical substances by application Substances 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 230000017448 oviposition Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
Abstract
The invention discloses a photovoltaic power short-term prediction method and a system based on an improved dung beetle optimization algorithm, wherein the method comprises the following steps: constructing a BP neural network, and determining the node number of an input layer, a hidden layer and an output layer of the BP neural network; optimizing the original threshold and the original weight of the BP neural network as the initial population position of the improved dung beetle optimization algorithm to obtain the optimal threshold and the optimal weight of the BP neural network; training a BP neural network comprising an optimal threshold and optimal weight to obtain a photovoltaic power short-term prediction model; and acquiring real-time multidimensional operation state parameters of the photovoltaic power generation equipment, inputting the real-time multidimensional operation state parameters into a photovoltaic power short-term prediction model, and outputting a photovoltaic power short-term prediction result by the photovoltaic power short-term prediction model. The photovoltaic short-term power prediction of the BP neural network after threshold and weight optimization by the improved dung beetle optimization algorithm can be more accurate, and the requirement of the photovoltaic short-term power can be met.
Description
Technical Field
The invention belongs to the technical field of photovoltaic prediction, and particularly relates to a photovoltaic power short-term prediction method and system based on an improved dung beetle optimization algorithm.
Background
The power generated by the photovoltaic is mainly affected by local meteorological conditions, and the factors of solar irradiance, temperature, cloud cover, humidity, wind speed and the like are mainly included. Due to uncertainty of weather environment changes, accuracy of weather forecast is not high, and accuracy of power prediction of the photovoltaic power generation system is difficult to guarantee. Errors in photovoltaic short-term power prediction can affect not only economic benefits, but more importantly, stability, reliability and scheduling of power system operation. The accuracy of photovoltaic power generation power prediction is improved, the influence of photovoltaic power uncertainty on a power grid can be effectively reduced, the reliability of the system is improved, the electric energy quality is maintained, and the penetration level of a photovoltaic system is improved. Therefore, reliable and accurate photovoltaic power short-term prediction is of great importance.
Short-term prediction of photovoltaic power predicts the change condition of photovoltaic power generation power in a future period of time according to the real-time state of the current photovoltaic power generation power, and the prediction time is generally 24 hours. The current short-term photovoltaic power generation power prediction method is based on the same thought, namely, a prediction formula or model is established by utilizing mathematic and physical theory and related data, and the generated energy of the photovoltaic power station is predicted by the prediction formula or model. These methods use data input from different sources, including ground cameras, satellite images, and numerical weather forecast (NWP), among others. Although ground cameras have high accuracy in short-term predictions, deployment and maintenance costs can be high. Meanwhile, satellite images and numerical weather forecast data perform well in long-term predictions, but perform poorly in short-term as well as high spatial resolution predictions. For example, when irregular flow generated by cloud layer is caused by atmospheric disturbance in a short time in the face of sudden procedural weather with strong locality, and local rainfall is caused by rain accumulation cloud formed by sudden convective weather, prediction accuracy is difficult to maintain.
Disclosure of Invention
The invention provides a photovoltaic power short-term prediction method and system based on an improved dung beetle optimization algorithm, which are used for solving the technical problem that the photovoltaic power short-term prediction precision cannot be improved.
In a first aspect, the invention provides a photovoltaic power short-term prediction method based on an improved dung beetle optimization algorithm, which comprises the following steps:
step 1, constructing a BP neural network, and determining the node number of an input layer, a hidden layer and an output layer of the BP neural network;
step 2, optimizing the original threshold value and the original weight of the BP neural network as the initial population position of the improved dung beetle optimization algorithm to obtain the optimal threshold value and the optimal weight of the BP neural network;
step 3, training the BP neural network comprising the optimal threshold and the optimal weight to obtain a photovoltaic power short-term prediction model;
and 4, acquiring real-time multidimensional operation state parameters of the photovoltaic power generation equipment, inputting the real-time multidimensional operation state parameters into the photovoltaic power short-term prediction model, and outputting a photovoltaic power short-term prediction result by the photovoltaic power short-term prediction model.
In a second aspect, the invention provides a photovoltaic power short-term prediction system based on an improved dung beetle optimization algorithm, which comprises:
the building module is configured to build the BP neural network and determine the node number of an input layer, a hidden layer and an output layer of the BP neural network;
the optimizing module is configured to take an original threshold value and an original weight of the BP neural network as an initial population position for improving a dung beetle optimizing algorithm to optimize, so as to obtain an optimal threshold value and an optimal weight of the BP neural network;
the training module is configured to train the BP neural network comprising the optimal threshold and the optimal weight to obtain a photovoltaic power short-term prediction model;
the output module is configured to acquire real-time multidimensional operation state parameters of the photovoltaic power generation equipment, input the real-time multidimensional operation state parameters into the photovoltaic power short-term prediction model, and output a photovoltaic power short-term prediction result by the photovoltaic power short-term prediction model.
In a third aspect, there is provided an electronic device, comprising: the system comprises at least one processor and a memory communicatively connected with 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 perform the steps of the method for short-term prediction of photovoltaic power based on the improved dung beetle optimization algorithm of any of the embodiments of the present invention.
In a fourth aspect, the present invention also provides a computer readable storage medium, on which a computer program is stored, where the program instructions, when executed by a processor, cause the processor to execute the steps of the method for short-term predicting photovoltaic power based on the improved dung beetle optimization algorithm according to any embodiment of the present invention.
According to the photovoltaic power short-term prediction method and system based on the improved dung beetle optimization algorithm, the BP neural network optimized by the improved dung beetle optimization algorithm is adopted to conduct short-term power prediction of the photovoltaic power generation equipment, the problem that the threshold value and the weight of the BP neural network are difficult to accurately select is solved, the short-term power prediction condition of the photovoltaic power generation equipment can be accurately output in real time through fusion of various parameters, the photovoltaic short-term power prediction of the BP neural network after the threshold value and the weight are optimized by the improved dung beetle optimization algorithm can be more accurate, the requirement of the photovoltaic short-term power can be met, and the scheme can achieve short-term power monitoring of the photovoltaic power generation equipment on the premise that the original tightness of the photovoltaic power generation equipment is not damaged, and safe scheduling and stable operation of a power system are ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a photovoltaic power short-term prediction method based on an improved dung beetle optimization algorithm according to an embodiment of the present invention;
FIG. 2 is a graph comparing convergence curves before and after improvement of a dung beetle optimization algorithm according to an embodiment of the present invention;
FIG. 3 is a block diagram of a photovoltaic power short-term prediction system based on an improved dung beetle optimization algorithm according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of a photovoltaic power short-term prediction method based on an improved dung beetle optimization algorithm is shown.
As shown in fig. 1, the photovoltaic power short-term prediction method based on the improved dung beetle optimization algorithm specifically comprises the following steps:
step 1, constructing a BP neural network, and determining the node number of an input layer, a hidden layer and an output layer of the BP neural network.
In the step, determining the node number of an input layer of the BP neural network, wherein the node number of the input layer is equal to the dimension of an input vector; in this embodiment, the dimension of the input vector is the dimension of the selected initial sample data set, and thus the number of input layer nodes of the BP neural network is 10.
Determining the node number of an output layer of the BP neural network, wherein the node number of the output layer is equal to the predicted result number; the output in this embodiment is a temperature value inside the photovoltaic power generation apparatus, and thus the number of nodes of the output layer is 1.
Determining the node number of a hidden layer of the BP neural network, wherein the expression for calculating the node number of the hidden layer is as follows:wherein->For the number of nodes of the hidden layer->For the number of nodes of the input layer, < > for>For the number of nodes of the output layer, < > for>Is [1,10]Constant of the same.
And 2, optimizing the original threshold and the original weight of the BP neural network as the initial population position of the improved dung beetle optimization algorithm to obtain the optimal threshold and the optimal weight of the BP neural network.
Step 2.1: taking an original threshold value and an original weight of the BP neural network as an initial position of a dung beetle population;
step 2.2: the rolling ball, dancing, foraging, breeding and stealing behavior of the dung beetles are designed to be used as updating rules so as to optimize the initial position, wherein each dung beetle population consists of four different agents, namely the rolling ball dung beetles, breeding dung beetles, small dung beetles and stealing dung beetles, and the method specifically comprises the following steps:
step 2.2.1: rolling ball dung beetle
In order to simulate rolling ball behaviors, the rolling ball dung beetles need to move in a given direction in the whole search space, and the positions of the rolling ball dung beetles of the rolling ball can be updated in the rolling process, wherein the expression of a rolling mathematical model of the rolling ball dung beetles is as follows:
，
，
，
in the method, in the process of the invention,for the current iteration number>Is->Only the ball dung beetles are in->Position information at the time of iteration, +.>In order to take the value within +.>First random number between->For natural coefficients, assign-1 or 1, < ->Is of->Constant of->Is the global worst position, +.>To simulate the change in light intensity, +.>Is->Only the ball dung beetles are in->The location information at the time of the iteration,is->Only the ball dung beetles are in->Position information at the time of iteration, +.>For the deflection coefficient, the value is at (0,0.2]；
When the dung beetles encounter obstacles and cannot advance, tangential functions are used for simulating the choreography of the ball dung beetles, a new rolling direction is obtained, when the ball dung beetles successfully determine a new direction, the ball dung beetles continue to roll the ball forwards, and the positions of the dancing behaviors of the ball dung beetles are defined as follows:
，
in the method, in the process of the invention,in order to take the value within +.>A second random number in between, when +.>When the position is 0, 0.5 or 1, the position of the rolling ball dung beetle is not updated;
step 2.2.2: breeding dung beetles
Providing a boundary selection strategy to simulate and breed the oviposition area of the dung beetles, wherein the expression of the boundary selection strategy is as follows:
in the method, in the process of the invention,for the current local best position +.>And->Respectively the lower boundary and the upper boundary of the spawning area,，/>for maximum number of iterations +.>And->The lower and upper bounds of the optimization problem, respectively;
once the spawning area is determined, the breeding ball of the spawning area is selected for spawning by breeding the dung beetles, and only one egg is produced by each breeding dung beetle in each iteration, and the boundary range of the spawning area is dynamically changed, so that the positions of the breeding balls are also dynamic in the iteration process, and the iteration process is expressed as follows:
，
in the method, in the process of the invention,is->First->Position information of individual breeding balls,/->And->Two sizes are respectively +.>Independent random vector, ">Dimension for optimization problem;
step 2.2.3: small dung beetle
Establishing an optimal foraging area to guide the foraging of the small dung beetles and simulating the foraging process of the small dung beetles in the natural world, wherein the boundary of the optimal foraging area of the small dung beetles is defined as:
，
in the method, in the process of the invention,for global best position, ++>And->The lower limit and the upper limit of the best foraging area, respectively,/->In order to take the value within +.>Random numbers in between;
the expression of the position update of the small dung beetles:
，
in the method, in the process of the invention,is->Only small dung beetles are at the->Position information of the iteration->Is->Only small dung beetles are atPosition information of the iteration->For random numbers subject to normal distribution +.>Is of->Is a random vector of (c).
Step 2.2.4: theft dung beetle
When (when)Is the best food source, supposing +.>The vicinity is the best place to fight for food, and in the iterative process, the position information of the stealing dung beetles is updated, the expression for updating the position information of the stealing dung beetles is as follows:
，
in the method, in the process of the invention,is->Only steal dung beetle at +.>Position information of the iteration->Is of a size of +.>Random vector of>Is constant;
step 2.3: selecting an average position of the small dung beetles, and integrating the searching process by utilizing the average position and the global optimal positionConsider global information, wherein updated firstOnly small dung beetles are at the->The expression of the position information of the iteration is:
，
，
in the method, in the process of the invention,for the total number of the small dung beetles>For the average position of all small dung beetles, < > about->Is the step length;
step 2.4: the ratio of the stealing dung beetles in all dung beetles is highest, the worst position of the stealing dung beetles is corrected based on a retaining elite strategy, so that the stealing dung beetles randomly move to the current optimal position, wherein the worst position is the worst positionOnly steal dung beetle at +.>The expression of the position information of the iteration is:
，
in the method, in the process of the invention,to be at the worst positionIs>Only steal dung beetle at +.>Position information of the iteration->Is the worst position +.>Only steal dung beetle at +.>Position information for the second iteration.
And step 3, training the BP neural network comprising the optimal threshold and the optimal weight to obtain a photovoltaic power short-term prediction model.
In the step, an initial sample data set is constructed according to the historical multidimensional operation state parameters of the photovoltaic power generation equipment and the actually measured power data; and carrying out normalization processing on the initial sample data set, and training the BP neural network containing the optimal threshold and the optimal weight according to the normalized initial sample data set to obtain a photovoltaic power short-term prediction model.
Specifically, the expression for normalizing the initial sample data set is:
，
in the method, in the process of the invention,normalized for historical multidimensional operating state parameters in the initial sample dataset at [0,1 ]]Value of interval>For a historical multidimensional operating state variable in the initial sample data set,/->For the maximum value of the historical multidimensional operating state variables in the initial sample dataset, +.>Is the minimum of the historical multidimensional operating state parameters in the initial sample dataset.
The historical multidimensional operating state parameter includes historical irradiance of the operating place of the equipmentHistorical temperature of plant operation site->And historical wind speed of equipment operation place->. The initial sample dataset constructed is represented as:t represents the matrix transpose.
In a specific embodiment, an original threshold value and an original weight of the BP neural network are used as initial population positions for improving a dung beetle optimization algorithm to perform optimization, and an optimal threshold value and an optimal weight of the BP neural network are obtained; the improvement of the dung beetle optimizing algorithm increases the algorithm convergence speed and optimizing precision, and increases the capability of jumping out of a local optimal solution, and the improvement of the dung beetle optimizing algorithm IDBO and the dung beetle optimizing algorithm DBO convergence curves are shown in figure 2.
And 4, acquiring real-time multidimensional operation state parameters of the photovoltaic power generation equipment, inputting the real-time multidimensional operation state parameters into the photovoltaic power short-term prediction model, and outputting a photovoltaic power short-term prediction result by the photovoltaic power short-term prediction model.
In summary, the method adopts the BP neural network optimized by the improved dung beetle optimization algorithm to predict the short-term power of the photovoltaic power generation equipment, solves the problem that the threshold value and the weight of the BP neural network are difficult to accurately select, can accurately output the short-term power prediction condition of the photovoltaic power generation equipment in real time through fusion of various parameters, can meet the requirement of the photovoltaic short-term power by optimizing the threshold value and the weight of the BP neural network by the improved dung beetle optimization algorithm, and can realize the short-term power monitoring of the photovoltaic power generation equipment on the premise of not damaging the original tightness of the photovoltaic power generation equipment, thereby ensuring the safe scheduling and stable operation of the power system.
Referring to fig. 3, a block diagram of a photovoltaic power short-term prediction system based on an improved dung beetle optimization algorithm is shown.
As shown in fig. 3, the photovoltaic power short-term prediction system 200 includes a construction module 210, an optimization module 220, a training module 230, and an output module 240.
The construction module 210 is configured to construct a BP neural network, and determine the node numbers of an input layer, a hidden layer and an output layer of the BP neural network; the optimizing module 220 is configured to use the original threshold value and the original weight of the BP neural network as an initial population position for improving a dung beetle optimizing algorithm to optimize, so as to obtain an optimal threshold value and an optimal weight of the BP neural network; the training module 230 is configured to train the BP neural network including the optimal threshold and the optimal weight to obtain a photovoltaic power short-term prediction model; the output module 240 is configured to obtain a real-time multi-dimensional operation state parameter of the photovoltaic power generation device, and input the real-time multi-dimensional operation state parameter into the photovoltaic power short-term prediction model, where the photovoltaic power short-term prediction model outputs a photovoltaic power short-term prediction result.
It should be understood that the modules depicted in fig. 3 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations and features described above for the method and the corresponding technical effects are equally applicable to the modules in fig. 3, and are not described here again.
In other embodiments, the present invention further provides a computer readable storage medium, on which a computer program is stored, where the program instructions, when executed by a processor, cause the processor to perform the photovoltaic power short-term prediction method based on the improved dung beetle optimization algorithm in any of the above method embodiments;
as one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions configured to:
constructing a BP neural network, and determining the node number of an input layer, a hidden layer and an output layer of the BP neural network;
optimizing the original threshold and the original weight of the BP neural network as the initial population position of the improved dung beetle optimization algorithm to obtain the optimal threshold and the optimal weight of the BP neural network;
training the BP neural network comprising the optimal threshold and the optimal weight to obtain a photovoltaic power short-term prediction model;
and acquiring real-time multidimensional operation state parameters of the photovoltaic power generation equipment, inputting the real-time multidimensional operation state parameters into the photovoltaic power short-term prediction model, and outputting a photovoltaic power short-term prediction result by the photovoltaic power short-term prediction model.
The computer readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the stored data area may store data created from the use of a photovoltaic power short-term prediction system based on a modified dung beetle optimization algorithm, and the like. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer readable storage medium optionally includes a memory remotely located with respect to the processor, the remote memory being connectable via a network to a photovoltaic power short-term prediction system based on a modified dung beetle optimization algorithm. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 4, where the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 may be connected by a bus or other means, for example in fig. 4. Memory 320 is the computer-readable storage medium described above. Processor 310 executes various functional applications and data processing of the server by running non-volatile software programs, instructions and modules stored in memory 320, i.e., implementing the photovoltaic power short-term prediction method of the method embodiments described above based on the improved dung beetle optimization algorithm. Input device 330 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the photovoltaic power short-term prediction system based on the improved dung beetle optimization algorithm. The output device 340 may include a display device such as a display screen.
The electronic equipment can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
As an implementation manner, the electronic device is applied to a photovoltaic power short-term prediction system based on an improved dung beetle optimization algorithm, and is used for a client, and the method comprises the following steps: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:
constructing a BP neural network, and determining the node number of an input layer, a hidden layer and an output layer of the BP neural network;
optimizing the original threshold and the original weight of the BP neural network as the initial population position of the improved dung beetle optimization algorithm to obtain the optimal threshold and the optimal weight of the BP neural network;
training the BP neural network comprising the optimal threshold and the optimal weight to obtain a photovoltaic power short-term prediction model;
and acquiring real-time multidimensional operation state parameters of the photovoltaic power generation equipment, inputting the real-time multidimensional operation state parameters into the photovoltaic power short-term prediction model, and outputting a photovoltaic power short-term prediction result by the photovoltaic power short-term prediction model.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. The photovoltaic power short-term prediction method based on the improved dung beetle optimization algorithm is characterized by comprising the following steps of:
step 1, constructing a BP neural network, and determining the node number of an input layer, a hidden layer and an output layer of the BP neural network;
step 2, optimizing the original threshold value and the original weight of the BP neural network as the initial population position of the improved dung beetle optimization algorithm to obtain the optimal threshold value and the optimal weight of the BP neural network, wherein optimizing the original threshold value and the original weight of the BP neural network as the initial population position of the improved dung beetle optimization algorithm to obtain the optimal threshold value and the optimal weight of the BP neural network comprises the following steps:
step 2.1: taking an original threshold value and an original weight of the BP neural network as an initial position of a dung beetle population;
step 2.2: the rolling ball, dancing, foraging, breeding and stealing behavior of the dung beetles are designed to be used as updating rules so as to optimize the initial position, wherein each dung beetle population consists of four different agents, namely the rolling ball dung beetles, breeding dung beetles, small dung beetles and stealing dung beetles, and the method specifically comprises the following steps:
step 2.2.1: ball dung beetles;
in order to simulate rolling ball behaviors, the rolling ball dung beetles need to move in a given direction in the whole search space, and the positions of the rolling ball dung beetles of the rolling ball can be updated in the rolling process, wherein the expression of a rolling mathematical model of the rolling ball dung beetles is as follows:
，
，
，
in the method, in the process of the invention,for the current iteration number>Is->Only the ball dung beetles are in->Position at time of iterationInformation (I)>In order to take the value within +.>First random number between->For natural coefficients, assign-1 or 1, < ->Is of->Constant of->Is the global worst position, +.>To simulate the change in light intensity, +.>Is->Only the ball dung beetles are in->The location information at the time of the iteration,is->Only the ball dung beetles are in->Position information at the time of iteration, +.>Is the deflection coefficient;
when the dung beetles encounter obstacles and cannot advance, tangential functions are used for simulating the choreography of the ball dung beetles, a new rolling direction is obtained, when the ball dung beetles successfully determine a new direction, the ball dung beetles continue to roll the ball forwards, and the positions of the dancing behaviors of the ball dung beetles are defined as follows:
，
in the method, in the process of the invention,in order to take the value within +.>A second random number in between, when +.>When the position is 0, 0.5 or 1, the position of the rolling ball dung beetle is not updated;
step 2.2.2: breeding dung beetles;
providing a boundary selection strategy to simulate and breed the oviposition area of the dung beetles, wherein the expression of the boundary selection strategy is as follows:
，
in the method, in the process of the invention,for the current local best position +.>And->Respectively the lower parts of spawning areasThe upper and lower border>，For maximum number of iterations +.>And->The lower and upper bounds of the optimization problem, respectively;
once the spawning area is determined, the breeding ball of the spawning area is selected for spawning by breeding the dung beetles, and only one egg is produced by each breeding dung beetle in each iteration, and the boundary range of the spawning area is dynamically changed, so that the positions of the breeding balls are also dynamic in the iteration process, and the iteration process is expressed as follows:
，
in the method, in the process of the invention,is->First->Position information of individual breeding balls,/->And->Two sizes are respectively +.>Is independent of (1)Vector of machine (I/O)>Dimension for optimization problem;
step 2.2.3: small dung beetles;
establishing an optimal foraging area to guide the foraging of the small dung beetles and simulating the foraging process of the small dung beetles in the natural world, wherein the boundary of the optimal foraging area of the small dung beetles is defined as:
，
in the method, in the process of the invention,for global best position, ++>And->The lower limit and the upper limit of the best foraging area, respectively,/->To take the value in the range ofRandom numbers in between;
the expression of the position update of the small dung beetles:
，
in the method, in the process of the invention,is->Only small dung beetles are at the->Position information of the iteration->Is->Only small dung beetles are at the->Position information of the iteration->For random numbers subject to normal distribution +.>Is of->Is a random vector of (a);
step 2.2.4: stealing dung beetles;
when (when)Is the best food source, supposing +.>The vicinity is the best place to fight for food, and in the iterative process, the position information of the stealing dung beetles is updated, the expression for updating the position information of the stealing dung beetles is as follows:
，
in the method, in the process of the invention,is->Only steal dung beetle at +.>Position information of the iteration->Is of a size of +.>Random vector of>Is constant;
step 2.3: selecting an average position of the small dung beetles, and comprehensively considering global information in a searching process by utilizing the average position and the global optimal position, wherein the updated first positionOnly small dung beetles are at the->The expression of the position information of the iteration is:
，
，
in the method, in the process of the invention,for the total number of the small dung beetles>For the average position of all small dung beetles, < > about->Is the step length;
step 2.4: the ratio of the stealing dung beetles in all dung beetles is highest, the worst position of the stealing dung beetles is corrected based on a retaining elite strategy, so that the stealing dung beetles randomly move to the current optimal position, wherein the worst position is the worst positionOnly steal dung beetle at +.>The expression of the position information of the iteration is:
，
in the method, in the process of the invention,is the worst position +.>Only steal dung beetle at +.>Position information of the iteration->Is the worst position +.>Only steal dung beetle at +.>Position information of the second iteration;
step 3, training the BP neural network comprising the optimal threshold and the optimal weight to obtain a photovoltaic power short-term prediction model;
and 4, acquiring real-time multidimensional operation state parameters of the photovoltaic power generation equipment, inputting the real-time multidimensional operation state parameters into the photovoltaic power short-term prediction model, and outputting a photovoltaic power short-term prediction result by the photovoltaic power short-term prediction model.
2. The method for short-term prediction of photovoltaic power based on the improved dung beetle optimization algorithm according to claim 1, wherein in step 1, determining the node numbers of the input layer, the hidden layer and the output layer of the BP neural network comprises:
determining the node number of an input layer of the BP neural network, wherein the node number of the input layer is equal to the dimension of an input vector;
determining the node number of an output layer of the BP neural network, wherein the node number of the output layer is equal to the predicted result number;
determining the node number of a hidden layer of the BP neural network, wherein the expression for calculating the node number of the hidden layer is as follows:
，
in the method, in the process of the invention,for the number of nodes of the hidden layer->For the number of nodes of the input layer, < > for>For the number of nodes of the output layer, < > for>Is [1,10]Constant of the same.
3. The method for short-term prediction of photovoltaic power based on the improved dung beetle optimization algorithm according to claim 1, wherein in step 3, training the BP neural network including the optimal threshold and the optimal weight to obtain a short-term prediction model of photovoltaic power includes:
constructing an initial sample data set according to the historical multidimensional operation state parameters of the photovoltaic power generation equipment and the actually measured power data;
and carrying out normalization processing on the initial sample data set, and training the BP neural network containing the optimal threshold and the optimal weight according to the normalized initial sample data set to obtain a photovoltaic power short-term prediction model.
4. The method for short-term prediction of photovoltaic power based on an improved dung beetle optimization algorithm according to claim 3, wherein the expression for normalizing the initial sample dataset is:
，
in the method, in the process of the invention,normalized for historical multidimensional operating state parameters in the initial sample dataset at [0,1 ]]Value of interval>For a historical multidimensional operating state variable in the initial sample data set,/->For the maximum value of the historical multidimensional operating state variables in the initial sample dataset, +.>Is the minimum of the historical multidimensional operating state parameters in the initial sample dataset.
5. A photovoltaic power short-term prediction system based on an improved dung beetle optimization algorithm is characterized by comprising:
the building module is configured to build the BP neural network and determine the node number of an input layer, a hidden layer and an output layer of the BP neural network;
the optimizing module is configured to optimize an original threshold value and an original weight of the BP neural network as an initial population position of an improved dung beetle optimizing algorithm to obtain an optimal threshold value and an optimal weight of the BP neural network, wherein the optimizing the original threshold value and the original weight of the BP neural network as the initial population position of the improved dung beetle optimizing algorithm to obtain the optimal threshold value and the optimal weight of the BP neural network comprises:
step 2.1: taking an original threshold value and an original weight of the BP neural network as an initial position of a dung beetle population;
step 2.2: the rolling ball, dancing, foraging, breeding and stealing behavior of the dung beetles are designed to be used as updating rules so as to optimize the initial position, wherein each dung beetle population consists of four different agents, namely the rolling ball dung beetles, breeding dung beetles, small dung beetles and stealing dung beetles, and the method specifically comprises the following steps:
step 2.2.1: ball dung beetles;
in order to simulate rolling ball behaviors, the rolling ball dung beetles need to move in a given direction in the whole search space, and the positions of the rolling ball dung beetles of the rolling ball can be updated in the rolling process, wherein the expression of a rolling mathematical model of the rolling ball dung beetles is as follows:
，
，
，
in the method, in the process of the invention,for the current iteration number>Is->Only the ball dung beetles are in->Position information at the time of iteration, +.>In order to take the value within +.>First random number between->For natural coefficients, assign-1 or 1, < ->Is of->Constant of->Is the global worst position, +.>To simulate the change in light intensity, +.>Is->Only the ball dung beetles are in->The location information at the time of the iteration,is->Only the ball dung beetles are in->Position information at the time of iteration, +.>Is the deflection coefficient;
when the dung beetles encounter obstacles and cannot advance, tangential functions are used for simulating the choreography of the ball dung beetles, a new rolling direction is obtained, when the ball dung beetles successfully determine a new direction, the ball dung beetles continue to roll the ball forwards, and the positions of the dancing behaviors of the ball dung beetles are defined as follows:
，
in the method, in the process of the invention,in order to take the value within +.>A second random number in between, when +.>When the position is 0, 0.5 or 1, the position of the rolling ball dung beetle is not updated;
step 2.2.2: breeding dung beetles;
providing a boundary selection strategy to simulate and breed the oviposition area of the dung beetles, wherein the expression of the boundary selection strategy is as follows:
，
in the method, in the process of the invention,for the current local best position +.>And->Lower and upper bounds of spawning area, respectively, < >>，For maximum number of iterations +.>And->The lower and upper bounds of the optimization problem, respectively;
once the spawning area is determined, the breeding ball of the spawning area is selected for spawning by breeding the dung beetles, and only one egg is produced by each breeding dung beetle in each iteration, and the boundary range of the spawning area is dynamically changed, so that the positions of the breeding balls are also dynamic in the iteration process, and the iteration process is expressed as follows:
，
in the method, in the process of the invention,is->First->Position information of individual breeding balls,/->And->Two sizes are respectively +.>Independent random vector, ">Dimension for optimization problem;
step 2.2.3: small dung beetles;
establishing an optimal foraging area to guide the foraging of the small dung beetles and simulating the foraging process of the small dung beetles in the natural world, wherein the boundary of the optimal foraging area of the small dung beetles is defined as:
，
in the method, in the process of the invention,for global best position, ++>And->The lower limit and the upper limit of the best foraging area, respectively,/->To take the value in the range ofRandom numbers in between;
the expression of the position update of the small dung beetles:
，
in the method, in the process of the invention,is->Only small dung beetles are at the->Position information of the iteration->Is->Only small dung beetles are at the->Position information of the iteration->For random numbers subject to normal distribution +.>Is of->Is a random vector of (a);
step 2.2.4: stealing dung beetles;
when (when)Is the best food source, supposing +.>The vicinity is the best for competing for foodIn the iterative process, the position information of the stealing dung beetles is updated, wherein the expression of the updated position information of the stealing dung beetles is as follows:
，
in the method, in the process of the invention,is->Only steal dung beetle at +.>Position information of the iteration->Is of a size of +.>Random vector of>Is constant;
step 2.3: selecting an average position of the small dung beetles, and comprehensively considering global information in a searching process by utilizing the average position and the global optimal position, wherein the updated first positionOnly small dung beetles are at the->The expression of the position information of the iteration is:
，
，
in the method, in the process of the invention,for the total number of the small dung beetles>For the average position of all small dung beetles, < > about->Is the step length;
step 2.4: the ratio of the stealing dung beetles in all dung beetles is highest, the worst position of the stealing dung beetles is corrected based on a retaining elite strategy, so that the stealing dung beetles randomly move to the current optimal position, wherein the worst position is the worst positionOnly steal dung beetle at +.>The expression of the position information of the iteration is:
，
in the method, in the process of the invention,is the worst position +.>Only steal dung beetle at +.>Position information of the iteration->Is the worst position +.>Only steal dung beetle at +.>Position information of the second iteration;
the training module is configured to train the BP neural network comprising the optimal threshold and the optimal weight to obtain a photovoltaic power short-term prediction model;
the output module is configured to acquire real-time multidimensional operation state parameters of the photovoltaic power generation equipment, input the real-time multidimensional operation state parameters into the photovoltaic power short-term prediction model, and output a photovoltaic power short-term prediction result by the photovoltaic power short-term prediction model.
6. An electronic device, comprising: at least one processor, and 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 perform the method of any one of claims 1 to 4.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311295678.2A CN117039894B (en) | 2023-10-09 | 2023-10-09 | Photovoltaic power short-term prediction method and system based on improved dung beetle optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311295678.2A CN117039894B (en) | 2023-10-09 | 2023-10-09 | Photovoltaic power short-term prediction method and system based on improved dung beetle optimization algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117039894A CN117039894A (en) | 2023-11-10 |
| CN117039894B true CN117039894B (en) | 2024-04-05 |
Family
ID=88645337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311295678.2A Active CN117039894B (en) | 2023-10-09 | 2023-10-09 | Photovoltaic power short-term prediction method and system based on improved dung beetle optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117039894B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743835B (en) * | 2024-02-20 | 2024-04-30 | 齐鲁工业大学(山东省科学院) | Underwater sound signal noise reduction method based on improved dung beetle algorithm optimization variational modal decomposition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852902A (en) * | 2019-11-14 | 2020-02-28 | 合肥工业大学 | Photovoltaic power generation power prediction method based on BAS-BP |
| CN113538125A (en) * | 2021-06-29 | 2021-10-22 | 百维金科(上海)信息科技有限公司 | Risk rating method for optimizing Hopfield neural network based on firefly algorithm |
| CN116796194A (en) * | 2023-06-27 | 2023-09-22 | 国网宁夏电力有限公司石嘴山供电公司 | IDBO-KELM-BiGRU neural network-based active power virtual collection method for distributed photovoltaic power station |
| CN116845875A (en) * | 2023-07-06 | 2023-10-03 | 南京师范大学 | WOA-BP-based short-term photovoltaic output prediction method and device |
-
2023
- 2023-10-09 CN CN202311295678.2A patent/CN117039894B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852902A (en) * | 2019-11-14 | 2020-02-28 | 合肥工业大学 | Photovoltaic power generation power prediction method based on BAS-BP |
| CN113538125A (en) * | 2021-06-29 | 2021-10-22 | 百维金科(上海)信息科技有限公司 | Risk rating method for optimizing Hopfield neural network based on firefly algorithm |
| CN116796194A (en) * | 2023-06-27 | 2023-09-22 | 国网宁夏电力有限公司石嘴山供电公司 | IDBO-KELM-BiGRU neural network-based active power virtual collection method for distributed photovoltaic power station |
| CN116845875A (en) * | 2023-07-06 | 2023-10-03 | 南京师范大学 | WOA-BP-based short-term photovoltaic output prediction method and device |
Non-Patent Citations (3)
| Title |
|---|
| Short-Term Load Forecasting Based on DBO-LSTM Model;Y. Zhang, T. Ma, T. Li and Y. Wang;《2023 3rd International Conference on Energy Engineering and Power Systems (EEPS)》;第972-977页 * |
| 改进蜣螂算法优化LSTM的光伏阵列故障诊断;李斌 等;《电力系统及其自动化学报》;第1-10页 * |
| 王建华.《高压开关电器发展前沿技术》.机械工业出版社,2019,第235-238页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117039894A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ridha et al. | Boosted mutation-based Harris hawks optimizer for parameters identification of single-diode solar cell models | |
| Ibrahim et al. | A novel hybrid model for hourly global solar radiation prediction using random forests technique and firefly algorithm | |
| CN111639787B (en) | Spatio-temporal data prediction method based on graph convolution network | |
| CN117039894B (en) | Photovoltaic power short-term prediction method and system based on improved dung beetle optimization algorithm | |
| JP2013074695A (en) | Device, method and program for predicting photovoltaic generation | |
| US11300707B2 (en) | Solar forecasting using machine learned cloudiness classification | |
| CN113762603B (en) | Photovoltaic base station short-term photovoltaic power prediction method based on improved sparrow algorithm optimization | |
| CN114240000A (en) | Air quality prediction method based on space-time graph convolution network | |
| CN110942205A (en) | Short-term photovoltaic power generation power prediction method based on HIMVO-SVM | |
| Niu et al. | Short-term wind speed hybrid forecasting model based on bias correcting study and its application | |
| CN114330100A (en) | Short-term photovoltaic power probability interval prediction method | |
| Wendt et al. | Knowledge-guided genetic algorithm for input parameter optimisation in environmental modelling | |
| Iqbal et al. | Stochastic maximum power point tracking of photovoltaic energy system under partial shading conditions | |
| CN116722545B (en) | Photovoltaic power generation prediction method based on multi-source data and related equipment | |
| Akar et al. | Evaluation of tree-based machine learning and deep learning techniques in temperature-based potential evapotranspiration prediction | |
| CN117217374A (en) | Short-term wind power prediction method based on DBO-ELM | |
| CN116796194A (en) | IDBO-KELM-BiGRU neural network-based active power virtual collection method for distributed photovoltaic power station | |
| CN112307672A (en) | BP neural network short-term wind power prediction method based on cuckoo algorithm optimization | |
| CN116579509A (en) | Photovoltaic power generation prediction method based on virtual reality | |
| CN116562455A (en) | Air temperature forecast data processing method and device of wind driven generator and computer equipment | |
| CN113487068B (en) | Short-term wind power prediction method based on long-term and short-term memory module | |
| CN112836885B (en) | Combined load prediction method, combined load prediction device, electronic equipment and storage medium | |
| Mu et al. | Optimal precursors identification for North Atlantic oscillation using the parallel intelligence algorithm | |
| Wang et al. | Optimization of Convolutional Long Short-Term Memory Hybrid Neural Network Model Based on Genetic Algorithm for Weather Prediction | |
| Penteliuc et al. | Short Term Cloud Motion Forecast based on Boid's Algorithm for use in PV Output Prediction |
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 |