CN116702598A - Training method, device, equipment and storage medium for building achievement prediction model - Google Patents
Training method, device, equipment and storage medium for building achievement prediction model Download PDFInfo
- Publication number
- CN116702598A CN116702598A CN202310627339.3A CN202310627339A CN116702598A CN 116702598 A CN116702598 A CN 116702598A CN 202310627339 A CN202310627339 A CN 202310627339A CN 116702598 A CN116702598 A CN 116702598A
- Authority
- CN
- China
- Prior art keywords
- park
- neural network
- sample
- value
- construction effect
- 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
- 238000012549 training Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000010276 construction Methods 0.000 claims abstract description 169
- 230000000694 effects Effects 0.000 claims abstract description 130
- 238000013528 artificial neural network Methods 0.000 claims abstract description 121
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 53
- 230000002068 genetic effect Effects 0.000 claims abstract description 52
- 238000005457 optimization Methods 0.000 claims abstract description 31
- 230000006870 function Effects 0.000 claims description 29
- 238000010248 power generation Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 230000035699 permeability Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 description 15
- 230000005611 electricity Effects 0.000 description 13
- 230000008569 process Effects 0.000 description 13
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 2
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 210000000349 chromosome Anatomy 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 108700028369 Alleles Proteins 0.000 description 1
- 241000764238 Isis Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010429 evolutionary process Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a training method, a training device, training equipment and a training storage medium for building a success prediction model, wherein the training method comprises the following steps: acquiring a construction effect influence factor value of a sample park and a real construction effect value of the sample park; inputting the construction effect influence factor value of the sample park into the BP neural network to obtain a predicted construction effect value of the sample park and parameters of the BP neural network, and determining a training error of the sample park according to the predicted construction effect value and the real construction effect value of the sample park; based on a genetic algorithm, taking the parameters of the BP neural network as individuals, and taking the training error of a sample park as an adaptability value of the genetic algorithm to optimize, so as to obtain the parameters of the BP neural network after optimization; and updating the BP neural network according to the optimized parameters of the BP neural network to obtain a building success prediction model of the park. The method improves the generalization capability of the park construction effect prediction model and improves the prediction precision of the construction effect.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a training method, device and equipment for a park construction success prediction model and a storage medium.
Background
At present, the construction of the demonstration park plays an increasingly important role in the power system, and meanwhile, the planning construction of the demonstration park requires organic unification among power generation side, power grid side, user side and social side main bodies, so that the planning construction effect of the demonstration park is remarkably improved.
The existing demonstration park planning construction effect prediction method adopts a traditional machine learning method, the model parameters are selected according to human experience, the model generalization capability is low, and therefore the demonstration park planning construction effect prediction precision is low.
Disclosure of Invention
The invention provides a training method, a training device, training equipment and training storage media for a park construction success prediction model, which are used for improving the generalization capability of the park construction success prediction model and improving the prediction precision of the construction success.
According to one aspect of the invention, there is provided a training method for a building success prediction model of a campus, comprising:
acquiring a construction effect influence factor value of a sample park and a real construction effect value of the sample park; the construction effect influencing factors comprise electric power investment, electric power generation capacity, average electricity consumption and renewable energy permeability;
inputting the construction effect influence factor value of the sample park into the BP neural network to obtain a predicted construction effect value of the sample park and parameters of the BP neural network, and determining a training error of the sample park according to the predicted construction effect value and the real construction effect value of the sample park;
based on a genetic algorithm, taking the parameters of the BP neural network as individuals, and taking the training error of a sample park as an adaptability value of the genetic algorithm to optimize, so as to obtain the parameters of the BP neural network after optimization;
and updating the BP neural network according to the optimized parameters of the BP neural network to obtain a building success prediction model of the park.
According to another aspect of the present invention, there is provided a training apparatus for a building success prediction model of a campus, comprising:
the construction effect acquisition module is used for acquiring a construction effect influence factor value of the sample park and a real construction effect value of the sample park; the construction effect influencing factors comprise electric power investment, electric power generation capacity, average electricity consumption and renewable energy permeability;
the training error determining module is used for inputting the construction effect influence factor value of the sample park into the BP neural network to obtain the predicted construction effect value of the sample park and parameters of the BP neural network, and determining the training error of the sample park according to the predicted construction effect value of the sample park and the real construction effect value;
the optimization model determining module is used for optimizing the parameters of the BP neural network based on a genetic algorithm by taking the parameters of the BP neural network as individuals and taking the training errors of the sample park as fitness values of the genetic algorithm to obtain the optimized parameters of the BP neural network;
and the prediction model determining module is used for updating the BP neural network according to the optimized parameters of the BP neural network to obtain a park construction success prediction model.
According to another aspect of the present invention, there is provided a training apparatus for a construction success prediction model of a campus, the training apparatus for a construction success prediction model comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of training the predictive model of the building performance of the campus of any one of the embodiments of the invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to perform the training method of the construction success prediction model of any of the embodiments of the present invention when executed.
According to the technical scheme, the construction effect influence factor value of the sample park and the real construction effect value of the sample park are obtained; the construction effect influencing factors comprise electric power investment, electric power generation capacity, average electricity consumption and renewable energy permeability; inputting the construction effect influence factor value of the sample park into the BP neural network to obtain a predicted construction effect value of the sample park and parameters of the BP neural network, and determining a training error of the sample park according to the predicted construction effect value and the real construction effect value of the sample park; based on a genetic algorithm, taking the parameters of the BP neural network as individuals, and taking the training error of a sample park as an adaptability value of the genetic algorithm to optimize, so as to obtain the parameters of the BP neural network after optimization; and updating the BP neural network according to the optimized parameters of the BP neural network to obtain a building success prediction model of the park. According to the technical scheme, in the park construction effect prediction process, parameters of the BP neural network are optimized through the genetic algorithm, the intervention of human experience is reduced through parameter optimization, and then the optimized planning construction effect prediction model is obtained, the generalization capability of the park construction effect prediction model is improved, and the prediction precision of the construction effect is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for training a predictive model of the building success of a campus according to a first embodiment of the invention;
fig. 2 is a schematic structural diagram of a BP neural network according to a first embodiment of the present invention;
FIG. 3 is a flow chart of a method for training a predictive model of the building success of a campus provided according to a second embodiment of the invention;
fig. 4 is a schematic structural diagram of a training device for a building success prediction model of a campus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device for implementing a training method for building a success prediction model according to a fourth embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a training method for a building success prediction model of a park, which is provided in an embodiment of the present invention, where the embodiment is applicable to a situation of predicting a building success of a park, the method may be performed by a training device for the building success prediction model, the training device for the building success prediction model may be implemented in a form of hardware and/or software, and the training device for the building success prediction model may be configured in an electronic device.
As shown in fig. 1, the training method for the building success prediction model of the park according to the first embodiment includes the following steps:
s101, acquiring a construction effect influence factor value of a sample park and a real construction effect value of the sample park; the construction effect influencing factors comprise electric power investment, power generation capacity, electricity consumption per capita and renewable energy permeability.
The construction effect influencing factors are factors influencing the park construction effect, and reasons and conditions for causing the park construction effect are contained in the factors. The construction effect influencing factors include electric power investment, electric power generation amount, electricity consumption per capita and renewable energy permeability, wherein the electric power investment is the construction behavior and capital action behavior of an electric power manufacturer on a power supply or a power grid, and represents the electric power supply capacity of a park; the generating capacity is the quantity of electric energy generated by energy conversion of the generator, and represents the generating capacity of the generator in the park; the electricity consumption of people is the average annual electricity consumption of each resident in a park, and the life quality of the resident is represented; the permeability of renewable energy is the ratio of the generated energy to the total generated energy of renewable energy, and the power generation mode of renewable energy can be wind power generation, hydroelectric power generation or solar power generation by way of example.
Specifically, by analyzing the current situation of planning construction of the sample park, the influence factors influencing the planning construction effect of the park are identified, the construction effect influence factor value of the sample park and the real construction effect value of the sample park are obtained, and the relation between the construction effect influence factor value and the real construction effect value is established.
The method for obtaining the construction effect influence factor value of the sample park and the sample park can be that historical effect data of the sample park is obtained from a data base of the park, wherein the historical effect data comprises the construction effect influence factor value and a real construction effect value; the method for acquiring the construction effect influence factor value of the sample park and the sample park can also be to acquire the historical effect data of the sample park from park related technicians; the manner of obtaining the construction performance factor value of the sample park and the sample park may be to go to the park to collect the historical performance data of the sample park according to a compliance manner, which is not limited in this embodiment.
S102, inputting the construction effect influence factor value of the sample park into the BP neural network to obtain the predicted construction effect value of the sample park and parameters of the BP neural network, and determining the training error of the sample park according to the predicted construction effect value and the real construction effect value of the sample park.
The BP neural network is a machine learning training model, in particular to a multi-layer feedforward neural network, each layer consists of neurons, and the training mode is forward transmission of signals and back propagation of errors. The BP neural network may be a three-layer neural network structure, i.e., an input layer, an hidden layer, and an output layer, and the specific BP network structure is shown in fig. 2. Each layer of neural network consists of neurons, the neurons of each neural network layer are fully connected, and the neurons in one layer are not connected. The parameters of the BP neural network are inherent adjustable scalar parameters of the BP neural network, and specifically comprise a connection weight and a threshold value, wherein the connection weight is the probability transmitted from a previous neuron to a current neuron, represents the connection strength of the neuron, and the threshold value is the critical value of the external stimulus of the neuron which is influenced by the stimulus received by the neuron. The training error is the difference degree between the predicted construction effect value and the real construction effect value of the sample park. Illustratively, the connection weight is a random value within the (0, 1) interval.
Specifically, the construction effect influence factor value of the sample park is input to the input layer of the BP neural network, and the output result of the output layer is the predicted construction effect value of the sample park. Specifically, the neurons of the input layer in the BP neural network receive the construction effect influence factor values of the sample park, the construction effect influence factor values of the sample park are transmitted to the hidden layer neurons in the BP neural network, the hidden layer neurons process and transform the received information, and the information is transmitted to the output layer in the BP neural network through the hidden layer of the last layer in the BP neural network, so that forward transmission of the BP neural network is realized. When the difference between the predicted construction effect value output by the BP neural network and the actual construction effect value of the sample park exceeds the expected value, the training process of the BP neural network enters an error back propagation process. Firstly, starting from an output layer, correcting the weight of each layer according to errors, and sequentially transmitting the weight to an implicit layer and an input layer. And through continuous forward information propagation and error reverse propagation, adjusting the connection weight of each layer, completing the training of the BP neural network, and determining the training error of the sample park according to the predicted construction effect value and the real construction effect value of the sample park.
And S103, optimizing the parameters of the BP neural network by taking the parameters of the BP neural network as individuals and taking the training errors of the sample park as fitness values of the genetic algorithm based on the genetic algorithm to obtain the optimized parameters of the BP neural network.
The genetic algorithm is an evolutionary algorithm, and searches an optimal solution by simulating a natural evolutionary process, and performs genetic operation on individuals in a population to generate new individuals which gradually approach the optimal solution. The fitness value is a function value of a genetic algorithm fitness function and represents the fitness of an individual.
Specifically, the parameters of the BP neural network are used as individuals in the genetic algorithm, namely, the individuals comprise the neural network connection weight and the threshold value. And initializing the population of individuals in the genetic algorithm according to the connection weight and the threshold of the BP neural network, and coding the individuals in a real number coding mode. The individuals in the genetic algorithm are initialized in a population mode, the individuals are encoded in a real number encoding mode, for example, a chromosome encoding mode is adopted, floating point number encoding is selected, and a connection weight and a threshold are obtained, wherein the formula is as follows:
s＝n 1 ×n 2 +n 2 ×n 3 +n 2 +n 3
wherein s is the length of the chromosome and n 1 N is the number of neurons of the input layer 2 The number of neurons being hidden layer, n 3 The number of output layer neurons.
And optimizing the training error between the predicted construction effect value and the real construction effect value of the park as a fitness value through a genetic algorithm, specifically optimizing the connection weight and the threshold of the BP neural network through the genetic algorithm, and obtaining the parameters of the BP neural network after optimization.
And S104, updating the BP neural network according to the optimized parameters of the BP neural network to obtain a park construction achievement prediction model.
The construction success prediction model is a BP neural network model optimized by a genetic algorithm. Specifically, parameters of the BP neural network, namely the original connection weight and the original threshold value are changed into new connection weight and threshold value through optimization processing of a genetic algorithm, the new connection weight and threshold value replace the original connection weight and the original threshold value of the BP neural network, and the parameters of the BP neural network are updated. And under the condition that the BP neural network meets the optimization target, obtaining a park construction success prediction model.
The prediction result of the construction success prediction model is evaluated by two evaluation indexes, namely, an average relative error (Mean Absolute Percentage Error, MAPE) and a root mean square error (Root Mean Squared Error, RMSE), as follows:
MAPE is the average value of relative errors of park planning construction effect influence indexes, and the calculation expression is as follows:
in the method, in the process of the invention,to construct the actual value of the effect, y i J is the number of samples for the construction outcome prediction value.
RMSE is the standard error of the park construction effect impact index, and the calculation expression is:
in the method, in the process of the invention,to construct the actual value of the effect, y i J is the number of samples for the construction outcome prediction value.
Specifically, the training method of the construction success prediction model of the sample park optimizes two parameters of the connection weight and the threshold of the BP neural network through a genetic algorithm to obtain an optimized BP neural network model, and predicts the construction success of the target park by using the optimized BP neural network model determined by the sample park.
In an alternative embodiment, the construction effect influence factor value of the target park is input into the construction effect prediction model of the park to obtain the construction effect of the target park.
Specifically, the construction effect influence factor values of the target park to be predicted and the target park are obtained, for example, the electric power investment, the electric power generation amount, the electricity consumption per capita and the renewable energy permeability of the target park are obtained; and inputting the electric power investment, the generated energy, the average electricity consumption and the renewable energy permeability of the target park into a pre-constructed construction effect prediction model to obtain the construction effect of the target park. Because the building achievement prediction model is used for optimizing the BP neural network by the sampling genetic algorithm in the training process, the building achievement characteristics of the sample park can be learned in the training process of the building achievement prediction model, and the optimization performance introduced by the genetic algorithm is also provided, so that the prediction precision of the building achievement of the target park can be improved.
According to the technical scheme, the construction effect influence factor value of the sample park and the real construction effect value of the sample park are obtained; the construction effect influencing factors comprise electric power investment, electric power generation capacity, average electricity consumption and renewable energy permeability; inputting the construction effect influence factor value of the sample park into the BP neural network to obtain a predicted construction effect value of the sample park and parameters of the BP neural network, and determining a training error of the sample park according to the predicted construction effect value and the real construction effect value of the sample park; based on a genetic algorithm, taking the parameters of the BP neural network as individuals, and taking the training error of a sample park as an adaptability value of the genetic algorithm to optimize, so as to obtain the parameters of the BP neural network after optimization; and updating the BP neural network according to the optimized parameters of the BP neural network to obtain a building success prediction model of the park. According to the technical scheme, the initial weight and the threshold value of the BP neural network are optimized through the genetic algorithm, so that the optimized BP neural network is obtained, the construction effect prediction model of the park is further obtained, the generalization capability of the construction effect prediction model of the park is improved, and the prediction precision of the construction effect is improved.
Example two
Fig. 3 is a flowchart of a training method for a building achievement model of a campus according to a second embodiment of the present invention, which is further refined based on the foregoing embodiments. As shown in fig. 3, the method comprises the following steps:
s201, acquiring a construction effect influence factor value of a sample park and a real construction effect value of the sample park; the construction effect influencing factors comprise electric power investment, power generation capacity, electricity consumption per capita and renewable energy permeability.
S202, inputting the construction effect influence factor value of the sample park into the BP neural network to obtain the predicted construction effect value of the sample park and parameters of the BP neural network, and determining the training error of the sample park according to the predicted construction effect value and the real construction effect value of the sample park.
S203, determining an fitness function according to the training error of the sample park based on a genetic algorithm.
The fitness function is a basis for finding out whether an optimal solution can be found by optimizing and searching through a genetic algorithm.
Specifically, in the process of training the BP neural network, the fitness function of the genetic algorithm is determined according to the training error of the sample park determined by the predicted construction effect value and the real construction effect value of the sample park.
Optionally, determining the fitness function according to the training error of the sample park includes:
wherein fit is a fitness function, and k is the logarithm of input and output sampling data; n is the number of network output nodes;is the expected output value of the kth node; y (k) is a predicted output value of the kth node, and ζ is a value approaching zero.
Specifically, the fitness function is determined according to the degree of data difference between the predicted output value and the ideal output value, which are the construction results of the sample park, specifically, the inverse of the sum of half of the square sum of errors of the predicted output value and the ideal output value and a value approaching zero. Exemplary, e.g., predicted output values of 10, 20, and 30 for each node of the construction effort, ideal output values of 15, 25, and 35, ζ is 0.1, then fitness value of the fitness function isIs 0.027.
S204, determining the probability of the individual being selected by adopting a fitness function.
Specifically, according to the fitness function, determining an individual fitness value of the fitness function, wherein the probability of the individual being selected is related to the individual fitness value, presetting a threshold value for the individual fitness value, and when the individual fitness value is greater than or equal to the threshold value, selecting the corresponding individual as an optimal individual; when the individual fitness value is less than the threshold value, the corresponding individual is not selected.
S205, selecting, crossing and mutating according to the probability of the individual being selected, and obtaining the mutated individual.
Specifically, the fitness function calculates the fitness value of each individual, and provides the fitness value for the genetic algorithm to carry out evolutionary calculation, so as to find the individual corresponding to the optimal fitness value, and the mutated individual is obtained. Specifically, the selection operation is to transfer the optimized individual to the next generation according to a certain method based on the individual fitness value, and the probability of selecting the individual i is that
Wherein P is i Probability of being selected for an individual, f i And m is the size of the population as a fitness function.
The crossover operation is to randomly match individuals in the population into pairs, each pair of individuals are crossed by an arithmetic, new individuals are generated after the arithmetic, and the formula for generating the new individuals is as follows:
in the method, in the process of the invention,and->Is->And->New individuals produced, alpha being interval [0,1]Random numbers uniformly distributed therein.
The mutation operation is to change the gene of one or some individuals into the corresponding allele according to the mutation probability for each individual in the population.
x k ＝x min +β(x min +x max )
Wherein x is k Is mutated gene, x min And x max The maximum and minimum of population individuals are intervals of [0,1 ]]Random numbers uniformly distributed therein.
S206, optimizing parameters of the BP neural network by adopting the mutated individuals.
Specifically, after genetic algorithm selection, crossover and mutation operation, a mutated individual is obtained, and the mutated individual is an optimized BP neural network connection weight and a threshold, namely parameters of the BP neural network are updated and optimized by the optimized individual.
Optionally, optimizing parameters of the BP neural network by using the mutated individual includes: determining whether the mutated individual meets the optimization target of the genetic algorithm; if the parameters are satisfied, selecting an optimal individual from the mutated individuals, and optimizing the parameters of the BP neural network by adopting the optimal individual.
Wherein, the optimization target of the genetic algorithm is to optimize the cut-off condition of the BP neural network. The determination manner of the cutoff condition may be determined according to the magnitude of the fitness value, or may be determined according to the iteration number of the genetic algorithm, which is not limited in comparison in this embodiment.
Specifically, whether the mutated individual meets the optimization target of the genetic algorithm is judged, if the optimization target is determined according to the fitness value, whether the mutated individual meets the fitness value is judged, if yes, the optimal individual is selected from the mutated individual, the parameters of the BP neural network are optimized by the optimal individual, if not, the parameters are input into the BP neural network, and the parameter adjustment of the network is carried out through forward information transmission and error back propagation of the BP neural network; if the determination mode of the optimization target is determined according to the iteration times of the genetic algorithm, judging whether the mutated individual meets the iteration times, if so, selecting an optimal individual from the mutated individual, optimizing parameters of the BP neural network by adopting the optimal individual, and if not, inputting the optimal individual into the BP neural network, and carrying out self-tuning of the network through forward information transmission and error back propagation of the BP neural network. For example, if the iteration parameter of the genetic algorithm is preset to be 100 times, the genetic algorithm is iterated for 100 times, so as to meet the optimization target, further, an optimal individual is selected from the mutated individuals, and the parameters of the BP neural network are optimized by adopting the optimal individual.
According to the technical scheme provided by the embodiment of the invention, the fitness function in the genetic algorithm is determined, so that the mutated individual is determined, and the mutated individual is adopted to optimize the parameters of the BP neural network, so that an optimized BP neural network model is obtained, and the generalization performance of the BP neural network model is improved.
Example III
Fig. 4 is a schematic structural diagram of a training device for a park construction success prediction model according to a third embodiment of the present invention. As shown in fig. 4, the training device for the construction success prediction model includes: a construction success acquisition module 401, a training error determination module 402, an optimization model determination module 403, and a prediction model determination module 404.
The construction effect obtaining module 401 is configured to obtain a construction effect influence factor value of the sample park and a real construction effect value of the sample park; the construction effect influencing factors comprise electric power investment, power generation capacity, electricity consumption per capita and renewable energy permeability.
The training error determining module 402 is configured to input a construction success factor value of the sample park into the BP neural network, obtain a predicted construction success value of the sample park and parameters of the BP neural network, and determine a training error of the sample park according to the predicted construction success value and the real construction success value of the sample park.
The optimization model determining module 403 is configured to optimize parameters of the BP neural network based on a genetic algorithm by using the parameters of the BP neural network as an individual and using a training error of the sample park as an fitness value of the genetic algorithm, so as to obtain the parameters of the BP neural network after optimization.
And the prediction model determining module 404 is configured to update the BP neural network according to the optimized parameters of the BP neural network, so as to obtain a building success prediction model of the park.
According to the technical scheme, the construction effect influence factor value of the sample park and the real construction effect value of the sample park are obtained; the construction effect influencing factors comprise electric power investment, electric power generation capacity, average electricity consumption and renewable energy permeability; inputting the construction effect influence factor value of the sample park into the BP neural network to obtain a predicted construction effect value of the sample park and parameters of the BP neural network, and determining a training error of the sample park according to the predicted construction effect value and the real construction effect value of the sample park; based on a genetic algorithm, taking the parameters of the BP neural network as individuals, and taking the training error of a sample park as an adaptability value of the genetic algorithm to optimize, so as to obtain the parameters of the BP neural network after optimization; and updating the BP neural network according to the optimized parameters of the BP neural network to obtain a building success prediction model of the park. According to the technical scheme, parameters of the BP neural network are optimized through the genetic algorithm, the intervention of human experience is reduced through parameter optimization, and then the optimized planning construction success prediction model is obtained, the generalization capability of the construction success prediction model of a park is improved, and the prediction precision of construction success is improved.
Optionally, the optimization model determining module includes:
the fitness function determining unit is used for determining a fitness function according to the training error of the sample park;
an individual probability determining unit for determining a probability of an individual being selected using the fitness function;
variant individual determination unit: the method comprises the steps of selecting, crossing and mutating according to the probability that an individual is selected to obtain a mutated individual;
parameter optimization unit: the method is used for optimizing parameters of the BP neural network by adopting mutated individuals.
Optionally, the fitness function determining unit specifically includes:
wherein fit is a fitness function, and k is the logarithm of input and output sampling data; n is the number of network output nodes;is the expected output value of the kth node; y (k) is a predicted output value of the kth node, and ζ is a value approaching zero.
Optionally, the parameter optimization unit includes:
an optimization target subunit, configured to determine whether the mutated individual meets an optimization target of the genetic algorithm;
and the optimal individual optimizing subunit is used for selecting an optimal individual from the mutated individual and optimizing parameters of the BP neural network by adopting the optimal individual if the parameters are met.
Optionally, the training device for building the success prediction model further includes:
and the target achievement determining module is used for inputting the construction achievement influence factor value of the target park into the construction achievement prediction model of the park to obtain the construction achievement of the target park.
The training device for the building success prediction model of the park provided by the embodiment of the invention can execute the training method for the building success prediction model provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 5 shows a schematic diagram of an electronic device 50 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 50 includes at least one processor 51, and a memory, such as a Read Only Memory (ROM) 52, a Random Access Memory (RAM) 53, etc., communicatively connected to the at least one processor 51, in which the memory stores a computer program executable by the at least one processor, and the processor 51 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 52 or the computer program loaded from the storage unit 58 into the Random Access Memory (RAM) 53. In the RAM 53, various programs and data required for the operation of the electronic device 50 can also be stored. The processor 51, the ROM 52 and the RAM 53 are connected to each other via a bus 54. An input/output (I/O) interface 55 is also connected to bus 54.
Various components in the electronic device 50 are connected to the I/O interface 55, including: an input unit 56 such as a keyboard, a mouse, etc.; an output unit 57 such as various types of displays, speakers, and the like; a storage unit 58 such as a magnetic disk, an optical disk, or the like; and a communication unit 59 such as a network card, modem, wireless communication transceiver, etc. The communication unit 59 allows the electronic device 50 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks.
The processor 51 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as a training method for a building outcome prediction model for a campus.
In some embodiments, the training method of building the success prediction model may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 58. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 50 via the ROM 52 and/or the communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the training method of building a success prediction model described above may be performed. Alternatively, in other embodiments, processor 51 may be configured as a training method to build a success prediction model in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A training method of a park construction success prediction model is characterized by comprising the following steps:
acquiring a construction effect influence factor value of a sample park and a real construction effect value of the sample park; the construction effect influencing factors comprise electric power investment, power generation capacity, average power consumption and renewable energy permeability;
inputting the construction effect influence factor value of the sample park into the BP neural network to obtain a predicted construction effect value of the sample park and parameters of the BP neural network, and determining a training error of the sample park according to the predicted construction effect value of the sample park and the real construction effect value;
based on a genetic algorithm, taking the parameters of the BP neural network as individuals, and taking the training error of a sample park as an adaptability value of the genetic algorithm to optimize, so as to obtain the parameters of the BP neural network after optimization;
and updating the BP neural network according to the optimized parameters of the BP neural network to obtain a building success prediction model of the park.
2. The method of claim 1, wherein optimizing the fitness value of the genetic algorithm with the training error of the sample park to obtain the parameters of the optimized BP neural network comprises:
determining an fitness function according to the training error of the sample park;
determining the probability of the individual being selected by adopting the fitness function;
selecting, crossing and mutating according to the probability that the individual is selected to obtain a mutated individual;
and optimizing parameters of the BP neural network by adopting the mutated individuals.
3. The method of claim 2, wherein determining the fitness function based on the training error for the sample park comprises:
wherein fit is a fitness function, and k is the logarithm of input and output sampling data; n is the number of network output nodes;is the expected output value of the kth node; y (k) Zeta is a value approaching zero, which is the predicted output value of the kth node.
4. The method of claim 2, wherein optimizing parameters of the BP neural network using the mutated individual comprises:
determining whether the mutated individual meets the optimization target of the genetic algorithm;
if the parameters are satisfied, selecting an optimal individual from the mutated individuals, and optimizing the parameters of the BP neural network by adopting the optimal individual.
5. The method according to claim 1, wherein the method further comprises:
and inputting the construction effect influence factor value of the target park into a construction effect prediction model of the park to obtain the construction effect of the target park.
6. The utility model provides a training device of construction success prediction model in garden, its characterized in that includes:
the construction effect acquisition module is used for acquiring a construction effect influence factor value of the sample park and a real construction effect value of the sample park; the construction effect influencing factors comprise electric power investment, power generation capacity, average power consumption and renewable energy permeability;
the training error determining module is used for inputting the construction effect influence factor value of the sample park into the BP neural network to obtain the predicted construction effect value of the sample park and parameters of the BP neural network, and determining the training error of the sample park according to the predicted construction effect value of the sample park and the real construction effect value;
the optimization model determining module is used for optimizing the parameters of the BP neural network based on a genetic algorithm by taking the parameters of the BP neural network as individuals and taking the training errors of the sample park as fitness values of the genetic algorithm to obtain the optimized parameters of the BP neural network;
and the prediction model determining module is used for updating the BP neural network according to the optimized parameters of the BP neural network to obtain a park construction success prediction model.
7. The apparatus of claim 6, wherein the optimization model determination module comprises:
the fitness function determining unit is used for determining a fitness function according to the training error of the sample park;
an individual probability determining unit for determining a probability of an individual being selected using the fitness function;
the variant individual determining unit is used for carrying out selection, crossing and variant processing according to the probability of the individual being selected to obtain a variant individual;
and the parameter optimization unit is used for optimizing the parameters of the BP neural network by adopting the mutated individuals.
8. The apparatus of claim 6, the apparatus further comprising:
and the target achievement determining module is used for inputting the construction achievement influence factor value of the target park into the construction achievement prediction model of the park to obtain the construction achievement of the target park.
9. Training equipment of construction success prediction model in garden, characterized by, construction success prediction model's training equipment includes: at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the training method of building a success prediction model of any of claims 1-6.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the training method of the build success prediction model of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310627339.3A CN116702598A (en) | 2023-05-30 | 2023-05-30 | Training method, device, equipment and storage medium for building achievement prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310627339.3A CN116702598A (en) | 2023-05-30 | 2023-05-30 | Training method, device, equipment and storage medium for building achievement prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116702598A true CN116702598A (en) | 2023-09-05 |
Family
ID=87844397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310627339.3A Pending CN116702598A (en) | 2023-05-30 | 2023-05-30 | Training method, device, equipment and storage medium for building achievement prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702598A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118014009A (en) * | 2024-02-26 | 2024-05-10 | 广芯微电子（广州）股份有限公司 | Neural network initial value optimizing method based on genetic algorithm |
-
2023
- 2023-05-30 CN CN202310627339.3A patent/CN116702598A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118014009A (en) * | 2024-02-26 | 2024-05-10 | 广芯微电子（广州）股份有限公司 | Neural network initial value optimizing method based on genetic algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5888640B2 (en) | Photovoltaic power generation prediction apparatus, solar power generation prediction method, and solar power generation prediction program | |
| CN106532778B (en) | Method for calculating maximum access capacity of distributed photovoltaic grid connection | |
| CN112464566B (en) | Transformer oil temperature prediction method based on genetic algorithm and BP neural network | |
| CN110910004A (en) | Reservoir dispatching rule extraction method and system with multiple uncertainties | |
| CN110751318A (en) | IPSO-LSTM-based ultra-short-term power load prediction method | |
| CN113722980B (en) | Ocean wave height prediction method, ocean wave height prediction system, computer equipment, storage medium and terminal | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN111598231A (en) | Cable connector wire temperature prediction based on GA (genetic algorithm) optimized serial BP (back propagation) network | |
| CN115833101B (en) | Power scheduling method, device, electronic equipment and storage medium | |
| CN116702598A (en) | Training method, device, equipment and storage medium for building achievement prediction model | |
| CN116523148A (en) | Distribution network distribution transformer overload early warning method, device and equipment | |
| CN115222046A (en) | Neural network structure searching method and device, electronic equipment and storage medium | |
| CN116796639A (en) | Short-term power load prediction method, device and equipment | |
| CN117907872A (en) | Battery life prediction method and device, electronic equipment and storage medium | |
| CN116683471B (en) | Configuration method, device and equipment of reactive power compensation resource | |
| CN117335425A (en) | Tidal current calculation method based on GA-BP neural network | |
| CN111859807A (en) | Initial pressure optimizing method, device, equipment and storage medium for steam turbine | |
| CN116128148A (en) | Photovoltaic power station output prediction network training method, prediction method, device and equipment | |
| CN115952921A (en) | Photovoltaic energy power prediction method and device, electronic equipment and storage medium | |
| CN111079996B (en) | Virtual seat system based on BP neural network power load prediction | |
| CN117767413A (en) | Distributed photovoltaic power grid division method, device, equipment and storage medium | |
| CN117130280B (en) | Pump room control method and device, electronic equipment and storage medium | |
| CN118100233B (en) | Micro-grid group energy storage capacity configuration method and device, electronic equipment and storage medium | |
| CN118508521A (en) | Power distribution method, device, equipment, storage medium and program product | |
| CN115860249A (en) | Distributed photovoltaic power generation power prediction method, device, equipment and medium |
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 |