CN117151265A - Power consumption difference analysis method and device, electronic equipment and storage medium - Google Patents
Power consumption difference analysis method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117151265A CN117151265A CN202310231687.9A CN202310231687A CN117151265A CN 117151265 A CN117151265 A CN 117151265A CN 202310231687 A CN202310231687 A CN 202310231687A CN 117151265 A CN117151265 A CN 117151265A
- Authority
- CN
- China
- Prior art keywords
- chromosome
- preset
- fitness value
- value
- chromosomes
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 24
- 230000002068 genetic effect Effects 0.000 claims abstract description 44
- 238000003062 neural network model Methods 0.000 claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 33
- 230000005611 electricity Effects 0.000 claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 210000000349 chromosome Anatomy 0.000 claims description 357
- 230000035772 mutation Effects 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 22
- 210000002569 neuron Anatomy 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 15
- 238000002922 simulated annealing Methods 0.000 claims description 11
- 230000009191 jumping Effects 0.000 claims description 4
- 230000003094 perturbing effect Effects 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 230000002028 premature Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010353 genetic engineering Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000000137 annealing Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 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
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a power consumption difference analysis method, a device, electronic equipment and a storage medium. The method comprises the following steps: acquiring user data of a target power user; predicting according to the user data and a preset prediction model to obtain the electricity demand of the target power user; the preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm; and determining a differential power consumption scheme matched with the target power consumer based on the power consumption requirement of the target power consumer. The method and the device can improve the accuracy of the power consumption difference analysis of the user, determine the differentiated power consumption scheme of the user and meet the power consumption requirement of the power user.
Description
Technical Field
The present invention relates to the field of power technologies, and in particular, to a power consumption difference analysis method, a device, an electronic apparatus, and a storage medium.
Background
Because the electricity demand of each user is gradually changed, the existing power supply service cannot completely meet the electricity demand of the user. Therefore, it is very important to accurately predict the power demand of each user and provide differentiated services based on the power demand of the user.
However, the existing method cannot accurately predict the electricity consumption of the user, is easy to converge too early, causes a large prediction error, and is difficult to meet the electricity consumption requirement of the user, so that how to predict the electricity consumption data more accurately, conduct differential analysis on the user, and provide differential service for the user is a problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention provides a power consumption difference analysis method, a device, electronic equipment and a storage medium, which are used for improving the accuracy of power consumption difference analysis of a user.
In a first aspect, an embodiment of the present invention provides a power consumption difference analysis method, including:
acquiring user data of a target power user;
predicting according to the user data and a preset prediction model to obtain the electricity demand of the target power user; the preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm;
and determining a differential power consumption scheme matched with the target power consumer based on the power consumption requirement of the target power consumer.
In one possible implementation manner, the preset prediction model is obtained by:
acquiring historical user data of a target power user;
Training a preset neural network model according to the historical user data to obtain a preset prediction model.
In one possible implementation, training a preset neural network model according to historical user data to obtain a preset prediction model includes:
setting related parameters for training a preset neural network model, wherein the related parameters comprise group size, iteration times, maximum iteration times, preset fitness value, temperature withdrawal rate, value ranges of all weights and value ranges of all thresholds;
randomly generating a corresponding number of weight and threshold combinations according to the population size in the value range of each weight and the value range of each threshold, and coding according to the randomly generated weight and threshold combinations to obtain a corresponding number of chromosomes, wherein the chromosomes form a chromosome population;
step three, respectively calculating a first fitness value of each chromosome according to the weight value and the threshold value corresponding to each chromosome in the chromosome population;
fourth, genetic operation is carried out on each chromosome according to the first fitness value of each chromosome, and a genetic chromosome population is obtained;
Step five, after performing simulated annealing operation on each chromosome in the genetic chromosome population, respectively calculating a second fitness value of each chromosome, and adding 1 to the current iteration times;
step six, judging whether the current iteration number reaches the maximum iteration number or whether the maximum second fitness value is larger than or equal to a preset fitness value;
step seven, if the current iteration number does not reach the maximum iteration number and the maximum second fitness value is smaller than the preset fitness value, performing temperature withdrawal according to the temperature withdrawal rate, determining the second fitness value of each chromosome as a new first fitness value of the chromosome, and jumping to the step four;
and step eight, stopping iteration if the current iteration number reaches the maximum iteration number or the maximum second fitness value is larger than or equal to a preset fitness value, and respectively determining a weight value and a threshold value corresponding to a chromosome with the maximum second fitness value as an optimal weight value and an optimal threshold value to obtain a preset prediction model.
In one possible implementation, the relevant parameters further include a preset variation rate;
performing genetic manipulation on each chromosome according to the first fitness value of each chromosome to obtain a genetic chromosome population, including:
Respectively determining the probability of each chromosome appearing in the filial generation according to the first fitness value corresponding to each chromosome, and determining the chromosome corresponding to the probability meeting the condition as a first target chromosome;
randomly determining two chromosomes in a first target chromosome, and performing cross treatment to obtain a new chromosome;
taking the new chromosome and the chromosomes of the first target chromosome except the two chromosomes subjected to the cross treatment as a first chromosome group;
generating a first random number according to each piece of point location information of each chromosome in the first chromosome group; the first random number is positioned in the value range of the corresponding point location information;
and carrying out mutation treatment on corresponding points of the corresponding chromosomes in sequence according to the preset mutation rate and each first random number to obtain a genetic chromosome population.
In one possible implementation, two chromosomes are randomly determined in the first target chromosome, and the two chromosomes are subjected to crossover processing to obtain a new chromosome, including:
randomly determining two chromosomes and a point position on each chromosome in a first target chromosome, and exchanging the numerical values corresponding to the two points to obtain a new chromosome;
Carrying out mutation processing on corresponding points of corresponding chromosomes in sequence according to a preset mutation rate and each first random number, wherein the mutation processing comprises the following steps:
generating a second random number for each locus of each chromosome in the first population of chromosomes; if the second random number is smaller than or equal to the preset mutation rate, replacing the numerical value of the corresponding point position of the corresponding chromosome in the first chromosome group with the corresponding first random number; if the second random number is larger than the preset mutation rate, the numerical value of the corresponding point position of the corresponding chromosome in the first chromosome group is not replaced.
In one possible implementation, after performing the simulated annealing operation on each chromosome in the population of genetic chromosomes, calculating the second fitness value of each chromosome, respectively, includes:
according to the weight and the threshold value corresponding to each chromosome in the genetic chromosome population, respectively calculating a third fitness value of each chromosome;
randomly perturbing each chromosome to obtain chromosome perturbation groups;
calculating a fourth fitness value of each chromosome in the chromosome disturbance population;
updating each chromosome in the chromosome disturbance group according to the third fitness value and the fourth fitness value, and taking the updated chromosomes as a new chromosome disturbance group;
Second fitness values are calculated for each chromosome in the new population of chromosome perturbations, respectively.
In one possible implementation manner, the encoding of the chromosome sequentially comprises encoding of the connection weight of the hidden layer and the input layer, encoding of the connection weight of the output layer and the hidden layer, encoding of the threshold value of the hidden layer and encoding of the threshold value of the output layer;
the coding length of the chromosome is s=r×s 1 +S 1 ×S 2 +S 1 +S 2 Wherein S is the coding length of the chromosome, R is the number of neurons of an input layer, S 1 Is hidden inNumber of layer-containing neurons, S 2 Is the number of neurons in the output layer.
In a second aspect, an embodiment of the present invention provides an electricity consumption differentiation analysis apparatus, including:
the acquisition module is used for acquiring user data of a target power user;
the prediction module is used for predicting according to the user data and a preset prediction model to obtain the electricity demand of the target power user; the preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm;
and the determining module is used for determining a differentiated power consumption scheme matched with the target power consumer based on the power consumption requirement of the target power consumer.
In a third aspect, an embodiment of the present invention provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method of the first aspect or any one of the possible implementations of the first aspect, when the computer program is executed by the processor.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method of the above first aspect or any of the possible implementations of the first aspect.
The embodiment of the invention provides a power consumption difference analysis method, which can accurately predict the power consumption requirement of a target power user by acquiring the user data of the target power user and predicting according to the user data and a preset prediction model; the preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm, and the disturbance is added to the preset neural network model, so that the early convergence of the neural network model can be avoided, and the accuracy of power consumption demand prediction is improved; based on the power consumption requirement matching differentiated power consumption scheme of the target power consumer, the differentiated power consumption scheme matched with the power consumption condition of the target power consumer can be determined, so that proper differentiated service is provided for the target power consumer, and the power consumption requirement of the target power consumer is met.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an implementation of a power consumption differentiation analysis method provided by an embodiment of the present invention;
FIG. 2 is a flowchart of an implementation of training a neural network model provided by an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an electricity differentiation analysis device according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.
Fig. 1 is a flowchart of an implementation of a power consumption differentiation analysis method according to an embodiment of the present invention, which is described in detail below:
step S101, user data of a target power user is acquired.
In this embodiment, the target power consumer is a power consumer needing to perform power consumption differentiation analysis, the user data may be a power consumption amount or an industrial increment value of the target power consumer, and when the target power consumer is an industrial park or a region, the user data may also be a high and new technology industrial increment value, a medium and large industrial increment value, an industrial increment value, a strategic emerging industrial increment value, a dominant industrial increment value, or the like of the industrial park or the region.
Step S102, predicting according to user data and a preset prediction model to obtain the electricity demand of a target electricity user; the preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm.
In the embodiment, a neighborhood disturbance is added into a preset neural network model, searching is performed in a local range, weights and thresholds obtained before and after the disturbance can be compared, the better weights and thresholds are selected for subsequent training, premature convergence in the training process is avoided, and a proper neural network model is obtained, so that a preset prediction model is obtained; and then according to the user data of the target power user and the preset prediction model, the power consumption requirement of the target power user can be accurately predicted.
Step S103, determining a differential power consumption scheme matched with the target power consumer based on the power consumption requirement of the target power consumer.
In this embodiment, a suitable differential electricity consumption scheme is matched for the target electricity consumer, so as to meet the electricity consumption requirement of the target electricity consumer.
According to the embodiment of the invention, the power consumption requirement of the target power user can be accurately predicted by acquiring the user data of the target power user and predicting according to the user data and the preset prediction model; the preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm, and the disturbance is added to the preset neural network model, so that the early convergence of the neural network model can be avoided, and the accuracy of power consumption demand prediction is improved; based on the power consumption requirement matching differentiated power consumption scheme of the target power consumer, the differentiated power consumption scheme matched with the power consumption condition of the target power consumer can be determined, so that proper differentiated service is provided for the target power consumer, and the power consumption requirement of the target power consumer is met.
In one possible implementation manner, the preset prediction model is obtained by: acquiring historical user data of a target power user; training a preset neural network model according to the historical user data to obtain a preset prediction model.
The neural network can adopt a three-layer structure, namely an input layer, an hidden layer and an output layer, and takes a target power user as an industrial park as an example, five neurons are determined on the input layer, and the five neurons are respectively a high and new technology industry added value, a large and medium industry added value, an industry added value, a strategic emerging industry added value and a dominant industry added value; the output layer is provided with a neuron which is the power consumption requirement of the target power user and can particularly represent industrial power consumption; the number of neurons of the hidden layer can be set to be four, seven, eleven or fifteen, the number of neurons of the hidden layer is set to be four, seven, eleven or fifteen respectively, training of the neural network model is carried out, prediction is carried out respectively by adopting the trained neural network model, and the number of neurons of the hidden layer in the neural network model with the optimal prediction effect is eleven, so that in the embodiment, the number of neurons of the hidden layer is set to be eleven.
In addition, the weights of the neural network model include implicit layer-to-input layer connection weights and output layer-to-implicit layer connection weights, and the thresholds include implicit layer thresholds and output layer thresholds.
In this embodiment, the preset neural network model is trained according to the historical user data of the target power user to be predicted, so as to obtain a prediction model suitable for the target power user, thereby more accurately predicting the power consumption requirement of the target power user.
In one possible implementation manner, referring to the implementation flowchart of the training neural network model shown in fig. 2, training the preset neural network model according to the historical user data to obtain the preset prediction model includes:
setting related parameters for training a preset neural network model, wherein the related parameters comprise group size, iteration times, maximum iteration times, preset fitness value, temperature withdrawal rate, value ranges of all weights and value ranges of all thresholds.
Referring to fig. 2, where i represents the number of iterations, the initial number of iterations is 0, i.e., i=0, i max Represents the maximum iteration number val 0 The preset fitness value is represented, T represents the current temperature, and a represents the temperature withdrawal rate
And secondly, randomly generating a corresponding number of combinations of weights and thresholds according to the population size in the value range of each weight and the value range of each threshold, and coding according to the randomly generated combinations of each weight and threshold to obtain a corresponding number of chromosomes, wherein the chromosomes form a chromosome population.
Specifically, the encoding of the chromosome sequentially comprises encoding of the connection weight of the hidden layer and the input layer, encoding of the connection weight of the output layer and the hidden layer, encoding of the threshold value of the hidden layer and encoding of the threshold value of the output layer; the connection weight of the hidden layer and the input layer is coded as W 1 ，W 1 Is R x S 1 The matrix of the output layer and the hidden layer are connected with the weight value and coded as W 2 ，W 2 Is S 1 ×S 2 Is coded as B for the matrix of hidden layer thresholds 1 ，B 1 Is of length S 1 The vector of (c) and the output layer threshold is coded as B 2 ，B 2 Is of length S 2 Is a vector of (2); the coding length of the chromosome is s=r×s 1 +S 1 ×S 2 +S 1 +S 2 Wherein S is the coding length of chromosome, R is the number of neurons of an input layer, S 1 S is the number of hidden layer neurons 2 Is the number of neurons in the output layer.
The encoding of the hidden layer and input layer connection weights can be expressed as:
W 1 (j,k)＝R×(j-1)+k,j∈[1,S 1 ],k∈[1,R]
the encoding of the output layer and hidden layer connection weights can be expressed as:
W 2 (j,k)＝S 1 ×(j-1)+k+R×S 1 ,j∈[1,S 2 ],k∈[1,S 1 ]
the coding of the hidden layer threshold can be expressed as:
B 1 (j)＝R×S 1 +S 1 ×S 2 +j,j∈[1,S 1 ]
the encoding of the output layer threshold can be expressed as:
B 2 (j)＝R×S 1 +S 1 ×S 2 +S 1 +j,j∈[1,S 2 ]
further, the initial encoding may be a real number, W, that increases from 1 bit by bit 2 At W 1 Increment on the basis of (B) 1 At W 2 Increment on the basis of (B) 2 At B 1 And (3) sequentially connecting the two parts on the basis of increasing, thereby forming a complete chromosome.
And thirdly, respectively calculating a first fitness value of each chromosome according to the weight value and the threshold value corresponding to each chromosome in the chromosome population.
Referring to FIG. 2, val is used 1 Representing a first fitness value for each chromosome.
In particular, according to And calculating fitness values of the chromosomes, wherein in the third step, the calculated fitness values of the chromosomes are the first fitness values of the chromosomes, val represents the fitness values of the chromosomes, and SE represents the sum of squares of errors of the predicted values and the true values calculated according to the weight values and the threshold values corresponding to the chromosomes.
And step four, carrying out genetic operation on each chromosome according to the first fitness value of each chromosome to obtain a genetic chromosome population.
In this embodiment, genetic operations are performed on each chromosome, specifically, selection, crossover and mutation operations are performed on each chromosome, and local search is performed, so that a chromosome with a higher fitness value is found conveniently, and thus the chromosome with a higher fitness value is inherited to the next generation, and a chromosome with a lower fitness is eliminated.
And fifthly, after performing simulated annealing operation on each chromosome in the genetic chromosome population, respectively calculating a second fitness value of each chromosome, and adding 1 to the current iteration number.
Referring to FIG. 2, val is used 2 A second fitness value representing each chromosome.
In this embodiment, the chromosome is also subjected to simulated annealing operation, that is, the chromosome is disturbed, so that the range of local searching of the chromosome is enlarged, and premature convergence of the neural network model in the training process is avoided.
Step six, judging whether the current iteration number reaches the maximum iteration number or whether the maximum second fitness value is larger than or equal to a preset fitness value.
As shown in FIG. 2, val 2max The largest second fitness value among the second fitness values representing the respective chromosomes.
And step seven, if the current iteration number does not reach the maximum iteration number and the maximum second fitness value is smaller than the preset fitness value, performing temperature withdrawal according to the temperature withdrawal rate, determining the second fitness value of each chromosome as a new first fitness value of the chromosome, and jumping to the step four.
In this embodiment, the current iteration number does not reach the maximum iteration number, and the maximum second fitness value is smaller than the preset fitness value, which indicates that the neural network model has not been trained yet and needs to be trained continuously, so the process jumps to step four to continue training.
In addition, the first and second are used only for distinguishing, and the first fitness value and the second fitness value are fitness values of chromosomes, so that when the step four is skipped, the second fitness value of each chromosome is determined as a new first fitness value of the chromosome, and genetic manipulation is performed on each chromosome according to the new first fitness value at this time, that is, based on the calculated second fitness value.
The temperature is set according to the temperature setting rate, specifically, the temperature after the temperature setting is calculated according to T=a×T,0< a <1, and the temperature setting is performed according to the temperature after the temperature setting, wherein T is the annealing temperature, and a is the temperature setting rate.
And step eight, stopping iteration if the current iteration number reaches the maximum iteration number or the maximum second fitness value is larger than or equal to a preset fitness value, and respectively determining a weight value and a threshold value corresponding to a chromosome with the maximum second fitness value as an optimal weight value and an optimal threshold value to obtain a preset prediction model.
The current iteration number reaches the maximum iteration number, or the maximum second fitness value is larger than or equal to a preset fitness value, which indicates that the neural network model training is completed, the larger the fitness value of the chromosome is, the smaller the error between the predicted value obtained by calculation according to the weight value and the threshold value corresponding to the chromosome and the true value is, therefore, the chromosome with the maximum fitness value is selected from the obtained values, the weight value and the threshold value corresponding to the chromosome with the maximum fitness value are used as the optimal weight value and the optimal threshold value, a preset prediction model is obtained, the target power user is predicted according to the preset prediction model, and the power consumption requirement of the target power user can be accurately obtained.
In the embodiment, the neural network model is trained through genetic operation, chromosomes with low fitness values can be removed according to preset fitness values, and chromosomes with high fitness values can be selected for subsequent operation; and then, the chromosome is disturbed through simulated annealing operation, so that the premature convergence of a neural network model in the training process is avoided, the chromosome with a higher fitness value is found, and the electricity consumption requirement of a target electricity user can be accurately predicted according to a preset prediction model.
In one possible implementation manner, the related parameters in the first step further include a preset mutation rate;
the fourth step is to perform genetic operation on each chromosome according to the first fitness value of each chromosome to obtain a genetic chromosome population, which can be described in detail as follows:
respectively determining the probability of each chromosome appearing in the filial generation according to the first fitness value corresponding to each chromosome, and determining the chromosome corresponding to the probability meeting the condition as a first target chromosome; randomly determining two chromosomes in a first target chromosome, and performing cross treatment to obtain a new chromosome; taking the new chromosome and the chromosomes of the first target chromosome except the two chromosomes subjected to the cross treatment as a first chromosome group; generating a first random number according to each piece of point location information of each chromosome in the first chromosome group; the first random number is positioned in the value range of the corresponding point location information; and carrying out mutation treatment on corresponding points of the corresponding chromosomes in sequence according to the preset mutation rate and each first random number to obtain a genetic chromosome population.
In this embodiment, a chromosome corresponding to a probability of meeting the condition is selected from among the chromosomes as a first target chromosome, and a chromosome having a large fitness value is reserved to the next generation; the two chromosomes are randomly determined to be crossed, so that the possibility of reduced fitness value caused by crossing can be reduced on the premise of generating new chromosomes; and carrying out mutation treatment on each point position of each chromosome, so that the chromosomes can be subjected to local search, and the chromosomes with better fitness values can be found conveniently.
Before determining the probability that each chromosome appears in the offspring according to the first fitness value corresponding to each chromosome, the method may further include: and arranging the chromosomes according to the first fitness value of each chromosome.
In this embodiment, each chromosome may be arranged first, the probability that each chromosome appears in the offspring is determined, and the cumulative probability of each chromosome is determined according to the arrangement order of the chromosomes and the probability of each chromosome; regenerating a target number of random numbers from 0 to 1, selecting corresponding chromosomes according to the random numbers, and determining the chromosomes as first target chromosomes.
In one possible implementation, two chromosomes are randomly determined in the first target chromosome, and the two chromosomes are subjected to crossover processing to obtain a new chromosome, including:
Randomly determining two chromosomes and a point position on each chromosome in a first target chromosome, and exchanging the numerical values corresponding to the two points to obtain a new chromosome.
In this embodiment, the values of a set of corresponding points on two chromosomes are exchanged, that is, the two chromosomes are replaced and recombined, so that the characteristics of the chromosomes before the exchange are maintained on the premise of generating new chromosomes, and the possibility of reducing the fitness of the chromosomes due to the exchange is reduced.
The way of exchanging may be to exchange the values of the corresponding points on the two chromosomes, or to exchange the values of the point and the values of the subsequent points with the point as the exchange point.
Carrying out mutation processing on corresponding points of corresponding chromosomes in sequence according to a preset mutation rate and each first random number, wherein the mutation processing comprises the following steps:
generating a second random number for each locus of each chromosome in the first population of chromosomes; if the second random number is smaller than or equal to the preset mutation rate, replacing the numerical value of the corresponding point position of the corresponding chromosome in the first chromosome group with the corresponding first random number; if the second random number is larger than the preset mutation rate, the numerical value of the corresponding point position of the corresponding chromosome in the first chromosome group is not replaced.
In this embodiment, the second random number may be any real number between 0 and 1, and for each point location of each chromosome in the first chromosome population, according to the second random number and the preset mutation rate, it is determined whether to replace the numerical value of the point location with the corresponding first random number, that is, each point location of each chromosome in the first chromosome population is mutated, so that the local search is performed on the chromosome, thereby finding the chromosome with the optimal fitness value, and facilitating the determination of the optimal weight and the optimal threshold.
In one possible implementation manner, after performing the simulated annealing operation on each chromosome in the genetic chromosome population in the fifth step, the second fitness value of each chromosome is calculated, which may be described in detail as follows:
according to the weight and the threshold value corresponding to each chromosome in the genetic chromosome population, respectively calculating a third fitness value of each chromosome; randomly perturbing each chromosome to obtain chromosome perturbation groups; calculating a fourth fitness value of each chromosome in the chromosome disturbance population; updating each chromosome in the chromosome disturbance group according to the third fitness value and the fourth fitness value, and taking the updated chromosomes as a new chromosome disturbance group; second fitness values are calculated for each chromosome in the new population of chromosome perturbations, respectively.
In this embodiment, random disturbance is performed on each chromosome, so that the chromosomes can be searched in a local range, and premature convergence in the training process is avoided, so that the searching range is enlarged, and the chromosome with optimal fitness is found.
Wherein, updating each chromosome in the chromosome disturbance group according to the third fitness value and the fourth fitness value can be detailed as follows:
according toCalculating the update probability of each chromosome; if update probability P r >random [0, 1), replacing the chromosome corresponding to the third fitness value with the chromosome corresponding to the fourth fitness value; if update probability P r Less than or equal to random [0,1 ], reserving a chromosome corresponding to the third fitness value; wherein P is r E is the update probability of chromosome 4 E, calculating the error square sum of the predicted value and the true value according to the weight value and the threshold value corresponding to the disturbed chromosome 3 And T is the current temperature, and is the sum of squares of errors of the predicted value and the true value obtained by calculation according to the weight and the threshold value corresponding to the chromosome before disturbance.
Further, during the updating process, the chromosome corresponding to the optimal third fitness value can be preserved, even if P r >The chromosome corresponding to the optimal third fitness value is not replaced either, so that the current optimal individual can be reserved, and the current optimal individual is prevented from being lost in the disturbance process.
According to the embodiment of the invention, the power consumption requirement of the target power user can be accurately predicted by acquiring the user data of the target power user and predicting according to the user data and the preset prediction model; the method comprises the steps that a preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm, the disturbance is added to the preset neural network model, so that the early convergence of the neural network model can be avoided, the accuracy of electricity demand prediction is improved, specifically, the neural network model is trained by genetic operation, chromosomes with lower fitness values can be removed according to preset fitness values, chromosomes with high fitness values are selected for subsequent operation, under the premise that new chromosomes are generated by cross treatment, the possibility of reduced fitness values caused by cross is reduced, and local search is performed by mutation treatment to find chromosomes with better fitness values; the chromosome is disturbed through simulated annealing operation, so that premature convergence of a neural network model in the training process is avoided, and the chromosome with higher fitness value can be found easily; meanwhile, in the disturbance process, the chromosome with the optimal fitness value is not replaced, the chromosome with the optimal fitness value at present is reserved, and the chromosome with the optimal fitness value at present is prevented from being lost in the disturbance process; based on the power consumption requirement matching differentiated power consumption scheme of the target power consumer, the differentiated power consumption scheme matched with the power consumption condition of the target power consumer can be determined, so that proper differentiated service is provided for the target power consumer, and the power consumption requirement of the target power consumer is met.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
The following are device embodiments of the invention, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 3 is a schematic structural diagram of an electricity differentiation analysis device according to an embodiment of the present invention, and for convenience of explanation, only a portion related to the embodiment of the present invention is shown, which is described in detail below:
as shown in fig. 3, the electricity differentiation analysis device 3 includes:
an acquisition module 31 for acquiring user data of a target power user;
the prediction module 32 is configured to predict according to the user data and a preset prediction model, so as to obtain a power consumption requirement of the target power user; the preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm;
the determining module 33 is configured to determine a differential power consumption scheme matched with the target power consumer based on the power consumption requirement of the target power consumer.
In one possible implementation, the obtaining manner of the prediction model preset in the prediction module 32 is:
Acquiring historical user data of a target power user;
training a preset neural network model according to the historical user data to obtain a preset prediction model.
In one possible implementation, training a preset neural network model according to historical user data to obtain a preset prediction model includes:
setting related parameters for training a preset neural network model, wherein the related parameters comprise group size, iteration times, maximum iteration times, preset fitness value, temperature withdrawal rate, value ranges of all weights and value ranges of all thresholds;
randomly generating a corresponding number of weight and threshold combinations according to the population size in the value range of each weight and the value range of each threshold, and coding according to the randomly generated weight and threshold combinations to obtain a corresponding number of chromosomes, wherein the chromosomes form a chromosome population;
step three, respectively calculating a first fitness value of each chromosome according to the weight value and the threshold value corresponding to each chromosome in the chromosome population;
fourth, genetic operation is carried out on each chromosome according to the first fitness value of each chromosome, and a genetic chromosome population is obtained;
Step five, after performing simulated annealing operation on each chromosome in the genetic chromosome population, respectively calculating a second fitness value of each chromosome, and adding 1 to the current iteration times;
step six, judging whether the current iteration number reaches the maximum iteration number or whether the maximum second fitness value is larger than or equal to a preset fitness value;
step seven, if the current iteration number does not reach the maximum iteration number and the maximum second fitness value is smaller than the preset fitness value, performing temperature withdrawal according to the temperature withdrawal rate, determining the second fitness value of each chromosome as a new first fitness value of the chromosome, and jumping to the step four;
and step eight, stopping iteration if the current iteration number reaches the maximum iteration number or the maximum second fitness value is larger than or equal to a preset fitness value, and respectively determining a weight value and a threshold value corresponding to a chromosome with the maximum second fitness value as an optimal weight value and an optimal threshold value to obtain a preset prediction model.
In one possible implementation, the relevant parameters further include a preset variation rate;
performing genetic manipulation on each chromosome according to the first fitness value of each chromosome to obtain a genetic chromosome population, including:
Respectively determining the probability of each chromosome appearing in the filial generation according to the first fitness value corresponding to each chromosome, and determining the chromosome corresponding to the probability meeting the condition as a first target chromosome;
randomly determining two chromosomes in a first target chromosome, and performing cross treatment to obtain a new chromosome;
taking the new chromosome and the chromosomes of the first target chromosome except the two chromosomes subjected to the cross treatment as a first chromosome group;
generating a first random number according to each piece of point location information of each chromosome in the first chromosome group; the first random number is positioned in the value range of the corresponding point location information;
and carrying out mutation treatment on corresponding points of the corresponding chromosomes in sequence according to the preset mutation rate and each first random number to obtain a genetic chromosome population.
In one possible implementation, two chromosomes are randomly determined in the first target chromosome, and the two chromosomes are subjected to crossover processing to obtain a new chromosome, including:
randomly determining two chromosomes and a point position on each chromosome in a first target chromosome, and exchanging the numerical values corresponding to the two points to obtain a new chromosome;
Carrying out mutation processing on corresponding points of corresponding chromosomes in sequence according to a preset mutation rate and each first random number, wherein the mutation processing comprises the following steps:
generating a second random number for each locus of each chromosome in the first population of chromosomes; if the second random number is smaller than or equal to the preset mutation rate, replacing the numerical value of the corresponding point position of the corresponding chromosome in the first chromosome group with the corresponding first random number; if the second random number is larger than the preset mutation rate, the numerical value of the corresponding point position of the corresponding chromosome in the first chromosome group is not replaced.
In one possible implementation, after performing the simulated annealing operation on each chromosome in the population of genetic chromosomes, calculating the second fitness value of each chromosome, respectively, includes:
according to the weight and the threshold value corresponding to each chromosome in the genetic chromosome population, respectively calculating a third fitness value of each chromosome;
randomly perturbing each chromosome to obtain chromosome perturbation groups;
calculating a fourth fitness value of each chromosome in the chromosome disturbance population;
updating each chromosome in the chromosome disturbance group according to the third fitness value and the fourth fitness value, and taking the updated chromosomes as a new chromosome disturbance group;
Second fitness values are calculated for each chromosome in the new population of chromosome perturbations, respectively.
In one possible implementation manner, the encoding of the chromosome sequentially comprises encoding of the connection weight of the hidden layer and the input layer, encoding of the connection weight of the output layer and the hidden layer, encoding of the threshold value of the hidden layer and encoding of the threshold value of the output layer;
the coding length of the chromosome is s=r×s 1 +S 1 ×S 2 +S 1 +S 2 Wherein S is the coding length of the chromosome, R is the number of neurons of an input layer, S 1 S is the number of hidden layer neurons 2 Is the number of neurons in the output layer.
Fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 4, the electronic apparatus 4 of this embodiment includes: a processor 40, a memory 41 and a computer program 42 stored in the memory 41 and executable on the processor 40. The steps of the above-described embodiments of the electricity differentiation analysis method, such as steps S101 to S103 shown in fig. 1, are implemented when the processor 40 executes the computer program 42. Alternatively, the processor 40, when executing the computer program 42, performs the functions of the modules of the apparatus embodiments described above, such as the functions of the modules 31 to 33 shown in fig. 3.
By way of example, the computer program 42 may be partitioned into one or more modules/units, which are stored in the memory 41 and executed by the processor 40 to complete the present invention. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions for describing the execution of the computer program 42 in the electronic device 4. For example, the computer program 42 may be split into the modules 31 to 33 shown in fig. 3.
The electronic device 4 may include, but is not limited to, a processor 40, a memory 41. It will be appreciated by those skilled in the art that fig. 4 is merely an example of the electronic device 4 and is not meant to be limiting of the electronic device 4, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device may further include an input-output device, a network access device, a bus, etc.
The processor 40 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or a memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 41 is used to store computer programs and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the apparatus/electronic device embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of each method embodiment described above may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
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, and are intended to be included in the scope of the present invention.
Claims (10)
1. A method of electricity usage differential analysis, comprising:
acquiring user data of a target power user;
predicting according to the user data and a preset prediction model to obtain the electricity demand of a target electricity user; the preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm;
and determining a differential power consumption scheme matched with the target power consumer based on the power consumption requirement of the target power consumer.
2. The electricity consumption difference analysis method according to claim 1, wherein the preset prediction model is obtained by:
Acquiring historical user data of a target power user;
training a preset neural network model according to the historical user data to obtain the preset prediction model.
3. The electricity consumption difference analysis method according to claim 2, wherein training a preset neural network model according to the historical user data to obtain the preset prediction model comprises:
setting related parameters for training a preset neural network model, wherein the related parameters comprise group size, iteration times, maximum iteration times, preset fitness value, temperature withdrawal rate, value ranges of all weights and value ranges of all thresholds;
randomly generating a corresponding number of weight and threshold combinations according to the population size in the value range of each weight and the value range of each threshold, and coding according to the randomly generated weight and threshold combinations to obtain a corresponding number of chromosomes, wherein the chromosomes form a chromosome population;
step three, respectively calculating a first fitness value of each chromosome according to the weight value and the threshold value corresponding to each chromosome in the chromosome population;
Step four, carrying out genetic operation on each chromosome according to the first fitness value of each chromosome to obtain a genetic chromosome population;
step five, after performing simulated annealing operation on each chromosome in the genetic chromosome population, respectively calculating a second fitness value of each chromosome, and adding 1 to the current iteration times;
step six, judging whether the current iteration number reaches the maximum iteration number or whether the maximum second fitness value is larger than or equal to a preset fitness value;
step seven, if the current iteration number does not reach the maximum iteration number and the maximum second fitness value is smaller than the preset fitness value, performing temperature withdrawal according to the temperature withdrawal rate, determining the second fitness value of each chromosome as a new first fitness value of the chromosome, and jumping to the step four;
and step eight, stopping iteration if the current iteration number reaches the maximum iteration number or the maximum second fitness value is larger than or equal to a preset fitness value, and respectively determining a weight and a threshold corresponding to a chromosome with the maximum second fitness value as an optimal weight and an optimal threshold to obtain the preset prediction model.
4. The electricity consumption difference analysis method according to claim 3, wherein the related parameters further include a preset mutation rate;
performing genetic operation on each chromosome according to the first fitness value of each chromosome to obtain a genetic chromosome population, wherein the genetic chromosome population comprises:
respectively determining the probability of each chromosome appearing in the filial generation according to the first fitness value corresponding to each chromosome, and determining the chromosome corresponding to the probability meeting the condition as a first target chromosome;
randomly determining two chromosomes in the first target chromosome, and performing cross treatment to obtain a new chromosome;
taking the chromosomes of the new chromosome and the first target chromosome except the two chromosomes subjected to the cross treatment as a first chromosome population;
generating a first random number according to each piece of point location information of each chromosome in the first chromosome group; the first random number is positioned in the value range of the corresponding point location information;
and carrying out mutation treatment on corresponding points of the corresponding chromosomes in sequence according to the preset mutation rate and each first random number to obtain a genetic chromosome population.
5. The method according to claim 4, wherein two chromosomes are randomly determined in the first target chromosome, and the crossing process is performed to obtain a new chromosome, comprising:
Randomly determining two chromosomes and a point position on each chromosome in the first target chromosome, and exchanging the numerical values corresponding to the two points to obtain a new chromosome;
and carrying out mutation processing on corresponding points of the corresponding chromosome according to the preset mutation rate and each first random number in sequence, wherein the mutation processing comprises the following steps:
generating a second random number for each locus of each chromosome in the first population of chromosomes; if the second random number is smaller than or equal to the preset mutation rate, replacing the numerical value of the corresponding point position of the corresponding chromosome in the first chromosome group with the corresponding first random number; and if the second random number is larger than the preset mutation rate, not replacing the numerical value of the corresponding point position of the corresponding chromosome in the first chromosome group.
6. The method according to claim 3 or 4, wherein after performing a simulated annealing operation on each chromosome in the population of genetic chromosomes, calculating a second fitness value of each chromosome, respectively, comprises:
according to the weight and the threshold value corresponding to each chromosome in the genetic chromosome population, respectively calculating a third fitness value of each chromosome;
Randomly perturbing each chromosome to obtain chromosome perturbation groups;
calculating a fourth fitness value for each chromosome in the chromosome disturbance population;
updating each chromosome in the chromosome disturbance group according to the third fitness value and the fourth fitness value, and taking the updated chromosomes as a new chromosome disturbance group;
and respectively calculating second fitness values of each chromosome in the new chromosome disturbance group.
7. The electricity consumption difference analysis method according to claim 3, wherein the encoding of the chromosome sequentially comprises encoding of a hidden layer and input layer connection weight, encoding of an output layer and hidden layer connection weight, encoding of a hidden layer threshold value and encoding of an output layer threshold value;
the chromosome has a coding length of s=r×s 1 +S 1 ×S 2 +S 1 +S 2 Wherein S is the coding length of the chromosome, R is the number of neurons of an input layer, S 1 S is the number of hidden layer neurons 2 Is the number of neurons in the output layer.
8. An electricity consumption difference analysis device, comprising:
the acquisition module is used for acquiring user data of a target power user;
the prediction module is used for predicting according to the user data and a preset prediction model to obtain the electricity demand of the target power user; the preset prediction model is obtained by adding disturbance to a preset neural network model and training by adopting a genetic algorithm;
And the determining module is used for determining a differentiated power consumption scheme matched with the target power consumer based on the power consumption requirement of the target power consumer.
9. An electronic device comprising a memory for storing a computer program and a processor for calling and running the computer program stored in the memory, characterized in that the processor implements the steps of the method according to any of the preceding claims 1-7 when the computer program is executed.
10. A computer-readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310231687.9A CN117151265A (en) | 2023-03-10 | 2023-03-10 | Power consumption difference analysis method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310231687.9A CN117151265A (en) | 2023-03-10 | 2023-03-10 | Power consumption difference analysis method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117151265A true CN117151265A (en) | 2023-12-01 |
Family
ID=88901423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310231687.9A Pending CN117151265A (en) | 2023-03-10 | 2023-03-10 | Power consumption difference analysis method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117151265A (en) |
-
2023
- 2023-03-10 CN CN202310231687.9A patent/CN117151265A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114186749B (en) | Flexible workshop scheduling method and model based on reinforcement learning and genetic algorithm | |
| CA2436352A1 (en) | Process and system for developing a predictive model | |
| CN111861013B (en) | Power load prediction method and device | |
| CN108446534A (en) | Select the method, apparatus and computer readable storage medium of neural network hyper parameter | |
| CN111898750A (en) | Neural network model compression method and device based on evolutionary algorithm | |
| CN110991724A (en) | Method, system and storage medium for predicting scenic spot passenger flow | |
| CN112580259A (en) | Intelligent mine automatic ore blending method and system based on genetic algorithm | |
| CN111538767B (en) | Data processing method, device, equipment and storage medium | |
| CN110009181A (en) | Distribution network transform measure and mistake load figureofmerit relevance method for digging and device | |
| CN115310664A (en) | RBF neural network training method and prediction system based on gene regulation genetic algorithm | |
| CN115185804A (en) | Server performance prediction method, system, terminal and storage medium | |
| JP7137074B2 (en) | Optimization calculation method, optimization calculation device, and optimization calculation program | |
| CN113381417B (en) | Three-phase load unbalance optimization method, device and terminal for power distribution network area | |
| CN111062524A (en) | Scenic spot short-term passenger flow volume prediction method and system based on optimized genetic algorithm | |
| CN113672871A (en) | High-proportion missing data filling method and related device | |
| CN110298506A (en) | A kind of urban construction horizontal forecast system | |
| Ming et al. | Intelligent approaches to tolerance allocation and manufacturing operations selection in process planning | |
| Hardas et al. | Development of a genetic algorithm for component placement sequence optimization in printed circuit board assembly | |
| CN117151265A (en) | Power consumption difference analysis method and device, electronic equipment and storage medium | |
| CN110647994A (en) | TSP (Total suspended particulate) optimization method based on improved mutation operator genetic algorithm | |
| CN114330940B (en) | Multi-objective mixed spider monkey optimization method for PCB electroplating task sequencing problem | |
| CN112819161B (en) | Neural network construction system, method and storage medium for variable-length gene genetic algorithm | |
| CN115619028A (en) | Clustering algorithm fusion-based power load accurate prediction method | |
| CN114969148A (en) | System access amount prediction method, medium and equipment based on deep learning | |
| CN113837474A (en) | Regional soil heavy metal pollution index prediction method and device |
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 |